CN113128080A - Method and apparatus for predicting temperature of wire harness - Google Patents
Method and apparatus for predicting temperature of wire harness Download PDFInfo
- Publication number
- CN113128080A CN113128080A CN201911412159.3A CN201911412159A CN113128080A CN 113128080 A CN113128080 A CN 113128080A CN 201911412159 A CN201911412159 A CN 201911412159A CN 113128080 A CN113128080 A CN 113128080A
- Authority
- CN
- China
- Prior art keywords
- harness
- wire
- temperature
- normalized
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012549 training Methods 0.000 claims abstract description 89
- 238000003062 neural network model Methods 0.000 claims abstract description 26
- 238000013507 mapping Methods 0.000 claims abstract description 17
- 238000013528 artificial neural network Methods 0.000 claims abstract description 9
- 239000011159 matrix material Substances 0.000 claims abstract description 7
- 239000010410 layer Substances 0.000 claims description 69
- 239000004020 conductor Substances 0.000 claims description 40
- 239000011241 protective layer Substances 0.000 claims description 28
- 238000004088 simulation Methods 0.000 claims description 26
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000009413 insulation Methods 0.000 claims description 15
- 230000015654 memory Effects 0.000 claims description 14
- 238000009529 body temperature measurement Methods 0.000 claims description 9
- 239000000463 material Substances 0.000 claims description 5
- 238000013401 experimental design Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002459 sustained effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Images
Landscapes
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The present disclosure provides a method and apparatus for predicting a temperature of a wiring harness, wherein the method for predicting a temperature of a wiring harness includes: training a preset neural network model by using a plurality of groups of normalized training sample data, wherein each group of training sample data in the plurality of groups of training sample data comprises input data and output data, the input data comprises a wire harness structure parameter value and a wire harness working parameter value within a preset range, and the output data comprises a wire harness temperature value; obtaining a mapping relation model for simulating a mapping relation between input data and output data based on a threshold value and a weight matrix of the neural network obtained by training; and inputting the structure parameter value and the working parameter value of the wire harness within a preset range based on the mapping relation model to obtain a predicted value of the temperature of the wire harness. The present disclosure can provide methods and apparatus for quickly, economically, and/or accurately predicting a temperature of a wiring harness.
Description
Technical Field
The present invention relates to a method and apparatus for predicting a wire rating parameter, and in particular to a method and apparatus for predicting the temperature of a wire in a wire harness.
Background
The current carrying capacity of a wire in a car is an important parameter. Ampacity refers to the maximum current that a wire can carry under sustained load at which the temperature of the conductor of the wire reaches but does not exceed the long term heat resistant temperature of the insulation of the wire. It is critical to those skilled in the art how to obtain the temperature of the wire under sustained load to know the current carrying capacity.
At present, the temperature of the wire under continuous load is generally obtained by the following two ways:
(1) measuring the temperature of the conducting wire when the conducting wire is electrified through a physical experiment;
(2) the temperature of the wire is calculated based on a theoretical model or a finite element model.
However, physical experiments have the following disadvantages:
(1) the cost is high;
(2) physical experiments usually involve measuring a single wire under ideal conditions, and the measured temperature does not reflect the actual conditions in real environments. Because during the actual use of the conductor, one or more conductors are usually protected by a protective layer such as tape or sleeve. Therefore, the experimental data measured on a single wire will have a large deviation from the actual situation.
Finite element modeling generally requires a corresponding expertise and is computationally lengthy.
Therefore, a new method for predicting the temperature of the wires in the wire harness and thus the current-carrying capacity of the wires needs to be provided.
Disclosure of Invention
The technical scheme provided by the invention aims to provide a method capable of quickly, economically and/or accurately predicting the temperature of a wiring harness.
In one aspect of the present invention, there is provided a method for predicting a temperature of a wire harness, the method comprising: training a preset neural network model by using a plurality of groups of normalized training sample data, wherein each group of training sample data in the plurality of groups of training sample data comprises input data and output data, the input data comprises a wire harness structure parameter value and a wire harness working parameter value within a preset range, and the output data comprises a wire harness temperature value; obtaining a mapping relation model for simulating the mapping relation between the input data and the output data based on the threshold value and the weight matrix of the neural network obtained by training; and inputting the wiring harness structure parameter value and the wiring harness working parameter value in the preset range based on the mapping relation model to obtain a wiring harness temperature predicted value.
In at least one embodiment of one aspect of the present invention, the method further comprises obtaining the normalized sets of training sample data, said obtaining the normalized sets of training sample data comprising: obtaining a measured value of the temperature of the wire harness through actual measurement; normalizing the input data and the output data to obtain a first normalized set of training sample data, wherein the first normalized set of training sample data comprises the normalized harness operating parameter value, the normalized harness structure parameter value, and the normalized harness temperature measurement value.
In at least one embodiment of one aspect of the present invention, the harness operating parameter values include lead operating current; the wire harness structure parameter values comprise the thickness of a wire insulating layer and the thickness of a wire harness protection layer; the harness temperature value comprises a temperature value of a conductor of the wire and a temperature value of an interface between the insulating layer of the wire and the protective layer of the harness; the predicted value of the temperature of the wire harness includes a predicted value of the temperature of the conductor of the wire and a predicted value of the temperature of an interface between the insulating layer of the wire and the protective layer of the wire harness.
In at least one embodiment of one aspect of the present invention, the harness operating parameter values further include at least one parameter value selected from the group consisting of: working environment temperature and conducting wire electrifying time; the harness structure parameter values further include at least one parameter value selected from the group consisting of: the heat conductivity coefficient of the wire conductor, the sectional area of the wire conductor, the heat conductivity coefficient of the wire insulating layer, the heat conductivity coefficient of the wire harness protective layer and the number of wires.
In at least one embodiment of one aspect of the present invention, the obtaining the normalized sets of training sample data further comprises: inputting the wiring harness working parameter value and the wiring harness structure parameter value based on a preset finite element simulation model to obtain the wiring harness temperature calculation value; normalizing the harness temperature calculation values to obtain a normalized second plurality of sets of training sample data, wherein the normalized second plurality of sets of training sample data comprises normalized harness operating parameter values, normalized harness structure parameter values, and normalized harness temperature calculation values; the step of training the pre-set neural network model with the normalized sets of training sample data comprises training the pre-set neural network model with at least a portion selected from the following sets of training sample data: the normalized first and second sets of training sample data.
In at least one embodiment of one aspect of the present invention, the obtaining the normalized sets of training sample data further comprises: calibrating the finite element simulation model with the harness temperature measurements; inputting the wiring harness working parameter value and the wiring harness structure parameter value based on the corrected finite element simulation model to obtain a corrected wiring harness temperature calculation value; normalizing the corrected harness temperature calculations to obtain a normalized third plurality of sets of training sample data, wherein the normalized third plurality of sets of training sample data comprises the normalized harness operating parameter value, the normalized harness structure parameter value, and the normalized corrected harness temperature calculations; the step of training the pre-set neural network model with the normalized sets of training sample data comprises training the pre-set neural network model with at least a portion selected from the following sets of training sample data: the normalized first, second and third sets of training sample data.
In at least one embodiment of one aspect of the present invention, the obtaining the normalized sets of training sample data includes obtaining the harness operating parameter values and the harness structure parameter values within the predetermined range based on a uniform experimental design.
In at least one embodiment of an aspect of the invention, the method further comprises: and obtaining a predicted value of the current-carrying capacity of the wire based on the predicted value of the temperature of the conductor of the wire.
In at least one embodiment of one aspect of the invention, obtaining a predicted value of current carrying capacity of the wire based on the predicted value of temperature of the wire conductor comprises: establishing a first fitting curve based on the lead working current and the corresponding predicted temperature value of the lead conductor; and obtaining the predicted value of the current-carrying capacity of the wire based on the first fitted curve and the target working temperature value.
In at least one embodiment of one aspect of the present invention, a second fitting curve is established based on the working current of the wire and the corresponding predicted temperature value of the interface between the wire insulation layer and the wire harness protection layer;
and obtaining a predicted temperature value of an interface between the wire insulating layer and the wire harness protective layer for selecting the material of the wire harness protective layer based on the second fitted curve and the predicted wire carrying capacity value.
In at least one embodiment of one aspect of the present invention, training the preset neural network model with the normalized sets of training sample data includes: and training the preset neural network model by using the normalized groups of training sample data by adopting a back propagation algorithm.
In another aspect of the invention, an apparatus for predicting a temperature of a wiring harness is provided, comprising a plurality of modules each for performing a corresponding step in any of the above methods.
In other aspects of the present invention, a system for predicting a temperature of a wiring harness is provided, comprising: a memory for storing program instructions; a processor for executing the program instructions to implement any of the above methods.
In yet another aspect of the invention, a computer-readable medium is provided for storing a plurality of instructions which, when executed by a computing device, cause the computing device to perform any of the above-described methods.
Compared with the prior art, the technical scheme provided by the invention has one or more of the following advantages:
(1) compared with a simple physical experiment, the experiment cost is obviously reduced;
(2) the prediction result is more accurate by considering the actual wiring harness state with a plurality of conducting wires and/or a protective layer;
(3) compared with finite element modeling, the time for obtaining the temperature of the wire harness is greatly reduced.
Drawings
To further clarify the above and other advantages and features of embodiments of the present invention, a more particular description of embodiments of the present invention will be rendered by reference to the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope as claimed.
Fig. 1 illustrates a process of a wiring harness temperature prediction method according to an embodiment of the present invention.
Fig. 2A and 2B show a wire harness having one wire and a wire harness having a plurality of wires, respectively.
FIG. 3 illustrates a neural network model in accordance with an embodiment of the present invention.
Fig. 4 shows a diagram of a predicted value of the temperature of a conductor predicted by a mapping relation model according to a change of an operating current value according to an embodiment of the present invention.
Detailed Description
While the invention will be described in further detail in connection with specific embodiments and with reference to the accompanying drawings, the following description sets forth numerous details for a thorough understanding of the invention, it will be readily apparent that the invention may be embodied in many other forms other than those described herein, and it will be readily apparent to those skilled in the art that the invention may be practiced with many modifications and alterations without departing from the spirit of the invention, and the scope of the invention should not be limited by the contents of this detailed embodiment.
This application uses specific words to describe embodiments of the application. Reference to "one embodiment," "another embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the application. Therefore, it is emphasized and should be appreciated that two or more references to "one embodiment" or "another embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the present application may be combined as appropriate.
It should be noted that in the foregoing description of embodiments of the present application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.
FIG. 1 illustrates a process 100 of a wiring harness temperature prediction method according to one embodiment of the invention.
At step 112, experimental data including a temperature measurement of the wiring harness is obtained. In some embodiments, an experimental test platform may be set up, and temperature sensors may be placed at the positions of the wire conductor and the interface between the wire insulation layer and the harness protection layer to measure the temperature measurement value of the wire conductor and the temperature measurement value of the interface between the wire insulation layer and the harness protection layer. For example, temperature sensors may be placed at the conductors 221 of the wire harness 220 having a single wire and at the interface between the insulating layer 223 and the protective layer 225 as shown in fig. 2A. Or a temperature sensor may be placed at the conductor 241 and at the interface between the insulating layer 243 and the protective layer 245 of the wire harness 240 having a plurality of wires as shown in fig. 2B. For a wire harness 240 having a plurality of wires, a temperature sensor may also be placed at each conductor 241 of the plurality of wires and at the interface between each insulation layer 243 of the plurality of wires and the corresponding protective layer 245, respectively. In each experiment, a predetermined operating current may be applied to a wire harness having a predetermined wire harness structural parameter value, and a temperature at a predetermined position within the wire harness may be measured by a temperature sensor, thereby obtaining a set of experimental data. In this set of experimental data [ X ]i,Yj]In (1), input data XiMay be predeterminedStructural parameter values and working parameter values of the wire harness structure, and output data YjMay be a measured temperature at a predetermined location within the wiring harness. In an embodiment, as illustrated in Table 1 below, the harness structure parameter values may include a thickness X of the wire insulation layer1And thickness X of wire harness protective layer2The wiring harness operating parameter value may include an operating current value X applied to the wire3. The measured harness temperature measurement may include a temperature value Y of the wire conductor1And temperature value Y of the interface between the wire insulating layer and the harness protective layer2. Further, as exemplified in table 1 below, the predetermined values of the harness structure parameters may further include the thermal conductivity X of the wire conductor4The sectional area X of the conductor5Thermal conductivity coefficient X of wire insulating layer6Thermal conductivity coefficient X of wire harness protection layer7And the number X of the wires in the wire harness8Or other harness configuration parameter values. The value of the wiring harness operating parameter may also include the operating environment temperature X9Conducting wire power-on time X10Or other harness operating parameter values. Wherein, X5Refers to the cross-sectional area of the conductor of a single wire. It should be understood that for a harness 240 having multiple wires, X5May have a plurality of conductor cross-sectional areas corresponding to the respective conductive lines, and similarly, the thickness X of the insulating layer of the conductive line1The working current value X applied to the wire3The thermal conductivity coefficient X of the conductor of the wire4Thermal conductivity coefficient X of wire insulating layer6Conducting wire power-on time X10Temperature value Y of conductor of wire1Or the temperature value Y of the interface between the wire insulating layer and the harness protective layer2There may also be multiple values corresponding to each wire. In some embodiments, the wires in the bundle are symmetrically distributed. In other embodiments, the wires in the bundle may be arranged in other distributions as desired.
Multiple sets of Experimental data [ X ]i,Yj]May be used to construct a first plurality of sets of training sample data.
Table 1: input data and output data
Returning to FIG. 1, at step 114, the pre-set finite element simulation model is corrected. In some embodiments, after obtaining the plurality of sets of experimental data at step 112, the plurality of sets of experimental data may be used to correct the predetermined finite element simulation model. For example, a predetermined finite element simulation model can be obtained by modeling in the finite element simulation software comsolmutiphics. The predetermined finite element simulation model is corrected using at least a portion of the sets of experimental data obtained in step 112 to obtain a corrected finite element simulation model. In one embodiment, the predetermined finite element simulation model may be adjusted by repartitioning the network or adjusting solver parameter settings such that the adjusted or corrected finite element simulation model is used at the same input XiDown calculated output Y'jOutput Y corresponding to the plurality of sets of experimental data obtained in step 112jWithin a predetermined error range.
At step 116, corrected analog data including the corrected wire harness temperature calculation is obtained. In some embodiments, using the corrected finite element simulation model, a value of a beam operating parameter and a value of a beam structure parameter X are inputiObtaining corrected wire harness temperature calculation value Y'jThereby obtaining corrected analog data [ X ] including input data and output datai,Y'j]. The corrected analog data [ X ]i,Y'j]Similar to the experimental data [ X ] described abovei,Yj]. Wherein the input data XiMay be a value of a harness structural parameter of the wire harness and a value of a wire harness operating parameter, for example, a thickness X of a wire insulation layer1Thickness X of wire harness protective layer2Operating current value X3The thermal conductivity coefficient X of the conductor of the wire4The sectional area X of the conductor5Thermal conductivity coefficient X of wire insulating layer6Thermal conductivity coefficient X of wire harness protection layer7And the number X of the wires in the wire harness8Temperature of working environment X9Conducting wire power-on time X10One or more of the output data Y'jMay be a calculated corrected calculated value of the temperature of the wire harness, e.g. the temperature value Y of the conductor of the wire1And temperature value Y of the interface between the wire insulating layer and the harness protective layer2One or both. Multiple sets of corrected analog data [ X ]i,Y'j]May be used to construct a second plurality of sets of training sample data.
At step 118, the training sample data is normalized to obtain normalized training sample data. In some embodiments, multiple sets of experimental data [ X ] obtained at step 112 may be pairedi,Yj]Normalization is performed to obtain a normalized first plurality of sets of training sample data [ X ]i,Yj]n, where the normalized first plurality of sets of training sample data [ Xi,Yj]n includes a normalized strand operating parameter value, a normalized strand structure parameter value, and a normalized strand temperature measurement value. In other embodiments, multiple sets of corrected analog data [ X ] obtained at step 116 may be comparedi,Y'j]n are normalized to obtain a normalized second plurality of sets of training sample data [ X ]i,Y'j]n, where the normalized second plurality of sets of training sample data [ Xi,Y'j]Including a normalized strand operating parameter value, a normalized strand structure parameter value, and a normalized corrected strand temperature calculation value. In addition, in another embodiment, the values of the working parameters of the wiring harness and the values of the structural parameters X of the wiring harness can be input by using a preset finite element simulation model, i.e. an uncorrected finite element simulation modeliObtaining a calculated value Y of the temperature of the wire harness "jThereby obtaining analog data [ X ] including input data and output datai,Y”j]. Similarly, the analog data [ X ]i,Y”j]Similar to the experimental data [ X ] described abovei,Yj]. Wherein the input data XiMay be a value of a harness structural parameter of the wire harness and a value of a wire harness operating parameter, for example, a thickness X of a wire insulation layer1Thickness X of wire harness protective layer2Operating current value X3The thermal conductivity coefficient X of the conductor of the wire4The sectional area X of the conductor5Thermal conductivity coefficient X of wire insulating layer6Thermal conductivity coefficient X of wire harness protection layer7And the number X of the wires in the wire harness8Temperature of working environment X9Conducting wire power-on time X10Of the output data Y "jMay be a calculated value of the temperature of the wire harness, such as the temperature value Y of the conductor of the wire1And temperature value Y of the interface between the wire insulating layer and the harness protective layer2One or both. In this further embodiment, multiple sets of analog data [ X ] may be obtainedi,Y”j]Normalizing to obtain a normalized third plurality of sets of training sample data [ X ]i,Y”j]n, where the normalized third plurality of sets of training sample data [ Xi,Y”j]n includes a normalized strand operating parameter value, a normalized strand structure parameter value, and a normalized strand temperature calculation value.
In the foregoing embodiments, the input data X falling within a predetermined numerical range is generally selectediAnd output data Y obtained accordinglyj、Y'jOr Y "jWill also fall within a range of values, normalizing the input data within the respective predetermined range, and normalizing the output data within the respective range, respectively.
At step 120, a preset neural network model is trained to obtain a mapping relationship model. In some embodiments, a neural network model may be preset first. In one embodiment, a neural network model 300, such as illustrated in FIG. 3, may be preset. As shown in fig. 3, the neural network model 300 may include three layers-an input layer, a hidden layer, and an output layer, wherein the input layer includes three nodes, the hidden layer includes four nodes, the output layer includes two nodes, and the neural network 300 is a Fully Connected (FC) neural network. In other embodiments, the number of layers of the preset neural network, the number of nodes in each layer, and the connection mode may be selected or adjusted to obtain other preset neural network models. In one embodiment, the normalized output in the normalized training sample dataEnter data XnComprising 3, normalized output data YnWhen 2 nodes are included, the number of nodes in the input layer may be set to 3, and the number of nodes in the output layer may be set to 2. And normalized input data X in the normalized training sample datanComprising 10, normalized output data YnWhen 2 nodes are included, the number of nodes in the input layer may be set to 10, and the number of nodes in the output layer may be set to 2. Furthermore, the number of nodes of the hidden layer can be obtained according to the following empirical formula (1), (2) or (3):
m＝log2n (2)
wherein m represents the number of nodes of the hidden layer, n represents the number of nodes of the input layer, l represents the number of nodes of the output layer, and α represents a constant between 1 and 10.
Subsequently, normalized sets of training sample data [ X ] may be usedi,Yj]n、[Xi,Y'j]n、[Xi,Y”j]n, for example, the preset neural network model 300 shown in fig. 3 is trained, and when the neural network training error is within the allowable range, the threshold and weight matrix W of the trained neural network can be obtained [ W ═1,w2]Wherein w is1Is a threshold value and weight matrix between the input layer and the hidden layer, w2The threshold value and the weight matrix between the hidden layer and the output layer are shown. In an embodiment, the back propagation algorithm may be used to train the neural network model 300 with at least a portion of the normalized sets of training sample data. In some embodiments, the preset neural network model 300 may be trained with some or all of one or more of the following training sample data: normalized first plurality of sets of training sample data [ X [ ]i,Yj]n, normalized second plurality of sets of training sample data [ Xi,Y'j]n, and a normalized third plurality of sets of training sample data [ X ]i,Y”j]n is the same as the formula (I). That is, training sample data for training a preset neural network model may be derived from physical experiments alone; or from a preset finite element simulation model separately; or separately from the corrected finite element simulation model; or from any two or three of a physical experiment, a pre-set finite element simulation model, and a corrected finite element simulation model. Further, input data uniformly distributed within a predetermined range may be obtained by uniform experimental design, and then measured and/or calculated at these input data X by one or more of physical experimental measurement, preset finite element simulation model and corrected finite element simulation modeliOutput data Y ofj、Y”jOr Y'jTo obtain experimental data [ X ]i,Yj]Analog data [ X ]i,Y”j]And corrected analog data [ X ]i,Y'j]And then further processed to obtain normalized training sample data. For example, as the operating current X of the input data3Between 0A-320A, 4 values, e.g., 80A, 160A, 240A, 320A, uniformly distributed within the predetermined range can be obtained by a uniform experimental design, followed by a physical experimental measurement at X3Output data Y at 80AjAnd calculating X by the corrected finite element simulation model3Output data Y 'under 80A, 160A, 240A, 320A'jFor obtaining normalized training sample data. Wherein X measured by physical experiment can be utilized3Output data Y at 80AjCorrecting the predetermined finite element simulation model to obtain a corrected finite element simulation model, and calculating X using the corrected finite element simulation model3Output data Y 'of 160A, 240A, 320A'j。
Based on the trained threshold value and weight matrix W, a mapping relation model for simulating a mapping relation between input data X and output data Y can be obtained. The basic expression of the mapping relationship is as follows: y ═ f (X, W).
At step 124, the temperature of the wire harness is predicted based on the mapping relationship model. In some embodiments, analog input data X within a predetermined range may be inputpObtaining output data Y by using the mapping relation modelq. Wherein XpMay be a value of a harness structural parameter and a value of a harness operating parameter within a predetermined range, for example, may be a thickness X of a wire insulation layer1Thickness X of wire harness protective layer2Operating current value X3，YqMay be a predicted value of the temperature of the wire harness, for example, a predicted value Y of the temperature of the conductor of the wire1And predicted value Y of temperature at interface between wire insulating layer and wire harness protective layer2。
How to predict the current-carrying capacity of the wire based on the predicted value of the temperature of the conductor of the wire is described below with reference to fig. 4. In some embodiments, sets of input data X may be input based on a trained neural network model, i.e., a mapping relationship model1-X10To obtain a plurality of sets of output data Yq. Wherein X's in several sets of input data can be maintained1-X2And X4-X10Constant, working current value X of the wire3Has a uniform distribution in [0A,300A ]]15-30 values in the range, sets of output data YiMay include a corresponding predicted value Y of the temperature of 15-30 wire conductors1. And may be further based on these 15-30 pairs of operating current values X3And predicted value Y of conductor temperature1To establish a fitted curve, resulting in the curve shown in fig. 4. As shown in fig. 4, when the temperature value of the working environment is 105 ℃, if the ultimate temperature resistance of the insulation layer of the wire, i.e. the target working temperature value, is 200 ℃, the current-carrying capacity of the wire is about 270A. Further, a plurality of sets of output data YiMay also include a predicted value Y of the temperature at the interface between the corresponding 15-30 wire insulation layers and the harness protection layer2Based further on these 15-30 pairs of operating current values X3And predicted value Y of temperature at interface between wire insulating layer and wire harness protective layer2To establish a fitted curve whereby the above illustrated 270A may be further utilizedWorking current, namely current-carrying capacity of the wire, to obtain a predicted temperature value Y of the interface between the corresponding wire insulation layer and the wire harness protection layer2. Obtaining a predicted value Y of the temperature of the interface between the corresponding wire insulation layer and the wire harness protection layer2Can be used to select a suitable harness protective layer material, such as a material having an ultimate temperature resistance greater than the predicted temperature value Y of the interface between the corresponding wire insulation layer and the harness protective layer2The wiring harness protective layer material of (1).
Also disclosed herein is an apparatus for predicting a temperature of a wire and/or a current carrying capacity of a wire in a harness, the apparatus comprising a plurality of modules operable to perform the steps of process 100 of the method for predicting a temperature of a wire harness described in connection with fig. 1 and the process for obtaining a predicted value of a current carrying capacity of a wire based on the predicted value of the temperature of the wire harness described in connection with fig. 4.
Additionally, a system for predicting a temperature of a wire and/or a current carrying capacity of the wire in a wire harness is disclosed and includes a memory and a processor. The memory may be a non-volatile memory, such as a non-transitory computer readable storage medium, an electrically erasable programmable read-only memory (EEPROM), or the like. The memory may be used to store one or more programs or program instructions that implement the various predictive methods of the present application. The memory may further be used to store various initial data, intermediate data, and result data, such as normalized sets of training sample data and thresholds and weight matrices W of the trained neural network. The processor may be used to execute one or more programs or program instructions stored in the memory.
One or more modules in the various embodiments of the disclosure may be implemented in software, hardware, or a combination of both. In a hardware implementation, for example, the implementation may be performed using at least one of Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), processors (processors), controllers (controllers), micro-controllers, micro-processors (micro-processors), and electrical units for performing other functions.
Portions of embodiments may be provided as a computer program product that may include a computer-readable medium having stored thereon computer program instructions that may be used to program a computer (or other electronic devices) to be executed by one or more processors to perform a process according to some embodiments. The computer-readable medium may include, but is not limited to, magnetic disks, optical disks, read-only memories (ROMs), Random Access Memories (RAMs), erasable programmable read-only memories (EPROMs), electrically erasable programmable read-only memories (EEPROMs), magnetic or optical cards, flash memory, or other type of computer-readable media suitable for storing electronic instructions. Moreover, embodiments may also be downloaded as a computer program product, wherein the program may be transferred from a remote computer to a requesting computer. In some embodiments, a non-transitory computer-readable storage medium has stored thereon data representing sequences of instructions that, when executed by a processor, cause the processor to perform certain operations.
While the present invention has been described in accordance with the preferred embodiments of the present disclosure, it is not intended to be limited thereto, but rather only by the scope set forth in the appended claims. It will be appreciated by persons skilled in the art that various modifications and changes may be made to the embodiments described herein without departing from the broader spirit and scope of the invention as set forth in the appended claims.
Claims (14)
1. A method for predicting a temperature of a wiring harness, the method comprising:
training a preset neural network model by using a plurality of groups of normalized training sample data, wherein each group of training sample data in the plurality of groups of training sample data comprises input data and output data, the input data comprises a wire harness structure parameter value and a wire harness working parameter value within a preset range, and the output data comprises a wire harness temperature value;
obtaining a mapping relation model for simulating the mapping relation between the input data and the output data based on the threshold value and the weight matrix of the neural network obtained by training;
and inputting the wiring harness structure parameter value and the wiring harness working parameter value in the preset range based on the mapping relation model to obtain a wiring harness temperature predicted value.
2. The method of claim 1, further comprising obtaining the normalized sets of training sample data, the obtaining the normalized sets of training sample data comprising:
obtaining a measured value of the temperature of the wire harness through actual measurement;
normalizing the input data and the output data to obtain a first normalized set of training sample data, wherein the first normalized set of training sample data comprises the normalized harness operating parameter value, the normalized harness structure parameter value, and the normalized harness temperature measurement value.
3. The method of claim 2,
the wire harness working parameter value comprises a wire working current;
the wire harness structure parameter values comprise the thickness of a wire insulating layer and the thickness of a wire harness protection layer;
the harness temperature value comprises a temperature value of a conductor of the wire and a temperature value of an interface between the insulating layer of the wire and the protective layer of the harness;
the predicted value of the temperature of the wire harness includes a predicted value of the temperature of the conductor of the wire and a predicted value of the temperature of an interface between the insulating layer of the wire and the protective layer of the wire harness.
4. The method of claim 3,
the harness operating parameter values further comprise at least one parameter value selected from the group consisting of: working environment temperature and conducting wire electrifying time;
the harness structure parameter values further include at least one parameter value selected from the group consisting of: the heat conductivity coefficient of the wire conductor, the sectional area of the wire conductor, the heat conductivity coefficient of the wire insulating layer, the heat conductivity coefficient of the wire harness protective layer and the number of wires.
5. The method of any of claims 2-4,
the obtaining the normalized plurality of sets of training sample data further comprises:
inputting the wiring harness working parameter value and the wiring harness structure parameter value based on a preset finite element simulation model to obtain the wiring harness temperature calculation value;
normalizing the harness temperature calculation values to obtain a normalized second plurality of sets of training sample data, wherein the normalized second plurality of sets of training sample data comprises normalized harness operating parameter values, normalized harness structure parameter values, and normalized harness temperature calculation values;
the step of training the pre-set neural network model with the normalized sets of training sample data comprises training the pre-set neural network model with at least a portion selected from the following sets of training sample data: the normalized first and second sets of training sample data.
6. The method of claim 5,
the obtaining the normalized plurality of sets of training sample data further comprises:
calibrating the finite element simulation model with the harness temperature measurements;
inputting the wiring harness working parameter value and the wiring harness structure parameter value based on the corrected finite element simulation model to obtain a corrected wiring harness temperature calculation value;
normalizing the corrected harness temperature calculations to obtain a normalized third plurality of sets of training sample data, wherein the normalized third plurality of sets of training sample data comprises the normalized harness operating parameter value, the normalized harness structure parameter value, and the normalized corrected harness temperature calculations;
the step of training the pre-set neural network model with the normalized sets of training sample data comprises training the pre-set neural network model with at least a portion selected from the following sets of training sample data: the normalized first, second and third sets of training sample data.
7. The method of claim 1, wherein the obtaining the normalized sets of training sample data comprises obtaining the harness operating parameter values and the harness structure parameter values within the predetermined range based on a uniform experimental design.
8. The method of claim 3, wherein the method further comprises: and obtaining a predicted value of the current-carrying capacity of the wire based on the predicted value of the temperature of the conductor of the wire.
9. The method of claim 8, wherein obtaining a wire ampacity prediction value based on the temperature prediction value of the wire conductor comprises:
establishing a first fitting curve based on the lead working current and the corresponding predicted temperature value of the lead conductor;
and obtaining the predicted value of the current-carrying capacity of the wire based on the first fitted curve and the target working temperature value.
10. The method of claim 9, wherein a second fit curve is established based on the operating current of the wire and a corresponding predicted value of the temperature of the interface between the wire insulation layer and the harness protection layer;
and obtaining a predicted temperature value of an interface between the wire insulating layer and the wire harness protective layer for selecting the material of the wire harness protective layer based on the second fitted curve and the predicted wire carrying capacity value.
11. The method of claim 1, wherein training a preset neural network model with the normalized sets of training sample data comprises: and training the preset neural network model by using the normalized groups of training sample data by adopting a back propagation algorithm.
12. An apparatus for predicting a temperature of a wiring harness, comprising a plurality of modules for performing respective steps of the method of any one of claims 1-11.
13. A system for predicting a temperature of a wiring harness, comprising:
a memory for storing program instructions;
a processor for executing the program instructions to implement the method of any of claims 1-11.
14. A computer-readable medium storing a plurality of instructions that, when executed by a computing device, cause the computing device to perform the method of any of claims 1-11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911412159.3A CN113128080A (en) | 2019-12-31 | 2019-12-31 | Method and apparatus for predicting temperature of wire harness |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911412159.3A CN113128080A (en) | 2019-12-31 | 2019-12-31 | Method and apparatus for predicting temperature of wire harness |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113128080A true CN113128080A (en) | 2021-07-16 |
Family
ID=76770206
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911412159.3A Pending CN113128080A (en) | 2019-12-31 | 2019-12-31 | Method and apparatus for predicting temperature of wire harness |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113128080A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115795979A (en) * | 2023-02-06 | 2023-03-14 | 广东电网有限责任公司中山供电局 | Three-core cable dynamic current-carrying capacity prediction method and system based on multilayer perceptron |
| CN115809610A (en) * | 2023-02-08 | 2023-03-17 | 广东电网有限责任公司中山供电局 | Direct-buried three-core cable current-carrying capacity prediction method and system based on multi-step load |
| CN116008706A (en) * | 2023-01-05 | 2023-04-25 | 广东电网有限责任公司 | A method and system for predicting the dynamic ampacity of a three-core cable based on multidimensional correlation |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886374A (en) * | 2014-04-22 | 2014-06-25 | 武汉大学 | Cable joint wire temperature prediction method based on RBF neural network |
| CN105205202A (en) * | 2015-07-14 | 2015-12-30 | 三峡大学 | Current carrying capacity calculation method |
| CN105205302A (en) * | 2015-04-08 | 2015-12-30 | 辽宁达能电气股份有限公司 | Cable dynamic flow calculation method based on optical fiber temperature measurement host |
| CN105550472A (en) * | 2016-01-20 | 2016-05-04 | 国网上海市电力公司 | Prediction method of transformer winding hot-spot temperature based on neural network |
| CN110083908A (en) * | 2019-04-19 | 2019-08-02 | 陕西科技大学 | Cable conductor temperature predicting method based on finite element analysis |
| CN110135019A (en) * | 2019-04-26 | 2019-08-16 | 广东工业大学 | A method for predicting power cable loss and core temperature |
-
2019
- 2019-12-31 CN CN201911412159.3A patent/CN113128080A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886374A (en) * | 2014-04-22 | 2014-06-25 | 武汉大学 | Cable joint wire temperature prediction method based on RBF neural network |
| CN105205302A (en) * | 2015-04-08 | 2015-12-30 | 辽宁达能电气股份有限公司 | Cable dynamic flow calculation method based on optical fiber temperature measurement host |
| CN105205202A (en) * | 2015-07-14 | 2015-12-30 | 三峡大学 | Current carrying capacity calculation method |
| CN105550472A (en) * | 2016-01-20 | 2016-05-04 | 国网上海市电力公司 | Prediction method of transformer winding hot-spot temperature based on neural network |
| CN110083908A (en) * | 2019-04-19 | 2019-08-02 | 陕西科技大学 | Cable conductor temperature predicting method based on finite element analysis |
| CN110135019A (en) * | 2019-04-26 | 2019-08-16 | 广东工业大学 | A method for predicting power cable loss and core temperature |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116008706A (en) * | 2023-01-05 | 2023-04-25 | 广东电网有限责任公司 | A method and system for predicting the dynamic ampacity of a three-core cable based on multidimensional correlation |
| CN115795979A (en) * | 2023-02-06 | 2023-03-14 | 广东电网有限责任公司中山供电局 | Three-core cable dynamic current-carrying capacity prediction method and system based on multilayer perceptron |
| CN115809610A (en) * | 2023-02-08 | 2023-03-17 | 广东电网有限责任公司中山供电局 | Direct-buried three-core cable current-carrying capacity prediction method and system based on multi-step load |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113128080A (en) | Method and apparatus for predicting temperature of wire harness | |
| CN110135019A (en) | A method for predicting power cable loss and core temperature | |
| JP6067728B2 (en) | Method and apparatus for monitoring high voltage current transmission lines | |
| CN108627766B (en) | Real-time measurement method for internal temperature of battery core in battery module and battery pack | |
| CN107609308B (en) | Method and device for measuring equivalent resistance at connecting pipe of cable joint | |
| CN109583083B (en) | Cable current-carrying capacity optimization method and device, computer equipment and storage medium | |
| CN110794706A (en) | Temperature measuring method and device for switch cabinet, computer equipment and storage medium | |
| CN116359653A (en) | Method, device, computer equipment and storage medium for determining cable ampacity | |
| CN110160492B (en) | Method and device for monitoring inclination of power transmission tower | |
| CN106599383B (en) | A method for obtaining transient temperature rise between two cables | |
| CN113468762A (en) | Hot spot temperature calculation method and device, computer equipment and storage medium | |
| CN110929999A (en) | Voltage sag severity calculation method considering tolerance characteristics of different devices | |
| CN119312088A (en) | Cable joint core temperature data prediction method and device | |
| CN114441833A (en) | Current measuring method, current measuring device, computer device, and storage medium | |
| CN106294966B (en) | A single-circuit cable core transient temperature acquisition method independent of skin temperature | |
| CN111521859B (en) | Line current measuring method and device of power equipment and computer equipment | |
| CN118281878A (en) | Power system flow determination method, device, computer equipment and storage medium | |
| CN112269060B (en) | Contact resistance and contact conductivity identification method and system | |
| CN114088237B (en) | Power cable temperature field evaluation method, system, equipment, medium and procedure | |
| CN116166511A (en) | Method, device, equipment and storage medium for evaluating service life of electric connector | |
| CN109682489B (en) | Selection method and device of thermistor based on protection characteristics of electric energy meter | |
| Tselepi et al. | An efficient approach for combined electromigration and thermomigration analysis based on the extended krylov subspace | |
| CN117172056A (en) | Training method and device for contact resistance prediction model and computer equipment | |
| CN112926246A (en) | Method for acquiring transient temperature rise of single cable in groove by considering nonlinear convection heat dissipation | |
| CN112161725A (en) | Method and device for determining temperature of stranded wire layer inside steel-cored aluminum strand |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210716 |
|
| RJ01 | Rejection of invention patent application after publication |