CN118690306A - Fault prediction method and system for regenerative thermal incinerator system based on digital twin - Google Patents

Abstract

The invention discloses a digital twin-based heat accumulating type thermal incinerator system fault prediction method and system, which relate to the technical field of intelligent fault prediction, solve the technical problems that single sensor data monitoring and parameter adjustment cannot realize the positioning of an abnormal cause and simultaneously cannot predict danger caused by the abnormal parameter, the real-time parameters are substituted into the model to be analyzed to obtain the whole working state of the incinerator, and the abnormal working state is analyzed according to the corresponding abnormal data, and the records of the same situation in the historical data are integrated in the analysis process to perform systematic analysis.

Description

Fault prediction method and system for regenerative thermal incinerator system based on digital twin

Technical Field

The present invention relates to the technical field of intelligent fault prediction, and specifically to a fault prediction method and system for a regenerative thermal incinerator system based on digital twins.

Background Art

Incinerator systems are important equipment for treating various types of waste, such as garbage, chemical waste, etc. During its operation, various faults may occur due to the influence of various factors such as operating parameters, environmental conditions, equipment status, etc. These faults not only affect the normal operation and efficiency of the incinerator system, but may also pose a threat to the environment and personnel safety.

According to Chinese patent application number CN202311741959.6, an artificial intelligence-based incinerator system fault prediction method and system are disclosed. The initial operation incineration control instance of the incinerator system is used as the basic incineration control instance. The fault path vectors covered by it are detected through the fault detection network, and the corresponding instance clustering attributes and incineration abnormality categories are generated. The impact of a specific incineration control instance on the incineration control instance can be effectively simulated, and possible abnormal situations can be predicted. Furthermore, by executing the simulation process to virtually run the parameter application instructions for each fault path vector, a deeper understanding of how various operation instructions affect the incineration process can be achieved. Finally, by constructing knowledge members and knowledge links and generating an incineration fault knowledge graph, a comprehensive and in-depth understanding and analysis of various possible faults in the incinerator system is achieved.

During the use of some existing thermal incinerator systems, most of them use sensors to obtain parameters during the incineration process, monitor and analyze the parameters, and adjust the parameters if there are abnormalities. This adjustment method cannot comprehensively analyze the causes of the overall state of the incinerator. A single adjustment can only temporarily normalize the state of the incinerator, and does not analyze the causes of the abnormalities, which makes it inconvenient for subsequent adjustments and danger predictions when the same situation occurs. In severe cases, it may pose a threat to personnel safety.

Summary of the invention

In response to the shortcomings of the prior art, the present invention provides a fault prediction method and system for a regenerative thermal incinerator system based on digital twins, which solves the problem that single sensor data monitoring and parameter adjustment cannot locate the cause of the abnormality and cannot predict the danger caused by parameter abnormalities.

To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for predicting failures of a regenerative thermal incinerator system based on digital twins, the method specifically comprising the following steps:

Step 1: Perform data analysis based on the acquired historical data to obtain correct data and incorrect data. At the same time, establish a digital twin model based on the correct data, and substitute real-time parameters into the model to obtain analysis results, and the analysis results include: normal status results and abnormal status results;

Step 2: Analyze the abnormal state results, compare the relationship between the real-time state parameters and the standard parameters, classify the real-time parameters into normal parameters and abnormal parameters, and analyze the normal parameters and abnormal parameters respectively;

Step 3: Monitor and analyze the normal parameters obtained through classification, and conduct periodic and continuous monitoring of the normal parameters in combination with historical data. Perform comprehensive analysis based on the changes in the normal parameters and the corresponding normal range values to generate normal signals and warning signals;

Step 4: Analyze the abnormal parameters obtained by classification, and generate early warning signals based on the risk impact of the abnormal parameters based on historical data.

As a further solution of the present invention: the specific method of substituting the real-time parameters into the model to obtain the analysis results in step 1 is:

Obtain the historical data corresponding to the thermal incinerator, identify the correct data and incorrect data in the historical data, extract the features of the correct data to obtain the data features, and then establish the digital twin model of the thermal incinerator based on the data features;

Then, the current real-time parameters of the thermal incinerator are obtained and substituted into the digital twin model. The digital twin model analyzes the state of the thermal incinerator according to the real-time parameters to generate analysis results, and the analysis results include normal state results and abnormal state results.

As a further solution of the present invention: the specific method of monitoring and analyzing the normal parameters in step 3 is:

The historical data is acquired, and the working parameters corresponding to all normal working states in the historical data are obtained as comparison parameters, and the corresponding normal intervals are generated according to the comparison parameters. Then, the normal parameters are monitored with time t as a period, and the changes of the normal parameters within the time period t are acquired. At the same time, the changes are classified into stable changes and unstable changes.

As a further solution of the present invention: the specific method of analyzing the stable change and the unstable change in step 3 is:

Analyze the stable changes, obtain the normal parameters corresponding to the adjacent time periods t, and compare the normal parameters corresponding to the two time periods. If the normal parameters in the adjacent time period t do not change, it means that the overall state of the thermal incinerator is normal, and a normal signal is generated. On the contrary, if the normal parameters in the adjacent time period t change, compare the normal parameters of the adjacent time period t with the normal interval. If the normal parameters belong to the normal interval, it means that the normal state of the thermal incinerator is normal, and a normal signal is generated. On the contrary, if the normal parameters do not belong to the normal interval, it means that the normal state of the thermal incinerator is abnormal, and an early warning signal is generated.

The unstable changes are analyzed, and the normal parameters of the adjacent time period y are compared with the normal interval. If the normal parameters belong to the normal interval, a secondary analysis signal is generated. Otherwise, if the normal parameters do not belong to the normal interval, it means that the normal state of the thermal incinerator is abnormal, and an early warning signal is generated, and the generated secondary analysis signal is processed.

As a further solution of the present invention: the specific method of processing the generated secondary analysis signal in step 3 is:

The corresponding identical records in the historical data are obtained, and the number of records with risk situations in the same records is obtained, and the corresponding risk record ratio is calculated. Then the risk record ratio is compared with the preset value. If the risk record ratio is greater than the preset value, a warning signal is generated. Otherwise, if the risk record ratio is less than the preset value, a normal signal is generated.

As a further solution of the present invention: the specific method of analyzing the abnormal parameters in step 4 is:

Obtain historical data, and obtain historical records of the same situation as the abnormal parameters in the historical data, and determine whether there are risk records in the historical records. If there are risk records, obtain the corresponding risk records and obtain the corresponding risk-free records;

Then, all risk records are analyzed and the types of risk records are identified. If there is only one type of risk record, a warning signal is generated with the corresponding risk record. If there are multiple types of risk records, the risk records are classified according to the risk type and labeled as i, and i=1, 2, ..., j, where j represents the number of risk types. Then, the number of risk records corresponding to different risk types is obtained and recorded as Li, and the risk features of the same type of risk types are extracted. At the same time, the abnormal features corresponding to the abnormal parameters are obtained, and the abnormal features are matched with the risk features to screen the risk records to obtain pre-selected records;

Then, risk-free records are obtained, and parameter features in the risk-free records are extracted. At the same time, the parameter features of the risk-free records are matched with the risk features of the pre-selected records to obtain specific risk information, and then an early warning signal is generated.

As a further solution of the present invention: a regenerative thermal incinerator system fault prediction system based on digital twins, comprising: a data acquisition module, a model building and analysis module, an abnormal state analysis module, an early warning analysis module and a prediction information output module;

Data acquisition module, which is used to acquire historical data and real-time parameters and transmit them to the model building and analysis module;

Model building and analysis module, which is used to build a digital twin model based on historical data and combined with artificial intelligence algorithms, and substitute real-time parameters into the digital twin model to obtain normal state results and abnormal state results, and transmit the abnormal state results to the abnormal state analysis module;

Abnormal state analysis module, which is used to analyze the abnormal state results, and compare the real-time state parameters with the standard parameters to obtain normal parameters and abnormal parameters, and transmit the abnormal parameters to the early warning analysis module, for the normal parameters, and in combination with the historical data, the normal parameters are periodically and continuously monitored, and the normal signals and early warning signals are generated according to the changes of the normal parameters and the corresponding normal range values. At the same time, the generated normal signals and early warning signals are transmitted to the prediction information output module;

The early warning analysis module is used to analyze the acquired abnormal parameters, analyze the risk impact of the abnormal parameters based on historical data, generate early warning signals, and transmit the generated early warning signals to the prediction information output module;

The prediction information output module is used to display the acquired warning signals, normal status results and normal signals to the corresponding operators.

The present invention provides a method and system for predicting failures of a regenerative thermal incinerator system based on digital twins. Compared with the prior art, it has the following beneficial effects:

The present invention establishes a corresponding digital twin model based on the correct data in the historical data and utilizes the digital twin technology and artificial intelligence recognition technology. The overall working status of the incinerator is obtained by substituting the real-time parameters into the model for analysis. For the abnormal working status, analysis is performed based on the corresponding abnormal data. In the process of analysis, the records of the same situation in the historical data are comprehensively analyzed for a systematic analysis. On the one hand, the accuracy of the analysis can be improved. On the other hand, the function of locating the specific cause corresponding to the abnormal data can be realized, thereby timely discovering the cause of the fault. At the same time, the overall fault situation can be predicted from the changes in the abnormal data.

BRIEF DESCRIPTION OF THE DRAWINGS

Fig. 1 is a diagram of the method of the present invention;

FIG. 2 is a system block diagram of the present invention.

DETAILED DESCRIPTION

The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

Embodiment 1, please refer to FIG1 , the present application provides a method for predicting a failure of a regenerative thermal incinerator system based on digital twins, the method specifically comprising the following steps:

Step 1: Perform data analysis based on the historical data obtained to obtain correct data and incorrect data. At the same time, establish a digital twin model based on the correct data, and substitute real-time parameters into the model to obtain analysis results. The analysis results include: normal status results and abnormal status results. The specific analysis method is as follows:

The historical data corresponding to the thermal incinerator is obtained, and the historical data obtained here represents all usage records within the past time T, and the correct data and the incorrect data in the historical data are identified, and the correct data is extracted to obtain data features, and the data features are identified and extracted through the corresponding artificial intelligence algorithm, and then a digital twin model of the thermal incinerator is established according to the data features. The specific process of establishing the digital twin model is the existing technology and will not be elaborated on here.

For example, suppose that the temperature, pressure, fuel consumption, and emission data of a thermal incinerator were collected in the operating records of the past 6 months. Some outliers were found through data analysis, such as an abnormally high pressure reading on a certain day, which may be erroneous data caused by sensor failure. After excluding these erroneous data, feature extraction was performed on the remaining correct data, and it was found that there was an obvious positive correlation between furnace temperature and fuel consumption, while pressure had a greater impact on emission levels. Based on these data features, a digital twin model was established that can simulate the behavior of the thermal incinerator under different operating conditions and predict its performance and maintenance needs.

Then, the current real-time parameters of the thermal incinerator are obtained, and the real-time parameters here include temperature, pressure, combustion consumption and emissions, etc., and the real-time parameters are substituted into the digital twin model. The digital twin model analyzes the state of the thermal incinerator according to the real-time parameters to generate analysis results, and the analysis results include normal state results and abnormal state results.

The digital twin model is an advanced dynamic simulation model that can accurately simulate the operating status of a thermal incinerator based on real-time data. The model processes these real-time parameters and predicts the behavior of the incinerator through complex calculations and pattern recognition techniques. Based on the results of the analysis, the model can determine whether the incinerator is in a normal state or has potential abnormal conditions.

Step 2: Analyze the abnormal state results, compare the relationship between the real-time state parameters and the standard parameters, classify the real-time parameters into normal parameters and abnormal parameters, and analyze the normal parameters and abnormal parameters respectively; the standard parameters here are specifically represented by the normal working parameters corresponding to the thermal incinerator under normal circumstances. This standard parameter represents the various indicators of the thermal incinerator under normal working conditions, such as the ideal temperature range, pressure value, fuel consumption rate and emission level.

During the analysis, real-time parameters are classified into normal parameters and abnormal parameters according to whether they deviate from standard parameters. Normal parameters are those that are within the preset normal working range, while abnormal parameters are indicators that are outside these ranges. This classification can more clearly identify where the problem lies and which system components may be in a non-ideal state.

Step 3: Monitor and analyze the normal parameters obtained through classification, and conduct periodic and continuous monitoring of the normal parameters in combination with historical data. Perform comprehensive analysis based on the changes in the normal parameters and the corresponding normal range values to generate normal signals and warning signals. The specific analysis method is as follows:

The historical data is acquired, and the working parameters corresponding to all normal working states in the historical data are acquired and recorded as comparison parameters, and the corresponding normal interval is generated according to the comparison parameters, and the normal interval here is obtained by combining the comparison parameters, specifically, the corresponding normal interval is obtained by acquiring the minimum value and the maximum value of the comparison parameters, and then the normal parameters are monitored with time t as a period, and the change of the normal parameters within the time period t is acquired, and the change is classified into stable change and unstable change, and the specific classification method here is to calculate the normal parameter change value corresponding to the time t1 within the time period t, and compare the calculated change value with the threshold, and the threshold is a range value, and the specific value is set by the operator, if the normal parameter change value is within the threshold range, it is represented as a stable change, and conversely, if the normal parameter change value is not within the threshold range, it is represented as an unstable change;

Analyze the stable changes, obtain the normal parameters corresponding to the adjacent time periods t, and compare the normal parameters corresponding to the two time periods, and the comparison here is mutual comparison. If the normal parameters in the adjacent time periods t do not change, and the lack of change indicates that the difference between the two is within the allowable range, it means that the overall state of the thermal incinerator is normal, and a normal signal is generated. On the contrary, if the normal parameters in the adjacent time periods t change, and the change indicates that the difference between the two is not within the allowable range, then the normal parameters of the adjacent time periods t are compared with the normal interval, and the normal parameters compared with the normal interval here are the normal parameters in the next time period t. If the normal parameters belong to the normal interval, it means that the normal state of the thermal incinerator is normal, and a normal signal is generated. On the contrary, if the normal parameters do not belong to the normal interval, it means that the normal state of the thermal incinerator is abnormal, and an early warning signal is generated.

Analyze the unstable changes, compare the normal parameters of the adjacent time period y with the normal interval, if the normal parameters belong to the normal interval, generate a secondary analysis signal, otherwise if the normal parameters do not belong to the normal interval, it means that the normal state of the thermal incinerator is abnormal, and generate an early warning signal, and process the generated secondary analysis signal, and the specific processing method is:

The corresponding identical records in the historical data are obtained, and the identical records here represent the records with normal parameters and unstable changes, and the number of records with risk conditions in the same records is obtained, and the corresponding risk record ratio is calculated, and then the risk record ratio is compared with the preset value. If the risk record ratio is greater than the preset value, it means that the current unstable change has risks, and a warning signal is generated. On the contrary, if the risk record ratio is less than the preset value, a normal signal is generated. The specific value of the preset value is formulated by the operator according to the actual situation.

Step 4: Analyze the abnormal parameters obtained by classification, analyze the risk impact of the abnormal parameters based on historical data, and generate early warning signals. The specific analysis method is:

Obtain historical data, and obtain historical records of the same situation as the abnormal parameters in the historical data, and determine whether there are risk records in the historical records. If there are risk records, obtain the corresponding risk records and obtain the corresponding risk-free records; specifically, here the historical records of the same situation are classified to obtain risk records and risk-free records.

Then, all risk records are analyzed and the types of risk records are identified. If there is only one type of risk record, a warning signal is generated with the corresponding risk record. If there are multiple types of risk records, the risk records are classified according to the risk type and labeled as i, and i=1, 2, ..., j, where j represents the number of risk types. Then, the number of risk records corresponding to different risk types is obtained and recorded as Li, and the risk features of the same type of risk types are extracted, and the risk features here are represented as corresponding parameter features. At the same time, the abnormal features corresponding to the abnormal parameters are obtained, and the abnormal features are matched with the risk features to screen the risk records to obtain pre-selected records;

Then, the risk-free records are obtained, and the parameter features in the risk-free records are extracted. At the same time, the parameter features of the risk-free records are matched with the risk features of the pre-selected records to obtain specific risk information, and then a warning signal is generated. Specifically, for example, the parameter feature corresponding to the risk-free record is temperature, and the risk features corresponding to a group of pre-selected records in the pre-selected records include temperature and pressure, which further indicates that temperature is a non-necessary factor for risk. Therefore, the temperature in the group of pre-selected records is eliminated and analyzed, and only the pressure is analyzed, and then the matching analysis is combined with the specific situation of the abnormal parameters to determine the specific risk information. If the abnormal parameter matches the pressure of the group, the group of pre-selected records is used as specific risk information and a warning signal is generated.

Embodiment 2, please refer to FIG2 , a regenerative thermal incinerator system fault prediction system based on digital twin, including: a data acquisition module, a model establishment and analysis module, an abnormal state analysis module, a warning analysis module and a prediction information output module;

Data acquisition module, which is used to acquire historical data and real-time parameters and transmit them to the model building and analysis module;

A model building and analysis module, which is used to build a digital twin model based on historical data and in combination with an artificial intelligence algorithm, and substitute real-time parameters into the digital twin model to obtain normal state results and abnormal state results, and transmit the abnormal state results to the abnormal state analysis module. The specific method of obtaining the normal state results and the abnormal state results is similar to the processing method of step 1 in embodiment 1;

An abnormal state analysis module is used to analyze the abnormal state results, and compare the real-time state parameters with the standard parameters to obtain normal parameters and abnormal parameters, and transmit the abnormal parameters to the early warning analysis module. For normal parameters, the normal parameters are periodically and continuously monitored in combination with historical data, and a normal signal and an early warning signal are generated according to a comprehensive analysis of the changes in the normal parameters and the corresponding normal range values. The generated normal signal and early warning signal are transmitted to the prediction information output module at the same time, and the specific processing method is the same as the analysis method of step three in embodiment one;

An early warning analysis module is used to analyze the acquired abnormal parameters, analyze the risk impact of the abnormal parameters based on historical data to generate an early warning signal, and transmit the generated early warning signal to the prediction information output module. The specific processing method is the same as the analysis method of step 4 in embodiment 1;

The prediction information output module is used to display the acquired warning signals, normal status results and normal signals to the corresponding operators.

Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims (7)

1. The digital twin-based heat accumulating type thermal incinerator system fault prediction method is characterized by comprising the following steps of:

Step one: performing data analysis according to the acquired historical data to obtain correct data and error data, simultaneously establishing a digital twin model based on the correct data, substituting real-time parameters into the model to obtain an analysis result, wherein the analysis result comprises: a state normal result and a state abnormal result;

Step two: analyzing the abnormal state result as an analysis result, comparing the relation between the real-time state parameter and the standard parameter, classifying the real-time parameter to obtain a normal parameter and an abnormal parameter, and analyzing the normal parameter and the abnormal parameter respectively;

Step three: monitoring and analyzing the classified normal parameters, and carrying out periodic continuous monitoring on the normal parameters by combining historical data, and comprehensively analyzing according to the change of the normal parameters and the corresponding normal range values to generate a normal signal and an early warning signal;

step four: and analyzing the classified abnormal parameters, and analyzing risk influence of the abnormal parameters according to the historical data to generate an early warning signal.

2. The digital twin based heat accumulating type thermal incinerator system fault prediction method according to claim 1, wherein the specific way of substituting the real-time parameters into the model to obtain the analysis result in the first step is as follows:

Acquiring historical data corresponding to the thermal incinerator, identifying correct data and error data in the historical data, extracting features of the correct data to obtain data features, and then establishing a digital twin model of the thermal incinerator according to the data features;

and then acquiring the current real-time parameters of the thermal incinerator, substituting the real-time parameters into a digital twin model, and analyzing the state of the thermal incinerator by the digital twin model according to the real-time parameters to generate an analysis result, wherein the analysis result comprises a normal state result and an abnormal state result.

3. The digital twin based heat accumulating type thermal incinerator system fault prediction method according to claim 1, wherein the specific mode of monitoring and analyzing the normal parameters in the third step is as follows:

And acquiring the historical data, recording the working parameters which are normally corresponding to all working states in the historical data as comparison parameters, generating a corresponding normal interval according to the comparison parameters, monitoring the normal parameters by taking the time t as a period, acquiring the change condition of the normal parameters in the time t, and classifying the change condition to obtain stable change and unstable change.

4. The digital twin based heat accumulating type thermal incinerator system fault prediction method according to claim 3, wherein the specific way of analyzing the stable change and the unstable change in the third step is as follows:

Analyzing the change condition as stable change, acquiring normal parameters corresponding to adjacent time periods t, comparing the normal parameters corresponding to the two time periods, generating a normal signal if the normal parameters in the adjacent time periods t are unchanged, otherwise comparing the normal parameters in the adjacent time periods t with a normal interval if the normal parameters in the adjacent time periods t are changed, generating a normal signal if the normal parameters belong to the normal interval, otherwise generating an early warning signal if the normal parameters do not belong to the normal interval;

And (3) analyzing the unstable change of the change condition, comparing the normal parameter of the adjacent time period y with the normal interval, generating a secondary analysis signal if the normal parameter belongs to the normal interval, otherwise, generating an early warning signal if the normal parameter does not belong to the normal interval, and processing the generated secondary analysis signal.

5. The digital twin based regenerative thermal incinerator system fault prediction method as claimed in claim 4, wherein the specific way of processing the generated secondary analysis signal in the third step is as follows:

And acquiring the corresponding same records in the historical data, acquiring the number of records with risk conditions in the same records, simultaneously calculating the corresponding risk record duty ratio, comparing the risk record duty ratio with a preset value, generating an early warning signal if the risk record duty ratio is larger than the preset value, and otherwise, generating a normal signal if the risk record duty ratio is smaller than the preset value.

6. The digital twin based heat accumulating type thermal incinerator system fault prediction method according to claim 1, wherein the specific way of analyzing the abnormal parameters in the fourth step is as follows:

Acquiring historical data, acquiring a historical record of the same condition as the abnormal parameter in the historical data, judging whether the historical record has a risk record or not, acquiring a corresponding risk record if the risk record exists, and acquiring a corresponding risk-free record;

Analyzing all risk records, identifying the types of the risk records, generating an early warning signal by using the corresponding risk records if the types of the risk records are of one type, classifying the risk records according to the types of the risk records and marking the risk records as i according to the types of the risk records, wherein i=1, 2, … and j, j represents the number of the risk types, acquiring and marking the number of the risk records corresponding to different risk types as Li, extracting the risk characteristics of the risk types of the same type, acquiring the abnormal characteristics corresponding to the abnormal parameters, matching the abnormal characteristics with the risk characteristics, and screening the risk records to obtain a preselected record;

And then acquiring a risk-free record, extracting parameter characteristics in the risk-free record, simultaneously matching the parameter characteristics of the risk-free record with the risk characteristics of a preselected record to obtain specific risk information, and then generating an early warning signal.

7. A digital twin based regenerative thermal incinerator system fault prediction system for performing the digital twin based regenerative thermal incinerator system fault prediction method of any of claims 1 to 6, comprising: the system comprises a data acquisition module, a model building analysis module, an abnormal state analysis module, an early warning analysis module and a prediction information output module;

The data acquisition module is used for acquiring historical data and real-time parameters and transmitting the historical data and the real-time parameters to the model building analysis module;

The model building analysis module is used for building a digital twin model according to historical data and combining an artificial intelligent algorithm, substituting real-time parameters into the digital twin model to obtain a normal state result and an abnormal state result, and transmitting the abnormal state result to the abnormal state analysis module;

The abnormal state analysis module is used for analyzing an abnormal state result, comparing and classifying the real-time state parameter with the standard parameter to obtain a normal parameter and an abnormal parameter, transmitting the abnormal parameter to the early warning analysis module, carrying out periodic continuous monitoring on the normal parameter aiming at the normal parameter by combining with the historical data, carrying out comprehensive analysis according to the change of the normal parameter and the corresponding normal range value to generate a normal signal and an early warning signal, and transmitting the generated normal signal and the early warning signal to the prediction information output module;

The early warning analysis module is used for analyzing the acquired abnormal parameters, analyzing risk influence of the abnormal parameters according to historical data to generate early warning signals, and transmitting the generated early warning signals to the prediction information output module;

And the prediction information output module is used for displaying the acquired early warning signals, the normal state results and the normal signals to corresponding operators.