CN120257188B - Metering and on-line control method for cement production water footprint - Google Patents
Metering and on-line control method for cement production water footprintInfo
- Publication number
- CN120257188B CN120257188B CN202510748588.7A CN202510748588A CN120257188B CN 120257188 B CN120257188 B CN 120257188B CN 202510748588 A CN202510748588 A CN 202510748588A CN 120257188 B CN120257188 B CN 120257188B
- Authority
- CN
- China
- Prior art keywords
- abnormal
- water consumption
- water
- deviation
- cement production
- 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.)
- Active
Links
Landscapes
- Testing And Monitoring For Control Systems (AREA)
- Feedback Control In General (AREA)
Abstract
本发明属于水泥生产技术领域，本发明提供了一种水泥生产水足迹的计量与在线控制方法，包括以下步骤：实时采集水泥生产过程中全流程用水数据，构建水泥生产实时用水数据库，并根据实时用水数据建立理论用水量计算模型；对实时用水量与理论用水量进行用水偏差分析，提取异常事件，通过用水偏差中的异常事件与异常事件的间隔事件次数两个指标判断用水量是否异常。本发明先基于偏差率限值筛选异常事件，再通过异常事件次数与间隔均值融合计算异常判断指数，快速识别异常环节，针对异常数据，利用Spearman秩相关系数与滑动窗口方差分析的双维度检验，区分平稳变化与非平稳变化，避免单一指标误判，为精准控制提供了关键依据。
The present invention belongs to the technical field of cement production. The present invention provides a method for measuring and online controlling the water footprint of cement production, comprising the following steps: real-time collection of water consumption data for the entire cement production process, construction of a real-time water consumption database for cement production, and establishment of a theoretical water consumption calculation model based on the real-time water consumption data; water consumption deviation analysis of the real-time water consumption and the theoretical water consumption, extraction of abnormal events, and determination of whether the water consumption is abnormal based on two indicators: the number of abnormal events in the water consumption deviation and the number of interval events between the abnormal events. The present invention first screens abnormal events based on a deviation rate limit, and then calculates an abnormal judgment index by fusing the number of abnormal events with the mean of the interval, quickly identifying abnormal links, and using a two-dimensional test of the Spearman rank correlation coefficient and the sliding window variance analysis for abnormal data to distinguish between steady changes and non-steady changes, thereby avoiding misjudgment of a single indicator and providing a key basis for precise control.
Description
Technical Field
The invention belongs to the technical field of cement production, and particularly relates to a metering and on-line control method for cement production water footprint.
Background
The cement industry is a globally important basic raw material industry and is one of the high-consumption water industries, and according to statistics, the annual water consumption of the cement industry in China exceeds 10 hundred million cubic meters, the water consumption (fresh water) of unit products is about 0.15-0.2 m < 3 >/ton of cement, and along with the aggravation of global water resource shortage and the strict environmental protection policy (such as the requirement of 2025 cement industry unit product water consumption reduction by 10% in industrial water efficiency promotion action plan in China), the water footprint is accurately metered, the high-efficiency control of water consumption is realized, and the cement industry sustainable development core requirement is realized;
however, in the process of controlling water management in cement production, the prior art often has insufficient analysis on the deviation of real-time water consumption and theoretical water consumption, in actual production, when the actual water consumption deviates from the theoretical water consumption, due to the lack of accurate judgment on the deviation property, a uniform and single adjustment strategy is adopted, so that not only is the water resource wasted easily, but also the cement production process is possibly unstable, for example, the water consumption deviation is treated in the same way, the water deviation control precision is low, and the continuity and quality stability of cement production are further affected, and in addition, the prior art lacks systematic classification and dynamic analysis on the water consumption deviation, so that effective support cannot be provided for controlling the water footprint of cement production, and the dual requirements of water conservation and process stability of cement production cannot be well met;
therefore, the invention provides a metering and on-line control method for cement production water footprint.
Disclosure of Invention
In order to overcome the deficiencies of the prior art, at least one technical problem presented in the background art is solved.
The invention solves the technical problems by adopting the technical scheme that the metering and on-line control method for the water footprint of cement production comprises the following steps:
Collecting water consumption data of the whole process in the cement production process in real time, constructing a cement production real-time water consumption database, and establishing a theoretical water consumption calculation model according to the real-time water consumption data;
Carrying out water deviation analysis on the real-time water consumption and the theoretical water consumption, extracting abnormal events, judging whether the water consumption is abnormal or not according to two indexes of the abnormal events in the water consumption deviation and the interval event times of the abnormal events, and carrying out stability analysis on a water consumption deviation data sequence according to two aspects of trend and fluctuation if the water consumption is abnormal, and judging whether the water consumption deviation data is stable or not;
and according to the stability judging result, calculating a deviation ratio of the stability result and the non-stability result, calculating a water regulating quantity based on the deviation ratio, and executing a control instruction.
The beneficial effects of the invention are as follows:
1. According to the invention, firstly, abnormal events are screened based on the deviation rate limit value, then, the abnormal judgment index is calculated through fusion of the number of the abnormal events and the interval mean value, abnormal links are rapidly identified, and for abnormal data, smooth changes and non-smooth changes are distinguished by utilizing the two-dimensional test of Spearman rank correlation coefficient and sliding window variance analysis, so that single index misjudgment is avoided, and a key basis is provided for accurate control;
2. According to the invention, a differentiated deviation proportion calculation mode is adopted aiming at different stationarity, the water adjustment quantity is used for adapting to the actual demand, the stability and water use efficiency of the cement production process are ensured, and the real-time acquisition, the theoretical model and the deviation analysis are combined to form a closed loop, so that the control precision of water management in the cement production process is improved.
Drawings
The invention is further described below with reference to the accompanying drawings.
FIG. 1 is a flow chart of the steps of a method for metering and on-line control of cement manufacturing water footprint in accordance with the present invention;
FIG. 2 is a block diagram of a metering and on-line control system for cement manufacturing water footprint in accordance with the present invention.
Detailed Description
The invention is further described in connection with the following detailed description in order to make the technical means, the creation characteristics, the achievement of the purpose and the effect of the invention easy to understand.
Example 1
Referring to fig. 1, the method for metering and controlling the water footprint of cement production according to the embodiment of the invention comprises the following steps:
The method comprises the steps of collecting water consumption data of the whole process in the cement production process in real time, constructing a cement production real-time water consumption database, and establishing a theoretical water consumption calculation model according to the real-time water consumption data;
the specific process of the method comprises the following steps:
firstly, the whole cement production process comprises three stages, namely a raw material preparation stage, a clinker calcination stage and a finished product treatment stage;
The raw material preparation stage comprises a crusher and a mill cooling circulating water system, wherein an electromagnetic flowmeter is arranged to collect cooling water circulation quantity, a temperature sensor monitors water inlet/return temperature (used for calculating evaporation loss), raw material storage yard dust settling water is used for measuring spraying water consumption through an ultrasonic flowmeter, and the evaporation quantity of the dust settling water is corrected by combining meteorological data (wind speed and air humidity);
The clinker calcination stage comprises the steps of arranging a vortex shedding flowmeter for monitoring cooling water consumption in real time, detecting water supply pressure (abnormal low-pressure early warning leakage) by a pressure sensor, measuring desulfurization and denitrification spray water consumption by a mass flowmeter, and monitoring pH value of circulating water by a pH sensor (guiding water quality adjustment);
the finished product treatment stage comprises the steps of cooling cement grinding system equipment, collecting closed circulation water flow by an electromagnetic flowmeter, monitoring water quality impurities by a conductivity sensor (judging whether water is needed to be changed or not), and calculating water consumption of a unit product by using dust fall of a finished product warehouse and water for stirring concrete by combining the ultrasonic flowmeter with wagon balance weighing data;
collecting water consumption data in real time, and particularly using a sensor to collect the water consumption data;
the sensor adopts an industrial level LoRaWAN wireless sensor network, supports multi-hop transmission, configures double-sensor redundant acquisition at a key water point, eliminates abnormal values through a data verification algorithm, and ensures data reliability;
wherein critical water usage points include, but are not limited to, rotary kiln cooling systems;
transmitting and synchronizing the collected water data;
Optionally, analyzing the sensor signal in real time through an edge computing gateway, converting the sensor signal into a unified data format, uploading the unified data format to a central server through an OPCUA protocol, setting the acquisition frequency to 1 time/10 seconds, and encrypting the high-frequency water using link (such as a spray tower) to 1 time/10 seconds to meet the real-time requirement of online control;
constructing a cement production real-time water database;
the method comprises the steps of constructing a data storage architecture according to a three-level catalogue of a production stage, equipment type and monitoring parameters, storing raw material preparation stage data in a raw material preparation water data table containing fields such as cooling circulating water quantity of a crusher, spraying water quantity of a raw material storage yard and the like, storing clinker calcination stage data in a clinker calcination water data table containing fields such as cooling water quantity of a rotary kiln and desulfurization and denitrification water quantity of a spray tower, storing finished product processing stage data in a finished product processing water data table containing fields such as cooling water quantity of a grinding system and dust settling water quantity of a finished product warehouse, and storing information such as acquisition time, equipment number, actual measurement value, verification state (valid/abnormal) and the like in each data record to support second-level data writing and millisecond-level query response;
Establishing a theoretical water consumption calculation model according to the real-time water consumption data;
The specific process for establishing the theoretical water consumption calculation model is as follows:
for continuous water environment under stable working conditions, such as rotary kiln supporting wheel bearing cooling and mill lubricating oil cooling systems, the water consumption and heat dissipation power and temperature difference are in clear physical relation, and a theoretical formula based on a physical mechanism is as follows:
Water for cooling equipment :Wherein P is the heat dissipation power of the device, c is the specific heat capacity of water,The temperature difference between the inlet and the outlet of cooling water is,In order for the leakage correction factor to be a function of,In order to cool the inlet temperature,Is the cooling water outlet temperature;
For nonlinear water links, such as dust spraying, LSTM modeling is adopted;
Taking dust spraying as an example for modeling process, inputting characteristics such as air humidity, dust concentration, yield and water consumption in the previous 3 hours in the current period, outputting a target such as theoretical spraying water consumption, collecting training data such as about 1 calendar history data (including normal working condition and abnormal working condition samples), and minimizing root mean square error by an Adam optimizer;
calculating the deviation rate of the real-time water consumption and the theoretical value, if the deviation is more than 15% in 3 continuous hours, triggering the model to learn automatically;
In summary, the steps of collecting raw material preparation, clinker calcination and finished product treatment full-process water data in cement production in real time, performing double-sensor redundancy collection at key water consumption points by using an industrial level LoRaWAN wireless sensor network, removing abnormal values by a data verification algorithm, analyzing by an edge computing gateway, uploading to a central server according to an OPCUA protocol, constructing a real-time water database stored according to a three-level catalog of production stage-equipment type-monitoring parameters, establishing a theoretical formula based on a physical mechanism for a continuous water environment under a stable working condition according to the real-time water data, modeling a nonlinear water link by adopting LSTM, establishing a theoretical water consumption computing model, calculating deviation rate of the real-time water consumption and the theoretical value, and triggering model self-learning or manually updating model coefficients under specific conditions;
The method has the advantages that the real-time, accurate and reliable acquisition and storage of the water data in the whole cement production process can be realized, the established theoretical water consumption calculation model can adapt to the characteristics of different water consumption links, and a solid data and model foundation is provided for the subsequent water consumption analysis and control;
The method has the advantages that the method provides real-time water consumption data and theoretical water consumption data for calculating deviation rate, and water consumption deviation analysis, abnormality judgment and other operations are preconditions and basis for water consumption deviation analysis;
step two, carrying out water deviation analysis on the real-time water consumption and the theoretical water consumption, judging whether the water deviation is abnormal, if so, carrying out stability analysis on the water deviation, and judging whether the water deviation is stable;
the specific process of the method comprises the following steps:
For each water flow link, carrying out deviation analysis in real time;
the specific process of carrying out deviation analysis is that the deviation rate E of the real-time water consumption and the theoretical water consumption is calculated in real time, and the calculation formula is as follows: wherein QZ is real-time water consumption, and QL is theoretical water consumption;
The theoretical water consumption is calculated by a theoretical water consumption calculation model;
comparing the deviation rate calculated in real time with a deviation rate limit interval, wherein the deviation rate limit interval is summarized and set by a person skilled in the art according to production specifications and historical production effects;
if the deviation rate is not in the deviation rate limit value interval, the deviation rate is larger than the theoretical water consumption, the abnormal event is judged, and the times of the abnormal event are counted;
calculating the times of normal events in the middle of adjacent abnormal events as the times of the interval events, and taking the average value of the times of all the interval events as the average value of the times of the interval events;
carrying out data fusion on the times of the abnormal events and the average value of the times of the interval events to obtain an abnormal judgment index;
Optionally, the data fusion may be performed by using a difference calculation, that is, performing a difference calculation on the average of the number of abnormal events and the number of interval events to obtain an abnormal judgment index;
comparing the abnormality judgment index with an abnormality judgment index limit value, wherein the abnormality judgment index limit value is summarized by a person skilled in the art according to the characteristics of the historical data;
If the abnormality judgment index is smaller than or equal to the abnormality judgment index limit value, the current water consumption is normal, and if the abnormality judgment index is larger than the abnormality judgment index limit value, the current water consumption is abnormal;
When the number of abnormal events is more and the average value of the number of interval events is smaller, the water flow link is abnormal, and the judgment of the stability of the water deviation is executed;
Specifically, the analysis and discrimination process of the horizontal deviation stability is as follows:
The time point corresponding to the current water consumption abnormal event is used as a starting point, and the deviation rate corresponding to all abnormal events is extracted forwards to be used as stability analysis data;
Acquiring a stationarity analysis data sequence, and judging whether a fitting curve of the stationarity analysis data sequence is a monotone trend or not by using a method combining a Spearman rank correlation coefficient (Spearman correlation coefficient) and a significance test;
It should be explained that, the Spearman rank correlation coefficient is a non-parameter statistic for measuring the monotonic relationship between two variables, if the fitted curve approaches to the level, the dependent variable does not change with the independent variable, the rank of the two does not have monotonic relationship, if the P value is greater than the significance level, meaning that there is no monotonic trend, otherwise, if the P value is less than the significance level, rejecting the original hypothesis, and considering that there is a significant monotonic relationship;
for calculating the Spearman rank correlation coefficient, the independent variable sequence is time x, and the dependent variable is the corresponding deviation rate y;
sorting independent variables and dependent variables respectively, and calculating rank order of each data point AndCalculating rank order difference,;
The Spearman rank correlation coefficient R is calculated by the following formula: wherein n is the number of samples;
wherein, the larger the absolute value is, the stronger the monotonic relation is, and R=0 indicates no monotonic relation;
if the Spearman rank correlation coefficient is in the correlation coefficient preset interval, the method shows that no obvious monotone trend exists, otherwise, the method shows that monotone relation exists;
it should be noted that the maximum value of the preset interval of the correlation coefficient is a positive value, the minimum value is a negative value, and both the maximum value and the minimum value approach zero;
the hypothesis test is set, and the original hypothesis is that the stability analysis data sequence has no monotonic trend;
calculating a P value through table lookup and statistical software, if the P value is larger than the significance level, judging that the original assumption is accepted, and judging that no significant monotone trend exists;
The P value is calculated by sampling distribution (such as permutation and combination based on rank order or asymptotic distribution) of the Spearman rank correlation coefficient;
Wherein the significance level may be set to 0.05;
in summary, if the Spearman rank correlation coefficient is within the correlation coefficient interval and the P value is greater than the significance level, it is indicated that the stability analysis data sequence has no monotonic trend;
based on the stability analysis data sequence, the sliding window variance analysis is carried out;
Dividing the stability analysis data sequence into a plurality of time windows on average, calculating the deviation rate variance of each time window, calculating the difference absolute value of the deviation rate variance of any two time windows, taking the difference absolute value as a variance difference value, and comparing with a variance difference value threshold;
the method comprises the steps of dividing a stationarity analysis data sequence into 3 time windows, respectively calculating deviation rate variances of the three time windows, namely a variance A, a variance B and a variance C, calculating difference values of two-by-two combinations based on the variance A, the variance B and the variance C, taking absolute values to obtain a plurality of variance difference values, and comparing the variance difference values with a variance difference value threshold;
if the variance difference value is larger than or equal to the difference value threshold, judging that the stability analysis data sequence is non-stable;
if the variance difference value is smaller than the difference value threshold, judging that the stability analysis data sequence is stable;
It is to be explained that the method based on the combination of Spearman rank correlation coefficient (Spearman correlation coefficient) and significance test firstly identifies whether a stationarity analysis data sequence is monotonous change, if so, the data sequence is unstable, if so, the data sequence is continuously changed stably based on sliding window variance analysis, and the key significance is that the method is characterized by covering two key dimensions of mean trend and variance stability, ensuring the comprehensiveness of stationarity judgment, optimizing the one-sided performance of a single method and improving the efficiency and accuracy of anomaly detection through the layering test, and is particularly suitable for distinguishing complex anomaly scenes in water flow;
In summary, the step calculates the deviation rate of the real-time water consumption and the theoretical water consumption in real time for each water flow link, compares the deviation rate with a limit value, and fuses the data of the average value of the abnormal event times and the interval event times to obtain an abnormal judgment index, so as to judge whether the water consumption is abnormal, if so, extracts the historical deviation rate data by taking an abnormal time point as a starting point, analyzes whether a monotonous trend exists by combining a Spearman rank correlation coefficient with a significance test, performs sliding window variance analysis on non-monotonous data, and finally judges whether the water consumption deviation is stable (no significant trend and stable variance) or non-stable (trend or variance fluctuation);
the method has the advantages that the method can quickly identify the specific link of water use abnormality through deviation rate calculation, abnormal event statistics and stability analysis, and provides basis for follow-up accurate control;
The method has the advantages that the key input is provided for the step three by defining the stability of the water deviation of the abnormal event, the stable change can adopt the average value proportion adjustment, the data of the fourth bit distance point is extracted by the non-stable change to be the proportion adjustment, the control strategy is more fit with the actual water characteristic, and the control precision and the production stability are improved;
Combining the Spearman rank correlation coefficient (average trend test) and sliding window variance analysis (fluctuation stability test), comprehensively judging the stability from two key dimensions, reducing the one-sided performance of a single method (such as only looking at average deviation), being particularly suitable for complex abnormal scenes of nonlinear water using links such as dust spraying, reducing misjudgment or missed judgment, and improving the robustness of the system;
The method has the advantages that through the trend analysis of the interval frequency (the average value of the interval event times) of the statistical abnormal events and the historical deviation data, early and progressive water consumption abnormality (such as slow rise of deviation rate caused by slight water leakage of equipment) can be identified, early warning is triggered before the problem is enlarged, enterprises are helped to check equipment faults or optimize technological parameters in advance, the risks of sudden water cut, equipment damage and the like are reduced, meanwhile, data support is provided for water saving technology improvement (such as nozzle replacement), and preventive water management is realized;
calculating a deviation ratio based on a stability judging result, calculating a water regulating quantity based on the deviation ratio, and executing a control instruction;
the method comprises two processes of calculating deviation proportion and executing control instruction;
the first specific process of calculating the deviation ratio is as follows:
If the stability analysis data sequence is stable, taking the mean value of the stability analysis data sequence as a deviation proportion;
If the stability analysis data sequence is unstable, arranging the stability analysis data in a sequence from small to large, counting the number of the stability analysis data, and extracting the stability analysis data of three-quarter number positions, namely, the deviation rate corresponding to the three-quarter number positions as a deviation proportion;
it should be noted that if three-quarters of the positions are non-integers, the back rounding is performed, that is, if three-quarters of the positions are 42.75, the deviation ratio corresponding to the position 43 is extracted as the deviation ratio;
The reason for the deviation rate corresponding to the three-quarter positions is that the first deviation rate can reduce the interference of extreme values, the second deviation rate can capture the overall trend, the smooth effect of the mean value on the high-frequency fluctuation can be avoided, and a clear regulating reference can be provided for the control strategy;
the second specific process of executing the control instruction is:
based on the deviation proportion, executing a control instruction, and specifically calculating the water regulating quantity QT by adopting a proportion regulating algorithm, wherein the calculation formula is as follows: Wherein, the method comprises the steps of, Is a proportionality coefficient, typically between 0 and 1, QL is the current theoretical water usage,Is the deviation proportion;
wherein, the Calibration according to water-using equipment characteristics, such as valve sensitivity and pipeline lag time;
It should be noted that, when executing the control instruction, a person skilled in the art sets an adjustment limit value interval range of the water use adjustment amount, and when the calculated water use adjustment amount is outside the adjustment limit value range, the interval limit value closest to the water use adjustment amount is selected, so that unstable cement production process caused by excessive adjustment can be reduced;
As an optional mode of this embodiment, if two devices are in the same direction deviation in the same water flow link, executing a device group linkage adjustment mechanism;
Alternatively, the number of equipment may be set to two, for example, the same direction deviation occurs in the 2 crusher cooling systems in the raw material preparation stage;
it should be explained that the homodromous deviation indicates that the difference value between the real-time water consumption and the theoretical water consumption of the plurality of devices is the same positive or the same negative;
taking the average value of the deviation proportions of all abnormal equipment, and calculating the total regulating quantity;
distributing the water usage adjustment amount according to the duty ratio of each abnormal device based on the calculated total water usage adjustment amount;
the duty ratio calculation mode of the abnormal equipment is that the ratio of the theoretical water consumption of each abnormal equipment to the sum of the theoretical water consumption of all abnormal equipment is used as the duty ratio of the abnormal equipment;
For each abnormal device, calculating the product of the duty ratio of the abnormal device and the total water consumption regulating quantity to obtain the water consumption regulating quantity of the abnormal device;
The method has the advantages that firstly, the total adjustment quantity is calculated by taking the average value of the deviation proportions of all abnormal equipment, a certain equipment is reduced to be excessively adjusted only according to the deviation degree of single equipment, the condition of each equipment is comprehensively considered in adjustment operation, the adjustment quantity is distributed according to the theoretical water consumption proportion of the abnormal equipment, the adjustment quantity is matched with the actual water consumption demand weight of the equipment, the unbalance problem caused by overlarge adjustment amplitude of the single equipment is prevented, and the operation balance among the equipment in the same link is maintained;
The method has the advantages that the total adjustment quantity is determined based on the deviation proportion average value, and the adjustment quantity is distributed by combining the theoretical water consumption proportion, so that the adjustment process is more reasonable, the integral level of equipment deviation is considered, the adjustment task is distributed according to the inherent water consumption characteristic of the equipment, the water consumption deviation can be corrected more accurately, the actual water consumption of each equipment is close to the theoretical value, and the water resource utilization efficiency is improved;
In summary, the step calculates the deviation ratio through the stability judging result and executes the control command, the average value of the stability analysis data sequence is taken as the deviation ratio when the stability is changed, the deviation ratio of three quarters of the bit distance is taken as the deviation ratio when the stability is changed, the water regulation quantity is calculated through the proportion regulation algorithm when the control command is executed, the regulation limit value interval is set at the same time, the nearest limit value is taken when the calculated value exceeds, and the influence of excessive regulation on the cement production stability is avoided;
The method has the advantages that a differential deviation proportion calculation mode is adopted aiming at different stationarity, the water adjustment quantity is used for adapting to actual demands, the stability and water use efficiency of a cement production process are guaranteed, a closed loop is formed by combining real-time acquisition of the first step, a theoretical model and deviation analysis of the second step, and the control precision of water management in the cement production process is improved.
Example 2
Based on the same inventive concept as the metering and on-line control method of a cement production water footprint in the foregoing embodiment, as shown in fig. 2, the present application provides a metering and on-line control system of cement production water footprint, wherein the system specifically includes:
The water consumption acquisition and calculation module 11 is used for acquiring the water consumption data of the whole process in the cement production process in real time, constructing a cement production real-time water consumption database and establishing a theoretical water consumption calculation model according to the real-time water consumption data;
The module is used for carrying out the following processes of collecting water data of the whole process of raw material preparation, clinker calcination and finished product treatment in cement production in real time, carrying out double-sensor redundancy collection at key water consumption points by using an industrial level LoRaWAN wireless sensor network, removing abnormal values by a data checking algorithm, analyzing by an edge computing gateway, uploading the abnormal values to a central server according to an OPCUA protocol, constructing a real-time water database stored according to a three-level catalogue of production stage-equipment type-monitoring parameters, establishing a theoretical formula based on a physical mechanism for a continuous water environment under a stable working condition according to the real-time water data, adopting LSTM modeling for a nonlinear water link, establishing a theoretical water consumption computing model, calculating the deviation rate of the real-time water consumption and the theoretical value, and triggering model self-learning or manually updating model coefficients under specific conditions;
The water analysis module 12 is used for carrying out water deviation analysis on the real-time water consumption and the theoretical water consumption, judging whether the water deviation is abnormal, if so, carrying out stability analysis on the water deviation, and judging whether the water deviation is stable;
Calculating the deviation rate of the real-time water consumption and the theoretical water consumption in real time for each water flow link, comparing the deviation rate with a limit value, fusing the data of the average value of the number of abnormal events and the average value of the number of interval events to obtain an abnormal judgment index, judging whether the water consumption is abnormal, if so, extracting historical deviation rate data by taking an abnormal time point as a starting point, analyzing whether a monotone trend exists through Spearman rank correlation coefficient and significance test, performing sliding window variance analysis on non-monotone data, and finally judging whether the water consumption deviation is stable change or non-stable change;
A control execution module 13 for calculating a deviation ratio based on the stability determination result, calculating a water adjustment amount based on the deviation ratio, and executing a control instruction;
The module is used for calculating the deviation ratio through the stability judging result and executing the control instruction, taking the average value of the stability analysis data sequence as the deviation ratio when the stability is changed, using the deviation ratio of three quarters of the bit distance as the deviation ratio when the stability is changed, calculating the water regulating quantity through the proportion regulating algorithm when the control instruction is executed, setting the regulating limit value interval, taking the nearest limit value when the calculated value exceeds, and avoiding the influence of the excessive regulation on the cement production stability. The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. The metering and on-line control method for the cement production water footprint is characterized by comprising the following steps of:
Collecting water consumption data of the whole process in the cement production process in real time, constructing a cement production real-time water consumption database, and establishing a theoretical water consumption calculation model according to the real-time water consumption data;
Carrying out water deviation analysis on the real-time water consumption and the theoretical water consumption, extracting abnormal events, judging whether the water consumption is abnormal or not according to two indexes of the abnormal events in the water consumption deviation and the interval event times of the abnormal events, and carrying out stability analysis on a water consumption deviation data sequence according to two aspects of trend and fluctuation if the water consumption is abnormal, and judging whether the water consumption deviation data is stable or not;
according to the stability judging result, calculating a deviation ratio of the stability result and the non-stability result respectively, calculating a water regulating quantity based on the deviation ratio, and executing a control instruction;
If the stability analysis data sequence is stable, taking the mean value of the stability analysis data sequence as a deviation proportion;
If the stability analysis data sequence is unstable, the stability analysis data are arranged in sequence from small to large, the quantity of the stability analysis data is counted, and the stability analysis data of three quarters of the quantity positions are extracted, namely, the deviation rate corresponding to the three quarters of the quantity positions is used as the deviation proportion.
2. The method for metering and controlling the water footprint of cement production on line according to claim 1, wherein the process of extracting the abnormal event is as follows:
Calculating the deviation rate of the real-time water consumption and the theoretical water consumption in real time, wherein the theoretical water consumption is calculated by a theoretical water consumption calculation model;
If the deviation rate is within the deviation rate limit section, it is determined as a normal event, and if the deviation rate is not within the deviation rate limit section, it is determined as an abnormal event.
3. The method for metering and controlling the water footprint of cement production on line according to claim 2, wherein the process for judging whether the water consumption is abnormal is as follows:
counting the times of abnormal events;
calculating the times of normal events in the middle of adjacent abnormal events as the times of the interval events, and taking the average value of the times of all the interval events as the average value of the times of the interval events;
And carrying out data fusion on the number of the abnormal events and the average value of the number of the interval events to obtain an abnormal judgment index, and judging whether the water consumption is abnormal or not according to an evaluation mechanism based on the abnormal judgment index.
4. The method for metering and controlling the water footprint of cement production on line according to claim 1, wherein the stability analysis is carried out by the following steps:
the time point corresponding to the current water use abnormal event is used as a starting point, and the deviation rate corresponding to all abnormal events is extracted forwards to be used as a stability analysis data sequence;
Firstly, judging whether a fitting curve of the stability analysis data sequence is a monotone trend or not, if so, judging that the fitting curve is not stable, if not, judging that the fitting curve is not stable, if so, judging that the fitting curve is not stable, and if not, judging that the fitting curve is stable.
5. The method for metering and controlling the water footprint of cement production on line according to claim 4, wherein the judging whether the water footprint is monotonous trend is carried out by the following steps:
And (3) using a method combining the Spearman rank correlation coefficient and the significance test, if the Spearman rank correlation coefficient is in a correlation coefficient interval and the P value is larger than the significance level, the stability analysis data sequence has no monotone trend, otherwise, the data sequence has the monotone trend.
6. The method for metering and controlling the water footprint of cement production on line according to claim 5, wherein the fluctuation judging process is as follows:
based on the stability analysis data sequence, the sliding window variance analysis is carried out;
Dividing the stability analysis data sequence into a plurality of time windows on average, calculating the deviation rate variance of each time window, calculating the difference absolute value of the deviation rate variance of any two time windows, and taking the difference absolute value as a variance difference value;
If the variance difference value is larger than or equal to the difference value threshold, the non-stationary change is performed, and if the variance difference value is smaller than the difference value threshold, the stationary change is performed.
7. The method for metering and controlling the water footprint of cement production on line according to claim 1, wherein the water adjustment amount is calculated by the following steps:
based on the deviation proportion, calculating the water regulating quantity QT by adopting a proportion regulating algorithm, wherein the calculation formula is as follows: Wherein, the method comprises the steps of, Is a proportionality coefficient, QL is the current theoretical water consumption,Is the deviation ratio.
8. The method for metering and controlling the water footprint of cement production according to claim 1, further comprising:
If the two devices are in the same direction deviation in the same water flow link, executing a device group linkage adjustment mechanism;
taking the average value of the deviation proportions of all abnormal equipment, and calculating the total regulating quantity;
Taking the ratio of the theoretical water consumption of each abnormal device to the sum of the theoretical water consumption of all abnormal devices as the duty ratio of the abnormal devices;
And for each abnormal device, calculating the product of the duty ratio of the abnormal device and the total water use regulating quantity to obtain the water use regulating quantity of the abnormal device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510748588.7A CN120257188B (en) | 2025-06-06 | 2025-06-06 | Metering and on-line control method for cement production water footprint |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510748588.7A CN120257188B (en) | 2025-06-06 | 2025-06-06 | Metering and on-line control method for cement production water footprint |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120257188A CN120257188A (en) | 2025-07-04 |
| CN120257188B true CN120257188B (en) | 2025-08-22 |
Family
ID=96181911
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510748588.7A Active CN120257188B (en) | 2025-06-06 | 2025-06-06 | Metering and on-line control method for cement production water footprint |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120257188B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011037253A (en) * | 2009-08-17 | 2011-02-24 | Tadahiko Murakami | Ready-mixed concrete controlling method by plurality of dynamic measurement values |
| CN102319612A (en) * | 2011-07-05 | 2012-01-18 | 中国科学院沈阳自动化研究所 | Method for intelligently controlling pressure difference of cement raw meal vertical mill |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE2855324C2 (en) * | 1978-12-21 | 1986-11-27 | Elba-Werk Maschinen-Gesellschaft Mbh & Co, 7505 Ettlingen | Process for regulating the addition of water during concrete preparation and device for carrying out the process |
| JP2000302492A (en) * | 1999-04-14 | 2000-10-31 | Taiheiyo Cement Corp | Cement-based composition for extrusion molding and extrusion molding product |
| AU2006261180A1 (en) * | 2005-06-17 | 2006-12-28 | Icrete, Llc | Methods and systems for redesigning pre-existing concrete mix designs and manufacturing plants and design-optimizing and manufacturing concrete |
| CN103226350B (en) * | 2013-04-22 | 2015-06-03 | 北京工业大学 | Metering and on-line control method of cement production water footprint |
| EP3112959B1 (en) * | 2015-06-29 | 2021-12-22 | SUEZ Groupe | Method for detecting anomalies in a water distribution system |
| CN111398089B (en) * | 2020-04-28 | 2025-03-11 | 成都天衡智造科技有限公司 | A device for automatically detecting the water content of sand and gravel |
| KR102700199B1 (en) * | 2020-09-11 | 2024-08-28 | 김범호 | Antibacterial cement based surface(wall) coating material with antibacterial properties and highly functional composite insulating materials for eco-friendly housing using the same |
| CN112819293B (en) * | 2021-01-14 | 2023-01-06 | 中国长江三峡集团有限公司 | Failure early warning analysis method for water reservoir scheduling rule under influence of climate change |
| CN114078339B (en) * | 2022-01-07 | 2022-05-31 | 北京航空航天大学杭州创新研究院 | A Grid Flight Conflict Detection Method Based on Flight Trend Reasoning |
| CN118331179A (en) * | 2023-12-29 | 2024-07-12 | 中控技术股份有限公司 | Cement firing system optimal control method based on industrial big data |
| CN119918797A (en) * | 2025-01-02 | 2025-05-02 | 燕山大学 | A real-time comprehensive performance evaluation method for cement calcination process |
| CN119671072A (en) * | 2025-02-21 | 2025-03-21 | 水利部水利水电规划设计总院 | An AI intelligent collaborative monitoring and management system for multi-indicator water quantity system |
-
2025
- 2025-06-06 CN CN202510748588.7A patent/CN120257188B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011037253A (en) * | 2009-08-17 | 2011-02-24 | Tadahiko Murakami | Ready-mixed concrete controlling method by plurality of dynamic measurement values |
| CN102319612A (en) * | 2011-07-05 | 2012-01-18 | 中国科学院沈阳自动化研究所 | Method for intelligently controlling pressure difference of cement raw meal vertical mill |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120257188A (en) | 2025-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110320892B (en) | Fault diagnosis system and method for sewage treatment equipment based on Lasso regression | |
| CN118336930B (en) | Electric power carbon emission early warning and response system | |
| CN112021626B (en) | Intelligent control system and method for tobacco shred making link | |
| CN117871771B (en) | Big data-based gas energy monitoring method | |
| CN106917742B (en) | A kind of air compressor energy-saving amount monitoring system and amount of energy saving remote upload method | |
| CN116320833B (en) | Heat supply pipe network monitoring method based on Internet of things technology | |
| CN118133017B (en) | Intelligent prediction system and prediction algorithm for energy consumption in industrial production process | |
| CN104504238A (en) | Method for predicting nitrogen oxide emission concentration of coal-fired unit based on neural network | |
| CN118900275A (en) | Industrial Internet cloud platform based on data intelligence | |
| CN116303391A (en) | Processing method for remote transmission of electric energy time sequence data by intelligent ammeter | |
| CN119558206A (en) | Intelligent refrigerating system efficiency optimization method, system and device based on deep learning | |
| CN117196120A (en) | Water consumption behavior analysis algorithm for user | |
| CN119225252A (en) | A multi-dimensional monitoring and energy-saving analysis and control method for a coating system | |
| CN118915677A (en) | Method for monitoring production process of numerical control machine tool casting | |
| CN118734614A (en) | An energy-saving optimization control method and system for screw air compressor station based on AI technology | |
| CN119758934A (en) | Intelligent electromechanical monitoring system based on industrial Internet | |
| CN118586552A (en) | A water resource water consumption verification and planned water consumption management system | |
| CN119468584A (en) | A circulating cooling water system integrating big data and artificial intelligence | |
| Wen et al. | A dual energy benchmarking methodology for energy-efficient production planning and operation of discrete manufacturing systems using data mining techniques | |
| CN119373672B (en) | Wind power generation equipment running state monitoring system | |
| CN119920363A (en) | Soft measurement method, system, medium and program product for flue gas flow of coal-fired boiler | |
| CN120181605A (en) | A method for network collaboration of expandable integrators | |
| CN120257188B (en) | Metering and on-line control method for cement production water footprint | |
| CN117869278B (en) | Energy-saving control method and system for air compressor unit | |
| CN111174824B (en) | A management and control platform for acid mist emission |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |