Data calibration method for a temperature, pressure, flow rate and humidity integrated monitor

Abstract

The present application provides a data correction method for a temperature, pressure, flow rate, and humidity integrated monitor, which relates to the technical field of data processing. The method includes: arranging the temperature, pressure, flow rate, and humidity integrated monitor according to the regional layout characteristics to obtain L temperature, pressure, flow rate, and humidity monitoring modules; performing real-time monitoring on the target area to obtain L sets of temperature, pressure, flow rate, and humidity monitoring data; performing acquisition process penalty correction to obtain an initial temperature, pressure, flow rate, and humidity correction data set; performing monitoring operation characteristic penalty correction according to the initial temperature, pressure, flow rate, and humidity correction data set to obtain a strengthened temperature, pressure, flow rate, and humidity correction data set; and drawing a global node temperature, pressure, flow rate, and humidity monitoring cloud map. Through the present application, the technical problem that due to the single data correction method and low intelligence level, data deviation cannot be accurately identified and corrected, resulting in large errors in temperature, pressure, flow rate, and humidity monitoring data can be solved. The accuracy and comprehensiveness of monitoring data correction can be improved, thereby improving the data monitoring quality and ensuring the authenticity and reliability of temperature, pressure, flow rate, and humidity monitoring data.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly relates to a data correction method for a temperature, pressure, flow rate, and humidity integrated monitor. Background Art

[0002] A temperature, pressure, flow rate, and humidity integrated monitor is a device specifically used for monitoring flue gas emissions. It can measure the temperature, pressure, flow rate, and humidity of flue gas in real time and provide data of these parameters through a specific signal output method. This instrument usually consists of a temperature sensor, a pressure sensor, a flow sensor, and a humidity sensor, and these sensors measure the target parameters through their respective working principles.

[0003] However, due to the interference of factors such as the external environment and the accuracy of the device itself, any measurement device may have monitoring errors. Therefore, data correction is also required when the temperature, pressure, flow rate, and humidity integrated monitor conducts data monitoring to ensure the accuracy and reliability of the monitoring data.

[0004] Currently, for the data correction method of the existing temperature, pressure, flow rate, and humidity integrated monitor, due to the single data correction method and low degree of intelligence, it is unable to accurately identify and correct data deviations, resulting in the technical problem of large errors in the temperature, pressure, flow rate, and humidity monitoring data. Summary of the Invention

[0005] The purpose of this application is to provide a data correction method for a temperature, pressure, flow rate, and humidity integrated monitor to solve the technical problem that the existing data correction method for the temperature, pressure, flow rate, and humidity integrated monitor, due to the single data correction method and low degree of intelligence, is unable to accurately identify and correct data deviations, resulting in large errors in the temperature, pressure, flow rate, and humidity monitoring data.

[0006] In view of the above problems, this application provides a data correction method for a temperature, pressure, flow rate, and humidity integrated monitor. The method includes: obtaining the regional layout feature information of the target area; arranging the temperature, pressure, flow rate, and humidity integrated monitor in the target area according to the regional layout feature information to obtain L temperature, pressure, flow rate, and humidity integrated monitoring modules corresponding to L regional monitoring nodes, where L is a positive integer greater than 1; performing real-time monitoring on the target area according to the L temperature, pressure, flow rate, and humidity integrated monitoring modules to obtain L sets of temperature, pressure, flow rate, and humidity monitoring data; performing acquisition process penalty correction on the L sets of temperature, pressure, flow rate, and humidity monitoring data to obtain an initial temperature, pressure, flow rate, and humidity correction data set; performing monitoring operation feature penalty correction on the initial temperature, pressure, flow rate, and humidity correction data set to obtain a strengthened temperature, pressure, flow rate, and humidity correction data set; and drawing a global node temperature, pressure, flow rate, and humidity monitoring cloud map according to the strengthened temperature, pressure, flow rate, and humidity correction data set.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] By obtaining the regional layout feature information of the target area; arranging the temperature, pressure, flow, and humidity integrated monitor for the target area according to the regional layout feature information to obtain L temperature, pressure, flow, and humidity integrated monitoring modules corresponding to L regional monitoring nodes, where L is a positive integer greater than 1; performing real-time monitoring on the target area according to the L temperature, pressure, flow, and humidity integrated monitoring modules to obtain L sets of temperature, pressure, flow, and humidity monitoring data; performing acquisition process penalty correction on the L sets of temperature, pressure, flow, and humidity monitoring data to obtain an initial temperature, pressure, flow, and humidity correction data set; performing monitoring operation feature penalty correction on the initial temperature, pressure, flow, and humidity correction data set to obtain a strengthened temperature, pressure, flow, and humidity correction data set; and drawing a global node temperature, pressure, flow, and humidity monitoring cloud map according to the strengthened temperature, pressure, flow, and humidity correction data set. That is to say, by performing acquisition process offset analysis to determine the acquisition process penalty factor and correcting the monitoring data according to the acquisition process penalty factor to obtain the initial temperature, pressure, flow, and humidity correction data set, data errors caused by improper operation during the acquisition process can be reduced or avoided; then performing monitoring operation feature offset analysis to determine the monitoring operation penalty factor and correcting the initial temperature, pressure, flow, and humidity correction data set to obtain the strengthened temperature, pressure, flow, and humidity correction data set, data errors caused by equipment status and environmental interference can be reduced or avoided; and finally drawing a global node temperature, pressure, flow, and humidity monitoring cloud map according to the strengthened temperature, pressure, flow, and humidity correction data set. The accuracy and comprehensiveness of the temperature, pressure, flow, and humidity monitoring data correction can be improved, thereby improving the data monitoring quality and ensuring the authenticity and reliability of the temperature, pressure, flow, and humidity monitoring data.

[0009] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of this application more obvious and understandable, the following specifically gives the specific implementation manners of this application. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of this application, nor is it used to limit the scope of this application. Other features of this application will become easily understood through the following description of the specification. Brief Description of the Drawings

[0010] In order to more clearly illustrate the technical solutions in this application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings described below are only exemplary, and for those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0011] Figure 1 It is a schematic flowchart of a data correction method for a temperature, pressure, flow, and humidity integrated monitor of this application;

[0012] Figure 2This is a schematic flowchart for obtaining the initial calibration dataset of temperature, pressure, flow rate, and humidity in a data calibration method for a temperature, pressure, flow rate, and humidity integrated monitor of this application. Detailed implementation manner

[0013] By providing a data calibration method for a temperature, pressure, flow rate, and humidity integrated monitor, this application solves the technical problem that the existing data calibration method for a temperature, pressure, flow rate, and humidity integrated monitor cannot accurately identify and correct data deviations due to a single data calibration method and low intelligence level, resulting in large errors in temperature, pressure, flow rate, and humidity monitoring data. It can improve the accuracy and comprehensiveness of temperature, pressure, flow rate, and humidity monitoring data calibration, thereby improving the data monitoring quality and ensuring the authenticity and reliability of temperature, pressure, flow rate, and humidity monitoring data.

[0014] Next, the technical solutions in this application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments of this application. It should be understood that this application is not limited by the example embodiments described here. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application. Additionally, it should be noted that for the sake of description, only the parts related to this application are shown in the accompanying drawings rather than all of them.

[0015] Embodiment

[0016] Please refer to the attached Figure 1 , this application provides a data calibration method for a temperature, pressure, flow rate, and humidity integrated monitor, and the method specifically includes the following steps:

[0017] Step 1: Obtain the regional layout feature information of the target area;

[0018] Specifically, the temperature, pressure, flow rate, and humidity integrated monitor is a new generation of on-line monitoring instrument, a measuring instrument for measuring temperature, flue gas pressure, flow rate, and humidity. Among them, the flow rate is designed based on the differential pressure measurement principle of a traditional pitot tube; the humidity is measured using the principle of a humidity-sensitive capacitor (realize temperature control and heating of the humidity probe to prevent condensation and protect the sensor), and can on-line monitor the gas flow rate, dynamic pressure, flue gas pressure, temperature, and humidity of various boilers, furnace flues, and mine exhaust ducts, etc., and is mainly applied to CEMS and VOC systems.

[0019] First, determine the target area, where the target area refers to the area where temperature, pressure, flow and humidity data monitoring is to be carried out, such as: furnace flue, mine exhaust duct, refinery, turbine, lime kiln, power boiler, etc., which can be set according to the actual situation; then analyze the regional layout characteristics of the target area to obtain the regional layout characteristic information of the target area, where the regional layout characteristic information includes the spatial planning and component structure in the region, such as: the regional layout characteristic information of the furnace flue mainly involves the design, structure, function of the flue and its positional relationship in the furnace system. By obtaining the regional layout characteristic information, it provides a basis for the subsequent precise deployment of the temperature, pressure, flow and humidity integrated monitoring instrument.

[0020] Step 2: deploying the temperature-pressure-flow-humidity integrated monitoring instrument in the target area according to the regional layout characteristic information, and obtaining L temperature-pressure-flow-humidity integrated monitoring modules corresponding to L regional monitoring nodes, where L is a positive integer greater than 1;

[0021] Specifically, based on the regional layout characteristic information, the temperature-pressure-flow-humidity integrated monitoring instrument is deployed in the target area, that is, based on the regional characteristic information, representative monitoring points are selected, which should be able to reflect the environmental conditions of different functional areas and try to avoid being affected by local factors; then, according to the number and location of the monitoring points, the layout of the monitoring network is planned to ensure that the monitoring network can cover the entire target area, and consider the mutual influence and complementarity between the monitoring points to reduce repeated monitoring and blind spots; obtain L temperature-pressure-flow-humidity integrated monitoring modules corresponding to L regional monitoring nodes, wherein each temperature-pressure-flow-humidity integrated monitoring module includes a temperature-pressure-flow-humidity integrated monitoring instrument, wherein L is a positive integer greater than 1, and the specific value of L can be set according to the actual situation of the target area. By deploying the temperature-pressure-flow-humidity integrated monitoring instrument according to the regional layout characteristic information, the accuracy of the deployment of the temperature-pressure-flow-humidity integrated monitoring instrument can be improved, thereby improving the accuracy of the temperature-pressure-flow-humidity monitoring data.

[0022] Step 3: Perform real-time monitoring of the target area according to the L temperature-pressure-flow-humidity integrated monitoring modules to obtain L groups of temperature-pressure-flow-humidity monitoring data;

[0023] Specifically, the target area is monitored in real time through the L integrated temperature, pressure, flow and humidity monitoring modules to obtain L groups of temperature, pressure, flow and humidity monitoring data, wherein each group of temperature, pressure, flow and humidity monitoring data includes temperature monitoring data, pressure monitoring data, flow rate monitoring data and humidity monitoring data.

[0024] Step 4: Performing collection process penalty correction based on the L groups of temperature, pressure, flow and humidity monitoring data to obtain an initial correction data set of temperature, pressure, flow and humidity;

[0025] Specifically, collect the acquisition process monitoring data of the L groups of temperature, pressure, flow rate, and humidity monitoring data, and then perform offset analysis on the data acquisition process based on the acquisition process monitoring data to determine the acquisition process penalty factor. Further, perform acquisition process penalty correction on the L groups of temperature, pressure, flow rate, and humidity monitoring data according to the acquisition process penalty factor to obtain the initial temperature, pressure, flow rate, and humidity correction data set. By performing offset analysis on the data acquisition process to determine the acquisition process penalty factor and correcting the temperature, pressure, flow rate, and humidity monitoring data according to the acquisition process penalty factor, data errors caused by improper operation during the acquisition process can be reduced or avoided, and the accuracy of data correction can be improved.

[0026] Step Five: Perform monitoring operation feature penalty correction based on the initial temperature, pressure, flow rate, and humidity correction data set to obtain the enhanced temperature, pressure, flow rate, and humidity correction data set;

[0027] Specifically, then perform offset analysis on the monitoring operation features based on the initial temperature, pressure, flow rate, and humidity correction data set to obtain the parameter monitoring operation penalty factor; further perform data correction on the initial temperature, pressure, flow rate, and humidity correction data set according to the parameter monitoring operation penalty factor to obtain the enhanced temperature, pressure, flow rate, and humidity correction data set. By performing offset analysis on the monitoring operation features to determine the parameter monitoring operation penalty factor and performing data correction on the initial temperature, pressure, flow rate, and humidity correction data set based on the parameter monitoring operation penalty factor, data errors caused by equipment status and environmental interference can be reduced or avoided, thereby improving the accuracy of data correction.

[0028] Step Six: Draw the global node temperature, pressure, flow rate, and humidity monitoring cloud map based on the enhanced temperature, pressure, flow rate, and humidity correction data set.

[0029] Specifically, finally, based on the three-dimensional visualization technology, draw the monitoring cloud map of the target area according to the enhanced temperature, pressure, flow rate, and humidity correction data set to obtain the global node temperature, pressure, flow rate, and humidity monitoring cloud map.

[0030] By the above method, the technical problem that the data correction method of the existing temperature, pressure, flow and humidity integrated monitor cannot accurately identify and correct data deviation due to the single data correction method and low intelligence, resulting in large errors in the temperature, pressure, flow and humidity monitoring data can be solved. First, obtain the regional layout feature information of the target area; then, deploy the temperature, pressure, flow and humidity integrated monitor in the target area according to the regional layout feature information to obtain L temperature, pressure, flow and humidity integrated monitoring modules corresponding to L regional monitoring nodes, where L is a positive integer greater than 1; then, perform real-time monitoring on the target area according to the L temperature, pressure, flow and humidity integrated monitoring modules to obtain L sets of temperature, pressure, flow and humidity monitoring data; then, perform acquisition process penalty correction according to the L sets of temperature, pressure, flow and humidity monitoring data to obtain an initial temperature, pressure, flow and humidity correction data set; further, perform monitoring operation feature penalty correction according to the initial temperature, pressure, flow and humidity correction data set to obtain a strengthened temperature, pressure, flow and humidity correction data set; finally, draw a global node temperature, pressure, flow and humidity monitoring cloud map according to the strengthened temperature, pressure, flow and humidity correction data set. By performing acquisition process offset analysis to determine the acquisition process penalty factor and correcting the monitoring data according to the acquisition process penalty factor, an initial temperature, pressure, flow and humidity correction data set can be obtained, which can reduce or avoid data errors caused during the acquisition process; then perform monitoring operation feature offset analysis to determine the monitoring operation penalty factor and perform data correction on the initial temperature, pressure, flow and humidity correction data set to obtain a strengthened temperature, pressure, flow and humidity correction data set, which can reduce or avoid data errors caused by equipment status and environmental interference; finally, draw a global node temperature, pressure, flow and humidity monitoring cloud map according to the strengthened temperature, pressure, flow and humidity correction data set. The accuracy and comprehensiveness of temperature, pressure, flow and humidity monitoring data correction can be improved, thereby improving the data monitoring quality and ensuring the authenticity and reliability of temperature, pressure, flow and humidity monitoring data.

[0031] Further, as shown in the appendix Figure 2 Step four of the present application includes:

[0032] Perform standardization processing on the L sets of temperature, pressure, flow and humidity monitoring data to obtain L temperature, pressure, flow and humidity monitoring standard groups;

[0033] Extract the first temperature, pressure, flow and humidity monitoring standard group from the L temperature, pressure, flow and humidity monitoring standard groups, where the first temperature, pressure, flow and humidity monitoring standard group is any one of the L temperature, pressure, flow and humidity monitoring standard groups;

[0034] Retrieve the acquisition process monitoring data corresponding to the first temperature, pressure, flow and humidity monitoring standard group;

[0035] Perform acquisition process offset analysis according to the acquisition process monitoring data to determine the acquisition process penalty factor;

[0036] Specifically, first, standardize the L groups of temperature, pressure, flow, and humidity monitoring data based on a predetermined data cleaning strategy. The predetermined data cleaning strategy includes missing value supplementation, redundant anomaly elimination, etc., which can be set according to actual needs, and obtain L standard groups of temperature, pressure, flow, and humidity monitoring after data cleaning is completed. Then, within the L standard groups of temperature, pressure, flow, and humidity monitoring, select the first standard group of temperature, pressure, flow, and humidity monitoring, where the first standard group of temperature, pressure, flow, and humidity monitoring is any one of the L standard groups of temperature, pressure, flow, and humidity monitoring. Further, retrieve the acquisition process monitoring data corresponding to the first standard group of temperature, pressure, flow, and humidity monitoring. The acquisition process monitoring data includes acquisition process monitoring images and acquisition transmission processing monitoring data. Then, perform acquisition process offset analysis based on the acquisition process monitoring data. The acquisition process offset analysis refers to analyzing the deviation of improper operation steps or states during the acquisition process, such as improper placement of the sensor probe, failure to perform initialization calibration before using the sensor, etc., and determine the acquisition process penalty factor.

[0037] Further, the present application further includes the following steps:

[0038] The acquisition process monitoring data includes acquisition process monitoring images and acquisition transmission processing monitoring data;

[0039] Perform acquisition process anomaly focusing based on the acquisition process monitoring images to obtain acquisition process anomaly feature data;

[0040] Perform temperature, pressure, flow, and humidity impact association based on the acquisition process anomaly feature data to obtain acquisition process impact association feature information;

[0041] Perform anomaly detection based on the acquisition transmission processing monitoring data to obtain acquisition processing anomaly feature data;

[0042] Perform temperature, pressure, flow, and humidity impact analysis based on the acquisition processing anomaly feature data to obtain acquisition processing anomaly impact feature information;

[0043] Fuse the acquisition process impact association feature information and the acquisition processing anomaly impact feature information to obtain the acquisition process penalty factor.

[0044] Specifically, the method for analyzing the offset of the acquisition process and determining the acquisition process penalty factor based on the monitored data of the acquisition process is as follows. First, obtain the monitored data of the acquisition process, which includes the monitored images of the acquisition process and the monitored data of acquisition transmission and processing. Then, perform abnormal focusing on the acquisition process based on the monitored images of the acquisition process. Abnormal focusing on the acquisition process refers to analyzing possible abnormal operation states during the acquisition process, such as improper placement of the sensor probe, unreasonable position of the air flow port, and failure to perform initialization calibration on the sensor before use, etc., to obtain the abnormal feature data of the acquisition process. Further, perform an impact correlation analysis of temperature, pressure, flow rate, and humidity based on the abnormal feature data of the acquisition process, that is, perform an impact correlation analysis on the deviation of the temperature, pressure, flow rate, and humidity monitoring data according to the abnormal feature data of the acquisition process. Existing statistical methods such as correlation analysis, regression analysis, or time series analysis can be used to quantify the degree of correlation between the abnormal feature data of the acquisition process and the deviation of the monitoring data, and obtain the impact correlation feature information of the acquisition process.

[0045] Perform abnormal detection based on the monitored data of acquisition transmission and processing. Among them, abnormal detection refers to analyzing the errors during data transmission and data processing. For example, errors may also occur during the transmission and processing of data collected from the monitor, such as packet loss during data transmission or inaccurate processing algorithms, etc., to obtain the abnormal feature data of acquisition processing. Then, perform an impact analysis of temperature, pressure, flow rate, and humidity based on the abnormal feature data of acquisition processing, that is, use existing statistical methods such as correlation analysis, regression analysis, or time series analysis to quantify the degree of correlation between the abnormal feature data of acquisition processing and the deviation of the monitoring data, and obtain the abnormal impact feature information of acquisition processing. Finally, fuse the impact correlation feature information of the acquisition process and the abnormal impact feature information of acquisition processing. That is, if there are the same or similar information in the impact correlation feature information of the acquisition process and the abnormal impact feature information of acquisition processing, only retain one to obtain the acquisition process penalty factor.

[0046] Correct the first temperature, pressure, flow rate, and humidity monitoring standard group according to the acquisition process penalty factor to generate the initial temperature, pressure, flow rate, and humidity correction data set.

[0047] Specifically, based on the acquisition process penalty factor, perform data correction on the first temperature, pressure, flow rate, and humidity monitoring standard group to obtain the initial temperature, pressure, flow rate, and humidity correction data set.

[0048] Furthermore, the present application further includes the following steps:

[0049] Retrieve the sample acquisition process penalty factor set and the sample acquisition process penalty compensation data set;

[0050] Based on the preset compensator establishment conditions, a collection process penalty compensator is built according to the sample collection process penalty factor set and the sample collection process penalty compensation data set. The preset compensator establishment conditions include a predetermined data division weight and a predetermined training convergence condition;

[0051] Input the collection process penalty factor into the collection process penalty compensator to obtain collection process penalty compensation data;

[0052] Compensate and optimize the first temperature, pressure, flow, and humidity monitoring standard group according to the collection process penalty compensation data to obtain the first temperature, pressure, flow, and humidity monitoring correction group;

[0053] Add the first temperature, pressure, flow, and humidity monitoring correction group to the temperature, pressure, flow, and humidity initial correction data set.

[0054] Specifically, first, retrieve the sample collection process penalty factor set and the sample collection process penalty compensation data set. The sample collection process penalty factors and the sample collection process penalty compensation data are in one-to-one correspondence and can be retrieved based on big data for information retrieval, or retrieved from historical monitoring logs for information extraction.

[0055] Build a collection process penalty compensator based on the BP neural network and the preset compensator establishment conditions. The collection process penalty compensator is a neural network model in machine learning that can be iteratively optimized and is obtained through supervised training with a data set. The collection process penalty compensator includes an input layer, multiple hidden layers, and an output layer. The input data of the input layer is the collection process penalty factor, and the output data is the collection process penalty compensation data. The preset compensator establishment conditions include a predetermined data division weight and a predetermined training convergence condition. The predetermined data division weight includes a training data weight and a validation data weight, which can be set according to the actual situation. For example, the training data weight is 0.8 and the validation data weight is 0.2, that is, the training data accounts for 80% and the validation data accounts for 20%. The predetermined training convergence condition is the expected output accuracy, which can be set according to actual requirements. For example, set the expected output accuracy to 93%. Use the sample collection process penalty factor set and the sample collection process penalty compensation data set as the sample data set; divide the sample data set according to the predetermined data division weight to obtain a sample training set and a sample validation set; then perform supervised training on the collection process penalty compensator based on the sample training set. When the collection process penalty compensator tends to a converged state, then use the sample validation set to perform validation training on the collection process penalty compensator until the output accuracy is greater than or equal to the predetermined training convergence condition to obtain the trained collection process penalty compensator.

[0056] Next, input the acquisition process penalty factor into the acquisition process penalty compensator to obtain acquisition process penalty compensation data; and further optimize the data compensation of the first temperature, pressure, flow rate, and humidity monitoring standard group according to the acquisition process penalty compensation data to obtain the first temperature, pressure, flow rate, and humidity monitoring correction group; then add the first temperature, pressure, flow rate, and humidity monitoring correction group to the initial temperature, pressure, flow rate, and humidity correction data set to obtain the initial temperature, pressure, flow rate, and humidity correction data set. By constructing an acquisition process penalty compensator based on a BP neural network to analyze the acquisition process penalty compensation data, the efficiency and accuracy of obtaining the acquisition process penalty compensation data can be improved, thereby improving the accuracy and efficiency of the temperature, pressure, flow rate, and humidity monitoring data correction.

[0057] Further, step five of this application includes:

[0058] Based on the initial temperature, pressure, flow rate, and humidity correction data set, perform a retrospective analysis of the monitoring operation characteristics of each parameter to obtain a data set of the monitoring operation characteristics of each parameter;

[0059] According to the data set of the monitoring operation characteristics of each parameter, perform an analysis of the deviation of the monitoring operation characteristics to generate a penalty factor for the monitoring operation of each parameter;

[0060] Specifically, first, based on the initial temperature, pressure, flow rate, and humidity correction data set, perform a retrospective analysis of the monitoring operation characteristics of each parameter, that is, collect the monitoring instrument status data and monitoring instrument environment data corresponding to each parameter in the initial temperature, pressure, flow rate, and humidity correction data set, where each parameter includes a temperature parameter, a pressure parameter, a flow rate parameter, and a humidity parameter, and each type of parameter corresponds to a different monitoring instrument, including a temperature sensor, a pressure sensor, a flow meter, and a humidity sensor; obtain a data set of the monitoring operation characteristics of each parameter. Then, according to the data set of the monitoring operation characteristics of each parameter, perform an analysis of the deviation of the monitoring operation characteristics, and obtain a penalty factor for the monitoring operation of each parameter according to the deviation analysis result.

[0061] Further, this application also includes the following steps:

[0062] According to the temperature, pressure, flow rate, and humidity integrated monitor, perform a benchmark analysis of the multi-parameter monitoring operation characteristics to construct a multi-dimensional monitoring operation characteristics benchmark matrix;

[0063] Specifically, the method for generating a penalty factor for the monitoring operation of each parameter by performing an analysis of the deviation of the monitoring operation characteristics according to the data set of the monitoring operation characteristics of each parameter is as follows. First, perform a benchmark analysis of the multi-parameter monitoring operation characteristics according to the temperature, pressure, flow rate, and humidity integrated monitor, where the benchmark analysis of the parameter monitoring operation characteristics refers to an analysis of the normal operation state corresponding to the parameter, and then construct a multi-dimensional monitoring operation characteristics benchmark matrix based on the benchmark analysis result.

[0064] Further, this application also includes the following steps:

[0065] Extract the first feature monitoring component according to the temperature, pressure, flow rate and humidity integrated monitor, where the temperature, pressure, flow rate and humidity integrated monitor includes a plurality of feature monitoring components corresponding to a plurality of feature monitoring indicators, and the first feature monitoring component is any one of the plurality of feature monitoring components;

[0066] Perform global backtracking of the normal samples of the monitoring operation features according to the first feature monitoring component to obtain the first component normal operation feature sample set;

[0067] Perform central tendency analysis according to the first component normal operation feature sample set to obtain the first component normal operation feature central interval set;

[0068] Construct the first component monitoring operation feature reference matrix according to the first component normal operation feature central interval set, and add the first component monitoring operation feature reference matrix to the multi-dimensional monitoring operation feature reference matrix.

[0069] Specifically, first, extract the first feature monitoring component in the temperature, pressure, flow rate and humidity integrated monitor. The temperature, pressure, flow rate and humidity integrated monitor includes a plurality of feature monitoring components corresponding to a plurality of feature monitoring indicators. The first feature monitoring component is any one of the plurality of feature monitoring components. The plurality of feature monitoring indicators include temperature parameters, pressure parameters, flow rate parameters and humidity parameters. The plurality of feature monitoring components include temperature sensors, pressure sensors, flow meters and humidity sensors.

[0070] Then perform global backtracking of the normal samples of the monitoring operation features according to the first feature monitoring component, that is, call the historical monitoring log, collect the first feature monitoring component, and the historical monitoring component state data and historical monitoring component environment data corresponding to the same model components of the first feature monitoring component when they are in the historical normal state, to obtain the first component normal operation feature sample set. Further perform central tendency analysis according to the first component normal operation feature sample set. Central tendency analysis refers to determining the balanced form in which the first component normal operation feature sample set concentrates towards the central position. Commonly used central tendency analysis methods include the average method, the median method, the mode method, etc. An appropriate method can be selected according to the actual scenario to obtain the first component normal operation feature central interval set, where the first component normal operation feature central interval refers to the normal fluctuation range of the operation features. Then construct the first component monitoring operation feature reference matrix according to the first component normal operation feature central interval set, and add the first component monitoring operation feature reference matrix to the multi-dimensional monitoring operation feature reference matrix to obtain the multi-dimensional monitoring operation feature reference matrix.

[0071] Perform standardization processing on each parameter monitoring operation feature data set to construct each parameter monitoring operation feature matrix;

[0072] Perform correlation mapping on the multi-dimensional monitoring operation feature reference matrix based on the monitoring operation feature matrix of each parameter to determine the reference matrix corresponding to each parameter;

[0073] Perform deviation calculation on the monitoring operation feature matrix of each parameter based on the reference matrix corresponding to each parameter to obtain the monitoring operation feature deviation matrix of each parameter;

[0074] Perform influence identification on each parameter according to the monitoring operation feature deviation matrix of each parameter to obtain the monitoring operation penalty factor of each parameter.

[0075] Specifically, first, perform standardization processing on the monitoring operation feature dataset of each parameter based on a predetermined data cleaning strategy. The predetermined data cleaning strategy includes missing value supplementation, redundant anomaly elimination, etc., which can be set according to actual needs; then construct the monitoring operation feature matrix of each parameter based on each standardized monitoring operation feature dataset of the parameter.

[0076] Then perform correlation mapping on the multi-dimensional monitoring operation feature reference matrix based on the monitoring operation feature matrix of each parameter, that is, establish a one-to-one correspondence between the monitoring operation feature of the parameter and the interval in the normal operation feature set to determine the reference matrix corresponding to each parameter. Further, perform deviation calculation on the monitoring operation feature matrix of each parameter based on the reference matrix corresponding to each parameter. That is, when the monitoring operation feature of the parameter is not within the interval of the normal operation feature set, calculate the feature deviation between the interval of the normal operation feature set and the monitoring operation feature of the parameter. The feature deviation includes the deviation greater than the upper limit of the interval and the deviation less than the lower limit of the interval to obtain the monitoring operation feature deviation matrix of each parameter. Finally, perform influence identification on each parameter according to the monitoring operation feature deviation matrix of each parameter, that is, quantify the influence of the monitoring operation feature deviation of each parameter on the accuracy of each parameter data monitoring, and extract the monitoring operation feature of the parameter whose influence degree is greater than the predetermined influence degree threshold as the monitoring operation penalty factor of the parameter to obtain the monitoring operation penalty factor of each parameter.

[0077] Build a monitoring operation penalty compensator;

[0078] Based on the monitoring operation penalty factor of each parameter, perform penalty compensation analysis according to the monitoring operation penalty compensator to obtain the monitoring operation penalty compensation data of each parameter;

[0079] Perform mapping compensation on each parameter of the initial temperature, pressure, flow, and humidity correction dataset according to the monitoring operation penalty compensation data of each parameter to obtain the enhanced temperature, pressure, flow, and humidity correction dataset.

[0080] Specifically, a monitoring operation penalty compensator is constructed based on a BP neural network. The monitoring operation penalty compensator is a neural network model in machine learning that can be iteratively optimized. The input data of the monitoring operation penalty compensator is the parameter monitoring operation penalty factor, and the output data is the parameter monitoring operation penalty compensation data. Then, a sample data set is obtained, and the sample data set is used to perform supervised training and validation training on the monitoring operation penalty compensator until a predetermined training constraint is satisfied, obtaining a trained monitoring operation penalty compensator. The construction and training process of the monitoring operation penalty compensator is the same as that of the acquisition process penalty compensator. For the sake of simplicity of the specification, it will not be elaborated here.

[0081] Then, the parameter monitoring operation penalty factors are input into the monitoring operation penalty compensator for penalty compensation analysis, and the parameter monitoring operation penalty compensation data is output; further, based on the parameter monitoring operation penalty compensation data, parameter mapping compensation is performed on the temperature, pressure, flow, and humidity initial correction data set to obtain the temperature, pressure, flow, and humidity enhanced correction data set. By constructing a monitoring operation penalty compensator based on a BP neural network to perform monitoring operation penalty compensation data analysis, the efficiency and accuracy of obtaining monitoring operation penalty compensation data can be improved, thereby improving the accuracy and efficiency of correcting the temperature, pressure, flow, and humidity initial correction data set.

[0082] Furthermore, the present application further includes the following steps:

[0083] According to the temperature, pressure, flow, and humidity enhanced correction data set, each parameter penalty factor set is retrieved;

[0084] Global cross-analysis is respectively performed on each parameter penalty factor set to obtain the global cross-analysis results of each parameter penalty;

[0085] According to the global cross-analysis results of each parameter penalty, penalty factor cross-interference impact correction is performed on the temperature, pressure, flow, and humidity enhanced correction data set.

[0086] Specifically, based on the temperature, pressure, flow rate, and humidity enhanced correction data set, each parameter penalty factor is determined to obtain each parameter penalty factor set. Then, global cross-analysis is performed on each parameter penalty factor set respectively. The global cross-analysis refers to analyzing the mutual interference between parameter penalty factors and quantifying the degree of interference. Among them, the global cross-analysis is a statistical method used to study the interaction effects between multiple parameters or variables, and the global cross-analysis results of each parameter penalty are obtained. Finally, based on the global cross-analysis results of each parameter penalty, the temperature, pressure, flow rate, and humidity enhanced correction data set is corrected for the influence of cross-interference of penalty factors. By performing global cross-analysis on each parameter penalty factor set and correcting the temperature, pressure, flow rate, and humidity enhanced correction data set according to the global cross-analysis results of each parameter penalty, the influence caused by the mutual interference of penalty factors on the monitoring data can be avoided, and the accuracy of the obtained temperature, pressure, flow rate, and humidity monitoring data can be further improved.

[0087] In summary, the data correction method for a temperature, pressure, flow rate, and humidity integrated monitor provided by this application has the following technical effects:

[0088] By performing acquisition process offset analysis, the acquisition process penalty factor is determined, and the monitoring data is corrected according to the acquisition process penalty factor to obtain the initial temperature, pressure, flow rate, and humidity correction data set, which can reduce or avoid data errors caused by improper operation during the acquisition process; then, monitoring operation characteristic offset analysis is performed, the monitoring operation penalty factor is determined, and the temperature, pressure, flow rate, and humidity initial correction data set is corrected to obtain the temperature, pressure, flow rate, and humidity enhanced correction data set, which can reduce or avoid data errors caused by equipment status and environmental interference; finally, the global node temperature, pressure, flow rate, and humidity monitoring cloud map is drawn based on the temperature, pressure, flow rate, and humidity enhanced correction data set. The accuracy and comprehensiveness of the temperature, pressure, flow rate, and humidity monitoring data correction can be improved, thereby improving the data monitoring quality and ensuring the authenticity and reliability of the temperature, pressure, flow rate, and humidity monitoring data.

[0089] The above description of the disclosed embodiments enables those skilled in the art to implement or use this application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application will not be limited to these embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0090] Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of this application and its equivalent technologies, this application is also intended to include these changes and modifications.

Claims

1. A data correction method for a temperature, pressure, flow and humidity integrated monitoring instrument, characterized in that: The method comprises: Obtaining regional layout feature information of the target area; Deploy the temperature-pressure-flow-humidity integrated monitoring instrument in the target area according to the regional layout characteristic information, and obtain L temperature-pressure-flow-humidity integrated monitoring modules corresponding to L regional monitoring nodes, where L is a positive integer greater than 1; Performing real-time monitoring of the target area according to the L temperature-pressure-flow-humidity integrated monitoring modules to obtain L groups of temperature-pressure-flow-humidity monitoring data; Performing collection process penalty correction based on the L groups of temperature, pressure, flow and humidity monitoring data to obtain an initial correction data set of temperature, pressure, flow and humidity; Performing a monitoring operation characteristic penalty correction according to the temperature, pressure, flow and humidity initial correction data set to obtain a temperature, pressure, flow and humidity enhanced correction data set; Draw a global node temperature, pressure, flow and humidity monitoring cloud map based on the temperature, pressure, flow and humidity enhanced correction data set; The monitoring operation characteristic penalty correction is performed according to the temperature, pressure, flow and humidity initial correction data set to obtain the temperature, pressure, flow and humidity enhanced correction data set, including: Based on the initial correction data set of temperature, pressure, flow and humidity, the characteristics of each parameter monitoring operation are traced back to obtain the characteristic data set of each parameter monitoring operation; Perform monitoring operation characteristic deviation analysis according to the characteristic data sets of each parameter monitoring operation to generate a penalty factor for each parameter monitoring operation; Build a monitoring operation penalty compensator; Based on the penalty factors of the monitoring operations of each parameter, penalty compensation analysis is performed according to the monitoring operation penalty compensator to obtain penalty compensation data of the monitoring operations of each parameter; The temperature, pressure, fluid and humidity initial correction data set is subjected to parameter mapping compensation according to the penalty compensation data of the parameter monitoring operations to obtain the temperature, pressure, fluid and humidity enhanced correction data set.

2. The method according to claim 1, characterized in that Performing collection process penalty correction according to the L groups of temperature, pressure, flow and humidity monitoring data to obtain an initial correction data set of temperature, pressure, flow and humidity, including: Performing standardization processing on the L groups of temperature, pressure, flow and humidity monitoring data to obtain L temperature, pressure, flow and humidity monitoring standard groups; Extracting a first temperature-pressure-flow-humidity monitoring standard group according to the L temperature-pressure-flow-humidity monitoring standard groups, wherein the first temperature-pressure-flow-humidity monitoring standard group is any one of the L temperature-pressure-flow-humidity monitoring standard groups; Retrieve the collection process monitoring data corresponding to the first temperature, pressure, flow and humidity monitoring standard group; Performing an acquisition process deviation analysis based on the acquisition process monitoring data to determine an acquisition process penalty factor; The first temperature-pressure-flow-humidity monitoring standard group is corrected according to the acquisition process penalty factor to generate the temperature-pressure-flow-humidity initial correction data set.

3. The method according to claim 2, characterized in that Performing an acquisition process deviation analysis based on the acquisition process monitoring data to determine an acquisition process penalty factor includes: The acquisition process monitoring data includes acquisition process monitoring images and acquisition transmission processing monitoring data; Focusing on the abnormality of the acquisition process according to the acquisition process monitoring image to obtain abnormal feature data of the acquisition process; According to the abnormal characteristic data of the acquisition process, the temperature, pressure, flow and humidity influence correlation is performed to obtain the influence correlation characteristic information of the acquisition process; Performing anomaly detection based on the collected, transmitted, processed and monitored data to obtain collected and processed abnormal feature data; Perform temperature, pressure, flow and humidity impact analysis based on the abnormal feature data collected and processed to obtain abnormal feature information of the impact; The collection process impact associated feature information and the collection processing abnormality impact feature information are integrated to obtain the collection process penalty factor.

4. The method according to claim 2, characterized in that According to the acquisition process penalty factor, the first temperature, pressure, flow and humidity monitoring standard group is corrected to generate the temperature, pressure, flow and humidity initial correction data set, including: Retrieve a sample collection process penalty factor set and a sample collection process penalty compensation data set; Based on the preset compensator establishment conditions, according to the sample acquisition process penalty factor set and the sample acquisition process penalty compensation data set, a collection process penalty compensator is built, wherein the preset compensator establishment conditions include a predetermined data partition weight and a predetermined training convergence condition; Inputting the acquisition process penalty factor into the acquisition process penalty compensator to obtain acquisition process penalty compensation data; According to the penalty compensation data of the acquisition process, compensation optimization is performed on the first temperature-pressure-flow-humidity monitoring standard group to obtain a first temperature-pressure-flow-humidity monitoring correction group; The first temperature-pressure-fluid-humidity monitoring correction group is added to the temperature-pressure-fluid-humidity initial correction data set.

5. The method according to claim 1, characterized in that Performing monitoring operation feature deviation analysis according to the parameter monitoring operation feature data set to generate each parameter monitoring operation penalty factor includes: Conducting a multi-parameter monitoring operation characteristic benchmark analysis based on the temperature, pressure, flow and humidity integrated monitoring instrument to construct a multi-dimensional monitoring operation characteristic benchmark matrix; Performing standardization processing on the characteristic data sets of each parameter monitoring operation to construct a characteristic matrix of each parameter monitoring operation; Based on the characteristic matrix of each parameter monitoring operation, the multi-dimensional monitoring operation characteristic reference matrix is ​​associated and mapped to determine the reference matrix corresponding to each parameter; Based on the reference matrix corresponding to each parameter, the deviation of the characteristic matrix of the monitoring operation of each parameter is calculated to obtain the characteristic deviation matrix of the monitoring operation of each parameter; The influence of each parameter is identified according to the characteristic deviation matrix of each parameter monitoring operation to obtain the penalty factor of each parameter monitoring operation.

6. The method according to claim 5, characterized in that A multi-parameter monitoring operation characteristic benchmark analysis is performed based on the temperature, pressure, flow and humidity integrated monitoring instrument to construct a multi-dimensional monitoring operation characteristic benchmark matrix, including: Extracting a first characteristic monitoring component according to the temperature-pressure-flow-humidity integrated monitoring instrument, wherein the temperature-pressure-flow-humidity integrated monitoring instrument includes a plurality of characteristic monitoring components corresponding to a plurality of characteristic monitoring indicators, and the first characteristic monitoring component is any one of the plurality of characteristic monitoring components; Perform global backtracking of normal samples of monitoring operation characteristics according to the first characteristic monitoring component to obtain a normal operation characteristic sample set of the first component; Performing a central tendency analysis on the first component normal operation feature sample set to obtain a first component normal operation feature concentrated interval set; According to the concentrated interval set of the normal operation characteristics of the first component, a first component monitoring operation characteristic benchmark matrix is ​​constructed, and the first component monitoring operation characteristic benchmark matrix is ​​added to the multi-dimensional monitoring operation characteristic benchmark matrix.

7. The method according to claim 1, characterized in that Obtain temperature, pressure, flow and humidity enhancement correction data set, including: According to the temperature, pressure, flow and humidity enhancement correction data set, a set of penalty factors for each parameter is retrieved; Performing global cross analysis on each parameter penalty factor set respectively to obtain global cross analysis results of each parameter penalty; The cross-interference effect of penalty factors is corrected for the temperature-pressure-flow-humidity enhancement correction data set according to the global cross-analysis results of the penalty for each parameter.

Images