An intelligent multi-parameter environmental monitoring method
Through intelligent multi-parameter environmental monitoring method, multi-dimensional environmental parameter acquisition and confidence optimization are used to identify abnormal states of combustion equipment, solving the problem that traditional environmental monitoring methods cannot comprehensively evaluate the operating status of combustion equipment, and achieving comprehensive monitoring and abnormality of combustion equipment Accurate identification of status and timely warning.
Patent Information
- Application Number
- CN202411224988.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-09-03
AI Technical Summary
Traditional environmental monitoring methods can only monitor single-dimensional environmental parameters and cannot comprehensively evaluate the operating status of combustion equipment. The identification of abnormal environmental parameters depends on empirical judgment, which is prone to missed or false alarms.
Using intelligent multi-parameter environmental monitoring method, confidence optimization and stability analysis are carried out by obtaining multi-dimensional environmental parameters such as gas flow rate, dynamic pressure, flue pressure, temperature and humidity, identifying the relationship between combustion efficiency and generating combustion efficiency loss indicators, and achieving the Comprehensive monitoring of combustion equipment and accurate identification of abnormal states.
It realizes comprehensive monitoring of the combustion equipment environment, improves the credibility of monitoring data and the accuracy of abnormal status identification, and issues abnormal operation warnings in a timely manner to ensure the safe operation of the equipment.
Smart Images

Figure CN118729315B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of environmental monitoring, and in particular to an intelligent multi-parameter environmental monitoring method. Background Art
[0002] In industrial production environments, the stable operation of combustion equipment is crucial to production efficiency, energy utilization efficiency and environmental protection. However, traditional environmental monitoring methods still have some technical problems. On the one hand, traditional environmental monitoring methods can usually only monitor single-dimensional environmental parameters, such as temperature or pressure, and cannot comprehensively evaluate the operating status of combustion equipment; on the other hand, traditional methods usually rely on experience and judgment to identify abnormal environmental parameters, which lack scientific basis, so there may be omissions or false alarms. Summary of the invention
[0003] This application provides an intelligent multi-parameter environmental monitoring method, which aims to solve the technical problem that traditional environmental monitoring methods can only collect environmental parameters of a single dimension and cannot comprehensively evaluate the operating status of the combustion equipment, resulting in poor monitoring effects.
[0004] In view of the above problems, the present application provides an intelligent multi-parameter environmental monitoring method.
[0005] The present application discloses an intelligent multi-parameter environmental monitoring method, the method comprising: obtaining an associated production control center of a preset monitoring area, establishing a connection with the associated production control center, and reading a preset production indicator sequence under a preset time zone; identifying production indicator change nodes based on the preset production indicator sequence to obtain a monitoring period; under the monitoring period, collecting multi-dimensional environmental parameters of the preset monitoring area through an environmental monitoring module, and optimizing the collected parameters with confidence to generate a multi-dimensional environmental monitoring list sequence; identifying the combustion efficiency influence relationship between the multi-dimensional environmental parameters and the combustion equipment in the preset monitoring area to generate a combustion efficiency influence relationship list, wherein the combustion efficiency influence relationship includes a positive incentive relationship and a negative inhibition relationship; performing a stability analysis of the multi-dimensional environmental parameters based on the multi-dimensional environmental monitoring list sequence to generate a multi-dimensional parameter stability trend; locating abnormal environmental parameters according to the multi-dimensional parameter stability trend, and performing a combustion efficiency loss analysis in combination with the combustion efficiency influence relationship list to obtain a combustion efficiency loss index; and providing an abnormal operation warning for the combustion equipment in the preset monitoring area based on the combustion efficiency loss index.
[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0007] By utilizing multi-dimensional environmental parameter collection, multiple parameters such as gas flow rate, dynamic pressure, flue pressure, temperature and humidity are covered, thereby realizing comprehensive monitoring of the combustion equipment environment; by optimizing the confidence of the collected parameters and combining the historical multi-dimensional monitoring data for credibility estimation, the credibility of the monitoring data is improved, thereby more accurately evaluating the operating status of the combustion equipment; through stability analysis and identification of combustion efficiency influencing relationships, abnormal environmental parameters can be accurately located, and efficiency loss analysis can be performed in combination with the influence relationship list, thereby improving the accuracy of abnormal status identification; through the analysis of combustion efficiency loss indicators, abnormal operation warnings can be issued in time to ensure the safe operation of the equipment.
[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] Figure 1 A schematic diagram of a process flow of an intelligent multi-parameter environmental monitoring method is provided for an embodiment of the present application;
[0010] Figure 2 A flow chart of generating a combustion efficiency influence relationship list in an intelligent multi-parameter environmental monitoring method is provided for an embodiment of the present application. DETAILED DESCRIPTION
[0011] The embodiment of the present application provides an intelligent multi-parameter environmental monitoring method to solve the technical problem that traditional environmental monitoring methods can only collect environmental parameters of a single dimension and cannot comprehensively evaluate the operating status of the combustion equipment, resulting in poor monitoring effects.
[0012] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.
[0013] Embodiment 1
[0014] like Figure 1 As shown, the embodiment of the present application provides an intelligent multi-parameter environment monitoring method, the method comprising:
[0015] Obtaining an associated production control center in a preset monitoring area, establishing a connection with the associated production control center, and reading a preset production indicator time sequence in a preset time zone;
[0016] First, determine the areas that need to be monitored, such as various boilers, furnace flues, etc., find the production control centers associated with these monitoring areas. These centers are systems responsible for monitoring and controlling equipment operation. Establish connections with these production control centers, and request preset production indicator timing data under preset time zones from the production control centers through corresponding interfaces. These indicators include equipment operating status, temperature, pressure, flow and other parameters, as well as production plans and goals, and other information. These parameters have time stamps.
[0017] Based on the preset production indicator time sequence, production indicator change nodes are identified to obtain a monitoring period;
[0018] The acquired preset production index time series data is analyzed, wherein, under a cycle with the same production index, the gas flow rate, dynamic pressure, flue pressure, temperature, and humidity should be consistent, otherwise the production equipment, i.e., the combustion equipment of the boiler and furnace flue, will have low combustion efficiency and equipment abnormalities. Therefore, the time series analysis method is used to identify change nodes, such as mutation point detection, trend analysis, and periodicity analysis. Exemplarily, a mutation point detection algorithm is used to detect mutation points in the production index time series data to determine the location of the change node, and the monitoring period is determined based on the change node. The starting point of the monitoring period is the node where the previous production task is completed and the next task is started.
[0019] In the monitoring cycle, the environment monitoring module collects multi-dimensional environmental parameters of the preset monitoring area, and optimizes the collected parameters to generate a multi-dimensional environmental monitoring list sequence;
[0020] According to the determined monitoring cycle, the time point for each environmental parameter collection is determined. In each monitoring cycle, the environmental monitoring module collects multi-dimensional environmental parameters of the preset monitoring area. These environmental parameters include gas flow rate, dynamic pressure, flue pressure, temperature, humidity and other parameters, which vary according to the specific application scenario.
[0021] The collected environmental parameters are optimized with confidence to ensure the quality and accuracy of the collected data. Confidence optimization estimates the multidimensional monitoring credibility of historical multidimensional monitoring data to obtain multidimensional credibility indicators, and then the collected parameters are optimized with confidence through multidimensional credibility indicators to remove abnormal data or noise and improve the credibility of the data. The confidence-optimized environmental parameters are organized into a multidimensional environmental monitoring list sequence in chronological order, which contains the values of each environmental parameter collected during the period. This sequence provides a data basis for subsequent environmental parameter stability analysis and combustion efficiency loss analysis.
[0022] Furthermore, the multi-dimensional environmental parameters include at least gas flow rate, dynamic pressure, flue pressure, temperature and humidity.
[0023] The multi-dimensional environmental parameters include at least gas flow rate, dynamic pressure, flue pressure, temperature and humidity, among which gas flow rate is the speed of gas flowing in a pipe or channel; dynamic pressure is the kinetic energy pressure generated by the fluid during the flow process due to the speed, also known as velocity pressure; flue pressure refers to the gas pressure measured in the flue or chimney of the combustion equipment, which is used to evaluate the exhaust conditions during the combustion process; temperature is the temperature in the environment, and humidity is an indicator of the water vapor content in the air. These parameters play an important role in the monitoring of combustion equipment, and are used to evaluate the operating status and efficiency of the equipment, as well as to detect potential problems and abnormal conditions.
[0024] Furthermore, the acquisition parameters are optimized with confidence, including:
[0025] Acquire historical multi-dimensional monitoring data of the environmental monitoring module;
[0026] Perform multidimensional monitoring credibility estimation based on the historical multidimensional monitoring data to obtain a multidimensional credibility index;
[0027] The acquisition parameters are confidence optimized through the multi-dimensional trust indicators.
[0028] The multi-dimensional monitoring data collected by the environmental monitoring module in the past is obtained, such as the gas flow rate, dynamic pressure, flue pressure, temperature and humidity data in the past year, to form the historical multi-dimensional monitoring data.
[0029] The historical multidimensional monitoring data are analyzed to evaluate the credibility of each monitoring parameter, for example, accuracy assessment, that is, by comparing the field measurement data with the standard value to check whether the data accurately reflects the monitored environmental conditions; integrity assessment, that is, assessing whether the data is complete, including whether there are missing or abnormal data points, which will affect the analysis and judgment of environmental parameters. Based on the evaluation of historical multidimensional monitoring data, the credibility indicators of each monitoring parameter can be calculated, which are used to indicate the reliability and accuracy of the data.
[0030] According to the multi-dimensional trust indicators, the acquisition parameters in the environmental monitoring module are optimized and adjusted. The optimization goal is to ensure the stability and accuracy of the acquisition parameters, thereby improving the quality of the monitoring data. Specifically, according to the credibility indicators of historical data, the acquisition frequency of the environmental monitoring module is adjusted. For parameters with high credibility, the acquisition frequency can be increased to obtain more accurate data; for parameters with low credibility, the acquisition frequency can be moderately reduced to reduce data noise and uncertainty. By optimizing the confidence of the acquisition parameters, the quality and reliability of the environmental monitoring data can be improved, providing a more reliable data basis for subsequent environmental analysis and combustion efficiency evaluation.
[0031] Identifying the combustion efficiency influence relationship between the multi-dimensional environmental parameters and the combustion equipment in the preset monitoring area, and generating a combustion efficiency influence relationship list, wherein the combustion efficiency influence relationship includes a positive incentive relationship and a negative inhibition relationship;
[0032] By analyzing the changing trends between environmental parameters and combustion efficiency, some environmental parameters are identified to have positive incentive effects on combustion efficiency. For example, when a certain environmental parameter increases, combustion efficiency also increases. Similarly, by analyzing the changing trends between environmental parameters and combustion efficiency, some environmental parameters are identified to have negative inhibitory effects on combustion efficiency. For example, an increase in a certain environmental parameter will lead to a decrease in combustion efficiency. The identified positive incentive relationships and negative inhibitory relationships are organized into a list, including information such as the type of relationship between each environmental parameter and combustion efficiency and the degree of influence, to obtain a list of relationships affecting combustion efficiency, providing a basis for subsequent stability analysis and anomaly detection.
[0033] Furthermore, if Figure 2 As shown, the combustion efficiency influence relationship between the multi-dimensional environmental parameters and the combustion equipment in the preset monitoring area is identified, and a combustion efficiency influence relationship list is generated, including:
[0034] Obtain environmental monitoring records, use the first dimension environmental parameters as variables and other dimension environmental parameters as quantities, search the environmental monitoring records, and generate a first dimension parameter sample set and a first dimension combustion efficiency sample set;
[0035] Identify a positive incentive relationship or a negative inhibition relationship based on the first dimension parameter sample set and the first dimension combustion efficiency sample set to obtain a first influence coefficient;
[0036] Establishing a mapping association between the first influence coefficient and the first dimensional environmental parameter;
[0037] The combustion efficiency influence relationship list is constructed according to the mapping association.
[0038] Obtain the historical monitoring data recorded by the environmental monitoring module. Randomly select a parameter from the collected monitoring data as the first dimension environmental parameter, as the variable of the sample set, and use the remaining other dimensional environmental parameters as quantitative references.
[0039] The selected first dimension environmental parameters and other dimension environmental parameters are used to search in the environmental monitoring records, and the other dimension environmental parameters are kept unchanged. According to the changes of the first dimension environmental parameters, the corresponding monitoring records are retrieved, and the corresponding combustion efficiency data is obtained. According to the retrieved environmental monitoring records, the values of the first dimension environmental parameters are used as the variables of the sample set to form the first dimension parameter sample set, and the combustion efficiency data of each sample is recorded at the same time to form the first dimension combustion efficiency sample set.
[0040] The first dimension parameter sample set is used as the independent variable, and the first dimension combustion efficiency sample set is used as the dependent variable. The relationship between the first dimension environmental parameter and the combustion efficiency is described by a linear regression model. When fitting the model, the first dimension environmental parameter is used as the independent variable, and the combustion efficiency is used as the dependent variable. According to the fitting results, if the increase of the first dimension environmental parameter is associated with the increase of the combustion efficiency, there is a positive incentive relationship; if the increase of the first dimension environmental parameter is associated with the decrease of the combustion efficiency, there is a negative inhibition relationship. After identifying the relationship, the first influence coefficient is obtained. This coefficient is the coefficient in the regression model, which indicates the degree of influence of the first dimension parameter on the combustion efficiency.
[0041] The first influence coefficient is associated with the first dimensional environmental parameter to establish a mapping association between the two, indicating that when the first dimensional environmental parameter is queried, the first influence coefficient can be obtained.
[0042] The same method is used to analyze each dimension of the multidimensional environmental parameters, obtain each dimensional environmental parameter and its corresponding influence coefficient, and their respective mapping associations, organize all mapping associations into a list form, and generate the combustion efficiency influence relationship list, in which each dimensional environmental parameter in the list has a corresponding influence coefficient one by one.
[0043] Performing stability analysis of multidimensional environmental parameters based on the multidimensional environmental monitoring list sequence to generate a multidimensional parameter stability trend;
[0044] Using the multi-dimensional environmental monitoring list sequence, the time series data of environmental parameters are collected. For each environmental parameter, the deviation between adjacent time nodes is calculated to represent the change of environmental parameters. For each environmental parameter, a series of same-dimensional parameter deviation vector sequences are generated, where each vector represents the deviation under an adjacent node. Multiple same-dimensional parameter deviation vector sequences of each environmental parameter are merged to obtain a stable vector sequence.
[0045] Curve fitting is performed on the stable vector sequence to analyze its changing trend. Based on the result of the curve fitting, the stable trend of each environmental parameter is generated, which can be a linear, nonlinear trend or a periodic trend, constituting the multidimensional parameter stable trend, which is used to represent the changing situation of the environmental parameters.
[0046] Furthermore, the stability analysis of multidimensional environmental parameters is performed based on the multidimensional environmental monitoring list sequence to generate a multidimensional parameter stability trend, including:
[0047] Calculate the same-dimensional parameter deviations under adjacent nodes according to the multi-dimensional environment monitoring list sequence to generate multiple same-dimensional parameter deviation vector sequences;
[0048] Perform stable vector merging based on the multiple same-dimensional parameter deviation vector sequences to obtain multiple merged vector sequences;
[0049] Curve fitting is performed on the plurality of merged vector sequences to generate the multi-dimensional parameter stable trend by fitting the curvature.
[0050] Each time node in the multidimensional environmental monitoring list sequence records the value of the multidimensional environmental parameters. For each dimension of environmental parameters, the deviation of the parameters is calculated between adjacent time nodes. The deviation can be calculated by subtracting the parameter value of the previous time node from the parameter value of the current time node. For each dimension of environmental parameters, the calculated deviation is combined into a vector sequence. Each vector sequence represents the deviation of the parameters of one dimension at adjacent time nodes. For each dimension of environmental parameters, the above calculation is repeated to finally generate multiple vector sequences of parameter deviations of the same dimension.
[0051] For each dimension of environmental parameters, compare the deviation values at adjacent time nodes. If the deviation values at adjacent nodes are very small, for example, less than the preset deviation threshold, merge them into a stable vector. Consider the positive and negative signs of the deviation values when merging, because the deviation has positive and negative signs, and this difference needs to be retained. For the case where the deviation values at adjacent nodes are small, calculate their mean as the merged deviation value. For each dimension of environmental parameters, combine the merged stable vectors into a new merged vector sequence. Each merged vector sequence represents the stable deviation of the environmental parameters of one dimension at adjacent time nodes. Repeat the merging operation for all dimensions of environmental parameters to obtain multiple merged vector sequences.
[0052] For each merged vector sequence, a curve fitting operation is performed, which can be accomplished through various curve fitting algorithms, such as polynomial fitting, spline interpolation, etc. The goal of curve fitting is to find the curve that best fits the characteristics of the merged vector sequence to minimize the fitting error. After the curve fitting is completed, the fitting function or curve equation of the curve is obtained, and the derivative of the fitting curve is used to calculate the curvature. The curvature describes the degree of curvature of the curve. If it tends to be stable, the curvature is close to 1.
[0053] The obtained curvature is taken as the stable trend of the multidimensional parameter. According to the change of curvature, it can be judged whether the stability of the environmental parameter increases, decreases or remains unchanged. By traversing each dimension, the stable trend of the environmental parameter in each dimension is finally obtained to form the stable trend of the multidimensional parameter.
[0054] According to the stable trend of the multi-dimensional parameters, locate the abnormal environmental parameters, and perform combustion efficiency loss analysis in combination with the combustion efficiency influence relationship list to obtain a combustion efficiency loss index;
[0055] The stability of each environmental parameter is analyzed using the generated multi-dimensional parameter stability trend, which includes the direction, rate, and periodicity of trend change. According to the stability trend of the multi-dimensional parameters, the environmental parameters that do not conform to the expected stability trend are identified. These abnormal environmental parameters are parameters that have undergone abnormal changes, which will affect the operating status and combustion efficiency of the combustion equipment.
[0056] Combine the combustion efficiency impact relationship list with the located abnormal environmental parameters to analyze the impact of abnormal environmental parameters on combustion efficiency. For environmental parameters with positive excitation relationships, their abnormal changes will lead to an increase or decrease in combustion efficiency; while for environmental parameters with negative inhibition relationships, their abnormal changes will have a negative impact on combustion efficiency. Based on the results of the combustion efficiency loss analysis, a combustion efficiency loss index is obtained to evaluate the operating status of the combustion equipment and the changes in combustion efficiency. The specific method for calculating the combustion efficiency loss index is described in detail in the subsequent steps and is only briefly mentioned here.
[0057] Based on the combustion efficiency loss index, an abnormal operation warning of the combustion equipment is issued to the preset monitoring area.
[0058] Set an abnormal operation warning threshold, which can be based on the statistical analysis results of historical data or a standard value determined according to equipment specifications and performance requirements. When the combustion efficiency loss index is monitored to exceed the set abnormal operation warning threshold, the abnormal operation warning is triggered, including sending an alarm notification, triggering an automated equipment shutdown or adjustment program, and initiating manual intervention measures to restore the normal operation of the equipment. By providing abnormal operation warnings for combustion equipment in the preset monitoring area based on the combustion efficiency loss index, the stability and safety of equipment operation can be guaranteed.
[0059] Furthermore, according to the stable trend of the multi-dimensional parameters, the abnormal environmental parameters are located, and in combination with the combustion efficiency influence relationship list, the combustion efficiency loss analysis is performed to obtain the combustion efficiency loss index, including:
[0060] According to the multi-dimensional parameter stability trend, locate the abnormal environmental parameters whose stability trend does not satisfy the preset trend reference wireframe;
[0061] Extracting the abnormal parameter time series of the abnormal environmental parameters based on the multi-dimensional environmental monitoring list sequence;
[0062] Obtaining a predicted stable combustion rate during the monitoring period;
[0063] Based on the abnormal parameter time series and the combustion efficiency influence relationship list, and on the basis of the predicted stable combustion rate, combustion rate loss identification is performed to generate the combustion efficiency loss index.
[0064] Get the preset trend reference wireframe, that is, the stable trend range of each environmental parameter. This range is usually constrained by two upper and lower reference wireframes, indicating the maximum acceptable value and minimum acceptable value of the environmental parameter. Traverse the stable trend of the environmental parameters of each dimension to check whether there is any situation that exceeds the preset trend reference wireframe. If the stable trend of a parameter is not within the reference wireframe, mark it as an abnormal environmental parameter.
[0065] Using a multidimensional environment monitoring list sequence, for the located abnormal environment parameters, the corresponding monitoring data time series is extracted from the multidimensional environment monitoring list sequence to obtain the abnormal parameter time series, wherein the abnormal parameter time series includes their monitoring values at different time points.
[0066] The predicted stable combustion rate under the monitoring period is obtained. Based on the obtained predicted stable combustion rate, combined with the abnormal parameter time series and the combustion efficiency influence relationship list, the combustion rate loss is identified, and the corresponding combustion efficiency loss index is generated. This index includes the percentage of loss, which is used to quantify the degree of combustion efficiency loss and provide data support for the analysis and processing of abnormal situations. The specific method for obtaining the predicted stable combustion rate and the method for identifying the combustion rate loss will be developed in the subsequent steps and will only be briefly mentioned here.
[0067] Furthermore, obtaining the predicted stable combustion rate in the monitoring period includes:
[0068] The historical maintenance update node of the combustion equipment is read through the associated production control center, and a plurality of stable value sequences of equipment combustion efficiency in a preset time zone are obtained, wherein the preset time zone includes a plurality of time zones, and the plurality of time zones are two adjacent node intervals in the historical maintenance update node;
[0069] Performing data stability center identification on the plurality of equipment combustion efficiency stable value sequences to obtain a plurality of equipment combustion efficiency center values;
[0070] Based on the Markov chain, the combustion rate attenuation prediction is performed in the monitoring period according to the central values of the combustion efficiencies of the multiple devices to obtain a predicted stable combustion rate.
[0071] By establishing a connection with the associated production control center, the historical maintenance update node of the combustion equipment is obtained. According to the historical maintenance update node, the preset time zone is determined. The preset time zone includes multiple time zones. Each time zone is determined by the time period between two adjacent historical maintenance update nodes. In this way, the preset time zone can cover the entire time range of historical maintenance updates. For each preset time zone, the corresponding multiple equipment combustion efficiency stable value sequences are obtained. These stable values represent the stable values of the combustion efficiency of multiple equipment in each time zone.
[0072] The data set analysis is performed on the stable value sequence of the combustion efficiency of each device, including analyzing the distribution of the data. Specifically, by calculating the mean of the data, the stable value range in the data set is identified, and the center position of the stable value is determined. The stable center of the stable value sequence of the combustion efficiency of each device is identified to obtain multiple center values of the combustion efficiency of the device. These center values represent the average level of the combustion efficiency of each device in the preset time zone.
[0073] The changes in the central values of the combustion efficiency of multiple devices during the monitoring period are regarded as a state sequence, in which each state represents the central value of the combustion efficiency of a device, and a Markov chain model is established to describe the transition probability between these states. The transition probability between each state in the Markov chain is estimated based on historical data. These transition probabilities reflect the change trend of the central value of the combustion efficiency of the equipment during the monitoring period. Using the established Markov chain model, the changes in the central value of the combustion efficiency of the equipment in the future monitoring period are predicted. By iteratively calculating the state transition probability, the probability distribution of each state in the future monitoring period can be obtained. According to the predicted probability distribution of the central value of the combustion efficiency of the equipment, the predicted stable combustion rate is calculated.
[0074] Furthermore, based on the abnormal parameter time series and the combustion efficiency influence relationship list, combustion rate loss identification is performed based on the predicted stable combustion rate to generate the combustion efficiency loss index, including:
[0075] Extracting the abnormal impact coefficient of the abnormal environmental parameter according to the combustion efficiency impact relationship list;
[0076] Extracting a first node parameter, a second node parameter, a third node parameter, and finally an Nth node parameter based on the abnormal parameter time sequence;
[0077] Based on the abnormal influence coefficient and in combination with parameter change information between the first node parameter and the second node parameter, an influence analysis is performed on the predicted stable combustion rate to obtain a first predicted combustion rate;
[0078] Based on the abnormal influence coefficient and in combination with parameter change information between the second node parameter and the third node parameter, an influence analysis is performed on the first predicted combustion rate to obtain a second predicted combustion rate;
[0079] Continue to perform impact analysis on the second predicted burning rate until the Nth node parameter is traversed to obtain the N-1th predicted burning rate;
[0080] calculating the combustion losses of the predicted stable combustion rate and the first predicted combustion rate, the second predicted combustion rate, and up to the N-1th predicted combustion rate, respectively, to obtain N-1 combustion rate loss values;
[0081] Data stability center identification is performed on the N-1 combustion rate loss values to obtain the combustion efficiency loss index.
[0082] A combustion efficiency influence relationship list is used, which records the influence relationship of various environmental parameters on combustion efficiency. For the located abnormal environmental parameters, the influence coefficient associated with the abnormal parameter is extracted from the combustion efficiency influence relationship list.
[0083] The first node parameter, the second node parameter, the third node parameter, and finally the Nth node parameter are extracted from the abnormal parameter time series. These parameters represent the values of the abnormal environment parameters at different time points, and N is the number of nodes.
[0084] Using the extracted abnormal influence coefficients, combined with the parameter change information between the first and second node parameters, their influence on the predicted stable combustion rate is analyzed, that is, how the stable combustion rate changes when the parameters change. Based on the results of the influence analysis, the first predicted combustion rate is calculated.
[0085] Similarly, according to the change information of the abnormal influence coefficient and the second and third node parameters, their influence on the first predicted combustion rate is analyzed, and according to the result of the influence analysis, the second predicted combustion rate is calculated.
[0086] Repeat the above process to perform an impact analysis on each node parameter, considering its relationship with the previous node parameter and the influence of the abnormal impact coefficient, until the Nth node parameter is traversed, and the N-1th predicted combustion rate is calculated based on the results of the impact analysis.
[0087] The combustion losses between the predicted stable combustion rate and the first predicted combustion rate, the second predicted combustion rate, and up to the N-1th predicted combustion rate are calculated respectively. This can be accomplished by comparing the difference between the predicted combustion rate and the preset stable combustion rate to obtain N-1 combustion rate loss values, which reflect the deviations between each predicted combustion rate and the preset stable combustion rate.
[0088] Statistical analysis is performed on N-1 combustion rate loss values to identify the stable center, such as calculating the mean, median, etc. According to the identification result of the stable center, a combustion efficiency loss index is obtained, which reflects the overall deviation of the combustion efficiency.
[0089] In summary, the intelligent multi-parameter environmental monitoring method provided by the embodiment of the present application has the following technical effects:
[0090] 1. Through the use of multi-dimensional environmental parameter collection, multiple parameters such as gas flow rate, dynamic pressure, flue pressure, temperature and humidity are covered, thus realizing comprehensive monitoring of the combustion equipment environment;
[0091] 2. By optimizing the confidence of the acquisition parameters and combining the historical multi-dimensional monitoring data for credibility estimation, the credibility of the monitoring data is improved, thereby more accurately evaluating the operating status of the combustion equipment;
[0092] 3. Through stability analysis and combustion efficiency impact relationship identification, abnormal environmental parameters can be accurately located, and efficiency loss analysis can be performed in combination with the impact relationship list, thereby improving the accuracy of abnormal state identification;
[0093] 4. Through the analysis of combustion efficiency loss indicators, abnormal operation warnings can be issued in time to ensure the safe operation of the equipment.
[0094] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. An intelligent multi-parameter environmental monitoring method, characterized in that: The method comprises: Obtaining an associated production control center in a preset monitoring area, establishing a connection with the associated production control center, and reading a preset production indicator time sequence in a preset time zone; Based on the preset production indicator time sequence, production indicator change nodes are identified to obtain a monitoring period; In the monitoring cycle, the environment monitoring module collects multi-dimensional environmental parameters of the preset monitoring area, and optimizes the collected parameters to generate a multi-dimensional environmental monitoring list sequence; Identifying the combustion efficiency influence relationship between the multi-dimensional environmental parameters and the combustion equipment in the preset monitoring area, and generating a combustion efficiency influence relationship list, wherein the combustion efficiency influence relationship includes a positive incentive relationship and a negative inhibition relationship; Performing stability analysis of multidimensional environmental parameters based on the multidimensional environmental monitoring list sequence to generate a multidimensional parameter stability trend; According to the stable trend of the multi-dimensional parameters, locate the abnormal environmental parameters, and perform combustion efficiency loss analysis in combination with the combustion efficiency influence relationship list to obtain a combustion efficiency loss index; Based on the combustion efficiency loss index, an abnormal operation warning of the combustion equipment in the preset monitoring area is performed; Wherein, the multi-dimensional environmental parameters include at least gas flow rate, dynamic pressure, flue pressure, temperature and humidity; Identifying the combustion efficiency influence relationship between the multi-dimensional environmental parameters and the combustion equipment in the preset monitoring area, and generating a combustion efficiency influence relationship list, including: Obtain environmental monitoring records, use the first dimension environmental parameters as variables and other dimension environmental parameters as quantities, search the environmental monitoring records, and generate a first dimension parameter sample set and a first dimension combustion efficiency sample set; Identify a positive incentive relationship or a negative inhibition relationship based on the first dimension parameter sample set and the first dimension combustion efficiency sample set to obtain a first influence coefficient; Establishing a mapping association between the first influence coefficient and the first dimensional environmental parameter; Constructing the combustion efficiency influence relationship list according to the mapping association; Based on the multidimensional environmental monitoring list sequence, a stability analysis of multidimensional environmental parameters is performed to generate a multidimensional parameter stability trend, including: Calculate the same-dimensional parameter deviations under adjacent nodes according to the multi-dimensional environment monitoring list sequence to generate multiple same-dimensional parameter deviation vector sequences; Perform stable vector merging based on the multiple same-dimensional parameter deviation vector sequences to obtain multiple merged vector sequences; Performing curve fitting on the plurality of merged vector sequences to generate the multi-dimensional parameter stable trend by fitting the curvature; According to the stable trend of the multi-dimensional parameters, the abnormal environmental parameters are located, and in combination with the combustion efficiency influence relationship list, the combustion efficiency loss analysis is performed to obtain the combustion efficiency loss index, including: According to the multi-dimensional parameter stability trend, locate the abnormal environmental parameters whose stability trend does not satisfy the preset trend reference wireframe; Extracting the abnormal parameter time series of the abnormal environmental parameters based on the multi-dimensional environmental monitoring list sequence; Obtaining a predicted stable combustion rate during the monitoring period; Based on the abnormal parameter time series and the combustion efficiency influence relationship list, and on the basis of the predicted stable combustion rate, combustion rate loss identification is performed to generate the combustion efficiency loss index; Obtaining the predicted stable combustion rate under the monitoring period, including: The historical maintenance update node of the combustion equipment is read through the associated production control center, and a plurality of stable value sequences of equipment combustion efficiency in a preset time zone are obtained, wherein the preset time zone includes a plurality of time zones, and the plurality of time zones are two adjacent node intervals in the historical maintenance update node; Performing data stability center identification on the plurality of equipment combustion efficiency stable value sequences to obtain a plurality of equipment combustion efficiency center values; Based on the Markov chain, a combustion rate attenuation prediction is performed in the monitoring period according to the central values of the combustion efficiencies of the multiple devices to obtain a predicted stable combustion rate; Based on the abnormal parameter time series and the combustion efficiency influence relationship list, based on the predicted stable combustion rate, combustion rate loss identification is performed to generate the combustion efficiency loss index, including: Extracting the abnormal impact coefficient of the abnormal environmental parameter according to the combustion efficiency impact relationship list; Extracting a first node parameter, a second node parameter, a third node parameter, and finally an Nth node parameter based on the abnormal parameter time sequence; Based on the abnormal influence coefficient and in combination with parameter change information between the first node parameter and the second node parameter, an influence analysis is performed on the predicted stable combustion rate to obtain a first predicted combustion rate; Based on the abnormal influence coefficient and in combination with parameter change information between the second node parameter and the third node parameter, an influence analysis is performed on the first predicted combustion rate to obtain a second predicted combustion rate; Continue to perform impact analysis on the second predicted burning rate until the Nth node parameter is traversed to obtain the N-1th predicted burning rate; calculating the combustion losses of the predicted stable combustion rate and the first predicted combustion rate, the second predicted combustion rate, and up to the N-1th predicted combustion rate, respectively, to obtain N-1 combustion rate loss values; Data stability center identification is performed on the N-1 combustion rate loss values to obtain the combustion efficiency loss index.
2. The method according to claim 1, characterized in that Confidence optimization of acquisition parameters, including: Acquire historical multi-dimensional monitoring data of the environmental monitoring module; Perform multidimensional monitoring credibility estimation based on the historical multidimensional monitoring data to obtain a multidimensional credibility index; The acquisition parameters are confidence optimized through the multi-dimensional trust indicators.
