Equipment state monitoring distributed control system and method

Abstract

The invention relates to the technical field of equipment state monitoring and control, and discloses an equipment state monitoring distributed control system and method, and the method comprises the steps: collecting the operation parameters of all equipment, and forming a first historical operation data set and a first real-time operation data set; performing cleaning, anomaly detection and feature extraction on the data to generate a feature data set; constructing an equipment parameter association network model; key features related to boiler performance are screened, a historical feature data set is generated, and a boiler performance prediction model is trained; inputting the real-time characteristic data set into a prediction model to obtain a boiler performance parameter prediction value, and comparing the boiler performance parameter prediction value with a preset performance threshold value; when the predicted value is lower than a threshold value, triggering a cooperative control process, calculating optimal operation parameters of desulfurization and denitrification equipment, a fan and an air compressor, and generating an adjustment parameter set; and generating a cooperative control strategy set according to the adjustment parameter set and issuing the cooperative control strategy set to each device for regulation and control. According to the invention, through multi-device collaborative optimization control, the energy efficiency and the operation stability of the system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment status monitoring and control, and more specifically, to an equipment status monitoring distributed control system and method. Background Art

[0002] With the continuous advancement of industrialization, equipment status monitoring and control technology plays an increasingly important role in industrial production. Efficient and intelligent equipment status monitoring and control can not only ensure production safety, but also improve production efficiency and product quality. At present, some technologies and methods have been accumulated for equipment status monitoring and control.

[0003] The Chinese patent application with publication number CN111027620A discloses a method for processing boiler operating parameters. This method uses a long short-term memory network trained with historical boiler operating parameters to process the boiler operating parameters at a deeper level with the help of a deep learning algorithm, and mines the implicit features hidden below the data surface, thereby extracting parameters that can more comprehensively and accurately feedback the actual operating conditions of the boiler, so as to more accurately and timely determine whether the boiler has safety hazards and adjust the operating status in a timely manner. The Chinese patent with authorization announcement number CN111090070B discloses a state control system and its state detection device. The device is applied to magnetic resonance equipment, and by setting a short-circuit protection branch, a load branch and a short-circuit detection branch, it realizes the detection of the off state of the coil unit and the switch assembly.

[0004] Although the above patents have made useful explorations in equipment status monitoring and control, most of the existing technologies focus on the monitoring and control of a single device and lack comprehensive analysis and optimized control of multiple devices working in a collaborative manner. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a distributed control system and method for equipment status monitoring.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A distributed control method for equipment status monitoring, comprising:

[0008] Collecting the operating parameters of each device to form a first historical operating data set and a first real-time operating data set; performing data cleaning, anomaly detection and feature extraction on the first historical operating data set and the first real-time operating data set to generate a first historical feature data set and a first real-time feature data set; and constructing a device parameter association network model based on the first historical operating data set;

[0009] Filter out key features closely related to boiler performance from the first historical feature data set, generate a second historical feature data set, and build and train a boiler performance prediction model based on the second historical feature data set; input the first real-time feature data set into the trained boiler performance prediction model to obtain a predicted value of boiler performance parameters; compare the predicted value of boiler performance parameters with a preset performance threshold, and when the predicted value of boiler performance parameters is lower than the preset performance threshold, trigger a collaborative control process;

[0010] Based on the predicted values ​​of boiler performance parameters and preset performance thresholds, the optimal operating parameters of the desulfurization and denitrification equipment are calculated to generate a first adjustment parameter set; with the goal of maximizing system energy efficiency, the optimal operating parameters of the fan and air compressor are calculated to generate a second adjustment parameter set and a third adjustment parameter set;

[0011] Based on the predicted values ​​of boiler performance parameters, the first adjustment parameter set, the second adjustment parameter set and the third adjustment parameter set, a collaborative control strategy set for the boiler, desulfurization and denitrification equipment, fans and air compressors is generated; the collaborative control strategy set is sent to each device for corresponding regulation and control operations.

[0012] Furthermore, the collecting of operating parameters of each device includes:

[0013] Install intelligent sensor networks on boilers, desulfurization and denitrification equipment, fans and air compressors to collect operating parameters of each device;

[0014] The first historical operation data set includes historical operation parameters of boilers, desulfurization and denitrification equipment, fans and air compressors;

[0015] The first real-time operation data set is composed of real-time operation parameters of the boiler;

[0016] The constructing of the equipment parameter association network model according to the first historical operation data set includes:

[0017] Calculate the correlation index coefficients between equipment operating parameters and construct the correlation matrix between equipment operating parameters;

[0018] Use time series analysis method to construct the cause-effect relationship diagram between equipment operation parameters;

[0019] The devices are mapped as network nodes, and the operating parameters of each device are used as node attributes. Based on the correlation matrix and causal relationship diagram, the edges between device nodes are established to construct a device parameter association network model.

[0020] Furthermore, the correlation matrix between the operating parameters of the constructed equipment includes:

[0021] Calculate the linear correlation coefficient of continuous operation parameters;

[0022] Calculate the mutual information value of discrete operating parameters;

[0023] A correlation matrix of equipment parameters is constructed based on the linear correlation coefficients and mutual information values ​​of the operating parameters;

[0024] The cause-effect relationship diagram between the operating parameters of the equipment is constructed as follows:

[0025] Calculate the mutual correlation coefficients between the time series of different operating parameters;

[0026] Use Granger causality test to determine whether the historical value of a parameter is helpful for predicting the future value of another parameter and obtain the causal test result;

[0027] Based on the mutual correlation coefficients and causal test results, a causal relationship diagram of the operating parameters is constructed.

[0028] Furthermore, the calculating of the optimal operating parameters of the desulfurization and denitrification equipment to generate the first adjustment parameter set includes:

[0029] Calculate the deviation between the predicted value of boiler performance parameters and the preset performance threshold value, and determine the adjustment direction and amplitude of the operating parameters of the desulfurization and denitrification equipment;

[0030] The optimization goal is to maximize the desulfurization efficiency and denitrification efficiency while minimizing the reagent consumption, the equipment operating parameters are used as the optimization variables, and the adjustment range of the desulfurization and denitrification equipment operating parameters is used as the constraint condition to construct the target optimization function;

[0031] By solving the target optimization function, the optimal operating parameter combination of the desulfurization and denitrification equipment is obtained; and the optimal operating parameter combination is used as the first adjustment parameter set.

[0032] Further, the calculating the optimal operating parameters of the fan and the air compressor to generate the second adjustment parameter set and the third adjustment parameter set includes:

[0033] Collect system load data, including historical load data and real-time load data, build a real-time load forecasting model based on the historical load data, input the real-time load data into the real-time load forecasting model, and obtain the load change curve in the future period;

[0034] Determine the adjustment direction and amplitude of the fan and air compressor according to the load change curve in the future period and the first real-time operation data set;

[0035] With the goal of maximizing system energy efficiency and the adjustment range of fans and air compressors as constraints, a fan and air compressor collaborative control optimization model is constructed.

[0036] Solve the fan and air compressor collaborative control optimization model to obtain the optimal operating parameter combination of the fan and air compressor, which are marked as the second adjustment parameter set and the third adjustment parameter set respectively.

[0037] Furthermore, the generating of the collaborative control strategy set of the boiler, the desulfurization and denitrification equipment, the fan and the air compressor according to the predicted value of the boiler performance parameter, the first adjustment parameter set, the second adjustment parameter set and the third adjustment parameter set includes:

[0038] Calculate the priority of each adjustment parameter set according to the deviation between the predicted value of the boiler performance parameter and the preset performance threshold, and the influence weight of the first adjustment parameter set, the second adjustment parameter set and the third adjustment parameter set on the boiler performance;

[0039] In descending order of priority, the three adjustment parameter sets are sent to the control systems of the corresponding devices in sequence; based on the logical associations between the devices, the execution sequence of the adjustment parameters of each device is coordinated to generate a collaborative control strategy set;

[0040] After each device completes the control operation according to the execution sequence of the adjustment parameters in the collaborative control strategy set, the improvement effect of the boiler performance parameters is evaluated; if the improvement effect does not meet expectations, the priority of the adjustment parameter set is recalculated until the boiler performance parameters meet the preset performance threshold requirements.

[0041] Furthermore, the method for calculating the priority of each adjustment parameter set includes:

[0042]

[0043] Among them, U i is the priority of the i-th adjustment parameter set, i = 1, 2, 3, P is the predicted value of boiler performance parameters, T is the preset performance threshold, W i is the weight of the influence of the i-th adjustment parameter set on boiler performance, W j is the influence weight of the jth adjustment parameter set on boiler performance, E i is the effect of the ith adjustment parameter set on boiler performance, E j is the effect of the jth adjustment parameter set on boiler performance, C i is the cost of the i-th adjustment parameter set, α is the weight coefficient of the deviation between the performance parameter prediction value and the preset performance threshold, β is the weight coefficient of the effect of the adjustment parameter set, is the synergistic effect between the adjustment parameter sets, and γ is the synergistic effect coefficient between the adjustment parameter sets.

[0044] A distributed control system for monitoring equipment status, which is used to implement the above-mentioned distributed control method for monitoring equipment status, and the system comprises:

[0045] Data collection module: used to collect the operating parameters of each device to form a first historical operating data set and a first real-time operating data set;

[0046] Data processing module: used for performing data cleaning, anomaly detection and feature extraction on the first historical operation data set and the first real-time operation data set to generate a first historical feature data set and a first real-time feature data set;

[0047] An association model building module: used for building an equipment parameter association network model according to the first historical operation data set;

[0048] Boiler performance prediction module: used to filter out key features closely related to boiler performance from the first historical feature data set, generate a second historical feature data set, build and train a boiler performance prediction model based on the second historical feature data set; input the first real-time feature data set into the trained boiler performance prediction model to obtain the predicted value of boiler performance parameters;

[0049] Collaborative control judgment module: used to compare the predicted value of boiler performance parameters with the preset performance threshold. When the predicted value of boiler performance parameters is lower than the preset performance threshold, the collaborative control process is triggered.

[0050] Adjustment parameter set generation module: used to calculate the optimal operating parameters of the desulfurization and denitrification equipment based on the predicted value of the boiler performance parameters and the preset performance threshold, and generate the first adjustment parameter set; with the goal of maximizing the system energy efficiency, calculate the optimal operating parameters of the fan and the air compressor, and generate the second adjustment parameter set and the third adjustment parameter set;

[0051] Collaborative control strategy generation module: used to generate collaborative control strategy sets for boilers, desulfurization and denitrification equipment, fans and air compressors according to the predicted values ​​of boiler performance parameters, the first adjustment parameter set, the second adjustment parameter set and the third adjustment parameter set;

[0052] Execution control module: used to send the collaborative control strategy set to each device for corresponding regulation operations.

[0053] An electronic device comprises a memory, a central processing unit and a computer program stored in the memory and executable on the central processing unit. When the central processing unit executes the computer program, the above-mentioned device status monitoring distributed control method is implemented.

[0054] A computer-readable storage medium stores a computer program, and when the computer program is executed, the above-mentioned equipment status monitoring distributed control method is implemented.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] By constructing a device parameter association network model, the present invention can better understand the mutual influence and association between various devices, thereby being more accurate in performance prediction and parameter adjustment, and effectively optimizing the operating status of the equipment.

[0057] The present invention takes into account the goal of minimizing reagent consumption when determining the optimal operating parameters of the desulfurization and denitrification equipment, and can reduce the operating cost to the maximum extent while ensuring the desulfurization and denitrification efficiency.

[0058] The present invention calculates the optimal operating parameters of the fan and the air compressor and optimizes them with the goal of maximizing the energy efficiency of the system, which can significantly improve the energy efficiency of the entire system and reduce energy consumption.

[0059] The present invention adopts intelligent sensor network and time series analysis method to realize intelligent monitoring and control of the operation status of complex equipment, reduce manual intervention and improve management efficiency.

[0060] The present invention realizes the linkage control of boilers, desulfurization and denitrification equipment, fans and air compressors by generating a collaborative control strategy set, which can better coordinate the operating status of each device and improve the performance of the overall system.

[0061] The equipment status monitoring distributed control system in the present invention can dynamically adjust the operating parameters of each device according to real-time data and prediction models, has strong adaptive capabilities, and can cope with different operating conditions and environmental changes.

[0062] The present invention constructs a prediction model by screening key features, which can more accurately predict boiler performance parameters, thereby better guiding subsequent control and regulation operations.

[0063] The method of the present invention can provide detailed operation data and analysis results for equipment management personnel, helping them to make more scientific decisions and improve the level of equipment management. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0065] Figure 1 It is a flow chart of a distributed control method for equipment status monitoring in the present invention;

[0066] Figure 2 A flow chart of a method for generating a first adjustment parameter set in a distributed control method for equipment status monitoring of the present invention;

[0067] Figure 3 A flow chart of a method for generating a collaborative control strategy set in a distributed control method for equipment status monitoring of the present invention;

[0068] Figure 4 It is a functional module diagram of a distributed control system for equipment status monitoring in the present invention. DETAILED DESCRIPTION

[0069] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0070] Example 1

[0071] See also Figure 1 As shown, this embodiment provides a device status monitoring distributed control method, including:

[0072] Step S1000, collecting the operating parameters of each device to form a first historical operating data set and a first real-time operating data set; performing data cleaning, anomaly detection and feature extraction on the first historical operating data set and the first real-time operating data set to generate a first historical feature data set and a first real-time feature data set; constructing a device parameter association network model according to the first historical operating data set;

[0073] Furthermore, step S1000 includes:

[0074] Step S1100, installing an intelligent sensor network on the boiler, desulfurization and denitration equipment, fan and air compressor, collecting operating parameters of each device, and forming a first historical operating data set and a first real-time operating data set; the first historical operating data set includes the historical operating parameters of the boiler, desulfurization and denitration equipment, fan and air compressor, and the first real-time operating data set consists of the real-time operating parameters of the boiler;

[0075] Specifically, select smart sensors suitable for high temperature, high pressure, and corrosive environments, such as thermocouples, pressure transmitters, flow meters, and accelerometers, to ensure the accuracy and reliability of data collection; install various types of smart sensors in key parts of boilers, desulfurization and denitrification equipment, fans, and air compressors, such as boiler furnaces, desulfurization towers, denitrification reactors, fan impellers, and air compressor rotors, to monitor the operating status of the equipment. The operating parameters of boilers include boiler load, excess air coefficient, furnace pressure, and flue gas oxygen content; the operating parameters of desulfurization and denitrification equipment include desulfurization tower pressure drop, desulfurizer flow, flue gas SO 2 Concentration and flue gas NO xconcentration, etc.; the operating parameters of the fan include fan speed, fan impeller temperature, fan vibration value and fan current, etc.; the operating parameters of the air compressor include air compressor speed, air compressor inlet temperature, air compressor outlet temperature, air compressor current and air compressor power, etc.; wireless sensor network technology, such as ZigBee, LoRa or NB-IoT, is used to achieve low power consumption and long-distance transmission of data, reducing wiring costs and maintenance difficulties. The data collected by the sensor is transmitted to the data processing module through the wireless sensor network to form the first historical operation data set and the first real-time operation data set, providing a basis for subsequent data fusion and equipment performance prediction.

[0076] Step S1200, performing data cleaning, anomaly detection and feature extraction on the first historical operation data set and the first real-time operation data set to generate a first historical feature data set and a first real-time feature data set;

[0077] Specifically, statistical methods, such as the 3σ principle and box plots, are used to clean the data, remove obvious outliers and outliers, and improve the reliability of the data. Machine learning algorithms, such as isolation forests and local anomaly factors, are used to detect anomalies in the data and identify abnormal patterns and potential faults during equipment operation. Based on domain knowledge and expert experience, key features of equipment operating parameters, such as mean, variance, trend, etc., are extracted to reduce the dimension and complexity of the data. Data standardization or normalization methods are used to scale feature data to eliminate the impact of different dimensions, which is convenient for subsequent model training and fusion. Data cleaning, anomaly detection, and feature extraction processes can effectively improve data quality, reduce data dimensions, and reduce computational complexity, laying the foundation for equipment performance prediction and collaborative control.

[0078] Step S1300, constructing a device parameter association network model according to the first historical operation data set;

[0079] Furthermore, step S1300 includes:

[0080] Step S1310, using a correlation analysis method to calculate the correlation index coefficients between the equipment operating parameters, and constructing a correlation matrix between the equipment operating parameters;

[0081] Further, step S1310 includes:

[0082] Step S1311, calculating the linear correlation coefficient of the continuous operation parameter;

[0083] Step S1312, calculating the mutual information value of the discrete operating parameters;

[0084] Step S1313, constructing a correlation matrix of equipment parameters based on the linear correlation coefficients and mutual information values ​​of the operating parameters;

[0085] Specifically, the correlation index coefficient includes the linear correlation coefficient and mutual information value of the equipment operating parameters. For continuous operating parameters (such as temperature, pressure, etc.), the Pearson correlation coefficient is used to measure their linear correlation. The larger the absolute value of the coefficient, the stronger the linear relationship between the parameters. For example, the amount of coal burned in a boiler and the steam pressure of the boiler usually have a strong positive correlation. For discrete or categorical parameters (such as equipment status, fault type, etc.), mutual information is used to measure their nonlinear correlation. The larger the mutual information value, the stronger the correlation between the parameters. The correlation matrix of the equipment parameters is constructed based on the linear correlation coefficient and mutual information value of the operating parameters to quantitatively characterize the degree of correlation between the parameters; correlation analysis can quickly screen out parameters with greater mutual influence, such as the amount of coal burned in the boiler and the furnace temperature, the active power of the generator, etc., which provides targeted data support for subsequent causal analysis and the construction of association network models, reducing the computational complexity. At the same time, the correlation matrix also provides researchers with a global parameter association view, which helps to grasp the interaction mode of parameters from a macro perspective.

[0086] Step S1320, constructing a cause-and-effect relationship diagram between equipment operating parameters using a time series analysis method;

[0087] Further, step S1320 includes:

[0088] Step S1321, calculating the mutual correlation coefficients between different operating parameter time series;

[0089] Step S1322, using Granger causality test to determine whether the historical value of a parameter is helpful for predicting the future value of another parameter, and obtaining the causality test result;

[0090] Step S1323, constructing a causal relationship diagram of the operating parameters based on the mutual correlation coefficient and the causal test result;

[0091] Specifically, cross-correlation analysis is used to calculate the mutual correlation coefficients between different parameter time series to measure the change pattern of correlation with time lag. The smaller the time lag and the larger the mutual correlation coefficient, the closer the dynamic correlation between the parameters. For example, the mutual correlation coefficient between the steam turbine inlet pressure and the generator power may reach the maximum under a time lag of 1 to 2 minutes, revealing the lag control effect of the steam turbine on the generator. Granger causality test is used to determine whether the historical value of a parameter is helpful for predicting the future value of another parameter, revealing the causal dependence between the parameters. If the historical value of parameter A significantly affects the prediction effect of parameter B, then A is called the Granger cause of B. For example, changes in the amount of coal burned in the boiler are usually the Granger cause of changes in the boiler steam pressure. The causal relationship diagram shows the relationship between causal dependence and time sequence, connects significant causal dependence pairs with directed edges, and connects close dynamic association pairs with undirected edges to form a directed acyclic graph, which condenses and characterizes the dynamic characteristics of the system. Causal analysis further distinguishes the dependency and sequence of "cause and effect" and "result" between parameters based on the "association" of parameters revealed by correlation analysis, that is, the possible direction and path of influence transmission, which is crucial for understanding the internal mechanism of power plant system and optimizing control strategy. Through the causal relationship diagram, the upstream and downstream status of each parameter in the causal chain can be intuitively judged, key influencing parameters (upstream parameters that have a greater impact on other parameters) and bottleneck parameters (downstream parameters that are greatly affected by other parameters) can be identified, and parameter optimization can be carried out in a targeted manner to improve system performance.

[0092] Step S1330, mapping devices to network nodes, using the operating parameters of each device as node attributes, establishing edges between device nodes based on the correlation matrix and causal relationship graph, and constructing a device parameter association network model;

[0093] Specifically, according to the system topology and process flow of power plant boilers, steam turbines, generators and other equipment, each device is abstracted as a node of the association network, and the operating parameters of the equipment such as temperature, pressure, flow, power, etc. are used as node attributes. The results of correlation analysis and causal analysis are used to measure the correlation strength between equipment operating parameters, and edges are established between parameters with correlation strength higher than a certain threshold to form an equipment parameter association network model of the power plant system. The degree distribution, clustering coefficient, average path length and other statistical characteristics of the association network are calculated. The degree distribution reflects the heterogeneity of the association network and the unique connection mode of key nodes; the clustering coefficient measures the local tightness of the network and quantifies the association and aggregation characteristics of equipment operating parameters; the average path length reflects the transmission efficiency of the network and describes the average association distance between equipment parameters. Through complex network modeling and analysis, the interaction mechanism between power plant equipment parameters is described from the perspective of association. The network topology and statistical characteristics help to understand the system behavior and provide new ideas for exploring the internal laws of the system and optimizing the scheduling strategy.

[0094] Step S2000, filtering out key features closely related to boiler performance from the first historical feature data set, generating a second historical feature data set, constructing and training a boiler performance prediction model based on the second historical feature data set; inputting the first real-time feature data set into the trained boiler performance prediction model to obtain a predicted value of boiler performance parameters; comparing the predicted value of boiler performance parameters with a preset performance threshold, and when the predicted value of boiler performance parameters is lower than the preset performance threshold, executing step S3000 to trigger a collaborative control process;

[0095] Furthermore, step S2000 includes:

[0096] Step S2100, selecting key features closely related to boiler performance from the first historical feature data set to generate a second historical feature data set; using a machine learning algorithm to construct and train a boiler performance prediction model based on the second historical feature data set;

[0097] Specifically, according to the complexity of the boiler performance prediction problem and the data characteristics, machine learning algorithms such as support vector machines, random forests or neural networks are selected to build a boiler performance prediction model to reveal the nonlinear mapping relationship between boiler operating parameters and performance indicators. Through feature selection or feature extraction methods, such as recursive feature elimination and principal component analysis, key features closely related to boiler performance, such as boiler load, fuel quality, superheater temperature, etc., are extracted from the first historical feature data set to generate a second historical feature data set, reduce the input dimension of the model, and improve training efficiency and prediction accuracy. Hyperparameter tuning techniques, such as grid search, random search or Bayesian optimization, are used to search for the optimal hyperparameter combination of machine learning algorithms, such as the kernel function type and penalty coefficient of the support vector machine, the number of trees of the random forest, the maximum tree depth, etc., to improve the prediction performance and robustness of the model. Using methods such as cross-validation or leave-one-out, the first historical feature data set is divided into training set, validation set and test set, and the model is trained, adjusted and evaluated. The model with the strongest generalization ability and the smallest prediction error is selected as the final boiler performance prediction model. The boiler performance prediction method based on machine learning can fully explore the laws and knowledge contained in historical operation data, establish a complex nonlinear relationship between boiler operating parameters and performance indicators, and provide strong support for boiler operation optimization and fault diagnosis.

[0098] Step S2200, inputting the first real-time feature data set into the trained boiler performance prediction model to obtain a predicted value of the boiler performance parameter; comparing the predicted value of the boiler performance parameter with a preset performance threshold, and when the predicted value of the boiler performance parameter is lower than the preset performance threshold, executing step S3000 to trigger the collaborative control process;

[0099] Specifically, the first real-time feature data set is input into the trained boiler performance prediction model, and the model calculates the boiler efficiency, NO x Performance parameters such as emission concentration reflect the real-time operating status of the boiler. According to the physical meaning of boiler performance parameters and engineering experience, preset performance thresholds are set, such as the lower limit of boiler efficiency is 90%, NO x The upper limit of emission concentration is 100mg / m 3 The boiler performance prediction model outputs a performance parameter prediction value that is compared with the preset performance threshold in real time. When the real-time predicted boiler efficiency is lower than 90% or NO x Emission concentration is higher than 100mg / m 3 When the boiler is running low, it means that the boiler is not in good condition. There may be problems such as incomplete combustion, increased heat loss, and excessive pollutants. It is necessary to trigger the coordinated control process to adjust the boiler operating parameters and the operating conditions of other equipment to achieve optimal control of the system. By predicting the boiler performance parameters in real time and comparing them with the preset performance thresholds, abnormal conditions in the boiler operation can be discovered in time, and measures can be taken in advance to optimize and adjust, thereby improving the safety, economy, and environmental protection of the system.

[0100] Step S3000, based on the predicted values ​​of boiler performance parameters and preset performance thresholds, calculate the optimal operating parameters of the desulfurization and denitrification equipment, and generate a first adjustment parameter set; with the goal of maximizing system energy efficiency, calculate the optimal operating parameters of the fan and the air compressor, and generate a second adjustment parameter set and a third adjustment parameter set; based on the predicted values ​​of boiler performance parameters, the first adjustment parameter set, the second adjustment parameter set and the third adjustment parameter set, generate a collaborative control strategy set for the boiler, desulfurization and denitrification equipment, the fan and the air compressor; and send the collaborative control strategy set to each device for corresponding regulation and control operations.

[0101] Furthermore, step S3000 includes:

[0102] Step S3100, based on the predicted value of boiler performance parameters and the preset performance threshold, calculate the optimal operating parameters of the desulfurization and denitrification equipment and generate a first adjustment parameter set;

[0103] Furthermore, if Figure 2 As shown, step S3100 includes:

[0104] Step S3110, calculating the deviation between the predicted value of the boiler performance parameter and the preset performance threshold, and determining the adjustment direction and amplitude of the desulfurization and denitrification equipment operation parameters;

[0105] Step S3120, taking maximizing desulfurization efficiency and denitrification efficiency and minimizing reagent consumption as optimization objectives, taking equipment operating parameters as optimization variables, and taking the adjustment range of desulfurization and denitrification equipment operating parameters as constraints, constructing a target optimization function; by solving the target optimization function, obtaining the optimal operating parameter combination of the desulfurization and denitrification equipment;

[0106] Taking desulfurization efficiency, denitrification efficiency and reagent consumption as optimization targets and equipment operation parameters as optimization variables, the methods for constructing the target optimization function include:

[0107] The objective optimization function is:

[0108] Maximize f(x)=ω 1 ×f 1 (x)+ω 2 ×f 2 (x)-ω 3 ×f 3 (x);

[0109]

[0110]

[0111] f 3 (x) = k 3 ·x 2 +k 4 ·x 6 ;

[0112] in:

[0113] f 1 (x): desulfurization efficiency function;

[0114] f 2 (x): denitrification efficiency function;

[0115] f 3 (x): medicine consumption function;

[0116] ω 1 : Weight coefficient of desulfurization efficiency, used to balance the importance of desulfurization efficiency;

[0117] ω 2 : Weight coefficient of denitrification efficiency, used to balance the importance of denitrification efficiency;

[0118] ω 3 : Weight coefficient of medicine consumption, used to balance the importance of medicine consumption;

[0119] x: optimization variable vector, including various operating parameters of desulfurization and denitrification equipment, x = [x 1 ,x 2 ,x3 ,x 4 ,x 5 ,x 6 ];

[0120] x 1 : pH value of the slurry affects the rate and efficiency of the reaction;

[0121] x 2 : Desulfurization agent flow rate directly affects the agent consumption of the desulfurization reaction;

[0122] x 3 : Flue gas flow rate, which affects the contact time of reactants and mass transfer efficiency;

[0123] x 4 : Denitrification catalyst activity, affecting the rate of denitrification reaction;

[0124] x 5 : Reaction temperature, which affects the reaction rate and efficiency;

[0125] x 6 : Ammonia flow rate affects the reagent consumption of denitrification reaction.

[0126] k 1 : Empirical constant of desulfurization efficiency;

[0127] k 2 : Empirical constant of denitrification efficiency;

[0128] k 3 : Weight coefficient of desulfurization agent flow rate in agent consumption function;

[0129] k 4 : Weight coefficient of ammonia flow rate in reagent consumption function;

[0130] a 1 : The empirical constant of slurry pH value in the desulfurization efficiency function;

[0131] a 2 : The empirical constant of the desulfurization agent flow rate in the desulfurization efficiency function;

[0132] a 3 : empirical constant of slurry pH value in denitrification efficiency function;

[0133] a 4 : Empirical constant of denitration catalyst activity in denitration efficiency function;

[0134] a 5 : The empirical constant of reaction temperature in the denitrification efficiency function;

[0135] b 1 : Weight coefficient of flue gas flow rate in desulfurization efficiency function;

[0136] b 2 : Weight coefficient of flue gas flow rate in denitrification efficiency function;

[0137] c 1 : Empirical constant of flue gas flow rate in desulfurization efficiency function;

[0138] c 2 : empirical constant of flue gas velocity in denitrification efficiency function;

[0139] The empirical constants and weight coefficients in the formula need to be obtained by technical personnel in this field based on specific practical needs, past experience, and a large number of experiments. The desulfurization efficiency increases with the increase of slurry pH value and desulfurization agent flow rate, but it will decrease with the increase of flue gas flow rate. The denitrification efficiency increases with the increase of slurry pH value, denitrification catalyst activity and reaction temperature, but it will decrease with the increase of flue gas flow rate. Agent consumption increases with the increase of desulfurization agent flow rate and ammonia flow rate; maximization of desulfurization efficiency and denitrification efficiency improves the effect of exhaust gas treatment, reduces pollutant emissions, and meets environmental protection requirements; minimization of agent consumption reduces operating costs and improves economic benefits; multi-objective optimization is to find a balance between the three goals of maximizing desulfurization efficiency and denitrification efficiency, and minimizing agent consumption, so that the overall system performance is optimized.

[0140] Step S3130, taking the optimal operating parameter combination as the first adjustment parameter set, and sending it to the control system of the desulfurization and denitrification equipment in real time, so as to guide the desulfurization and denitrification equipment to perform parameter adjustment and optimization control;

[0141] Step S3140, after the desulfurization and denitrification equipment executes the first adjustment parameter set, continuously monitor the operation status and pollutant emission indicators of the equipment to evaluate the adjustment effect;

[0142] Specifically, when the predicted value of boiler performance parameters deviates from the preset performance threshold, the coordinated control process of desulfurization and denitrification equipment is triggered. xThe degree of emission concentration exceeding the standard determines the adjustment direction and amplitude of the operating parameters of the desulfurization and denitrification equipment, such as increasing the pH value of the limestone slurry, extending the regeneration cycle of the denitrification catalyst, etc., so as to determine the approximate range of the adjustment amplitude (for example, increase by 10% or decrease by 5%). A multi-objective optimization algorithm, such as genetic algorithm, particle swarm optimization, etc., is used, with desulfurization efficiency, denitrification efficiency and reagent consumption as optimization targets, slurry pH value, ammonia flow rate, catalyst activity, reaction temperature, etc. as optimization variables, and within the constraints of the equipment operating parameters, the optimal operating parameter combination of the desulfurization and denitrification equipment is searched. Step S3110 is to preliminarily adjust the direction and amplitude as the initial constraints of the optimization algorithm, and step S3120 uses the multi-objective optimization algorithm to further refine and search for the optimal operating parameter combination of the desulfurization and denitrification equipment based on the above preliminary conditions. The optimal operating parameter combination is used as the first adjustment parameter set, and is sent to the DCS or PLC control system of the desulfurization and denitrification equipment in real time through communication protocols such as OPC, Modbus or field bus technology to perform equipment parameter adjustment and optimization control. After the desulfurization and denitrification equipment implements the first adjustment parameter set, the operating status of the equipment and SO 2 、NO x The pollutant emission indicators such as the following are used to evaluate the adjustment effect. If the pollutant emission indicators meet the standards, the current operating parameters are maintained; if the pollutant emission indicators still do not meet the requirements, multiple rounds of iterative optimization are carried out until the emission standards are met. By optimizing the operating parameters of the desulfurization and denitrification equipment, the pollutant removal efficiency can be improved, the environmental impact can be reduced, and the consumption of desulfurization and denitrification agents can be reduced, saving operating costs.

[0143] Step S3200, taking the system energy efficiency maximization as the goal, calculating the optimal operating parameters of the fan and the air compressor, and generating a second adjustment parameter set and a third adjustment parameter set;

[0144] Further, step S3200 includes:

[0145] Step S3210, collecting system load data, including historical load data and real-time load data, building a real-time load prediction model based on the historical load data, inputting the real-time load data into the real-time load prediction model, and obtaining a load change curve for a period of time in the future; determining the adjustment direction and amplitude of the fan and the air compressor based on the load change curve for a period of time in the future and the first real-time operation data set;

[0146] Specifically, historical load data, weather data, holiday data, etc. are collected to form a sample set for load forecasting. Machine learning algorithms such as support vector machines, random forests, and long short-term memory networks are used to build real-time load forecasting models. Sample data is divided into training sets, validation sets, and test sets. Random sampling is performed according to a certain ratio. The training set data is used to estimate the parameters and optimize the structure of the model. Hyperparameters are adjusted through cross-validation and other methods to improve the model's fitting ability and generalization performance. The validation set data is used to evaluate the performance of the trained model, and evaluation indicators such as root mean square error and mean absolute percentage error are calculated. The model is further optimized based on the evaluation results, such as adjusting the model structure, introducing regularization terms, and increasing data samples. The model training and evaluation process is continuously iterated until the optimal model that meets the forecasting requirements is obtained. The model is predicted using real-time data to obtain the load change curve (trend) in the future. The load forecast results are combined with the real-time boiler performance parameters to determine the adjustment direction and amplitude of the fan and air compressor, providing a decision-making basis for collaborative control.

[0147] The following is a specific example to illustrate how to determine the adjustment direction and amplitude of the fan and air compressor based on the load change curve in the future and the first real-time operation data set:

[0148] Assume that the load change curve predicted by the real-time load forecasting model within the next hour is as follows:

[0149] First 20 minutes: Load increased from 400MW to 450MW;

[0150] 20-40 minutes: Load increases from 450MW to 500MW;

[0151] 40-60 minutes: The load is maintained at 500MW.

[0152] The performance parameters of the current boiler obtained from the first real-time operation data set are as follows:

[0153] Boiler efficiency: 90%;

[0154] Main steam flow: 1000t / h;

[0155] Main steam pressure: 16MPa;

[0156] Main steam temperature: 540℃;

[0157] Reheat steam temperature: 540℃;

[0158] Furnace negative pressure: -500Pa;

[0159] NO x Emission concentration: 100mg / m 3 .

[0160] According to the predicted load change curve and the first real-time operation data set, formulate the adjustment strategy of fans and air compressors:

[0161] The load increases from 400MW to 450MW in the first 20 minutes:

[0162] Fan adjustment direction: appropriately increase the air supply volume, maintain the negative pressure in the furnace, and improve the combustion efficiency;

[0163] Fan adjustment range: one-time air volume from 400km 3 / h increased to 420km / h 3 / h, secondary air volume from 200km 3 / h increased to 210km 3 / h;

[0164] Air compressor adjustment direction: Increase output power accordingly to ensure fan operation;

[0165] Air compressor adjustment range: Air compressor output power increases from 5000kW to 5250kW.

[0166] 20-40 minutes load increases from 450MW to 500MW:

[0167] Fan adjustment direction: further increase air supply and control NO x generate;

[0168] Fan adjustment range: one-time air volume from 420km 3 / h increased to 440km 3 / h, secondary air volume from 210km 3 / h increased to 220km 3 / h;

[0169] Air compressor adjustment direction: further increase output power to meet fan demand;

[0170] Air compressor adjustment range: Air compressor output power increases from 5250kW to 5500kW.

[0171] The load is maintained at 500MW for 40-60 minutes:

[0172] Fan adjustment direction: fine-tune air volume, optimize combustion, and reduce NO x emission;

[0173] Fan adjustment range: one-time air volume from 440km 3 / h reduced to 435km / h 3 / h, secondary air volume from 220km 3 / h reduced to 215km / h 3 / h;

[0174] Air compressor adjustment direction: fine-tune output power and reduce energy consumption;

[0175] Air compressor adjustment range: air compressor output power decreases from 5500kW to 5400kW.

[0176] Step S3220, taking the maximization of system energy efficiency as the goal and the adjustment range of the fan and the air compressor as the constraint condition, constructing a fan and air compressor collaborative control optimization model; solving the fan and air compressor collaborative control optimization model to obtain the optimal working parameter combination of the fan and the air compressor, which are marked as the second adjustment parameter set and the third adjustment parameter set respectively;

[0177] The method of constructing the fan and air compressor coordinated control optimization model includes:

[0178] Objective function:

[0179]

[0180] in:

[0181] η: system energy efficiency;

[0182] P out : total system output power;

[0183] P in : total system input power;

[0184] P fan : fan output power;

[0185] P comp : Output power of air compressor;

[0186] P coal : coal-fired input power;

[0187] P elec : Electric power input power;

[0188] Coal input power refers to the heat energy generated by burning coal, and electric input power refers to the power input from the external power supply during the operation of the system. This part of the power input may be used to drive auxiliary equipment, such as fans, pumps, conveying devices, etc., to ensure the normal operation of the entire system. The total system input power refers to the total energy input required when the system is running. It is equal to the sum of the heat energy obtained from coal and the electric energy obtained from the external power grid. The coal input power can be calculated from the boiler coal consumption, and the electric input power can be read from the electric meter.

[0189] Constraints:

[0190]

[0191] Q fan+Q comp =Q load ;

[0192] in:

[0193] Q fan : Fan air volume;

[0194] The lower limit of the fan air volume;

[0195] Upper limit of fan air volume;

[0196] The lower limit of fan output power;

[0197] The upper limit of the fan output power;

[0198] η fan : Fan efficiency;

[0199] The lower limit of fan efficiency;

[0200] The upper limit of fan efficiency;

[0201] Q comp : Air compressor air volume;

[0202] The lower limit of air compressor air volume;

[0203] The upper limit of air compressor air volume;

[0204] The lower limit of air compressor output power;

[0205] The upper limit of the air compressor output power;

[0206] η comp : Air compressor efficiency;

[0207] The lower limit of air compressor efficiency;

[0208] The upper limit of air compressor efficiency;

[0209] Q load : Air volume required by system load;

[0210] The optimization model aims to maximize the system energy efficiency and takes into account the operating parameters of fans and air compressors, such as efficiency, power, and air volume. Among them, the efficiency, power, and air volume of fans and air compressors can be measured by the sensors of the equipment itself; the system load refers to the total power consumption of all electrical equipment in the system at a certain moment, reflecting the total power demand of the system; the system load demand air volume refers to the amount of air required by the boiler system under specific load conditions to ensure the normal combustion process and the best combustion efficiency. It refers to the amount of oxygen required to meet the combustion requirements of the boiler under the current operating state plus the appropriate amount of excess air to ensure the complete combustion of the fuel and reduce pollutant emissions. The system load demand air volume can be estimated based on the boiler combustion oxygen demand and excess air coefficient. The excess air coefficient refers to the ratio of the actual amount of air supplied during the combustion process to the theoretical amount of air required for complete combustion. By solving the optimization model, the optimal working parameter combination of fans and air compressors can be obtained to maximize the system energy efficiency. Modern heuristic optimization algorithms, such as differential evolution, harmonic search, particle swarm optimization, etc., are used to search for the optimal solution of the fan and air compressor collaborative control optimization model in the multidimensional parameter space, and the optimal working parameter combination of the fan and air compressor is obtained, which is used as the second adjustment parameter set and the third adjustment parameter set respectively. As the system load changes, the optimization parameters of the fan and air compressor will also be adjusted accordingly, and the efficient collaborative operation state will always be maintained. The optimized fan and air compressor have higher efficiency and lower energy consumption, which helps to improve the boiler combustion efficiency, reduce fuel consumption and pollutant emissions. At the same time, the optimization model can also adjust the fan and air compressor parameters in advance according to the load forecast results to improve the dynamic response capability and stability of the system. In short, the fan and air compressor collaborative control optimization model comprehensively considers the energy efficiency goals and equipment constraints, and provides a theoretical basis and decision support for the collaborative optimization control of the boiler system through mathematical modeling and intelligent solution, which is of great significance for improving the economic and environmental protection of power plant operation.

[0211] Step S3230: Send the second adjustment parameter set and the third adjustment parameter set to the fan control system and the air compressor control system respectively to perform equipment parameter adjustment and optimization control.

[0212] Through OPC, Modbus and other communication protocols or fieldbus technologies, the second adjustment parameter set and the third adjustment parameter set are sent to the fan control system and the air compressor control system, such as DCS, PLC, etc., to perform equipment parameter adjustment and optimization control, and realize the coordinated operation of the fan and the air compressor. After the equipment executes the adjustment parameters, the system energy efficiency indicators and equipment operating status are continuously monitored, the optimization control effect is evaluated, and multiple rounds of iterative optimization are performed when necessary. Through the coordinated control of fans and air compressors, the system energy conversion efficiency can be improved, energy consumption can be reduced, the equipment operating cost can be reduced, and the energy-saving operation of the system can be realized.

[0213] Step S3300, based on the predicted value of boiler performance parameters, the first adjustment parameter set, the second adjustment parameter set and the third adjustment parameter set, generate a collaborative control strategy set for the boiler, desulfurization and denitrification equipment, fans and air compressors; and send the collaborative control strategy set to each device for corresponding regulation and control operations.

[0214] Furthermore, if Figure 3 As shown, step S3300 includes:

[0215] Step S3310, calculating the priority of each adjustment parameter set according to the deviation value between the predicted value of the boiler performance parameter and the preset performance threshold value, and the influence weight of the first adjustment parameter set, the second adjustment parameter set and the third adjustment parameter set on the boiler performance;

[0216] The weight of the influence of the first adjustment parameter set on the boiler performance is greater than the weight of the influence of the second adjustment parameter set on the boiler performance; the weight of the influence of the second adjustment parameter set on the boiler performance is greater than the weight of the influence of the third adjustment parameter set on the boiler performance;

[0217] The method for calculating the priority of each adjustment parameter set includes:

[0218]

[0219] in:

[0220] U i : The priority of the i-th (i=1, 2, 3) adjustment parameter set;

[0221] P: predicted value of boiler performance parameters;

[0222] T: preset performance threshold;

[0223] W i : The influence weight of the i-th adjustment parameter set on boiler performance;

[0224] W j : The influence weight of the jth adjustment parameter set on boiler performance;

[0225] E i : The effect of the i-th adjustment parameter set on boiler performance. The larger the value, the better the effect.

[0226] E j : The effect of the jth adjustment parameter set on boiler performance;

[0227] C i : The cost of the i-th adjustment parameter set;

[0228] α: weight coefficient of the deviation between the predicted value of the performance parameter and the preset performance threshold, used to adjust the impact of the deviation on the priority, determined by those skilled in the art based on a large number of experiments;

[0229] β: weight coefficient of the effect of adjusting the parameter set, determined by technicians in this field based on a large number of experiments;

[0230] Adjusting synergies between parameter sets;

[0231] γ: the synergistic effect coefficient between the adjustment parameter sets, which is determined by those skilled in the art based on a large number of experiments;

[0232] The effect of the adjustment parameter set on boiler performance is determined by technical personnel in this field through experiments and historical data analysis; the synergistic effect between adjustment parameter sets is used to quantify the synergistic effect between different adjustment parameter sets, reflecting their mutually reinforcing effect. The cost of the adjustment parameter set is determined through cost analysis, including equipment, labor, time and other aspects of the cost, reflecting the resources and costs required to implement a certain adjustment parameter set. This formula comprehensively considers the deviation of boiler performance parameters, the influence weights and effects of each adjustment parameter set, the synergistic effect between adjustment parameter sets and the adjustment cost, and can more comprehensively evaluate the priority of each adjustment parameter set, helping decision makers to choose the most effective and lowest cost solution among multiple adjustment solutions.

[0233] Specifically, in step S3310, the severity of boiler performance deterioration is determined by calculating the deviation value (deviation size) between the predicted value of boiler performance parameters and the preset performance threshold. The larger the deviation, the more serious the boiler performance deterioration, and measures need to be taken as a priority for optimization control. At the same time, different influence weights are assigned based on the importance of the first adjustment parameter set, the second adjustment parameter set, and the third adjustment parameter set in the coordinated control of the equipment. Generally speaking, since the coupling relationship between the desulfurization and denitrification equipment and the boiler is the closest, the weight of the first adjustment parameter set can be set to the highest; followed by the adjustment of the fan parameters directly related to the operation of the boiler, and the second adjustment parameter set is second; the adjustment of the air compressor parameters has a relatively small impact on the boiler, and the weight of the third adjustment parameter set can be set to the lowest. The adjustment parameter set with a high priority should be issued and executed first. Such a priority sorting method can maximize the effect of the coordinated control of each device and improve the boiler performance in the shortest time.

[0234] Step S3320: Send three adjustment parameter sets to the control systems of corresponding devices in descending order of priority; coordinate the execution sequence of adjustment parameters of each device according to the logical association between the devices to generate a collaborative control strategy set;

[0235] Specifically, the first adjustment parameter set, the second adjustment parameter set, and the third adjustment parameter set are sent to the control system of the corresponding device in order of priority from high to low. At the same time, due to the logical association between the devices in the system, the parameter adjustment of some devices may need to be based on other devices. For example, only when the compressed air provided by the air compressor is sufficient can the fan increase the air supply appropriately; only when the air supply and temperature of the fan meet the requirements can the desulfurization and denitrification equipment optimize the operating parameters. Therefore, it is necessary to comprehensively consider the logical relationship between the devices, coordinate the execution sequence of the adjustment parameters of each device, and ensure the safety and effectiveness of the coordinated operation of the equipment. This coordination mechanism can maximize the synergy between devices, avoid negative interference from parameter adjustment, and improve the reliability of the control strategy.

[0236] Step S3330, after each device completes the control operation according to the execution sequence of the adjustment parameters in the collaborative control strategy set, evaluate the improvement effect of the boiler performance parameters; if the improvement effect does not meet expectations, return to step S3310 and recalculate the priority of the adjustment parameter set until the boiler performance parameters meet the preset performance threshold requirements.

[0237] Specifically, the operating status of each device after executing the adjustment parameter set is evaluated, with a focus on the improvement effect of boiler performance parameters. If the improvement effect meets expectations, the boiler's efficiency, NO x If the emission and other indicators meet the preset performance threshold requirements, it is considered that the multi-device collaborative control has achieved good results and the current round of control process can be terminated. On the contrary, if the boiler performance improvement is not obvious and the expected goal has not been achieved, it is necessary to return to step S3310, re-evaluate the current boiler performance deterioration and adjust the parameter set influence weight, generate a new priority sequence, and start a new round of equipment collaborative control based on this until the boiler performance meets the preset threshold requirements. This iterative optimization strategy can continuously improve boiler performance, break through the bottleneck of single equipment regulation, and ultimately achieve the optimization of multi-device collaborative operation.

[0238] Through step S3300, the multi-device collaborative control strategy can be automatically generated and optimized according to the real-time performance prediction of the boiler and the collaborative relationship between the equipment, so as to maximize the synergistic effect of desulfurization and denitrification equipment, fans, air compressors and other equipment, and improve the economy and environmental protection of the system operation under the premise of meeting the boiler performance constraints. This collaborative control method based on real-time optimization provides a new idea for power plants to achieve refined boiler control and efficient collaboration of multiple equipment, which is of great significance for improving the comprehensive performance of boiler systems.

[0239] Example 2

[0240] This embodiment provides a device status monitoring distributed control system based on embodiment 1, such as Figure 4 As shown, including:

[0241] Data collection module: used to collect the operating parameters of each device to form a first historical operating data set and a first real-time operating data set;

[0242] Data processing module: used for performing data cleaning, anomaly detection and feature extraction on the first historical operation data set and the first real-time operation data set to generate a first historical feature data set and a first real-time feature data set;

[0243] An association model building module: used for building an equipment parameter association network model according to the first historical operation data set;

[0244] Boiler performance prediction module: used to filter out key features closely related to boiler performance from the first historical feature data set, generate a second historical feature data set, build and train a boiler performance prediction model based on the second historical feature data set; input the first real-time feature data set into the trained boiler performance prediction model to obtain the predicted value of boiler performance parameters;

[0245] Collaborative control judgment module: used to compare the predicted value of boiler performance parameters with the preset performance threshold. When the predicted value of boiler performance parameters is lower than the preset performance threshold, the collaborative control process is triggered.

[0246] Adjustment parameter set generation module: used to calculate the optimal operating parameters of the desulfurization and denitrification equipment based on the predicted value of the boiler performance parameters and the preset performance threshold, and generate the first adjustment parameter set; with the goal of maximizing the system energy efficiency, calculate the optimal operating parameters of the fan and the air compressor, and generate the second adjustment parameter set and the third adjustment parameter set;

[0247] Collaborative control strategy generation module: used to generate collaborative control strategy sets for boilers, desulfurization and denitrification equipment, fans and air compressors according to the predicted values ​​of boiler performance parameters, the first adjustment parameter set, the second adjustment parameter set and the third adjustment parameter set;

[0248] Execution control module: used to send the collaborative control strategy set to each device for corresponding regulation operations.

[0249] Example 3

[0250] This embodiment discloses an electronic device, including a memory, a central processing unit, and a computer program stored in the memory and executable on the central processing unit. When the central processing unit executes the computer program, the above-mentioned device status monitoring distributed control method is implemented.

[0251] Since the electronic device introduced in this embodiment is an electronic device used to implement a device status monitoring and distributed control method in the embodiment of this application, based on the device status monitoring and distributed control method introduced in the embodiment of this application, the technical personnel of this field can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as the technical personnel of this field implement the electronic device used in the device status monitoring and distributed control method in the embodiment of this application, it belongs to the scope of protection of this application.

[0252] Example 4

[0253] This embodiment discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, the above-mentioned device status monitoring distributed control method is implemented.

[0254] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0255] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD) or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0256] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0257] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0258] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0259] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0260] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0261] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0262] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A distributed control method for equipment status monitoring, characterized in that: include: Collecting operating parameters of each device to form a first historical operating data set and a first real-time operating data set; Performing data cleaning, anomaly detection, and feature extraction on the first historical operation data set and the first real-time operation data set to generate a first historical feature data set and a first real-time feature data set; Building a device parameter association network model based on the first historical operation data set; Select key features closely related to boiler performance from the first historical feature data set, generate a second historical feature data set, build and train a boiler performance prediction model based on the second historical feature data set; input the first real-time feature data set into the trained boiler performance prediction model to obtain a predicted value of boiler performance parameters; Compare the predicted value of the boiler performance parameter with the preset performance threshold, and when the predicted value of the boiler performance parameter is lower than the preset performance threshold, trigger the collaborative control process; Based on the predicted value of boiler performance parameters and the preset performance threshold, the optimal operating parameters of the desulfurization and denitrification equipment are calculated to generate a first adjustment parameter set; Taking the system energy efficiency maximization as the goal, the optimal operating parameters of the fan and the air compressor are calculated to generate the second adjustment parameter set and the third adjustment parameter set; Based on the predicted values ​​of boiler performance parameters, the first adjustment parameter set, the second adjustment parameter set and the third adjustment parameter set, a collaborative control strategy set for the boiler, desulfurization and denitrification equipment, fans and air compressors is generated; the collaborative control strategy set is sent to each device for corresponding regulation and control operations.

2. A distributed control method for equipment status monitoring according to claim 1, characterized in that: The collecting of the operating parameters of each device includes: Install intelligent sensor networks on boilers, desulfurization and denitrification equipment, fans and air compressors to collect operating parameters of each device; The first historical operation data set includes historical operation parameters of boilers, desulfurization and denitrification equipment, fans and air compressors; The first real-time operation data set is composed of real-time operation parameters of the boiler; The constructing of the equipment parameter association network model according to the first historical operation data set includes: Calculate the correlation index coefficients between equipment operating parameters and construct the correlation matrix between equipment operating parameters; Use time series analysis method to construct the cause-effect relationship diagram between equipment operation parameters; The devices are mapped as network nodes, and the operating parameters of each device are used as node attributes. Based on the correlation matrix and causal relationship diagram, the edges between device nodes are established to construct a device parameter association network model.

3. A distributed control method for equipment status monitoring according to claim 2, characterized in that: The correlation matrix between the operating parameters of the construction equipment includes: Calculate the linear correlation coefficient of continuous operation parameters; Calculate the mutual information value of discrete operating parameters; A correlation matrix of equipment parameters is constructed based on the linear correlation coefficients and mutual information values ​​of the operating parameters; The cause-effect relationship diagram between the operating parameters of the equipment is constructed as follows: Calculate the mutual correlation coefficients between the time series of different operating parameters; Use Granger causality test to determine whether the historical value of a parameter is helpful for predicting the future value of another parameter and obtain the causal test result; Based on the mutual correlation coefficients and causal test results, a causal relationship diagram of the operating parameters is constructed.

4. The device status monitoring distributed control method according to claim 1, characterized in that: The calculating of the optimal operating parameters of the desulfurization and denitration equipment to generate the first adjustment parameter set comprises: Calculate the deviation between the predicted value of boiler performance parameters and the preset performance threshold value, and determine the adjustment direction and amplitude of the operating parameters of the desulfurization and denitrification equipment; The optimization goal is to maximize the desulfurization efficiency and denitrification efficiency while minimizing the reagent consumption, the equipment operating parameters are used as the optimization variables, and the adjustment range of the desulfurization and denitrification equipment operating parameters is used as the constraint condition to construct the target optimization function; By solving the target optimization function, the optimal operating parameter combination of the desulfurization and denitrification equipment is obtained; and the optimal operating parameter combination is used as the first adjustment parameter set.

5. The distributed control method for equipment status monitoring according to claim 1, characterized in that: The calculating the optimal operating parameters of the fan and the air compressor to generate the second adjustment parameter set and the third adjustment parameter set includes: Collect system load data, including historical load data and real-time load data, build a real-time load forecasting model based on the historical load data, input the real-time load data into the real-time load forecasting model, and obtain the load change curve in the future period; Determine the adjustment direction and amplitude of the fan and air compressor according to the load change curve in the future period and the first real-time operation data set; With the goal of maximizing system energy efficiency and the adjustment range of fans and air compressors as constraints, a fan and air compressor collaborative control optimization model is constructed. Solve the fan and air compressor collaborative control optimization model to obtain the optimal operating parameter combination of the fan and air compressor, which are marked as the second adjustment parameter set and the third adjustment parameter set respectively.

6. The distributed control method for equipment status monitoring according to claim 1, characterized in that: The generating of the coordinated control strategy set of the boiler, the desulfurization and denitrification equipment, the fan and the air compressor according to the predicted value of the boiler performance parameter, the first adjustment parameter set, the second adjustment parameter set and the third adjustment parameter set includes: Calculate the priority of each adjustment parameter set according to the deviation between the predicted value of the boiler performance parameter and the preset performance threshold, and the influence weight of the first adjustment parameter set, the second adjustment parameter set and the third adjustment parameter set on the boiler performance; In descending order of priority, the three adjustment parameter sets are sent to the control systems of the corresponding devices in sequence; based on the logical associations between the devices, the execution sequence of the adjustment parameters of each device is coordinated to generate a collaborative control strategy set; After each device completes the control operation according to the execution sequence of the adjustment parameters in the collaborative control strategy set, the improvement effect of the boiler performance parameters is evaluated; if the improvement effect does not meet expectations, the priority of the adjustment parameter set is recalculated until the boiler performance parameters meet the preset performance threshold requirements.

7. A distributed control method for equipment status monitoring according to claim 6, characterized in that: The method for calculating the priority of each adjustment parameter set includes: Among them, U i is the priority of the i-th adjustment parameter set, i = 1, 2, 3, P is the predicted value of boiler performance parameters, T is the preset performance threshold, W i is the weight of the influence of the i-th adjustment parameter set on boiler performance, W j is the influence weight of the jth adjustment parameter set on boiler performance, E i is the effect of the ith adjustment parameter set on boiler performance, E j is the effect of the jth adjustment parameter set on boiler performance, C i is the cost of the i-th adjustment parameter set, α is the weight coefficient of the deviation between the performance parameter prediction value and the preset performance threshold, β is the weight coefficient of the effect of the adjustment parameter set, is the synergistic effect between the adjustment parameter sets, and γ is the synergistic effect coefficient between the adjustment parameter sets.

8. A distributed control system for monitoring equipment status, used to implement a distributed control method for monitoring equipment status according to any one of claims 1 to 7, characterized in that: The system comprises: Data collection module: used to collect the operating parameters of each device to form a first historical operating data set and a first real-time operating data set; Data processing module: used for performing data cleaning, anomaly detection and feature extraction on the first historical operation data set and the first real-time operation data set to generate a first historical feature data set and a first real-time feature data set; An association model building module: used for building an equipment parameter association network model according to the first historical operation data set; Boiler performance prediction module: used to filter out key features closely related to boiler performance from the first historical feature data set, generate a second historical feature data set, build and train a boiler performance prediction model based on the second historical feature data set; input the first real-time feature data set into the trained boiler performance prediction model to obtain the predicted value of boiler performance parameters; Collaborative control judgment module: used to compare the predicted value of boiler performance parameters with the preset performance threshold. When the predicted value of boiler performance parameters is lower than the preset performance threshold, the collaborative control process is triggered. Adjustment parameter set generation module: used to calculate the optimal operating parameters of the desulfurization and denitrification equipment based on the predicted value of the boiler performance parameters and the preset performance threshold, and generate the first adjustment parameter set; with the goal of maximizing the system energy efficiency, calculate the optimal operating parameters of the fan and the air compressor, and generate the second adjustment parameter set and the third adjustment parameter set; Collaborative control strategy generation module: used to generate collaborative control strategy sets for boilers, desulfurization and denitrification equipment, fans and air compressors according to the predicted values ​​of boiler performance parameters, the first adjustment parameter set, the second adjustment parameter set and the third adjustment parameter set; Execution control module: used to send the collaborative control strategy set to each device for corresponding regulation operations.

9. An electronic device comprising a memory, a central processing unit, and a computer program stored in the memory and executable on the central processing unit, characterized in that: When the central processing unit executes the computer program, a distributed control method for equipment status monitoring according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the device status monitoring distributed control method according to any one of claims 1 to 7 is implemented.

Images