Optimization control method and apparatus for device operating state, and electronic device and storage medium

Abstract

An optimization control method and apparatus for a device operating state, and an electronic device and a storage medium. The method comprises: acquiring historical data and real-time data regarding device operation, and performing screening to obtain key features related to a device operating state; preprocessing the historical data, classifying the preprocessed historical data into several categories, and generating a reference sample set for each category; using the analytic hierarchy process to calculate the weights of the key features, and constructing a feature weight matrix; using an improved multivariate state estimation algorithm to perform state estimation; predicting a device operating state on the basis of a state estimation result, and determining whether the device operating state is normal; and if the device operating state is normal, writing back into a distributed control system an optimization control parameter generated on the basis of a predicted operating state.

Description

Equipment operation status optimization control methods, devices, electronic equipment and storage media Technical Field

[0001] This application relates to the field of industrial automation equipment technology, and in particular to a method, device, electronic equipment and storage medium for optimizing equipment operation status control. Background Technology

[0002] With the acceleration of urbanization in China, the amount of urban waste generated has increased significantly, driving the development of the waste-to-energy incineration industry. However, waste-to-energy incineration faces many challenges, especially at the technological level. The maturity of complex technologies such as waste sorting, pretreatment, combustion control, and pollutant treatment directly affects the operational efficiency and environmental impact of power generation projects. Therefore, improving the energy efficiency and resource utilization rate of waste-to-energy incineration, and reducing energy loss and environmental impact, has become an important direction for technological research and development in this field.

[0003] Technical challenges are particularly prominent in the production and operation phases of the waste-to-energy incineration industry. As the core equipment in waste-to-energy incineration, the boiler's operating status is significantly affected by the complexity of waste composition, the instability of calorific value, and the lag in combustion. Existing distributed control systems (DCS) primarily formulate control strategies by collecting data such as temperature, air pressure, oxygen content, and steam volume within the furnace. However, due to the difficulty in accurately measuring the boiler's internal temperature, traditional DCS data-driven strategies fail to accurately reflect the combustion state. Airflow control, material feeding, and material adjustment are ineffective, requiring operators to observe equipment operation and manually intervene to correct control. This results in low automation levels and difficulty in achieving closed-loop control.

[0004] Compared to conventional power plants, waste-to-energy plants, due to the complex composition of waste and the uncontrollable nature of combustion, require a higher degree of automation and control precision. Existing automatic combustion control (ACC) systems can achieve some automatic adjustment functions, including feeding speed, grate speed, airflow regulation, and feed rate control, but their control effectiveness is limited. For example, current technology struggles to precisely adjust grate speed, and the judgment of waste combustion status still relies on operator observation. Existing predictive models based on neural networks or other algorithms predict steam pressure and flue gas oxygen content, but feature selection is insufficient, resulting in a poor overall reflection of waste combustion status. Furthermore, the use of neural networks requires a large amount of data, training time, and hardware costs, making operation difficult and failing to effectively reduce operator workload. Summary of the Invention

[0005] In view of this, embodiments of this application provide a method, apparatus, electronic device, and storage medium for optimizing and controlling the operating status of equipment, in order to solve the problems of insufficient signal regulation, low regulation accuracy, and poor prediction accuracy in the prior art, which lead to reduced equipment operating efficiency.

[0006] A first aspect of this application provides a method for optimizing and controlling the operating state of equipment, comprising: acquiring historical and real-time data of equipment operation and filtering out key features related to the operating state of the equipment; preprocessing the historical data, dividing the preprocessed historical data into several categories using a clustering algorithm, and generating a reference sample set for each category; calculating the weights of the key features using the analytic hierarchy process (AHP) and constructing a feature weight matrix, wherein the feature weight matrix is ​​used to adjust the influence weights of different key features in subsequent matching calculations; using an improved multivariate state estimation algorithm to estimate the state based on the similarity between the real-time data and the reference sample set; predicting the operating state of the equipment based on the state estimation results and determining the deviation between the predicted operating state and the actual operating state to determine whether the operating state of the equipment is normal; if the operating state of the equipment is normal, writing back the optimized control parameters generated based on the predicted operating state to the distributed control system so that the distributed control system adjusts the operating parameters of the equipment according to the optimized control parameters.

[0007] A second aspect of this application provides a device for optimizing and controlling the operating state of an equipment, comprising: an acquisition module for acquiring historical and real-time data of equipment operation and filtering out key features related to the operating state of the equipment; a classification module for preprocessing the historical data, dividing the preprocessed historical data into several categories using a clustering algorithm, and generating a reference sample set for each category; a construction module for calculating the weights of key features using the analytic hierarchy process (AHP) and constructing a feature weight matrix, wherein the feature weight matrix is ​​used to adjust the influence weights of different key features in subsequent matching calculations; an estimation module for estimating the state based on the similarity between real-time data and the reference sample set using an improved multivariate state estimation algorithm; a prediction module for predicting the operating state of the equipment based on the state estimation results and determining the deviation between the predicted operating state and the actual operating state to determine whether the operating state of the equipment is normal; and an adjustment module for writing back the optimized control parameters generated based on the predicted operating state to the distributed control system if the operating state of the equipment is normal, so that the distributed control system adjusts the operating parameters of the equipment according to the optimized control parameters.

[0008] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method.

[0009] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method.

[0010] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects:

[0011] This application acquires historical and real-time data on equipment operation and filters out key features related to the equipment's operating status. The historical data is preprocessed, and a clustering algorithm is used to divide the preprocessed historical data into several categories, generating a reference sample set for each category. The Analytic Hierarchy Process (AHP) is used to calculate the weights of the key features and construct a feature weight matrix, which is used to adjust the influence weights of different key features in subsequent matching calculations. An improved multivariate state estimation algorithm is used to estimate the state based on the similarity between real-time data and the reference sample set. The equipment's operating status is predicted based on the state estimation results, and the deviation between the predicted and actual operating status is determined to assess whether the equipment is operating normally. If the equipment is operating normally, the optimized control parameters generated based on the predicted operating status are written back to the distributed control system, enabling the distributed control system to adjust the equipment's operating parameters according to the optimized control parameters. This application can improve parameter adjustment accuracy and prediction precision, thereby enhancing equipment operating efficiency. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 is a flowchart illustrating the equipment operation status optimization control method provided in an embodiment of this application;

[0014] Figure 2 is a schematic diagram illustrating the improved principle of the MSET algorithm provided in the embodiments of this application;

[0015] Figure 3 is a schematic diagram of the equipment operation status optimization control device provided in an embodiment of this application;

[0016] Figure 4 is a schematic diagram of the structure of the electronic device provided in an embodiment of this application. Detailed Implementation

[0017] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0018] With the rapid expansion of cities in China, the amount of waste generated is constantly increasing, which has driven the rapid development of the waste-to-energy incineration industry. However, the process of waste-to-energy incineration has also brought about many problems, especially environmental, social, economic, and technological challenges. The technical difficulties mainly focus on waste sorting, pretreatment, combustion control, and pollutant treatment. These technical issues often affect the efficiency and environmental impact of waste-to-energy incineration, particularly in improving energy efficiency, resource utilization, and reducing energy loss and environmental impact, which has become an important direction for current technological research and development.

[0019] Waste-to-energy incineration technology is highly complex, involving multiple fields such as waste composition identification, combustion control, and boiler internal operation monitoring. Existing technologies primarily focus on improving boiler operational stability and energy efficiency, as well as addressing the challenges of complex waste composition and unstable calorific value. Specifically, most existing solutions rely on distributed control systems (DCS) and automated control equipment to regulate boiler operation.

[0020] The main function of an automatic combustion control (ACC) system is to optimize the combustion process by automatically adjusting various parameters within the boiler, such as furnace temperature, feed rate, and primary air volume. It typically includes the following aspects:

[0021] Furnace main control temperature interlock: The burner is started by temperature control.

[0022] Automatic adjustment of feeding speed and grate movement speed: These adjustments help ensure a smooth combustion process.

[0023] Oxygen content adjustment: Adjust the secondary air volume according to the oxygen content at the boiler outlet to maintain efficient combustion.

[0024] Feed rate adjustment: The feed rate and primary air volume are adjusted by the boiler steam volume or pressure.

[0025] Although these technologies have been applied, there are still many shortcomings, especially in terms of automated control and precise adjustment.

[0026] The main problems existing in the current waste incineration process are as follows:

[0027] Inaccurate temperature measurement: Precise measurement of the boiler's internal temperature is difficult. Current technology relies on data collected by DCS equipment, such as temperature, air pressure, and oxygen content, to infer the actual conditions inside the boiler. However, this data is insufficient to accurately reflect the actual situation, leading to poor performance in airflow and feeding control.

[0028] Excessive operator intervention: Although existing control systems have automated adjustment functions, operators still need to monitor the boiler's operating status in real time and manually adjust the system based on data from the DCS system and furnace flame video to determine the combustion situation. This "human-in-the-loop" control mode is inefficient and cannot achieve a high level of automation.

[0029] Insufficient grate speed control: The existing ACC system has failed to achieve the expected results in controlling the grate speed, resulting in uneven distribution and combustion of waste during the incineration process, which in turn affects the efficiency of the entire combustion process.

[0030] The data prediction lacks comprehensiveness: Existing prediction methods typically rely solely on data from DCS equipment (such as steam volume and flue gas oxygen content), failing to consider factors like grate speed and waste thickness, and lacking targeted data feature selection. This makes it difficult for existing technologies to provide comprehensive solutions for complex waste incineration processes.

[0031] Therefore, existing boiler automatic combustion control (ACC) systems mainly have the following problems:

[0032] 1. Auxiliary control of primary air fan speed control signal in drying section: Since the control of primary air fan speed control signal in waste incineration is difficult, it is necessary to further improve the level of automation control and assist in adjusting the speed control signal of the fan to optimize the combustion process in drying section.

[0033] 2. Auxiliary control of feed grate speed: In waste incineration, the adjustment of feed grate speed is crucial for the combustion process. However, existing technologies fail to fully consider the distribution and combustion state of waste, resulting in uneven waste distribution (such as uneven accumulation and incomplete combustion) having a significant impact on grate speed. Auxiliary control technologies are needed to optimize feed grate speed and reduce the impact of uneven waste distribution.

[0034] 3. Steam Quantity Prediction: Due to the inherent uncontrollability of the calorific value and combustion state of waste, current technologies are not accurate in predicting steam quantity and cannot reflect the real-time combustion status of waste. Therefore, a more precise prediction mechanism is needed to assist in the operation of the control system and improve energy efficiency.

[0035] 4. Prediction of Oxygen Content at the Outlet: Oxygen content at the outlet is an important indicator for assessing combustion status. Current technologies do not provide entirely accurate predictions of oxygen content at the outlet, requiring the integration of more parameters for prediction and control to reflect the actual situation of waste combustion and allow for corresponding adjustments.

[0036] In view of the problems existing in the prior art, this application proposes a method for optimizing and controlling the operating status of equipment, aiming to solve the problems of low automation, insufficient operating efficiency, and reliance on manual intervention by operators in the operation of waste incineration boilers. This application optimizes the boiler operation control strategy by combining data-driven technology with expert experience, thereby improving combustion efficiency and system stability, and reducing energy consumption and environmental impact. This application includes the following main contents:

[0037] Historical and real-time boiler operation data are acquired through a distributed control system (DCS) to identify key features related to boiler operating status, such as furnace temperature, outlet oxygen content, steam flow rate, and grate speed. Historical data is preprocessed using an interval sampling method to reduce data redundancy, improve computational efficiency, and provide fundamental data support for subsequent modeling and optimization.

[0038] The K-means clustering algorithm is used to cluster preprocessed historical data, dividing the data into multiple categories and generating a reference sample set for each category. A memory matrix is ​​constructed by calculating the centroids of each category, providing an efficient reference database for multivariate state estimation techniques (MSET) and improving the model's predictive ability in complex data environments.

[0039] The Analytic Hierarchy Process (AHP) is used to calculate the weights of key features and construct a feature weight matrix. A consistency check is performed to ensure the reasonable allocation of feature weights and to highlight the influence of key features in subsequent similarity calculations, thereby enhancing the accuracy and reliability of state estimation.

[0040] State estimation is performed based on the similarity between real-time data and a reference sample set. By combining the feature weight matrix and the Euclidean distance calculation method, several samples most similar to the real-time data are selected to predict the future operating state of the boiler, especially the dynamic changes of key operating parameters such as steam output, outlet oxygen content, and grate speed.

[0041] Based on the residual between the predicted and actual states, the system determines whether the equipment is operating normally. If the equipment is operating normally, the generated optimized control parameters are written back to the DCS to achieve closed-loop dynamic adjustment of the boiler operating parameters. The optimization includes grate speed regulation, primary air fan volume regulation, steam volume control, and optimized regulation of outlet oxygen content, thereby achieving precise automated control.

[0042] This application achieves closed-loop control and dynamic optimization at each key stage of boiler operation through improved data processing and control strategies. This overcomes the reliance on manual intervention in traditional methods, improves the automation level, combustion efficiency and operational stability of waste incineration power generation, and solves the adverse effects of complex waste composition and uncontrollable combustion on boiler operation, thereby improving energy efficiency and reducing environmental pollution.

[0043] The technical solution of this application will now be described in detail with reference to the accompanying drawings and specific embodiments.

[0044] Figure 1 is a flowchart illustrating the equipment operation state optimization control method provided in an embodiment of this application. As shown in Figure 1, the equipment operation state optimization control method may specifically include:

[0045] S101, acquire historical and real-time data of equipment operation, and filter out key features related to the equipment's operating status;

[0046] S102, preprocess the historical data, use clustering algorithms to divide the preprocessed historical data into several categories, and generate a reference sample set for each category;

[0047] S103, use the analytic hierarchy process to calculate the weights of key features and construct a feature weight matrix, where the feature weight matrix is ​​used to adjust the influence weights of different key features in subsequent matching calculations.

[0048] S104 utilizes an improved multivariate state estimation algorithm to estimate the state based on the similarity between real-time data and a reference sample set;

[0049] S105, Based on the state estimation results, predict the equipment operating state and determine the deviation between the predicted operating state and the actual operating state in order to determine whether the equipment operating state is normal.

[0050] S106 If the equipment is operating normally, the optimized control parameters generated based on the predicted operating status will be written back to the distributed control system so that the distributed control system can adjust the operating parameters of the equipment according to the optimized control parameters.

[0051] In some embodiments, preprocessing of historical data includes:

[0052] Historical data is cleaned to remove outliers and fill in missing values. Time series data in historical data are sampled at equal intervals to eliminate data redundancy and noise and retain key data trends.

[0053] Specifically, the first step is to clean the historical data, which mainly includes the following operations:

[0054] Outlier removal: Statistical analysis methods are used to filter historical data and detect outliers that clearly exceed reasonable ranges. Specifically, for key characteristics such as furnace temperature, outlet oxygen content, and steam volume, reasonable threshold ranges are set (e.g., based on the 3σ rule or box plot method) to remove outliers.

[0055] Imputing missing values: For missing data, interpolation or regression prediction methods are used to impute missing values. For example, for missing values ​​in time series data, linear interpolation is used to estimate the missing values ​​based on the trend of adjacent data points, thereby ensuring the continuity and integrity of the data.

[0056] Furthermore, for time-series data in historical data, equal-interval sampling is implemented to reduce data redundancy and noise. For example, this may include the following operations:

[0057] Determine a reasonable sampling time interval based on the typical cycle of boiler operating status changes. For example, if the characteristic parameters of the waste combustion process change every minute, the sampling interval can be set to 30 seconds, thereby reducing the number of samples while preserving key data trends.

[0058] During the sampling process, the moving average method is used to smooth the time series data and eliminate noise interference caused by short-term fluctuations. For example, for furnace temperature series data, a moving average is calculated using data points with a window size of 3 to obtain a smoother temperature trend.

[0059] The distribution trend of the preprocessed data remains consistent with the overall trend of the original data, while significantly reducing the number of data entries to be stored. For example, in a practical application, after sampling 1 million historical data entries at equal intervals, the data volume was reduced to 200,000 entries, retaining approximately 98% of the key trend features. Verification showed that when the preprocessed data was used for subsequent model training, training time was shortened by approximately 50%, without significantly affecting prediction accuracy.

[0060] The method described in this embodiment effectively reduces data redundancy and noise interference through the preprocessing of historical data, while accelerating the training speed of subsequent models, significantly improving prediction efficiency and model practicality, and providing high-quality basic data support for the optimized control of waste incineration power generation boilers.

[0061] In some embodiments, a clustering algorithm is used to divide the preprocessed historical data into several categories, and a reference sample set is generated for each category, including:

[0062] Clustering algorithms are used to cluster the feature vectors of preprocessed historical data, dividing the preprocessed historical data into multiple categories.

[0063] Calculate the data center points for each category, use the data center points for each category as reference samples, and generate a reference sample set containing data center points for multiple categories based on the reference samples;

[0064] The reference sample set is used as the memory matrix for the multivariate state estimation algorithm, and provides a reference for subsequent state estimation based on real-time data.

[0065] Specifically, firstly, key features are extracted from the preprocessed historical data to form feature vectors for cluster analysis. Key features include, but are not limited to, operating parameters such as furnace temperature, outlet oxygen content, steam flow rate, and grate speed. These feature vectors are then standardized to eliminate the influence of different feature dimensions on the clustering results. For example, mean normalization is used to scale the value range of each feature to [0,1].

[0066] Furthermore, the K-means clustering algorithm is used to perform clustering analysis on the feature vectors, specifically including the following operations:

[0067] First, multiple initial cluster centers are randomly selected, and the distance between each sample point and each cluster center is calculated based on Euclidean distance.

[0068] Next, each sample point is assigned to the category of the cluster center that is closest to it.

[0069] Next, calculate the mean of all sample points within each category, and use the mean as the new cluster center.

[0070] Finally, repeat the sample point classification and cluster center update steps until the change in the position of the cluster center is less than the set threshold, or the preset maximum number of iterations is reached.

[0071] Through the above process, the feature vectors of historical data are divided into multiple categories (such as 5 or 10 categories). The data within each category have high similarity, while the data between different categories have significant differences.

[0072] Furthermore, for each cluster category, the mean vector of all sample points within that category is calculated and used as the centroid of that category. The centroids of all categories are then aggregated to generate a reference sample set. For example, after performing 5-category clustering on 100,000 historical data points, a reference sample set containing 5 centroids is obtained. These centroids are highly representative and can be used to describe the typical operating conditions of boilers under different operating conditions.

[0073] The generated reference sample set is stored as a memory matrix for the Multivariate State Estimation Algorithm (MSET), serving as a reference database for subsequent state estimation. During real-time data input, the current operating state is quickly matched with historical typical states through similarity calculation with the reference sample set, providing a foundation for operating state prediction.

[0074] In practical applications, cluster analysis was performed on historical boiler operation data to verify the representativeness and coverage of the reference sample set. Experimental results show that the generated reference sample set can cover the main operating conditions of the boiler, and through fast matching of the memory matrix, the computational efficiency of MSET state estimation is improved by about 30%, and the error of state prediction is reduced by about 15%.

[0075] The technical solution in this embodiment can efficiently classify historical data and generate a reference sample set that can accurately describe typical operating states, providing reliable data support for the intelligent optimization control of waste incineration power generation boilers.

[0076] In some embodiments, the analytic hierarchy process (AHP) is used to calculate the weights of key features and construct a feature weight matrix, including:

[0077] Based on expert experience, key features are scored for importance, and an initial feature score matrix is ​​generated.

[0078] Based on the initial feature scoring matrix, a feature decision matrix is ​​constructed using the analytic hierarchy process. The feature decision matrix is ​​used to characterize the relative importance of each key feature.

[0079] Perform a consistency check on the decision matrix, solve for the eigenvalues ​​and eigenvectors of the decision matrix, extract the eigenvector corresponding to the largest eigenvalue, and use each component of the eigenvector as the weight of each key feature.

[0080] A feature weight matrix is ​​constructed using the weights of each key feature, where each weight is used to characterize the degree of influence of the corresponding key feature in the similarity calculation of the multivariate state estimation algorithm.

[0081] Specifically, considering the multidimensional data characteristics of waste-to-energy boiler operation, the Analytic Hierarchy Process (AHP) is used to calculate the weights of key features and construct a feature weight matrix to improve the accuracy and relevance of the Multivariate State Estimation Algorithm (MSET) in similarity calculation. The specific implementation steps are as follows:

[0082] First, based on experts' extensive experience in boiler operation, key characteristics closely related to boiler operating conditions (such as furnace temperature, outlet oxygen content, steam output, and grate speed) were assigned importance scores. These scores were based on the degree to which each characteristic affected combustion efficiency, pollutant emissions, and boiler stability. For example, experts considered furnace temperature and outlet oxygen content to be more significant in reflecting combustion conditions, and therefore assigned them higher scores, while steam output and grate speed were assigned lower scores.

[0083] Next, based on the initial scores, the key features are compared pairwise to create a feature judgment matrix. This matrix is ​​used to characterize the relative importance of each pair of key features. For example, if one feature is significantly more important than another, it is represented by a higher value in the matrix.

[0084] Furthermore, to ensure the logical consistency of the feature judgment matrix, a consistency check is performed. This check determines if any unreasonable comparison relationships exist. For example, if feature A is found to be more important than feature B, feature B is more important than feature C, but feature C is more important than feature A, then the scoring matrix needs to be adjusted to eliminate the inconsistency. After the consistency check passes, the next calculation step begins.

[0085] Furthermore, for the decision matrix that passes the consistency test, the importance weights of each feature are calculated. Specifically, a weight vector is obtained through matrix calculation, where each component corresponds to the weight of a key feature. This weight reflects the importance of the feature in the estimation of boiler operating status. For example, the calculation results may indicate that furnace temperature accounts for 40% of the weight, outlet oxygen content accounts for 30%, steam quantity accounts for 20%, and grate speed accounts for 10%.

[0086] Furthermore, a feature weight matrix is ​​constructed based on the calculated weight vector. This matrix is ​​used to adjust the influence of different features on similarity calculation in the multivariate state estimation algorithm. For example, features with higher weights (such as furnace temperature) are given a greater influence in similarity calculation, while features with lower weights (such as grate speed) have a relatively smaller influence.

[0087] Furthermore, the constructed feature weight matrix is ​​applied to the MSET algorithm for similarity calculation between real-time data and the reference sample set. In practice, after real-time data is input into the system, the weight matrix adjusts the contribution ratio of different features to state matching, thereby improving the accuracy of state estimation. For example, furnace temperature, which has a larger weight, will dominate the similarity calculation, while grate speed, which has a smaller weight, has a less significant impact.

[0088] In practical operation, the effect was verified by applying the feature weight matrix to boiler state estimation. Experimental results show that after weight adjustment, the accuracy of state estimation is significantly improved, while reducing over-reliance on secondary features and enhancing the robustness of the model under complex operating conditions.

[0089] The following example illustrates the principle and process of calculating feature weights using the Analytic Hierarchy Process (AHP) in this application, and may include the following:

[0090] First, the equipment items are scored based on expert experience.

[0091] Secondly, the feature matrix is ​​designed based on AHP, and the weight of each feature is obtained through a consistency check:

[0092] Where J is the decision matrix, n is the number of feature points, and I iAssign a score to the importance of the i-th feature. Then calculate the eigenvalues ​​and eigenvectors corresponding to the decision matrix: fn,fv=eig(J) w=max(fv)

[0093] Wherein, the eig function is used to find the eigenvalues ​​and eigenvectors of the function, fn is the eigenvalue, fv is the eigenvector, and w is the value corresponding to the largest eigenvector.

[0094] Finally, the weights are used in the similarity calculation of the MSET algorithm to adjust the influence of each feature in the matching process.

[0095] The technical solution in this embodiment can reasonably allocate the weight of key features, highlight the features that have a greater impact on the boiler's operating status, and provide a more accurate reference for the intelligent control of waste incineration power generation boilers.

[0096] In some embodiments, an improved multivariate state estimation algorithm is used to estimate the state based on the similarity between real-time data and a reference sample set, including:

[0097] The preprocessed real-time data is input into the multivariate state estimation algorithm model. The real-time data includes key features.

[0098] Sample data is extracted from the reference sample set and combined with the feature weight matrix to determine the weight ratio of different features in state estimation;

[0099] Based on similarity calculation methods and feature weight matrices, the similarity between real-time data and reference samples is calculated to obtain similarity values;

[0100] Based on the similarity value, several samples that are most similar to the current real-time data are selected from the reference sample set, and the operating status of the equipment is estimated based on the status information of the selected samples.

[0101] Specifically, the preprocessed real-time data is input into the multivariate state estimation algorithm model. The real-time data includes key characteristics of boiler operation, such as furnace temperature, steam output, outlet oxygen content, and grate speed. The real-time data undergoes standardization to ensure consistent numerical ranges for each feature, preventing bias in subsequent similarity calculations due to differences in feature units.

[0102] Furthermore, sample data is extracted from the reference sample set generated by cluster analysis of historical data. The reference sample set is obtained by feature clustering based on historical data and includes centroids of multiple categories, each centroid representing a typical operating state of the boiler. These reference samples are stored as a memory matrix for the multivariate state estimation algorithm, providing basic data support for real-time state estimation.

[0103] Furthermore, based on the feature weight matrix previously calculated using the Analytic Hierarchy Process (AHP), the weight ratios of different key features in the state estimation are adjusted. Features with larger weights (such as furnace temperature) will play a more significant role in the similarity calculation, while features with smaller weights (such as grate speed) will have a relatively minor impact, thus making the estimation more closely reflect actual operating conditions.

[0104] Furthermore, the similarity between real-time data and reference samples is calculated. A weighted similarity method, combined with a feature weight matrix, is used to calculate the degree of matching between real-time data and each reference sample. A higher similarity value indicates a closer relationship between the real-time data and the reference sample's state. This calculation process allows for the rapid selection of the reference sample set that best matches the current boiler operating state.

[0105] Furthermore, based on the similarity calculation results, several samples most similar to the real-time data are selected from the reference sample set. For example, among all the calculated similarity values, the top 5 samples with the highest similarity values ​​are selected as the basis for estimating the current state of the boiler. The selected samples cover typical operating conditions of the boiler and can fully reflect the matching between the real-time state and the historical state.

[0106] Furthermore, based on the status information of the selected samples and the changing trends of real-time data, the current operating status of the boiler is estimated. Specifically, the estimation includes the fluctuation range of real-time steam volume, the adjustment requirements of outlet oxygen content, and the changing trend of grate speed. These estimation results provide important basis for further control of boiler operating parameters.

[0107] Furthermore, based on the future state data of the most similar samples, the future operating state of the boiler can be predicted. For example, by analyzing similar state change trajectories in historical operating data, the potential parameter change trends of the current boiler in the short term can be predicted, such as a gradual increase in steam volume or a gradual decrease in outlet oxygen content.

[0108] The following example illustrates the principle and process by which this application calculates the similarity between the current sample and the reference set using AHP weights and Euclidean distance. Specifically, this may include the following:

[0109] First, in the clustered reference database, the similarity between the current sample and the reference set is calculated using the AHP weighting and Euclidean distance methods: D = M * dist(M, M) -1

[0110] Where d represents the current input, D is the similarity calculation factor, dist is the distance calculation function, and this application uses Euclidean distance for measurement, and M is the memory matrix.

[0111] Secondly, select the most similar samples as the basis for estimating the system state.

[0112] This embodiment utilizes an improved multivariate state estimation algorithm to achieve accurate estimation of boiler operating status, providing effective data support for intelligent control of waste incineration power generation boilers and significantly improving combustion efficiency and operational stability.

[0113] The improvement process and method of the MSET (Multivariate State Estimation) algorithm of this application will be described in detail below with reference to specific embodiments and accompanying drawings. Figure 2 is a schematic diagram of the improvement principle of the MSET algorithm provided in the embodiment of this application. As shown in Figure 2, the improvement process of the MSET algorithm may include the following:

[0114] This application combines the MSET algorithm with equal-interval sampling, K-means clustering, and the Analytic Hierarchy Process (AHP) to enhance its predictive ability in multi-dimensional data, especially when the data features are complex.

[0115] The specific improvement methods for the MSET algorithm are as follows:

[0116] 1. Equal-interval sampling: In time series data, equal-interval sampling reduces data redundancy and improves computational efficiency. This step is used to smooth the data and eliminate noise interference with the model. In this application, due to the large volume and difficulty in processing historical data, this method reduces the number of data entries while preserving key trends, ensuring that the data distribution trend is consistent with the original data, thereby accelerating model training speed and prediction efficiency.

[0117] 2. K-means Clustering: This application employs K-means clustering to group historical data into several categories, maximizing intra-category similarity and inter-category differences. This provides a basis for feature classification, and the model can assign different sensitivities to features of different categories. This method facilitates the selection of a suitable reference set when MSET performs similarity matching, and can classify data categories for different working conditions or states, thereby improving prediction accuracy.

[0118] 3. Analytic Hierarchy Process (AHP): The Analytic Hierarchy Process (AHP) is a multi-criteria decision analysis method that assigns weights to each decision factor by constructing a hierarchical structure and a judgment matrix. In this application, there are many data features. By calculating the weights of the features using AHP, the importance of key features is highlighted, helping the MSET algorithm to select reference samples more rationally, thereby improving the accuracy of state prediction. In addition, the weight allocation results can be directly used for anomaly detection and model optimization.

[0119] In some embodiments, determining the deviation between the predicted operating state and the actual operating state to determine whether the equipment is operating normally includes:

[0120] Based on the residual between the predicted value corresponding to the predicted operating state and the actual value corresponding to the actual operating state, it is determined whether the equipment is operating normally. When the residual exceeds the residual threshold, a fault warning is triggered and the fault point is identified. When the residual does not exceed the residual threshold, an optimized control operation is performed based on the predicted operating state.

[0121] Specifically, the predicted values ​​of boiler operating state parameters (such as steam output, furnace temperature, and outlet oxygen content) based on a multivariate state estimation algorithm are compared with the actual operating parameters collected in real time, and the difference between the two, i.e., the residual, is calculated. The residual is used to quantify the degree of deviation between the predicted and actual values, reflecting the degree of conformity between the equipment operating state and the expected state.

[0122] Furthermore, the calculated residuals are compared with a pre-set residual threshold: if the residuals do not exceed the residual threshold, the equipment is considered to be operating normally, and no warning needs to be triggered. If the residuals exceed the residual threshold, the equipment is considered to be operating abnormally, a fault warning is triggered, and the fault point is further analyzed.

[0123] Furthermore, once the residual exceeds a threshold, the fault warning module is triggered, issuing an alarm message to alert operators to the equipment's operating status. Simultaneously, specific fault points are identified by combining operating parameters with large residuals (such as abnormally high outlet oxygen content or abnormally low steam volume). By analyzing the historical changes in the fault point's status, the possible causes of the anomaly are further inferred. For example, if the outlet oxygen content residual consistently exceeds the standard, it may indicate incomplete combustion or a deviation in secondary air volume control.

[0124] Furthermore, when the residual does not exceed the threshold or after the fault warning process is completed, the following optimization control operations are performed:

[0125] Based on the optimized control parameters generated from the predicted operating status, the key operating parameters of the boiler are adjusted, such as dynamically optimizing the grate speed, primary air fan volume, or feed rate, in order to maintain the boiler's efficient operating status.

[0126] The optimized control operation is carried out in a closed-loop manner, and the adjusted operating parameters are written back to the distributed control system (DCS) and the adjustment effect is monitored in real time to ensure that the boiler operating status gradually approaches the predicted state.

[0127] Furthermore, to verify the effectiveness of the residual judgment mechanism, the prediction error, anomaly detection rate, and robustness of the operating state are evaluated. For example, the following evaluations may be included:

[0128] Prediction error: Based on the difference between the actual operating state and the predicted state, the overall prediction accuracy of the system is statistically analyzed, and the fluctuation range of the residual under normal operating conditions is evaluated.

[0129] Anomaly detection rate: The ratio of the number of times a fault warning is triggered when the residual exceeds the standard to the actual number of faults, which evaluates the system's ability to capture abnormal operating conditions.

[0130] Robustness: Under conditions of large fluctuations in the calorific value of waste, verify the stability of the system to ensure that the model can still accurately output the predicted state and perform effective optimization control under complex working conditions.

[0131] The method described in this embodiment can effectively combine the residual between the predicted operating state and the actual operating state to achieve real-time judgment of equipment operating status, fault warning and optimized control operation, providing a strong guarantee for the efficient operation of waste incineration power generation boilers.

[0132] In some embodiments, the equipment is a waste-to-energy incineration boiler, and adjusting the operating parameters of the equipment according to optimized control parameters includes:

[0133] By utilizing optimized control parameters, the operating parameters of the waste-to-energy incineration boiler are adjusted in real time. These optimized control parameters include adjustment values ​​related to grate speed, steam volume, outlet oxygen content, and primary air fan operation.

[0134] Specifically, the optimized control parameters are generated by an improved multivariate state estimation algorithm (MSET), which dynamically adjusts the grate speed, steam flow, outlet oxygen content, and primary air fan operating parameters based on a comparison between the boiler's real-time operating state and the predicted operating state. These optimized control parameters can provide accurate adjustment values ​​for different operating conditions. For example, in cases of incomplete waste combustion, combustion efficiency can be improved by adjusting the primary air fan flow rate and grate speed.

[0135] For example, in some cases, the grate speed of a waste-to-energy boiler is adjusted in real time based on optimized control parameters.

[0136] When the waste burns too slowly, increase the grate speed to reduce the time the waste stays in the furnace and prevent waste accumulation; when the waste burns too quickly, reduce the grate speed to ensure complete combustion and improve combustion efficiency.

[0137] By dynamically adjusting the grate speed, it is ensured that the waste is evenly distributed and fully burned in the furnace, avoiding a decrease in combustion efficiency caused by uneven waste distribution or combustion.

[0138] Furthermore, based on real-time monitoring data of boiler steam output, the steam volume is adjusted using optimized control parameters. For example:

[0139] When the calorific value of the waste fluctuates, resulting in insufficient steam, increase the primary air volume to improve combustion intensity and increase steam output; when the steam volume is too high, reduce the feed rate or the primary air volume to stabilize the internal pressure of the boiler and avoid overpressure.

[0140] Furthermore, the outlet oxygen content is a key indicator reflecting combustion completeness. Based on optimized control parameters, the airflow of the secondary air fan is dynamically adjusted, for example:

[0141] When the oxygen content at the outlet is too low, increase the air volume of the secondary air fan to improve the oxygen supply in the furnace and improve combustion conditions; when the oxygen content at the outlet is too high, reduce the air volume of the secondary air fan to avoid increased energy consumption due to excessive oxygen.

[0142] Furthermore, the primary airflow directly affects the combustion state of the waste in the drying section. Based on optimized control parameters, the operating parameters of the primary air blower are adjusted in real time, for example:

[0143] When the moisture content of the waste is high, increase the air volume of the primary blower to accelerate the evaporation rate of moisture in the drying section; after the waste is dried, appropriately reduce the air volume of the primary blower to save energy and prevent over-combustion.

[0144] Furthermore, after optimizing the application of control parameters, the adjustment effect can be evaluated using the following four indicators:

[0145] Mean Square Error (MSE): Used to measure the average deviation between predicted and actual values, reflecting the accuracy of adjustment parameters.

[0146] Mean Absolute Error (MAE): Used to measure the absolute deviation between the actual value and the predicted value, and to assess the overall error level.

[0147] R²: Used to evaluate the degree of matching between the prediction model and the actual operating state. The higher the R², the better the adjustment effect.

[0148] Mean Absolute Percentage Error (MAPE): Used to evaluate the percentage error of the predicted value relative to the actual value, reflecting the consistency of the adjustment effect under different operating conditions.

[0149] Table 1 shows the prediction error of different equipment points inside the boiler. As can be seen from Table 1, the various indicators of different equipment points are all performing well and can meet the automation investment requirements in different scenarios.

[0150] Table 1 Evaluation Indicators for Different Equipment Points

[0151] Practical applications have demonstrated that, under different waste compositions and calorific values, optimizing control parameters can effectively adjust boiler operating parameters, ensuring that actual values ​​closely match predicted values. The mean square error, mean absolute error, and mean absolute percentage error are all significantly reduced, with a fitting degree exceeding 95%. After adjustment, combustion efficiency increased by approximately 10%, boiler operating energy consumption decreased by approximately 8%, and reliance on operator intervention was reduced.

[0152] The technical solution in this embodiment utilizes optimized control parameters to precisely adjust the key operating parameters of the waste-to-energy boiler, significantly improving the boiler's automation control level, combustion efficiency, and operational stability, thus providing reliable technical support for the intelligent development of the waste-to-energy industry.

[0153] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0154] Figure 3 is a schematic diagram of the equipment operation status optimization control device provided in an embodiment of this application. As shown in Figure 3, the equipment operation status optimization control device includes:

[0155] The acquisition module 301 is used to acquire historical and real-time data of the equipment operation and filter out key features related to the equipment operation status.

[0156] The classification module 302 is used to preprocess historical data, divide the preprocessed historical data into several categories using a clustering algorithm, and generate a reference sample set for each category.

[0157] Module 303 is used to calculate the weights of key features using the analytic hierarchy process and to construct a feature weight matrix, which is used to adjust the influence weights of different key features in subsequent matching calculations.

[0158] The estimation module 304 is used to perform state estimation based on the similarity between real-time data and a reference sample set using an improved multivariate state estimation algorithm.

[0159] The prediction module 305 is used to predict the operating status of the equipment based on the state estimation results, and to determine the deviation between the predicted operating status and the actual operating status, so as to determine whether the operating status of the equipment is normal.

[0160] The adjustment module 306 is used to write back the optimized control parameters generated based on the predicted operating status to the distributed control system if the equipment is operating normally, so that the distributed control system can adjust the operating parameters of the equipment according to the optimized control parameters.

[0161] In some embodiments, the classification module 302 of Figure 3 performs data cleaning on historical data, removes outliers from historical data, fills in missing values, and samples time series data in historical data at equal intervals to eliminate data redundancy and noise and retain key data trends.

[0162] In some embodiments, the classification module 302 of FIG3 uses a clustering algorithm to cluster the feature vectors of the preprocessed historical data, dividing the preprocessed historical data into multiple categories; calculates the data center point of each category, uses the data center point of each category as a reference sample, generates a reference sample set containing data center points of multiple categories based on the reference sample; uses the reference sample set as the memory matrix of the multivariate state estimation algorithm, and provides a reference for subsequent state estimation based on real-time data.

[0163] In some embodiments, the construction module 303 of Figure 3 scores the importance of key features based on expert experience, generating an initial feature score matrix; based on the initial feature score matrix, a feature decision matrix is ​​constructed using the analytic hierarchy process (AHP), which is used to characterize the relative importance relationship between each key feature; the decision matrix is ​​subjected to a consistency check, and the eigenvalues ​​and eigenvectors of the decision matrix are solved, the eigenvector corresponding to the largest eigenvalue is extracted, and each component of the eigenvector is used as the weight of each key feature; a feature weight matrix is ​​constructed using the weights of each key feature, where each weight is used to characterize the degree of influence of the corresponding key feature in the similarity calculation of the multivariate state estimation algorithm.

[0164] In some embodiments, the estimation module 304 of FIG3 inputs the preprocessed real-time data into the multivariate state estimation algorithm model. The real-time data includes key features. Sample data is extracted from the reference sample set, and the weight ratio of different features in the state estimation is determined by combining the feature weight matrix. Based on the similarity calculation method and the feature weight matrix, the similarity between the real-time data and the reference samples is calculated to obtain the similarity value. According to the similarity value, several samples that are most similar to the current real-time data are selected from the reference sample set, and the operating state of the equipment is estimated according to the state information of the selected samples.

[0165] In some embodiments, the prediction module 305 in FIG3 determines whether the equipment operating status is normal based on the residual between the predicted value corresponding to the predicted operating status and the actual value corresponding to the actual operating status. When the residual exceeds the residual threshold, a fault warning is triggered and the fault point is identified. When the residual does not exceed the residual threshold, an optimization control operation is performed based on the predicted operating status.

[0166] In some embodiments, the device is a waste-to-energy incineration boiler. The adjustment module 306 in FIG3 uses optimized control parameters to adjust the operating parameters of the waste-to-energy incineration boiler in real time. The optimized control parameters include adjustment values ​​related to grate speed, steam volume, outlet oxygen content and primary air fan operation.

[0167] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0168] Figure 4 is a schematic diagram of an electronic device 4 provided in an embodiment of this application. As shown in Figure 4, the electronic device 4 of this embodiment includes: a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. When the processor 401 executes the computer program 403, it implements the steps in the various method embodiments described above. Alternatively, when the processor 401 executes the computer program 403, it implements the functions of each module / unit in the various device embodiments described above.

[0169] Electronic device 4 can be a desktop computer, laptop, handheld computer, cloud server, or other electronic device. Electronic device 4 may include, but is not limited to, processor 401 and memory 402. Those skilled in the art will understand that FIG4 is merely an example of electronic device 4 and does not constitute a limitation on electronic device 4, and may include more or fewer components than shown, or different components.

[0170] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0171] The memory 402 can be an internal storage unit of the electronic device 4, such as a hard disk or RAM of the electronic device 4. The memory 402 can also be an external storage device of the electronic device 4, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc., equipped on the electronic device 4. The memory 402 can also include both internal and external storage units of the electronic device 4. The memory 402 is used to store computer programs and other programs and data required by the electronic device.

[0172] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0173] If integrated modules / units are implemented as software functional units and sold or used as independent products, they can be stored in a readable storage medium (e.g., a computer-readable storage medium). Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program may include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. A computer-readable storage medium may include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0174] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for optimizing and controlling the operating status of equipment, characterized in that, include: Acquire historical and real-time data on equipment operation and filter out key features related to the equipment's operating status; The historical data is preprocessed, and a clustering algorithm is used to divide the preprocessed historical data into several categories, and a reference sample set for each category is generated. The key features are weighted using the analytic hierarchy process (AHP) and a feature weight matrix is ​​constructed. The feature weight matrix is ​​used to adjust the influence weight of different key features in subsequent matching calculations. An improved multivariate state estimation algorithm is used to estimate the state based on the similarity between the real-time data and the reference sample set; Based on the state estimation results, the operating state of the equipment is predicted, and the deviation between the predicted operating state and the actual operating state is determined to determine whether the operating state of the equipment is normal. If the equipment is operating normally, the optimized control parameters generated based on the predicted operating status will be written back to the distributed control system, so that the distributed control system can adjust the operating parameters of the equipment according to the optimized control parameters.

2. The method according to claim 1, characterized in that, The preprocessing of the historical data includes: The historical data is cleaned to remove outliers and fill in missing values. Time series data in the historical data are sampled at equal intervals to eliminate data redundancy and noise and retain key data trends.

3. The method of claim 1, wherein, The process involves using a clustering algorithm to divide the preprocessed historical data into several categories and generating a reference sample set for each category, including: Clustering algorithms are used to cluster the feature vectors of the preprocessed historical data, dividing the preprocessed historical data into multiple categories; Calculate the data center points for each category, use the data center points for each category as reference samples, and generate a reference sample set containing data center points for multiple categories based on the reference samples; The reference sample set is used as the memory matrix for the multivariate state estimation algorithm and provides a reference for subsequent state estimation based on real-time data.

4. The method of claim 1, wherein, The step of using the analytic hierarchy process (AHP) to calculate the weights of the key features and construct a feature weight matrix includes: The key features are scored based on expert experience to generate an initial feature score matrix; Based on the initial feature scoring matrix, a feature determination matrix is ​​constructed using the analytic hierarchy process (AHP). The feature determination matrix is ​​used to characterize the relative importance of each key feature. The decision matrix is ​​subjected to a consistency check, and the eigenvalues ​​and eigenvectors of the decision matrix are solved. The eigenvector corresponding to the largest eigenvalue is extracted, and each component of the eigenvector is used as the weight of each key feature. A feature weight matrix is ​​constructed using the weights of each key feature, where each weight is used to characterize the degree of influence of the corresponding key feature in the similarity calculation of the multivariate state estimation algorithm.

5. The method according to claim 1, characterized in that, The improved multivariate state estimation algorithm, which estimates the state based on the similarity between the real-time data and the reference sample set, includes: The preprocessed real-time data is input into the multivariate state estimation algorithm model, and the real-time data includes the key features; Sample data is extracted from the reference sample set, and the weight ratio of different features in state estimation is determined by combining the feature weight matrix. Based on the similarity calculation method and the feature weight matrix, the similarity between real-time data and reference samples is calculated to obtain a similarity value; Based on the similarity value, several samples that are most similar to the current real-time data are selected from the reference sample set, and the operating status of the device is estimated based on the status information of the selected samples.

6. The method according to claim 1, characterized in that, The process of determining the deviation between the predicted operating state and the actual operating state to judge whether the equipment is operating normally includes: Based on the residual between the predicted value corresponding to the predicted operating state and the actual value corresponding to the actual operating state, it is determined whether the equipment is operating normally. When the residual exceeds the residual threshold, a fault warning is triggered and the fault point is identified. When the residual does not exceed the residual threshold, an optimization control operation is performed based on the predicted operating state.

7. The method according to claim 1, characterized in that, The equipment is a waste incineration power generation boiler, and adjusting the operating parameters of the equipment according to the optimized control parameters includes: The operating parameters of the waste incineration power generation boiler are adjusted in real time using the optimized control parameters, which include adjustment values ​​related to grate speed, steam volume, outlet oxygen content, and primary air fan operation.

8. A device for optimizing and controlling the operating status of equipment, characterized in that, include: The acquisition module is used to acquire historical and real-time data of device operation and filter out key features related to the device's operating status. The classification module is used to preprocess the historical data, divide the preprocessed historical data into several categories using a clustering algorithm, and generate a reference sample set for each category. A construction module is used to calculate the weights of the key features using the analytic hierarchy process and to construct a feature weight matrix, wherein the feature weight matrix is ​​used to adjust the influence weights of different key features in subsequent matching calculations. An estimation module is used to perform state estimation based on the similarity between the real-time data and the reference sample set using an improved multivariate state estimation algorithm; The prediction module is used to predict the operating status of the equipment based on the state estimation results, and to determine the deviation between the predicted operating status and the actual operating status in order to determine whether the equipment is operating normally. The adjustment module is used to write back the optimized control parameters generated based on the predicted operating status to the distributed control system if the equipment is operating normally, so that the distributed control system can adjust the operating parameters of the equipment according to the optimized control parameters.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in claim 1.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in claim 1.

Images