Industrial dust removal equipment remote monitoring system based on Internet of Things

Through the remote monitoring system of industrial dust removal equipment based on the Internet of Things, data is collected and preprocessed in real time, abnormalities are identified and strategic space is built, and the problem of insufficient data processing and analysis capabilities in the existing technology is solved, and accurate monitoring and prediction of industrial dust removal equipment is achieved, reducing the risk of equipment damage and production accidents.

CN120145099APending Publication Date: 2025-06-13NANTONG HAIYING MECHANICAL&ELECTRICAL GRP CO LTD

Patent Information

Application Number
CN202510069476.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-01-16
Publication Date
2025-06-13

AI Technical Summary

Technical Problem

When the existing industrial dust removal equipment monitoring system deals with multi-node and multi-variable complex systems, the data processing and analysis capabilities are insufficient, resulting in the inability to comprehensively and accurately analyze and predict the operating status of the equipment, affecting the timely discovery and handling of abnormal situations, and may lead to equipment damage or production accidents.

Method used

Provide a remote monitoring system for industrial dust removal equipment based on the Internet of Things, including a dust removal equipment operation data flow acquisition module, anomaly operation identification module, dust removal strategy simulation database acquisition module and remote monitoring and control module. Through these modules, they collect, preprocess, identify abnormalities, build policy space and conduct simulation evaluation, and finally determine the device node control policy parameters to realize remote monitoring and control.

Benefits of technology

It realizes accurate monitoring and prediction in multi-node, multi-variable complex systems, and can comprehensively and timely detect and deal with equipment abnormalities, reduce the risk of equipment damage and prevent production accidents.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120145099A_ABST
    Figure CN120145099A_ABST
Patent Text Reader

Abstract

The invention provides an industrial dust removal equipment remote monitoring system based on the Internet of Things, and relates to the technical field of separation control, and the system comprises the steps: collecting and obtaining the operation data flow of dust removal equipment; key node extraction is carried out on the target dust removal equipment through the remote monitoring Internet of Things platform; preprocessing and shunting the operation data flow of the dust removal equipment; performing abnormal operation identification on the operation data streams of the K dust removal nodes; constructing a global dust removal strategy space, and performing simulation evaluation on the global dust removal strategy space; and performing control optimization on the dust removal strategy simulation database, and performing remote monitoring control on the target dust removal equipment. According to the method and the device, the technical problem of insufficient data processing and analysis capability in coping with a multi-node and multi-variable complex system in the prior art can be solved, the technical goal of accurate monitoring and prediction is realized, and the technical effect of comprehensively and timely discovering and processing the abnormal condition of the equipment is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of separation control technology, and particularly to a remote monitoring system for industrial dust removal equipment based on the Internet of Things. Background Art

[0002] With the continuous development of industrial automation and intelligence, the remote monitoring system for industrial dust removal equipment has become an important technical means to improve production efficiency and reduce environmental pollution. However, there are still many problems and deficiencies in the application of existing industrial dust removal equipment monitoring systems, which limit their wide application and effect optimization in actual production.

[0003] Currently, the existing technology has insufficient capabilities in data processing and analysis, especially when dealing with complex systems with multiple nodes and variables. These systems usually rely only on simple algorithms and models and cannot comprehensively and accurately analyze and predict the operating status of equipment. Therefore, when abnormal conditions occur in the dust removal equipment, the existing monitoring systems often have difficulty in detecting and handling them in a timely manner, which may lead to further damage to the equipment or accidents. In addition, the existing monitoring systems usually lack effective abnormal handling strategies, resulting in unsatisfactory efficiency and effect of abnormal handling.

[0004] In summary, there is a technical problem in the existing technology that due to insufficient data processing and analysis capabilities when dealing with complex systems with multiple nodes and variables, the existing monitoring systems cannot comprehensively and accurately analyze and predict the operating status of equipment, further affecting timely detection and handling in abnormal situations, and may lead to further damage to the equipment or production accidents. Summary of the Invention

[0005] The purpose of this application is to provide a remote monitoring system for industrial dust removal equipment based on the Internet of Things to solve the technical problem in the existing technology that due to insufficient data processing and analysis capabilities when dealing with complex systems with multiple nodes and variables, the existing monitoring systems cannot comprehensively and accurately analyze and predict the operating status of equipment, further affecting timely detection and handling in abnormal situations, and may lead to further damage to the equipment or production accidents.

[0006] In view of the above problems, the present application provides a remote monitoring system for industrial dust removal equipment based on the Internet of Things, including: a dust removal equipment operation data stream acquisition module, which is used to connect a target dust removal equipment to a remote monitoring Internet of Things platform through an industrial intelligent gateway, and collect and obtain the dust removal equipment operation data stream in real time through the industrial intelligent gateway, and wirelessly transmit the dust removal equipment operation data stream to the remote monitoring Internet of Things platform; a dust removal equipment operation node acquisition module, which is used to extract key nodes of the target dust removal equipment through the remote monitoring Internet of Things platform to obtain K dust removal equipment operation nodes; a dust removal node operation data stream acquisition module, which is used to preprocess and split the dust removal equipment operation data stream based on the K dust removal equipment operation nodes to obtain K dust removal node operation data streams; an abnormal operation identification module, which is used to respectively identify abnormal operations of the K dust removal node operation data streams to obtain an abnormal dust removal node set and an abnormal node influence factor set; a dust removal strategy simulation database obtaining module, which is used to construct a global dust removal strategy space according to the abnormal dust removal node set and the abnormal node influence factor set, and perform simulation evaluation on the global dust removal strategy space to obtain a dust removal strategy simulation database; a remote monitoring control module, which is used to define an abnormal balance target to control and optimize the dust removal strategy simulation database, determine the device node control strategy parameters, and perform remote monitoring control on the target dust removal equipment through the device node control strategy parameters.

[0007] One or more technical solutions provided in the present application have at least the following technical effects or advantages: Through a dust removal equipment operation data stream acquisition module, the dust removal equipment operation data stream acquisition module is used to connect a target dust removal equipment to a remote monitoring Internet of Things platform through an industrial intelligent gateway, and through the industrial intelligent gateway, it collects and obtains the dust removal equipment operation data stream in real time, and wirelessly transmits the dust removal equipment operation data stream to the remote monitoring Internet of Things platform; a dust removal equipment operation node obtaining module, the dust removal equipment operation node obtaining module is used to extract key nodes of the target dust removal equipment through the remote monitoring Internet of Things platform to obtain K dust removal equipment operation nodes; a dust removal node operation data stream acquisition module, the dust removal node operation data stream acquisition module is used to preprocess and split the dust removal equipment operation data stream based on the K dust removal equipment operation nodes to obtain K dust removal node operation data streams; an abnormal operation identification module, the abnormal operation identification module is used to respectively perform abnormal operation identification on the K dust removal node operation data streams to obtain an abnormal dust removal node set and an abnormal node influence factor set; a dust removal strategy simulation database obtaining module, the dust removal strategy simulation database obtaining module is used to construct a global dust removal strategy space according to the abnormal dust removal node set and the abnormal node influence factor set, perform simulation evaluation on the global dust removal strategy space to obtain a dust removal strategy simulation database; a remote monitoring control module, the remote monitoring control module is used to define an abnormal balance target to perform control optimization on the dust removal strategy simulation database, determine the device node control strategy parameters, and perform remote monitoring control on the target dust removal equipment through the device node control strategy parameters, so as to achieve the technical goal of precise monitoring and prediction in a multi-node and multi-variable complex system, and achieve the technical effect of being able to comprehensively and timely discover and handle equipment abnormal conditions, reduce the risk of equipment damage and prevent production accidents.

[0008] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specifically illustrates the specific embodiments of this application. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of this application, nor is it used to limit the scope of this application. Other features of this application will become easily understood through the following description. Brief Description of the Drawings

[0009] In order to more clearly illustrate the technical solutions in this application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings described below are only exemplary, and for those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0010] Figure 1This is a schematic structural diagram of the remote monitoring system for industrial dust removal equipment based on the Internet of Things in this application; Figure 2 This is a schematic flow diagram of obtaining the abnormal dust removal node set and the abnormal node influence factor set in the remote monitoring system for industrial dust removal equipment based on the Internet of Things in this application.

[0011] Explanation of the reference numerals: Dust removal equipment operation data stream acquisition module 11, dust removal equipment operation node acquisition module 12, dust removal node operation data stream acquisition module 13, abnormal operation identification module 14, dust removal strategy simulation database acquisition module 15, remote monitoring control module 16. Detailed implementation manners

[0012] By providing a remote monitoring system for industrial dust removal equipment based on the Internet of Things in this application, the technical problem in the prior art that due to insufficient data processing and analysis capabilities when dealing with complex systems with multiple nodes and multiple variables, the existing monitoring system cannot comprehensively and accurately analyze and predict the operating status of the equipment, further affecting the timely discovery and handling in abnormal situations, and may lead to further damage to the equipment or production accidents is solved. The technical goal of achieving precise monitoring and prediction in a complex system with multiple nodes and multiple variables is realized, and the technical effect of being able to comprehensively and timely discover and handle equipment abnormalities, reducing the risk of equipment damage and preventing production accidents is achieved.

[0013] Next, the technical solutions in this application will be described clearly and completely with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments of this application. It should be understood that this application is not limited by the example embodiments described here. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of this application without creative efforts fall within the scope of protection of this application. Additionally, it should be noted that for the sake of description, only the parts related to this application are shown in the accompanying drawings rather than all of them.

[0014] Please refer to the attached Figure 1 , this application provides a remote monitoring system for industrial dust removal equipment based on the Internet of Things, specifically including: Dust removal equipment operation data stream acquisition module 11, the dust removal equipment operation data stream acquisition module 11 is used to connect the target dust removal equipment to the remote monitoring Internet of Things platform through an industrial intelligent gateway, and through the industrial intelligent gateway, the dust removal equipment operation data stream is collected in real time, and the dust removal equipment operation data stream is wirelessly transmitted to the remote monitoring Internet of Things platform.

[0015] Specifically, the industrial intelligent gateway is a bridge between devices and platforms. The target dust removal device is connected to the remote monitoring Internet of Things platform through the industrial intelligent gateway. At the same time, the operation data stream of the dust removal device is collected and obtained in real time through the industrial intelligent gateway, and the operation data stream of the dust removal device is transmitted to the remote monitoring Internet of Things platform wirelessly, so as to realize the real-time monitoring of the operation status of the device, ensuring the efficient operation and timely maintenance of the device.

[0016] The dust removal device operation node obtaining module 12 is used to extract key nodes from the target dust removal device through the remote monitoring Internet of Things platform, and obtain K dust removal device operation nodes.

[0017] Specifically, using the dust removal device connected to the remote monitoring Internet of Things platform, key nodes of great significance are identified from the operation data of the dust removal device. Key node extraction refers to screening out the part that has a decisive impact on the operation status or performance of the dust removal device from a large batch of data, and obtaining K dust removal device operation nodes, that is, K specific and representative operation nodes are identified and confirmed during the extraction process, which can reflect the operation status and performance of the dust removal device, and may be directly related to the normal operation, fault warning or other important indicators of the device, ensuring that the most important information is accurately captured in the ocean of data for more effective monitoring and management of the device.

[0018] The dust removal node operation data stream obtaining module 13 is used to preprocess and split the dust removal device operation data stream based on the K dust removal device operation nodes, and obtain K dust removal node operation data streams.

[0019] Specifically, the operation data stream of the entire dust removal device is sorted and split according to the K dust removal device operation nodes, that is, preprocessing and splitting. Among them, preprocessing and splitting means preliminary screening, classification and sorting before processing data, so that subsequent analysis and processing are more efficient and accurate. By preprocessing and splitting, K dust removal node operation data streams are obtained, that is, the original operation data stream is divided into K independent data streams, and each dust removal node operation data stream corresponds to a key operation node of a dust removal device, which can make the monitoring system more targeted to pay attention to the operation of each key node, helping to improve the accuracy and efficiency of data analysis, and thus better mastering the operation status of the device.

[0020] The abnormal operation identification module 14 is used to respectively identify the abnormal operation of the K dust removal node operation data streams, and obtain an abnormal dust removal node set and an abnormal node influence factor set.

[0021] Specifically, by separately identifying abnormal operations for the data streams running on K dust removal nodes to detect whether there are abnormal situations, abnormal problems that may occur during the operation of the equipment can be effectively discovered, obtaining an abnormal dust removal node set and a corresponding abnormal node impact factor set. This not only identifies the nodes with abnormalities but also calculates the impact factors that may be generated by the abnormal nodes, helping to accurately locate the problem nodes and evaluate their potential impact on the overall system, facilitating the timely adoption of targeted maintenance measures.

[0022] The dust removal strategy simulation database obtaining module 15 is used to construct a global dust removal strategy space based on the abnormal dust removal node set and the abnormal node impact factor set, and perform simulation evaluation on the global dust removal strategy space to obtain a dust removal strategy simulation database.

[0023] Specifically, using the identified abnormal dust removal node set and abnormal node impact factor set to generate a comprehensive dust removal strategy framework that covers a variety of dust removal strategies, ensuring that the generated strategies cover different scenarios and conditions to comprehensively evaluate the dust removal effect. Subsequently, the global dust removal strategy space is simulated and evaluated through simulation technology, testing and analyzing the effect of the strategies in actual applications, aiming to verify the effectiveness and reliability of the strategies. Finally, a dust removal strategy simulation database is obtained, indicating that the evaluation results are saved as a database, serving as a reference for subsequent optimization and actual applications, and being used in actual operations, improving the response ability of the dust removal system.

[0024] The remote monitoring and control module 16 is used to define an abnormal balance target to perform control optimization on the dust removal strategy simulation database, determine the control strategy parameters of the equipment nodes, and perform remote monitoring and control on the target dust removal equipment through the control strategy parameters of the equipment nodes.

[0025] Specifically, the abnormal balance target can be to minimize the abnormal degree of the dust removal nodes, or to minimize resource consumption, etc. Defining an abnormal balance target to perform control optimization on the dust removal strategy simulation database aims to balance abnormal situations and strategy selection. By optimizing and searching for the dust removal strategies in the simulation database through the abnormal balance target, the best control strategy parameters can be found. Optimized according to the abnormal balance target and the simulation results in the database, the specific control strategy parameters suitable for each equipment node are finally identified. Finally, performing remote monitoring and control on the target dust removal equipment through the control strategy parameters of the equipment nodes means remotely managing and controlling the target dust removal equipment to ensure the efficient operation of the equipment under abnormal conditions, ensuring that the equipment can be effectively monitored and controlled under remote conditions, thereby improving the stability and efficiency of the overall system.

[0026] The remote monitoring system for industrial dust removal equipment based on the Internet of Things can achieve the technical goal of precise monitoring and prediction in response to complex systems with multiple nodes and multiple variables, and achieve the technical effect of being able to comprehensively and timely discover and handle equipment anomalies, reducing the risk of equipment damage and preventing production accidents.

[0027] Further, as Figure 2 shown, this application further includes: Performing data standardization analysis on the K dust removal equipment operation nodes respectively to obtain K available node data standards, and determining K node data preprocessing programs according to the K available node data standards; preprocessing the operation data streams of the K dust removal nodes respectively based on the K node data preprocessing programs to obtain K standard operation data streams of the dust removal nodes; extracting operation indicators for the K dust removal equipment operation nodes respectively to obtain a set of K node equipment operation indicators; and performing abnormal operation identification on the K standard operation data streams of the dust removal nodes based on the set of K node equipment operation indicators to obtain the set of abnormal dust removal nodes and the set of abnormal node impact factors.

[0028] Specifically, perform data standardization processing on each dust removal equipment operation node separately to unify the operation data of different nodes into a comparable standard range, obtain K available node data standards, and determine the process of obtaining the K available node data standards as K node data preprocessing programs. Data standardization analysis helps to eliminate the differences between different nodes, making subsequent data processing more accurate and consistent, and ensuring the unity and comparability of data. For example, set preprocessing steps for different node data according to a preset standard, and perform processing steps such as removing outliers and normalization.

[0029] Then, execute the data preprocessing program for the operation data stream of the corresponding dust removal node according to each node data preprocessing program in the K node data preprocessing programs to obtain K standard operation data streams of the dust removal nodes, better processing and optimizing the data stream of the nodes, ensuring that the data of each node can be processed according to a program suitable for its characteristics, and improving the quality and efficiency of data processing.

[0030] Next, extract the key indicators reflecting the equipment operation status, that is, operation indicators, from each standardized dust removal equipment operation node to obtain a set of K node equipment operation indicators. The operation indicators are the key data points used to evaluate the equipment performance, and they collect the performance and status information shown by each node during operation, providing a basis for subsequent anomaly detection. Among them, the operation evaluation indicators corresponding to different operation nodes are different. For example, the equipment operation indicators of the filtration and purification node include the processing air volume, filtration air velocity, particulate matter removal rate, etc.

[0031] Finally, using the set of K node device operation metrics extracted, analyze the standardized operation data streams of the K dust removal nodes to identify abnormal operation conditions in the corresponding nodes, obtaining a set of abnormal dust removal nodes. Meanwhile, a set of impact factors for abnormal nodes is also generated to help understand and analyze the possible impacts of these abnormalities on the entire device system.

[0032] By ensuring that the monitoring and management of dust removal equipment can be more precise and efficient, the safety and stability of the system are improved.

[0033] Furthermore, this application also includes: Mine and obtain the operation data set of the dust removal equipment, classify and label the operation data set of the dust removal equipment according to the set of K node device operation metrics, obtaining a set of operation data streams of K node metrics; perform abnormal metric identification training and abnormal degree analysis training on the set of operation data streams of K node metrics in sequence, obtaining K node abnormal device branch models and K node abnormal degree branch models; logically merge the K node abnormal device branch models and the K node abnormal degree branch models to generate a K node abnormal operation identification model; based on the K node abnormal operation identification model, perform abnormal operation identification on the operation data streams of the K dust removal nodes to obtain the set of abnormal dust removal nodes and the set of abnormal node impact factors.

[0034] Specifically, through data mining techniques, collect and organize a large amount of data sets from the operation of the dust removal equipment. Classify and label the operation data set of the dust removal equipment according to the set of K node device operation metrics, categorize a large amount of operation data, so that each category of data corresponds to a specific node operation metric, thereby forming a set of operation data streams of K node metrics, and more targeted analysis and processing of the operation data of different nodes.

[0035] Then, further analyze each set of operation data streams of node metrics, through machine learning or other algorithms, perform abnormal metric identification training and abnormal degree analysis training, respectively establish an abnormal device model and an abnormal degree model corresponding to each set of operation data streams of node metrics, and integrate to obtain K node abnormal device branch models and K node abnormal degree branch models, so as to identify nodes with abnormal conditions and evaluate the severity of the abnormality, providing a model basis for subsequent abnormal detection and ensuring the accuracy and effectiveness of abnormal detection.

[0036] Then, after obtaining the K node abnormal device branch models and the K node abnormality degree branch models, the corresponding branch models need to be merged into a complete abnormal operation recognition model to obtain the K node abnormal operation recognition models. For example, the merging can be achieved through logical integration, enabling the model to not only identify the existence of abnormalities but also evaluate the impact and degree of the abnormalities, and comprehensively identify and evaluate the abnormal conditions of each node.

[0037] Finally, use the K node abnormal operation recognition models to analyze the operation data streams of the K dust removal nodes, identify the nodes with abnormal operations, obtain a set of abnormal dust removal nodes, and the corresponding set of abnormal node impact factors, which helps to further analyze and understand the impact of the abnormalities on the overall system, so that appropriate countermeasures can be taken.

[0038] By ensuring that any potential abnormalities can be detected and accurately evaluated during the operation of the dust removal equipment, the operation efficiency and safety of the equipment are improved.

[0039] Furthermore, this application also includes: Using the dust removal expert system to perform strategy analysis on the set of abnormal dust removal nodes and the set of abnormal node impact factors to obtain an initial set of abnormal dust removal node strategies; evaluating and selecting each node strategy in the initial set of abnormal dust removal node strategies to determine the set of parent strategy parameters; performing cross-combination and random perturbation on the set of parent strategy parameters to expand and update the initial set of abnormal dust removal node strategies to obtain a set of node update strategy parameters; performing iterative comparison and optimization on the set of node update strategy parameters respectively to determine a preset proportion of the set of dust removal strategy parameters for abnormal nodes, and constructing the global dust removal strategy space according to the set of dust removal strategy parameters for abnormal nodes.

[0040] Specifically, use the dust removal expert system to conduct a detailed analysis of the identified abnormal nodes and impact factors. The expert system generates a set of preliminary countermeasures through the application of algorithms, provides a preliminary solution for dealing with abnormal nodes, obtains the initial set of abnormal dust removal node strategies, and then provides guiding suggestions for subsequent actions after identifying the abnormalities.

[0041] Next, conduct a detailed evaluation of the initially generated set of strategies to select the optimal or most suitable strategy parameters. The selected strategy parameters are called the set of parent strategy parameters, which will be used as the basis for expansion and update, providing seeds for subsequent strategy optimization and evolution, and ensuring that the best-performing strategy parameters are selected from among the numerous initial strategies as the basis for further optimization.

[0042] Then, by cross - combining and introducing random perturbations to the parent policy parameters, a set of node update policy parameters is obtained. For example, by introducing mutation and combination, the initial policy set is extended and updated to obtain more potential optimization solutions, generate more new sets of policy parameters, and then by increasing the diversity of the policies, better solutions can be found.

[0043] Next, the extended and updated set of node update policy parameters is iterated and compared multiple times to find the optimal policy parameters. The optimized policy parameters are screened out, and the optimal policies are retained according to a preset ratio to form a set of dust removal policy parameters for abnormal nodes. Then, among numerous possible solutions, the best coping strategy is found to ensure that abnormal nodes can be effectively processed, and then a global dust removal policy space is constructed to provide a unified and optimized policy framework for the entire dust removal system.

[0044] By ensuring that the dust removal system can use the optimal strategy to cope with abnormal nodes, the overall efficiency and stability of the system are improved.

[0045] Furthermore, this application also includes: Based on the set of abnormal node impact factors, the set of abnormal dust removal nodes is compared to determine the first abnormal dust removal node, which has the largest abnormal node impact factor corresponding to it; the dust removal strategy simulation database is evaluated according to the abnormal equilibrium target to obtain a set of dust removal strategy simulation effect operators; the first dust removal strategy set of the first abnormal dust removal node is obtained, and based on the set of dust removal strategy simulation effect operators, the first dust removal strategy set is compared and optimized to determine the first node dust removal strategy combination with the best dust removal simulation effect; a Nash equilibrium cost function is introduced, and based on the first node dust removal strategy combination, the dust removal strategy simulation database is controlled and optimized to determine the device node control strategy parameters.

[0046] Specifically, the abnormal node impact factors in the set of abnormal dust removal nodes are compared, and the node with the largest impact factor is identified from the set of abnormal dust removal nodes to determine the first abnormal dust removal node, finding the node that has the greatest impact on the system among numerous abnormal nodes for key processing.

[0047] Then, under the defined abnormal equilibrium target, the constructed dust removal strategy simulation database is evaluated, and the evaluation results generate a set of dust removal strategy simulation effect operators, which represent the effects of each dust removal strategy in different situations, aiming to quantify and compare the effects of different strategies for subsequent optimal selection.

[0048] Then, a set of strategies is selected from the dust removal strategies of the first abnormal node as the first dust removal strategy set, and the dust removal strategy simulation effect operator set is used for comparison and optimization. The finally determined strategy combination is the solution with the optimal simulation effect, showing the best performance in the simulation evaluation and expected to achieve the best effect in actual applications as the dust removal strategy combination for the first node.

[0049] Next, the Nash equilibrium cost function is introduced. Based on the dust removal strategy combination of the first node, the dust removal strategy simulation database is controlled and optimized to ensure a random set of strategies when the strategy parameters of the first abnormal dust removal node are optimal. Cost calculation is performed in this way to make the strategy parameters of other nodes balanced and optimal under this condition, determine the device node control strategy parameters, and then use them to actually control the device node to achieve an ideal equilibrium state and optimal dust removal effect.

[0050] By ensuring that the dust removal system can adopt the most effective and balanced strategies to handle complex anomalies, the overall efficiency and stability of the system are improved.

[0051] Furthermore, this application also includes: Construct the Nash equilibrium cost function: ; where is the cost function of the first node dust removal strategy combination of the first abnormal dust removal node relative to the dust removal strategy set of the remaining abnormal dust removal nodes , is a dust removal strategy set with one missing, , , is the total number of dust removal equipment operation nodes; is the global dust removal strategy space, represents the set of dust removal strategies available for selection in the th abnormal dust removal node, represents the probability of selecting the dust removal strategy at the th construction position under , is the abnormal payment cost of the first abnormal dust removal node generating losses based on the global dust removal strategy space Let the minimum converge to output the device node control strategy parameters.

[0052] Specifically, a mathematical model is created to measure and optimize the process of selecting dust removal strategies. Under the conditions of multiple nodes and multiple strategies, a balance point is found such that in the strategy combinations of all nodes, no single node can obtain better results by unilaterally changing its strategy. The Nash equilibrium cost function is to achieve this balance in a complex system and ensure the rationality and stability of strategy selection.

[0053] Next, the first abnormal dust removal node The first node dust removal strategy combination Relative to the dust removal strategy sets of the remaining abnormal dust removal nodes The cost function , which is used to measure the cost or loss of the strategy combination of this node relative to the strategies of other abnormal nodes, helps evaluate whether the current strategy is reasonable and whether it is possible to reduce losses or optimize the effect by adjusting the strategy.

[0054] Then, the exclusive dust removal strategy set , which refers to the set formed by the remaining strategy combinations after a certain specific strategy is removed, indicating the situation in the strategy selection process considering that some strategies may be excluded. The exclusive dust removal strategy set is used to simulate the effects under different strategy combinations, so as to find the optimal strategy selection.

[0055] Next, the global dust removal strategy space covers the strategy sets that all abnormal nodes can choose, representing all possible strategy combinations in the system. The global dust removal strategy space provides a complete strategy library for the overall optimization of the system. The dust removal strategy set available for selection in the th abnormal dust removal node represents the strategy combinations in the global dust removal strategy space.

[0056] Then, the probability of selecting a dust removal strategy at the th construction location under describes the probability of strategy selection, indicating that at a specific construction location, each strategy has a certain probability of being selected, which affects the execution effect of the final strategy. Through probability analysis, the strategy selection process can be better evaluated and optimized.

[0057] Next, the first abnormal dust removal node generates an abnormal payment cost of loss based on the global dust removal strategy space Explains the calculation method of losses. The first abnormal node may incur losses after selecting a strategy, and the losses are measured by the abnormal payment cost. This cost is used to evaluate whether the strategy selection is reasonable and how to adjust the strategy to reduce losses and improve the overall dust removal effect.

[0058] Finally, let The minimum convergence output device node control strategy parameter represents the ultimate goal of optimization, that is, by continuously adjusting and optimizing the strategy parameters, finding the strategy combination that minimizes the system losses, obtaining the control strategy parameters of the device node, and using them in actual device control to ensure the efficient operation of the system.

[0059] By finding the optimal device control strategy in a complex system, ensuring the best overall effect of the dust removal system, and achieving the stable and efficient operation of the system.

[0060] Furthermore, this application also includes: Screening and obtaining N abnormal dust removal nodes from the remaining abnormal dust removal nodes based on the abnormal node influence factor set; excluding the first abnormal dust removal node and successively performing strategy comparison and optimization and equilibrium cost analysis on the N abnormal dust removal nodes to obtain N device control strategy parameters; performing intersection optimization and update on the device node control strategy parameters based on the N device control strategy parameters.

[0061] Specifically, using the abnormal node influence factor set, screening among the remaining abnormal dust removal nodes, selecting N abnormal nodes with a greater impact on the system, obtaining N abnormal dust removal nodes, and further determining the nodes in the system that require the most attention and optimization, so that subsequent processing is more targeted. Among them, screening is performed on a preset number of nodes with a larger abnormal influence factor, and the preset number can be determined according to the actual abnormal situation and abnormal handling requirements.

[0062] Then, without considering the first abnormal dust removal node, performing cost analysis on the previously screened N abnormal nodes to obtain N groups of node equilibrium control strategy parameters corresponding to the N abnormal dust removal nodes, that is, N device control strategy parameters, and further finding the optimal control strategy for each node. The equilibrium cost analysis is used to evaluate the cost and benefit of the strategy, and finally generates the corresponding device control strategy parameters for each node, thereby optimizing the control effect of each abnormal node.

[0063] Then, using the obtained N device control strategy parameters, further optimizing the device node control strategy parameters of the entire system. By means of intersection, integrating and adjusting the strategy parameters of different nodes to ensure that the final control strategy is optimal within the global scope, which helps to coordinate the strategies of each node and makes the overall system more efficient and balanced during execution.

[0064] By ensuring that the system can take optimal countermeasures in the face of multi-node anomalies, the overall stability and operating efficiency of the system are improved.

[0065] Furthermore, this application also includes: Performing an intersection operation on the N device control policy parameters to obtain a set of intersection frequency of node policy parameters; screening the N device control policy parameters based on the set of intersection frequency of node policy parameters to obtain a set of superior node policy parameters; and performing substitution optimization update on the device node control policy parameters based on the set of superior node policy parameters.

[0066] Specifically, perform an intersection operation on the generated N device control policy parameters, that is, count the frequencies of the node policy parameters that appear multiple times in each node parameter of the N device control policy parameters respectively, and form a set through statistics, that is, the set of intersection frequency of node policy parameters.

[0067] Next, screen the N device control policy parameters based on the set of intersection frequency of node policy parameters, and analyze the overlapping degree of the N device control policy parameters among different nodes. Through the intersection operation, it is possible to find the policy parameters that are frequently adopted in multiple nodes, that is, select the policy parameter with the highest frequency of occurrence in each node for the corresponding node parameter in the device node control policy parameters.

[0068] Then, perform substitution optimization update on the device node control policy parameters based on the set of superior node policy parameters. By substituting the original parameters and using the optimized superior parameters to improve the control effect of the overall system. For example, for the second abnormal dust removal node, if the second policy parameter has the highest frequency of occurrence, then substitute it for the original second node policy parameter in the device node control policy parameters. The process of substitution optimization ensures that the system can adopt the optimal policy parameters during execution, improving the operating efficiency and stability of the system.

[0069] By ensuring that in a multi-node system, control can be performed with optimal policy parameters, the overall performance and reliability of the system are improved.

[0070] In summary, the industrial dust removal equipment remote monitoring system based on the Internet of Things provided by this application has the following technical effects: Through a dust removal equipment operation data stream acquisition module, the dust removal equipment operation data stream acquisition module is used to connect a target dust removal equipment to a remote monitoring Internet of Things platform through an industrial intelligent gateway, and collect and acquire the dust removal equipment operation data stream in real time through the industrial intelligent gateway, and wirelessly transmit the dust removal equipment operation data stream to the remote monitoring Internet of Things platform; a dust removal equipment operation node acquisition module, the dust removal equipment operation node acquisition module is used to extract key nodes from the target dust removal equipment through the remote monitoring Internet of Things platform to obtain K dust removal equipment operation nodes; a dust removal node operation data stream acquisition module, the dust removal node operation data stream acquisition module is used to preprocess and split the dust removal equipment operation data stream based on the K dust removal equipment operation nodes to obtain K dust removal node operation data streams; an abnormal operation identification module, the abnormal operation identification module is used to respectively identify abnormal operations for the K dust removal node operation data streams to obtain an abnormal dust removal node set and an abnormal node influence factor set; a dust removal strategy simulation database obtaining module, the dust removal strategy simulation database obtaining module is used to construct a global dust removal strategy space according to the abnormal dust removal node set and the abnormal node influence factor set, and perform simulation evaluation on the global dust removal strategy space to obtain a dust removal strategy simulation database; a remote monitoring control module, the remote monitoring control module is used to define an abnormal balance target to control and optimize the dust removal strategy simulation database, determine equipment node control strategy parameters, and perform remote monitoring control on the target dust removal equipment through the equipment node control strategy parameters, so as to achieve the technical goal of precise monitoring and prediction in a complex system with multiple nodes and multiple variables, and achieve the technical effect of being able to comprehensively and timely discover and handle equipment abnormal conditions, reduce the risk of equipment damage and prevent production accidents.

[0071] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0072] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is also intended to include these changes and variations.

Claims

1. The remote monitoring system of industrial dust removal equipment based on the Internet of Things is characterized by: The industrial dust removal equipment remote monitoring system based on the Internet of Things includes: A dust removal equipment operation data stream acquisition module, which is used to connect the target dust removal equipment to the remote monitoring Internet of Things platform through the industrial intelligent gateway, and to collect and acquire the dust removal equipment operation data stream in real time through the industrial intelligent gateway, and to wirelessly transmit the dust removal equipment operation data stream to the remote monitoring Internet of Things platform; A dust removal equipment operation node acquisition module, wherein the dust removal equipment operation node acquisition module is used to extract key nodes of the target dust removal equipment through the remote monitoring Internet of Things platform to obtain K dust removal equipment operation nodes; A dust removal node operation data flow acquisition module, wherein the dust removal node operation data flow acquisition module is used to pre-process and divert the dust removal equipment operation data flow based on the K dust removal equipment operation nodes to obtain K dust removal node operation data flows; An abnormal operation identification module, the abnormal operation identification module is used to identify abnormal operations of the K dust removal node operation data streams respectively, and obtain an abnormal dust removal node set and an abnormal node impact factor set; A dust removal strategy simulation database obtaining module, wherein the dust removal strategy simulation database obtaining module is used to construct a global dust removal strategy space according to the abnormal dust removal node set and the abnormal node impact factor set, simulate and evaluate the global dust removal strategy space, and obtain a dust removal strategy simulation database; A remote monitoring and control module is used to define an abnormal balance target to control and optimize the dust removal strategy simulation database, determine the device node control strategy parameters, and remotely monitor and control the target dust removal equipment through the device node control strategy parameters.

2. The remote monitoring system for industrial dust removal equipment based on the Internet of Things according to claim 1, characterized in that: The obtaining of the abnormal dust removal node set and the abnormal node impact factor set includes: Performing data standardization analysis on the K dust removal equipment operation nodes respectively to obtain K available node data standards, and determining K node data preprocessing procedures according to the K available node data standards; Preprocessing the K dust removal node operation data streams respectively based on the K node data preprocessing programs to obtain K dust removal node standard operation data streams; Extracting operating indicators of the K dust removal equipment operating nodes respectively to obtain a set of operating indicators of K node equipment; Based on the K node equipment operation indicator sets, abnormal operation of the K dust removal node standard operation data streams is identified to obtain the abnormal dust removal node set and the abnormal node impact factor set.

3. The remote monitoring system for industrial dust removal equipment based on the Internet of Things as claimed in claim 2, characterized in that: The obtaining of the abnormal dust removal node set and the abnormal node impact factor set includes: Mining and acquiring a dust removal equipment operation data set, classifying and identifying the dust removal equipment operation data set according to the K node equipment operation indicator sets, and obtaining K node indicator operation data flow sets; Perform abnormal indicator recognition training and abnormal degree analysis training on the K node indicator operation data flow sets in sequence to obtain K node abnormal device branch models and K node abnormal degree branch models; Logically merging the K node abnormal device branch models and the K node abnormal degree branch models to generate a K node abnormal operation identification model; Based on the K node abnormal operation identification model, abnormal operation of the K dust removal node operation data streams is identified to obtain the abnormal dust removal node set and the abnormal node impact factor set.

4. The remote monitoring system for industrial dust removal equipment based on the Internet of Things as claimed in claim 1, characterized in that: The construction of the global dust removal strategy space includes: Using the dust removal expert system to perform strategy analysis on the abnormal dust removal node set and the abnormal node influencing factor set to obtain an initial abnormal dust removal node strategy set; Evaluate and select each node strategy in the initial abnormal dust removal node strategy set to determine a parent strategy parameter set; The parent generation strategy parameter set is cross-combined and randomly disturbed, the initial abnormal dust removal node strategy set is expanded and updated, and a node update strategy parameter set is obtained; The node update strategy parameter sets are respectively iteratively compared and optimized to determine a preset ratio of abnormal node dust removal strategy parameter sets, and the global dust removal strategy space is constructed according to the abnormal node dust removal strategy parameter sets.

5. The remote monitoring system for industrial dust removal equipment based on the Internet of Things as claimed in claim 1, characterized in that: The determining of the device node control strategy parameters includes: Comparing the abnormal dust removal node set based on the abnormal node impact factor set, determining a first abnormal dust removal node, wherein the abnormal node impact factor corresponding to the first abnormal dust removal node is the largest; Performing an effect evaluation on the dust removal strategy simulation database according to the abnormal balance target to obtain a dust removal strategy simulation effect operator set; Obtaining a first dust removal strategy set for the first abnormal dust removal node, comparing and optimizing the first dust removal strategy set based on the dust removal strategy simulation effect operator set, and determining a first node dust removal strategy combination with an optimal dust removal simulation effect; A Nash equilibrium cost function is introduced to control and optimize the dust removal strategy simulation database based on the first node dust removal strategy combination to determine the device node control strategy parameters.

6. The remote monitoring system for industrial dust removal equipment based on the Internet of Things as claimed in claim 5, characterized in that: The determining of the device node control strategy parameters includes: Construct the Nash equilibrium cost function: ; in, The first abnormal dust removal node The first node dust removal strategy combination The dust removal strategy set relative to other abnormal dust removal nodes The cost function of For a set of dust removal strategies that are missing, , , The total number of nodes running for dust removal equipment; is the global dust removal strategy space, Indicates The set of dust removal strategies available for selection in the abnormal dust removal nodes, Indicated in Next Select dust removal strategy for each construction location The probability of The first abnormal dust removal node Based on the global dust removal strategy space The abnormal payment cost that caused the loss The minimum convergence output is the device node control strategy parameter.

7. The remote monitoring system for industrial dust removal equipment based on the Internet of Things according to claim 6, characterized in that: Also includes: Based on the abnormal node impact factor set, N abnormal dust removal nodes are screened and obtained from the remaining abnormal dust removal nodes; Eliminate the first abnormal dust removal node, perform strategy comparison and optimization and equilibrium cost analysis on the N abnormal dust removal nodes in turn, and obtain N equipment control strategy parameters; The device node control strategy parameters are updated by intersection optimization based on the N device control strategy parameters.

8. The remote monitoring system for industrial dust removal equipment based on the Internet of Things according to claim 7, characterized in that: The step of performing intersection optimization and updating on the device node control strategy parameters based on the N device control strategy parameters includes: Performing strategy parameter intersection on the N device control strategy parameters to obtain a node strategy parameter intersection frequency set; Filter the N device control policy parameters based on the node policy parameter intersection frequency set to obtain a node priority policy parameter set; The device node control policy parameters are replaced and optimized and updated based on the node priority policy parameter set.

Citation Information

Patent Citations

  • Industrial de-dusting equipment's intelligent monitoring system and method based on embedded technology

    CN107065681A

  • Intelligent monitoring method and system for distribution transformer district based on Internet of Things technology

    CN118157333A

  • Electric precipitation efficient control method and system for industrial waste gas treatment

    CN118904542A

  • Environmental comfort control method and system, electronic device, and storage medium

    WO2021073299A1

Cited By

  • Intelligent control system for construction site dust fall equipment based on Internet of Things

    CN120610479A