Intelligent assisted monitoring system and method

Abstract

The present invention relates to the technical field of intelligent monitoring, and in particular to an intelligent assisted monitoring system and method. The intelligent assisted monitoring system comprises control modules: a data processing module (100), a monitoring and alarm module (200) connected to the data processing module (100), an operating condition analysis module (300) connected to the data processing module (100), an evaluation and decision-making module (400) simultaneously connected to the monitoring and alarm module (200) and the operating condition analysis module (300), an interaction module (500) connected to the operating condition analysis module (300), a communication and notification module (600) connected to the interaction module (500), and a configuration management module (700) simultaneously connected to the monitoring and alarm module (200), the operating condition analysis module (300), and the evaluation and decision-making module (400).

Description

An intelligent assisted inventory monitoring system and method Technical Field

[0001] This invention relates to the field of intelligent inventory monitoring technology, and in particular to an intelligent auxiliary inventory monitoring system and method. Background Technology

[0002] In recent years, with the continuous increase in the grid-connected capacity of new energy sources, the load rate of thermal power units has gradually declined, deep peak shaving has become more frequent, and the equipment failure rate has increased significantly. At the same time, persistently high coal prices have made it increasingly difficult for thermal power companies to operate, leading to frequent instances of under-maintenance equipment and units operating with defects, further exacerbating equipment damage. On the other hand, increasingly stringent national requirements for thermal power generating units—such as high efficiency, energy conservation, environmental protection, the ability to reduce loads and maintain grid stability—contradict the complex operating conditions, resulting in an increasingly severe economic situation for thermal power units relying solely on traditional control methods.

[0003] In centralized control operation, monitoring personnel need to monitor and analyze system process parameters in real time and perform corresponding operations to maximize the unit's energy-saving potential. Simultaneously, they must constantly monitor the safety status of the system and equipment to ensure safe unit operation. Monitoring work is not only intensive and time-consuming, but also extremely stressful. The knowledge and operational experience of the monitoring personnel play a decisive role in the quality of the monitoring. Summary of the Invention

[0004] In view of the problems existing in the above or prior art, the present invention is proposed.

[0005] Therefore, the purpose of this invention is to provide an intelligent auxiliary monitoring method that can improve the accuracy, real-time performance, and economy of power plant monitoring through intelligent means, so as to optimize the production process and improve equipment performance.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: an intelligent auxiliary monitoring system, comprising a control module: a data processing module, a monitoring and alarm module connected to the data processing module, a working condition analysis module connected to the data processing module, an evaluation and decision module connected to both the monitoring and alarm module and the working condition analysis module, an interaction module connected to the working condition analysis module, a communication and notification module connected to the interaction module, and a configuration management module connected to the monitoring and alarm module, the working condition analysis module, and the evaluation and decision module.

[0007] As a preferred embodiment of the intelligent auxiliary monitoring system of the present invention, the data processing module includes a database and server hardware;

[0008] The database serves as the core, storing and providing storage and query services for all monitoring data.

[0009] Server hardware provides computing and data processing capabilities for the software that runs databases and other modules.

[0010] As a preferred embodiment of the intelligent auxiliary monitoring system of the present invention, the monitoring and alarm module includes a parameter analysis and trend prediction program, as well as intelligent monitoring;

[0011] The parameter analysis and trend prediction program analyzes data from the database to provide degradation analysis and failure prediction.

[0012] Intelligent monitoring obtains real-time data from the database, as well as the results of parameter analysis and trend prediction, and performs monitoring and alarm functions simultaneously.

[0013] As a preferred embodiment of the intelligent auxiliary monitoring system of the present invention, the working condition analysis module includes a clustering analysis program, a pattern recognition model, a data mining program, and a working condition optimization program.

[0014] Clustering analysis programs, pattern recognition models, and data mining programs all use data from the database for operational condition analysis and optimization.

[0015] The operational optimization program guides operational optimization based on the results of cluster analysis, pattern recognition, and data mining.

[0016] As a preferred embodiment of the intelligent auxiliary monitoring system of the present invention, the evaluation and decision-making module includes a quality management program for monitoring the operational quality of the entire system.

[0017] As a preferred embodiment of the intelligent auxiliary monitoring system of the present invention, the interactive module includes a monitoring interface and an assessment cockpit. The interactive module is used to display intelligent monitoring and the analysis results of each module in the system to the user.

[0018] As a preferred embodiment of the intelligent auxiliary monitoring system of the present invention, the communication notification module includes a notification program and an information publishing program.

[0019] The notification process includes receiving alarm information from intelligent monitoring and sending notifications to users;

[0020] The information publishing program is used to publish information from the monitoring interface and the assessment cockpit.

[0021] As a preferred embodiment of the intelligent auxiliary monitoring system of the present invention, the configuration management module includes configuration management and data management, and the configuration management module provides configuration and data management support for the monitoring alarm module, the working condition analysis module and the evaluation decision module.

[0022] To solve the above-mentioned technical problems, the present invention also provides the following technical solution: an intelligent assisted monitoring method, which includes predicting equipment status changes and fault trends through real-time monitoring and historical data analysis, and performing deterioration analysis and early warning of the equipment;

[0023] Clustering algorithms are used to classify operating conditions, and pattern recognition technology is used to calculate and identify boiler operating modes online.

[0024] Based on data mining technology, operational patterns are extracted from historical data to optimize operating conditions and improve unit operating efficiency.

[0025] As a preferred embodiment of the intelligent auxiliary monitoring method of the present invention, the clustering algorithm is an unsupervised learning method used to divide the samples in the collected operating condition dataset into several non-overlapping clusters, so that the samples within the same cluster have high similarity and the samples between different clusters have low similarity.

[0026] The beneficial effects of this invention are as follows: Through integrated monitoring and data analysis, this invention significantly improves the informatization level of power plant operation, optimizes operation guidance, reduces costs and enhances economic efficiency. By adopting advanced clustering analysis and pattern recognition technology, it realizes real-time monitoring and intelligent early warning of equipment status and operating conditions, thereby improving the maintenance level and operational reliability of equipment. Attached Figure Description

[0027] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0028] Figure 1 is a schematic diagram of the operation monitoring principle of an intelligent auxiliary monitoring system.

[0029] Figure 2 is a schematic diagram showing the trend of parameter anomaly analysis in an intelligent auxiliary monitoring system.

[0030] Figure 3 is a schematic diagram of the parameter anomaly configuration page of an intelligent auxiliary monitoring system.

[0031] Figure 4 is a schematic diagram of the K-means algorithm clustering analysis process of an intelligent assisted monitoring system.

[0032] Figure 5 is a schematic diagram of a pattern recognition model for an intelligent auxiliary monitoring system.

[0033] Figure 6 is a schematic diagram of the abnormal operation analysis page of an intelligent auxiliary monitoring system.

[0034] Figure 7 is a schematic diagram of the configurable associated parameters of an intelligent auxiliary monitoring system.

[0035] Figure 8 shows a first implementation of an intelligent auxiliary monitoring system.

[0036] Figure 9 shows a second implementation of an intelligent auxiliary monitoring system. Detailed Implementation

[0037] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0038] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0039] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0040] Example 1

[0041] Referring to Figures 1 to 9, the first embodiment of the present invention provides an intelligent auxiliary monitoring system that can improve the accuracy, real-time performance, and economy of power plant monitoring through intelligent means, thereby optimizing the production process and improving equipment performance.

[0042] Specifically, the control module includes: a data processing module 100, a monitoring and alarm module 200 connected to the data processing module 100, a working condition analysis module 300 connected to the data processing module 100, an evaluation and decision module 400 connected to both the monitoring and alarm module 200 and the working condition analysis module 300, an interaction module 500 connected to the working condition analysis module 300, a communication and notification module 600 connected to the interaction module 500, and a configuration management module 700 connected to the monitoring and alarm module 200, the working condition analysis module 300, and the evaluation and decision module 400.

[0043] Furthermore, the data processing module 100 includes a database 101 and server hardware 102;

[0044] Database 101 serves as the core, storing and providing storage and query services for all monitoring data;

[0045] It should be noted that database 101 adopts SCSY-DB distributed real-time historical database 101. As a distributed database 101, SCSY-DB distributed real-time historical database 101 can store and manage a large amount of production data from all units and auxiliary workshops in the plant. It can also process real-time data and store historical data for a long time, meeting the needs of complete monitoring and long-term storage of production data.

[0046] In addition, Database 101 connects to the monitoring information system via a network interface to achieve integrated data monitoring, facilitating timely access to operating parameters for production and management personnel. Simultaneously, the SCSY-DB distributed real-time historical database 101 can also perform unit and plant-level performance calculations and analyses, identifying the causes of high coal consumption in real time and providing operational or maintenance guidance. Beyond its basic functionalities, the SCSY-DB distributed real-time historical database 101 supports in-depth data mining analysis, adding diagnostic, analytical, and optimization capabilities. For SIS project implementation, SCSY-DB provides a quick and simple integration method, facilitating access to lower-level data and shortening the project implementation timeline.

[0047] Server hardware 102 provides computing and data processing capabilities for the software that runs database 101 and other modules.

[0048] It should be noted that the server hardware 102 includes dual CPUs with a 2.4GHz clock speed and 16 cores, equipped with 24MB of cache; two 32GB DDR3 memory modules; a 5TB solid-state drive (SSD) configured in RAID 5 to provide data redundancy and performance; four Gigabit Ethernet interface cards for high-speed network connectivity; and two 900W power supply units to ensure stable power supply to the server.

[0049] Furthermore, the monitoring and alarm module 200 includes a parameter analysis and trend prediction program 201, and intelligent monitoring 202;

[0050] The parameter analysis and trend prediction program 201 analyzes data based on the data in the database 101 to provide degradation analysis and failure prediction.

[0051] It should be noted that the parameter analysis and trend forecasting steps include:

[0052] Check if the equipment status is within the normal range;

[0053] Observe the changing trends of the equipment's status and establish a trend model;

[0054] Predict when the equipment will develop to a dangerous level;

[0055] Early detection of equipment malfunctions allows for timely countermeasures.

[0056] The intelligent monitoring system 202 obtains real-time data from the database 101, as well as the results of parameter analysis and trend prediction, and performs monitoring and alarm functions simultaneously.

[0057] It should be noted that the monitoring and alarm module 200 monitors the operating parameters of important equipment. Under set conditions, if the rate of change of a parameter continuously exceeds a set value and shows a continuous increasing trend, an early warning message will be issued. If the rate of change is not large, but compared with previous statistical data (default 48 hours), if it exceeds a certain range, an early warning will be issued. Warnings can be promptly communicated to relevant personnel via the SIS system's publishing page, SMS, or email.

[0058] Specifically, the main functions of the monitoring and alarm module 200 include:

[0059] Equipment condition (leakage, wear, etc.) detection based on parameter degradation analysis mainly includes: detecting whether equipment parameters are within the normal range; and issuing attention signals to relevant personnel when equipment parameters are found to deviate from the normal range.

[0060] It has a real-time parameter degradation analysis function;

[0061] It has the function of analyzing the history of parameter degradation;

[0062] Customizable timing and customizable data analysis features.

[0063] Furthermore, the working condition analysis module 300 includes a clustering analysis program 301, a pattern recognition model 302, a data mining program 303, and a working condition optimization program 304.

[0064] Clustering analysis program 301, pattern recognition model 302, and data mining program 303 all use data from database 101 for working condition analysis and optimization.

[0065] It's important to note that clustering analysis program 301 divides a dataset into different classes or clusters according to a specific criterion (such as a distance criterion, i.e., the distance between data points), maximizing the similarity of data objects within the same cluster while maximizing the differences between data objects in different clusters. The clustering algorithm divides database 101 into different groups, with significant differences between groups and similarity between data points within the same group. Unlike classification, before clustering, it's unclear how many groups the data will be divided into or how to divide it. Commonly used clustering algorithms include k-means, KNN, hierarchical clustering, and FCM clustering.

[0066] The metric for evaluating the accuracy of clustering algorithms is the clustering goodness of fit. Generally, a goodness of fit of fit greater than or equal to 80% indicates that the clustering algorithm is accurate. A goodness of fit of fit less than 80% indicates that the clustering process has a large error and the clustering algorithm needs to be re-implemented.

[0067] The formula for calculating clustering goodness of function is as follows:

[0068] If we perform cluster analysis on the historical data of these parameters using the K-means algorithm, as shown in Figure 4, the clustering results show that they are clustered into N classes. For example, the operating conditions of the boiler system can be divided into N types.

[0069] As shown in Figure 5, the pattern recognition model 302 is mainly implemented through a classification algorithm. The classification algorithm learns and trains on known data samples and their categories. After training, when new data samples are input, the algorithm automatically calculates the category corresponding to the sample. By analyzing the data in the example database 101, it accurately describes each category, builds an analytical model, or mines classification rules. These rules are then used to classify records in other databases 101. Commonly used classification algorithms include SVM, logistic regression, Bayesian classification, and decision trees.

[0070] The decision tree algorithm constructs decision trees to discover classification rules inherent in data. The core of the decision tree algorithm lies in constructing decision trees with high accuracy and small size. Decision tree construction can be divided into two steps. The first step is decision tree generation: the process of generating a decision tree from a training sample set. Generally, the training sample dataset is a historical dataset with a certain degree of aggregation, used for data analysis and processing, based on actual needs. The second step is decision tree pruning: decision tree pruning is the process of verifying, correcting, and refining the decision tree generated in the previous stage. It mainly involves using data from a new sample dataset (called the test dataset) to verify the initial rules generated during the decision tree generation process, and pruning branches that affect the accuracy of the prediction.

[0071] The 304 operating condition optimization program guides operational optimization based on the results of cluster analysis, pattern recognition, and data mining.

[0072] It should be noted that the operating condition optimization program 304 can find similar operating conditions that the system has previously operated under, based on the required operating conditions. According to the current operating requirements, it can find suitable and feasible operating conditions and bring out the values ​​of the associated parameters under these operating conditions, providing them to the operators. The operators can then adjust the operation of the unit based on the operating requirements and the provided associated parameter values, thereby achieving the best operating conditions that the unit and equipment can achieve under the existing conditions.

[0073] The operating condition optimization program 304 includes the following functions: multi-condition combination of operating conditions, stable operating condition search function, automatic establishment of a typical operating condition database 101 of the unit at 40%-100% load, providing operating condition combinations of the current operating status, providing non-combination constraints of the current operating status, comprehensive real-time comparison of operating condition stability, economy, environmental protection, and comprehensive comparison, query of the current operating condition and the corresponding optimal operating condition, comparison of design operating condition and actual optimal operating condition, comparison of test operating condition and actual optimal operating condition, query of any historical optimal value, operating condition trend analysis, operating condition query function with multiple modes, query of different demand functions, multiple query methods, user-friendly operation, multiple display of operating conditions, and flexible configuration function.

[0074] Among them, the multi-condition combination of working conditions refers to the fact that each working condition can be composed of multiple parameters, currently not exceeding four parameters (which can be expanded later according to needs). For some equipment, if only three conditions are required for the working condition, the fourth condition can be omitted. If several conditions are set, the working condition will be combined according to the set parameter conditions.

[0075] The stable operating condition search function has the function of finding the optimal stable operating condition. The parameters run continuously, and the value of the parameters does not exceed 5% of the set conditions (configurable). If the continuous operation exceeds 20 minutes, it becomes an operating condition.

[0076] Automatically establish a database of typical operating conditions for the unit at 40%-100% load 101, and achieve full-condition modeling through data accumulation;

[0077] It has multiple modes of working condition query function, which can query similar working conditions according to the entered working condition data, or automatically query related working conditions according to the current operating conditions; according to the operational requirements, it can query related working conditions to provide basic data support for operation.

[0078] Different query functions are available. On the display page, you must first select the query method. If you choose manual input of working conditions, you need to enter the relevant parameter values ​​of the working conditions. If you select the current working conditions, the values ​​of the current working conditions will be read from the real-time database 101 and displayed automatically.

[0079] Multiple query methods are available. The system offers various query options for different time periods, which can be flexibly switched. For example, the default time period can be selected as one day, one week, one month, one quarter, six months, one year, or two years (the longer the time period, the longer the query time, the lower the efficiency, and the slower the system). If a non-default time period is selected, the start and end times must be manually chosen (the program's span is set to no more than two years).

[0080] User-friendly operation. The business development page displays the number of similar working conditions searched. At the same time, users need to manually select the parameters of interest based on the current operational requirements (these parameters are related to the associated parameters of the working condition settings and must be selected from the associated parameters). Users also need to manually select the rules (initially, rules such as maximum, minimum, and center can be used, and the rule library can be expanded later).

[0081] Multiple display options for operating conditions. The operating condition display page shows the final operating condition details, including: start time, end time, duration, and data for selected parameters (average, maximum, and minimum values ​​within this operating condition segment). Operating conditions that meet the rules are highlighted in blue and can be notified to relevant personnel via SMS or email. The specific values ​​of associated parameters under this operating condition (average values ​​over this operating condition's time) are displayed item by item. Operators adjust the unit's operation based on operational requirements, associated parameters, and operational measures to achieve the desired operational goals.

[0082] It features flexible configuration capabilities. The operating conditions of the unit and different equipment can be freely, conveniently, and flexibly configured, allowing for the addition, modification, deletion, and configuration of operating conditions. Operating condition settings can be freely and flexibly configured (currently, four sets of conditional operating condition configurations are supported, requiring configuration of measurement point names, descriptions, units, etc., and data query functions are available, such as testing whether the configured measurement points are correct and whether data can be retrieved normally). Related parameters can also be freely and flexibly configured, allowing for common functions such as adding, modifying, and deleting related parameters, including measurement point names, descriptions, units, and upper / lower limits. Measurement point names can be directly copied from the SIS system; simply copy and paste. The display order of related parameters on the page is related to the sequence number of the configured parameters.

[0083] Furthermore, the evaluation decision module 400 includes a quality management procedure 401 for monitoring the operational quality of the entire system.

[0084] Furthermore, the interaction module 500 includes a monitoring interface 501 and an assessment cockpit 502. The interaction module 500 is used to display the intelligent monitoring 202 and the analysis results of each module in the system to the user.

[0085] It should be noted that, as shown in Figure 2, the monitoring interface 501 displays the parameter anomaly analysis trend by calculating the mean μ and standard deviation σ of the analyzed parameter over the previous 48 hours. It displays the trend curve of the analyzed parameter and five reference curves: the upper warning line is μ+9σ, the upper attention line is μ+3σ, the mean line is μ, the lower attention line is μ-3σ, and the lower warning line is μ-9σ.

[0086] You can select any time period to query parameter anomalies or perform real-time degradation analysis. The statistics column on the right can list the parameters that exceed the limit and the number of times they are counted.

[0087] As shown in Figure 3, the parameter anomaly configuration page allows for hierarchical configuration of units, systems, equipment, parameters, etc., and also requires configuration of the condition points for operational parameter analysis.

[0088] As shown in Figure 6, the monitoring interface 501 displays the following on the abnormal operating condition analysis page:

[0089] Automatic refresh of operating conditions. The system refreshes automatically every five minutes (time can be set), automatically compares operating conditions, and if operating conditions change, the system automatically searches for and analyzes operating conditions according to the default time period and compares relevant values.

[0090] Multiple query methods are available. The working condition query time period offers multiple methods that can be flexibly switched. If a default time period is selected, it can be one day, one week, one month, one quarter, half a year, one year, or two years (the longer the time period, the longer the query time, the lower the efficiency, and the slower the system). If a non-default time period is selected, the start and end times must be manually selected (the program must be set so that the span cannot exceed two years).

[0091] Centralized display of operating condition parameters. On the display page, if the default period is selected, the system can automatically find all similar operating conditions within that period and display them one by one. The displayed content includes the start time, end time, and duration of the operating condition, as well as the average, maximum, and minimum values ​​of relevant parameters under that condition. If the deviation of the parameter value of the current operating condition from the average value of previous operating conditions exceeds the set range or exceeds the maximum or minimum value of previously queried operating conditions, an alarm will be triggered. Alarm information will be promptly notified to relevant personnel via the SIS publishing page, SMS, and email.

[0092] The operating condition parameter monitoring page automatically monitors the operating conditions of all equipment and related parameters, and displays the number of statistical parameters, the number of normal parameters, and the number of abnormal parameters.

[0093] Furthermore, the communication notification module 600 includes a notification program 601 and an information publishing program 602;

[0094] The notification procedure 601 includes receiving alarm information from the intelligent monitoring 202 and sending a notification to the user;

[0095] The information publishing program 602 is used to publish information from the monitoring interface 501 and the assessment cockpit 502.

[0096] Furthermore, the configuration management module 700 includes configuration management 701 and data management 702. The configuration management module 700 provides configuration and data management 702 support for the monitoring and alarm module 200, the operating condition analysis module 300 and the evaluation and decision-making module 400.

[0097] It should be noted that the configuration management module 700 provides configuration and data management 702 to the operating condition analysis module 300, supporting convenient and flexible configuration of the operating conditions of the unit and different equipment, including adding, modifying, deleting, and configuring operating conditions. Operating condition conditions can be freely and flexibly configured, supporting four sets of conditional operating condition configurations. Parameter names, descriptions, and units need to be configured, and a data query function is available (to test whether the configured parameter names are correct and whether data can be retrieved normally). Parameter names can be directly copied and pasted from the SIS publication. The display order of related parameters on the display page is related to the sequence number of the configuration parameters.

[0098] As shown in Figure 7, the abnormal operating condition configuration page displays the devices and their associated parameters involved in the operating condition analysis. Each device can be configured with four associated parameter information.

[0099] The system operates as follows: It collects production data from all units and auxiliary workshops across the plant in real time via a network interface connected to the SIS system. The collected data is stored in the SCSY-DB distributed real-time historical database 101, including both real-time and long-term historical data. Simultaneously, the system analyzes and monitors the plant's production data in real time to understand power generation. Through unit and plant-level performance calculations and analysis, the system identifies the causes of excessive coal consumption and provides operational or maintenance guidance. At this point, the system monitors the operating parameters of critical equipment using an anomaly alarm module and issues warnings when parameters deviate from normal values. It also detects equipment status, including leaks and wear, through a parameter degradation analysis module, and analyzes equipment parameters in real time and historically. Using data fusion technology, it quickly analyzes equipment system faults, provides timely equipment risk assessments and intelligent warnings, and generates alarm events by processing a large amount of parameter exceedance and alarm data, notifying relevant personnel in various ways. Users can interact with the system through a web client for configuration management, performance data queries, and system monitoring.

[0100] In summary, this invention significantly improves the informatization level of power plant operation through integrated monitoring and data analysis, optimizes operation guidance, reduces costs and enhances economic efficiency. By employing advanced clustering analysis and pattern recognition technologies, it achieves real-time monitoring and intelligent early warning of equipment status and operating conditions, thereby improving equipment maintenance and operational reliability.

[0101] Example 2

[0102] This embodiment is the second embodiment of the present invention. This embodiment provides an intelligent auxiliary monitoring method, which can improve the accuracy, real-time performance and economy of power plant monitoring through intelligent means, so as to optimize the production process and improve equipment performance.

[0103] Specifically, through real-time monitoring and historical data analysis, we can predict changes in equipment status and failure trends, and conduct deterioration analysis and early warning for the equipment.

[0104] Clustering algorithms are used to classify operating conditions, and pattern recognition technology is used to calculate and identify boiler operating modes online.

[0105] Based on data mining technology, operational patterns are extracted from historical data to optimize operating conditions and improve unit operating efficiency.

[0106] Furthermore, clustering algorithms are unsupervised learning methods used to divide samples in a collected operational data set into several non-overlapping clusters, such that samples within the same cluster have high similarity, while samples between different clusters have low similarity.

[0107] Specifically, a sample library is established for each operating condition. For each operating condition, parameters such as the mode name, boiler efficiency, boiler load rate, outlet pressure, and chain speed are entered into the operating sample library. Optimization is then performed on each operating mode in the operating sample library to calculate the strongly correlated adjustable parameters corresponding to the highest boiler efficiency under each operating condition, thereby forming the optimal parameter combination for each operating condition.

[0108] Establishing an operational sample library requires the following data processing capabilities:

[0109] It supports commonly used supervised and unsupervised learning algorithms, and encapsulates toolboxes such as Support Vector Machine (SVM), Neural Network, Decision Tree, Random Forest, Clustering Algorithm, Anomaly Detection Algorithm to provide users with machine learning algorithm support;

[0110] It provides a web-based graphical mathematical formula editing function, supporting users to easily and quickly define rich algorithm models;

[0111] It provides an API as an open interface to support user-programmable custom algorithm implementations;

[0112] It supports mathematical modeling, mining, and analysis of historical and real-time data, and provides functions such as data playback, monitoring, and alarms.

[0113] It supports users in creating, storing, modifying, and deleting data models.

[0114] In summary, this invention significantly improves the informatization level of power plant operation through integrated monitoring and data analysis, optimizes operation guidance, reduces costs and enhances economic efficiency. By employing advanced clustering analysis and pattern recognition technologies, it achieves real-time monitoring and intelligent early warning of equipment status and operating conditions, thereby improving equipment maintenance and operational reliability.

[0115] It is important to note that the constructions and arrangements of this application shown in several different exemplary embodiments are merely illustrative. Although only a few embodiments are described in detail in this disclosure, those who consult this disclosure will readily understand that many modifications are possible (such as variations in installation arrangement, use of materials, color, orientation, etc.) without substantially departing from the novel teachings and advantages of the subject matter described in this application. For example, an element shown as integrally formed may be composed of multiple parts or elements, the position of the element may be inverted or otherwise changed, and the nature or number or position of the discrete elements may be altered or changed. Therefore, all such modifications are intended to be included within the scope of the invention. The order or sequence of any process or method steps may be changed or rearranged according to alternative embodiments. In the claims, any "support plus function" clause is intended to cover the structure performing the function described herein, and not only structurally equivalent but also equivalent in structure. Other substitutions, modifications, alterations, and omissions may be made in the design, operation, and arrangement of the exemplary embodiments without departing from the scope of the invention. Therefore, the invention is not limited to the particular embodiments but extends to a variety of modifications that still fall within the scope of the appended claims.

[0116] Furthermore, in order to provide a concise description of exemplary embodiments, not all features of actual embodiments may be omitted.

[0117] It should be understood that numerous specific implementation decisions can be made during the development of any practical implementation, such as in any engineering or design project. Such development efforts may be complex and time-consuming, but for those of ordinary skill in the art who benefit from this disclosure, the development effort will be a routine task in design, manufacturing, and production without requiring extensive experimentation.

[0118] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An intelligent auxiliary monitoring system, characterized in that: include, The system includes a data processing module (100), a monitoring and alarm module (200) connected to the data processing module (100), a working condition analysis module (300) connected to the data processing module (100), an evaluation and decision module (400) connected to both the monitoring and alarm module (200) and the working condition analysis module (300), an interaction module (500) connected to the working condition analysis module (300), a communication and notification module (600) connected to the interaction module (500), and a configuration management module (700) connected to both the monitoring and alarm module (200), the working condition analysis module (300), and the evaluation and decision module (400).

2. The intelligent auxiliary monitoring system as described in claim 1, characterized in that: The data processing module (100) includes a database (101) and server hardware (102); The database (101) serves as the core, storing and providing storage and query services for all monitoring data; The server hardware (102) provides computing and data processing capabilities for the software that runs the database (101) and other modules.

3. The intelligent auxiliary monitoring system as described in claim 2, characterized in that: The monitoring and alarm module (200) includes a parameter analysis and trend prediction program (201) and intelligent monitoring (202); The parameter analysis and trend prediction program (201) analyzes data in the database (101) to provide degradation analysis and failure prediction; The intelligent monitoring (202) obtains real-time data from the database (101) and receives the results of parameter analysis and trend prediction, while simultaneously monitoring and alarming.

4. The intelligent auxiliary monitoring system as described in claim 3, characterized in that: The operating condition analysis module (300) includes a clustering analysis program (301), a pattern recognition model (302), a data mining program (303), and an operating condition optimization program (304); The clustering analysis program (301), the pattern recognition model (302), and the data mining program (303) all use data from the database (101) for working condition analysis and optimization; The operating condition optimization procedure (304) guides operation optimization based on the results of cluster analysis, pattern recognition, and data mining.

5. The intelligent auxiliary monitoring system as described in claim 4, characterized in that: The evaluation decision module (400) includes a quality management procedure (401) for monitoring the operational quality of the entire system.

6. The intelligent auxiliary monitoring system as described in claim 5, characterized in that: The interactive module (500) includes a monitoring interface (501) and an assessment cockpit (502). The interactive module (500) is used to display the intelligent monitoring (202) and the analysis results of each module in the system to the user.

7. The intelligent auxiliary monitoring system as described in claim 7, characterized in that: The communication notification module (600) includes a notification program (601) and an information publishing program (602); The notification program (601) includes receiving alarm information from the intelligent monitoring (202) and sending a notification to the user; The information publishing program (602) is used to publish information from the monitoring interface (501) and the assessment cockpit (502).

8. The intelligent auxiliary monitoring system as described in claim 7, characterized in that: The configuration management module (700) includes configuration management (701) and data management (702). The configuration management module (700) provides configuration and data management (702) support for the monitoring and alarm module (200), the operating condition analysis module (300), and the evaluation and decision module (400).

9. An intelligent assisted inventory monitoring method, based on the above-mentioned intelligent assisted inventory monitoring system, characterized in that: include, By using real-time monitoring and historical data analysis, we can predict changes in equipment status and failure trends, and perform equipment degradation analysis and early warning. Clustering algorithms are used to classify operating conditions, and pattern recognition technology is used to calculate and identify boiler operating modes online. Based on data mining technology, operational patterns are extracted from historical data to optimize operating conditions and improve unit operating efficiency.

10. The intelligent assisted monitoring method as described in claim 9, characterized in that: The clustering algorithm is an unsupervised learning method used to divide samples in the collected operating condition dataset into several non-overlapping clusters, so that the samples within the same cluster have high similarity and the samples between different clusters have low similarity.

Images