Power plant intelligent management and monitoring method

Abstract

The invention discloses an intelligent management and monitoring method for a power plant, and the method comprises the steps: carrying out the real-time collection and preprocessing of the data information of equipment in the power plant, building an integrated three-dimensional model through the preprocessed data information, extracting the data information of the integrated three-dimensional model, and building a knowledge base. Classifying the knowledge base into a full life cycle power plant intelligent management system, establishing a production period energy auditing model in the power plant intelligent management system to carry out unit efficiency analysis and energy consumption analysis, constructing a deep learning model, carrying out fault detection and fault early warning through the deep learning model, and deploying distributed intelligent monitoring nodes. Equipment behaviors are monitored in real time, and equipment parameters are adjusted in different data intervals; the invention provides an intelligent management and monitoring method for a power plant, which can solve the problem that the accuracy of energy consumption analysis is influenced by deviation between a model and an actual equipment state due to the lack of self-adaptive capability of a traditional three-dimensional model updating mechanism.

Description

Technical Field

[0001] The present invention relates to the technical field of power plant equipment management, and in particular to a method for intelligent management and monitoring of power plants. Background Art

[0002] In the field of power industry, with the rapid development of information technology, the management and monitoring technology of power plants has also experienced a transformation from traditional manual management to automated and intelligent management. Early power plant management mainly relied on manual inspections and simple monitoring systems, which had great limitations in data processing capabilities, real-time performance and accuracy. In recent years, although some advanced monitoring technologies such as SCADA systems and DCS systems have been widely used in power plants, these systems can only achieve centralized data monitoring, but are still insufficient in equipment status prediction, fault diagnosis and intelligent management. First, the existing technologies often lack real-time and integration in the collection and processing of equipment data information, resulting in the inability to fully and accurately reflect the operating status of power plant equipment; second, the existing knowledge base construction method fails to fully utilize the advantages of three-dimensional models, which limits the intelligence level of power plant management systems. Third, although the existing technologies can perform unit efficiency analysis and energy consumption analysis, they lack effective fault detection methods and are difficult to achieve early warning of potential faults; finally, the existing monitoring technologies lack flexibility and pertinence in real-time monitoring and strategy adjustment of equipment behavior. The smart management and monitoring method for power plants invented by us builds an integrated three-dimensional model through real-time collection and preprocessing of equipment data, and on this basis establishes a knowledge base and a full life cycle smart management system for power plants. It is expected to achieve significant improvements in unit efficiency analysis, energy consumption analysis, fault detection, and real-time monitoring, thereby providing strong support for the stable operation and smart management of power plants. Summary of the invention

[0003] In view of the above existing problems, the present invention is proposed.

[0004] Therefore, the present invention provides a method for intelligent management and monitoring of power plants, which can solve the problem that the traditional three-dimensional model update mechanism lacks adaptive ability, resulting in a large deviation between the model and the actual equipment status, thereby affecting the accuracy of energy consumption analysis; in terms of identifying key factors of energy consumption, the existing technology does not mine production data and environmental data deeply enough, making it difficult to find effective operating parameter combinations to reduce energy consumption.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions, a method for intelligent management and monitoring of power plants, comprising:

[0006] Collect data information from equipment in the power plant in real time, pre-process the collected data, and use the pre-processed data information to build an integrated three-dimensional model;

[0007] Extract data information from the integrated 3D model to establish a knowledge base, and include the knowledge base in the full life cycle power plant smart management system;

[0008] Establish a production period energy audit model in the power plant smart management system to perform unit efficiency analysis and energy consumption analysis, use unit efficiency and energy consumption analysis to build a deep learning model, and use the deep learning model to perform fault detection and fault warning;

[0009] Deploy distributed intelligent monitoring nodes in the power plant to monitor equipment behavior in real time and adjust equipment parameters in different data ranges.

[0010] As a preferred solution of the power plant intelligent management and monitoring method described in the present invention, the real-time data information collection includes collecting geometric data, physical parameters, electrical data, environmental data, safety data, maintenance and operation data, sensor and monitoring equipment data of power plant equipment;

[0011] The geometric data includes equipment size, equipment layout and relative position, and geometric parameters of buildings and infrastructure; the physical parameters include temperature data of each part, pressure data in pipes and containers, and vibration frequency and amplitude of equipment; the electrical data includes operating data of the electrical system, distribution of power supply and load, and layout and status of cables and connectors; the environmental data includes air quality, humidity level, and lighting conditions; the safety data includes the status of the fire detection system, and the location and status of safety protection devices; the maintenance and operation data includes equipment operating time, maintenance and repair history, and activity records of operators; the sensor and monitoring equipment data includes sensor location and type, and data output of monitoring equipment.

[0012] As a preferred solution of the power plant intelligent management and monitoring method described in the present invention, the preprocessing includes cleaning, denoising, standardization and data fusion of the collected data;

[0013] The data cleaning includes removing invalid, erroneous and incomplete data;

[0014] The data standardization includes minimum-maximum standardization, that is, converting the data by applying the following formula according to the minimum and maximum values ​​of the data:

[0015]

[0016] Among them, X is the original collected data, X min To collect the minimum value of data, X max To collect the maximum value of data, X std is the standardized data;

[0017] The data fusion includes selecting a machine learning algorithm to fuse feature values ​​from different sources, and generating final data through voting and weighted averaging;

[0018] The preprocessed optimized data is used to construct an integrated three-dimensional model, and the data of the integrated three-dimensional model is extracted to establish a knowledge base.

[0019] As a preferred solution of the power plant intelligent management and monitoring method described in the present invention, wherein: the establishment of the knowledge base includes performing demand analysis on the power plant intelligent management system, establishing long-term and short-term goals, classifying the extracted data according to the demand analysis, constructing a knowledge system structure, and selecting technology according to the knowledge system to operate and maintain the knowledge base;

[0020] Analyze the data extracted from the integrated three-dimensional model, form knowledge items, build a knowledge base system, and incorporate the knowledge base system into the power plant intelligent management system for integration.

[0021] As a preferred solution of the power plant intelligent management and monitoring method described in the present invention, the unit efficiency analysis includes calculating the unit efficiency using the data information extracted from the knowledge base in the production period audit model, and distinguishing the equipment status of different unit efficiency intervals. The formula is as follows:

[0022]

[0023] Among them, η is the comprehensive efficiency index of the unit, t 0 is the start time of the audit cycle, t f is the end time of the audit cycle, m is the number of units, P j (t) is the power output of the jth unit at time t, E j (t) is the energy input of the jth unit at time t, E total (t) is the total energy input at time t, λ j is the energy attenuation coefficient of the jth unit;

[0024] The value range of η is [0, +∞). When 0≤η<0.7, it is determined that the unit efficiency is lower than the normal operating level and the equipment fails. Parameter adjustment and equipment maintenance are required. After adjustment, the unit efficiency is calculated until the calculated η after adjustment reaches the normal operating level. When 0.7≤η≤1, the unit efficiency is normal and the equipment is operating normally. The current operation and equipment parameters are maintained, and the equipment status is monitored in real time. When η>1, it means that the unit efficiency exceeds the normal operating level and the monitoring equipment has a detection error, which requires re-detection and recalculation.

[0025] As a preferred solution of the power plant intelligent management and monitoring method described in the present invention, the energy consumption analysis includes extracting knowledge base data, performing energy consumption analysis in the production period audit model, and adjusting the equipment status according to different energy consumption intervals. The energy consumption calculation formula is as follows:

[0026]

[0027] Among them, E eff is the power plant energy efficiency index, which indicates the ability to convert input energy into useful output energy in the entire cycle, t s is the start time of the audit cycle, t l is the end time of the audit cycle, n is the number of different energy consumption systems in the power plant, E i (t) is the energy consumption of the ith system at time t, E z (t) is the total energy consumption at time t, E i，base is the baseline energy consumption of the ith system;

[0028] When E eff When ≥0, it is the normal operating range, indicating that the equipment is in normal operation and continues to maintain the current operation and maintenance process;

[0029] When -0.1≤E eff <0, it is a warning interval, indicating that the equipment is abnormal and needs to be checked and maintained. The system with energy consumption higher than the normal operating level needs to be adjusted, and the energy consumption needs to be recalculated after adjustment until E eff Reach normal operating range;

[0030] When E eff When <-0.1, it is the fault interval, indicating that the equipment has failed. The equipment should be stopped immediately, the fault should be checked, the maintenance plan should be updated, and E should be recalculated after the update. eff , until it reaches the normal range.

[0031] As a preferred solution of the power plant intelligent management and monitoring method described in the present invention, the deep learning model construction includes extracting the pre-processed unit efficiency and energy consumption historical data through the knowledge base, dividing the data into time series segments, and inputting them into the LSTM model;

[0032] Building an LSTM deep learning model includes determining the number of LSTM layers, the number of hidden units and the input and output layers, training the model using the extracted data, and adjusting hyperparameters to optimize model performance; optimizing model performance includes obtaining parameter settings through cross-validation, using regularization technology to prevent overfitting, adjusting model performance based on model prediction results, and using the optimized deep learning model to monitor the performance of the equipment in real time, and issuing fault warnings for the equipment based on new data.

[0033] As a preferred solution of the power plant intelligent management and monitoring method described in the present invention, the equipment parameter adjustment includes deploying distributed intelligent monitoring nodes in the power plant to monitor the equipment behavior in real time. When the deep learning model performs unit efficiency and energy consumption analysis, when 0≤η<0.7 or E eff <-0.1, the equipment fails, the system issues an immediate shutdown order for the equipment whose unit efficiency and energy consumption are lower than the normal operating level, and performs maintenance and equipment parameter adjustment. After adjustment, monitoring and unit efficiency and energy consumption calculations continue until the normal operating level is reached; when 0.7≤η≤1 and E eff ≥0, the equipment operates normally, continues to maintain the current operation and equipment parameters, and continues to monitor the equipment in real time; when η>1 or -0.1≤E eff <0, the monitoring point continues to perform real-time monitoring, re-extracts data, and continues to calculate the unit efficiency and energy consumption through the deep learning model, and adjusts the equipment parameters based on the calculation results.

[0034] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of a power plant intelligent management and monitoring method are implemented.

[0035] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of a method for intelligent management and monitoring of a power plant are implemented.

[0036] Beneficial effects of the present invention: The method of the present invention not only ensures the real-time data collection and the high efficiency of preprocessing, but also provides intuitive visual assistance for power plant management through the construction of an integrated three-dimensional model, so that managers can have a deeper understanding of the interaction between equipment; the integration of the knowledge base injects decision-making support capabilities into the smart management system, so that the system can make intelligent decisions based on historical data and real-time information. In particular, on the basis of unit efficiency analysis and energy consumption analysis, the use of deep learning models has greatly enhanced the predictability and accuracy of fault detection, reducing maintenance costs and downtime risks; the deployment of distributed intelligent monitoring nodes is like installing countless sensitive nerve endings for power plants, which can perceive changes in equipment status in real time, make timely strategy adjustments and fault warnings, thereby ensuring the continuous and stable operation of the power plant, achieving optimal resource allocation and risk minimization, and providing strong technical support for the sustainable development of the power plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0038] Figure 1 A flowchart of a method for intelligent management and monitoring of a power plant is provided for one embodiment of the present invention.

[0039] Figure 2 A data integration diagram of a power plant intelligent management and monitoring method provided by an embodiment of the present invention.

[0040] Figure 3 A schematic diagram of the structure and function of a knowledge base data processing for a power plant intelligent management and monitoring method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0042] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0043] 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 term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0044] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0045] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0046] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0047] Example 1

[0048] Reference Figure 1-Figure 3 , which is the first embodiment of the present invention, provides a method for intelligent management and monitoring of a power plant, including:

[0049] S1: Collect data information of the equipment in the power plant in real time, pre-process the collected data, and use the pre-processed data information to build an integrated three-dimensional model;

[0050] Furthermore, the real-time data information collection includes collecting geometric data, physical parameters, electrical data, environmental data, safety data, maintenance and operation data, sensor and monitoring equipment data of power plant equipment;

[0051] It should be noted that the geometric data includes equipment size, equipment layout and relative position, and geometric parameters of buildings and infrastructure; the physical parameters include temperature data of each part, pressure data in pipes and containers, and vibration frequency and amplitude of equipment; the electrical data includes operating data of the electrical system, distribution of power supply and load, and layout and status of cables and connectors; the environmental data includes air quality, humidity level, and lighting conditions; the safety data includes the status of the fire detection system, and the location and status of safety protection devices; the maintenance and operation data includes equipment operating time, maintenance and overhaul history, and activity records of operators; the sensor and monitoring equipment data includes sensor location and type, and data output of monitoring equipment.

[0052] Furthermore, the preprocessing includes cleaning, denoising, standardizing and data fusion of the collected data;

[0053] It should be further explained that the data cleaning includes removing invalid, erroneous and incomplete data;

[0054] The data standardization includes minimum-maximum standardization, that is, converting the data by applying the following formula according to the minimum and maximum values ​​of the data:

[0055]

[0056] Among them, X is the original collected data, X min To collect the minimum value of data, X max To collect the maximum value of data, X std is the standardized data;

[0057] The data fusion includes selecting a machine learning algorithm to fuse feature values ​​from different sources, and generating final data through voting and weighted averaging;

[0058] The preprocessed optimized data is used to construct an integrated three-dimensional model, and the data in the integrated three-dimensional model is extracted to establish a knowledge base.

[0059] S2: Extract the data information of the integrated 3D model to establish a knowledge base, and include the knowledge base in the smart management system of the power plant throughout its life cycle;

[0060] The knowledge base includes storing equipment parameters, historical fault maintenance records and operating procedures, analyzing historical data to predict the type and time of equipment failures, optimizing maintenance plans and strategies, and providing detailed operating procedures and steps.

[0061] Going further, the "integrated 3D model" refers to a 3D graphical representation that integrates all the equipment in the power plant and their relationships. It contains detailed information such as the equipment's geometry, physical properties, and operating status. The "knowledge base" is a database that contains knowledge such as standard operations, historical failures, and maintenance records of power plant equipment, which provides decision support for the smart management system.

[0062] It should be noted that the creativity of extracting the data information of the integrated three-dimensional model to establish a knowledge base lies in the integration of the static and dynamic data of the equipment to build a comprehensive knowledge system. Through the establishment of the knowledge base, the smart management system of the power plant throughout the life cycle can achieve an in-depth understanding of the performance of the equipment and predictive maintenance. The purpose is that the integration of the knowledge base enables the smart management system of the power plant to not only perform daily monitoring, but also provide a scientific basis for equipment maintenance, fault diagnosis and energy efficiency optimization based on historical and real-time data analysis, thereby improving the overall operational efficiency and safety of the power plant.

[0063] S3: Establish a production period energy audit model in the power plant smart management system to perform unit efficiency analysis and energy consumption analysis, use unit efficiency and energy consumption analysis to build a deep learning model, and use the deep learning model to perform fault detection and fault warning;

[0064] The unit efficiency analysis includes calculating the unit efficiency using the data information extracted from the knowledge base in the production audit model, and distinguishing the equipment status of different unit efficiency intervals. The formula is as follows:

[0065]

[0066] Among them, η is the comprehensive efficiency index of the unit, t 0 is the start time of the audit cycle, t f is the end time of the audit cycle, m is the number of units, P j (t) is the power output of the jth unit at time t, E j (t) is the energy input of the jth unit at time t, E total (t) is the total energy input at time t, λ j is the energy attenuation coefficient of the jth unit;

[0067] in, is the efficiency of the jth unit at time t;

[0068] in, It is an exponential decay function. As time goes by, the contribution of each unit's efficiency to the overall efficiency gradually decreases;

[0069] in, During the entire audit cycle 0 to f The sum of the weighted average values ​​of the instantaneous efficiency of each unit within the

[0070] in, is the ratio of the energy input of the jth unit to the total energy input at time t. The square of the ratio emphasizes the impact of the energy input ratio of each unit on the total energy input distribution.

[0071] in, It is a comprehensive indicator to measure the distribution and stability of energy input ratio of each unit during the entire audit period;

[0072] The value range of η is [0, +∞). When 0≤η<0.7, the unit efficiency is low, the equipment fails and parameter adjustment and equipment maintenance are required. After adjustment, the unit efficiency is calculated again until η reaches the normal operating level; when 0.7≤η≤1, the unit efficiency is normal and the equipment operates normally. Continue to maintain the current operation and equipment parameters, and monitor the equipment status in real time; when η>1, it means that the unit efficiency exceeds the normal state, and the monitoring equipment has a detection error, so re-detection and calculation are required.

[0073] The energy consumption analysis includes extracting knowledge base data, performing energy consumption analysis in the production audit model, and adjusting the equipment status according to different energy consumption intervals. The energy consumption calculation formula is as follows:

[0074]

[0075] Among them, E eff is the power plant energy efficiency index, which indicates the ability to convert input energy into useful output energy in the entire cycle, t s is the start time of the audit cycle, t l is the end time of the audit cycle, n is the number of different energy consumption systems in the power plant, E i (t) is the energy consumption of the ith system at time t, E z (t) is the total energy consumption at time t, E i，base is the baseline energy consumption of the ith system;

[0076] in, is the proportion of the energy consumption of the ith system at time t to the total energy consumption;

[0077] in, Used to handle the exponential growth of energy consumption ratio and reduce the impact of the baseline energy consumption system on the overall results;

[0078] in, Indicates the change of the energy consumption ratio of the system over time;

[0079] in, The inverse tangent function is used to process the difference between energy consumption and the benchmark energy consumption, reducing the impact of the benchmark energy consumption system on the overall results;

[0080] in, Indicates the change of the energy consumption ratio of the system over time;

[0081] When E eff When ≥0, it is the normal operating range, indicating that the equipment is in normal operation and continues to maintain the current operation and maintenance process;

[0082] When -0.1≤E eff<0, it is a warning interval, indicating that there is a problem with the equipment. Check and maintain the system with high energy consumption, adjust the equipment parameters, and recalculate the energy consumption after adjustment until E eff Reach normal operating range;

[0083] When E eff When <-0.1, it is the fault interval, indicating that the equipment has failed. The equipment should be stopped immediately, the fault should be checked, the maintenance plan should be updated, and E should be recalculated after the update. eff , until it reaches the normal range.

[0084] The construction of the deep learning model includes extracting pre-processed unit efficiency and energy consumption historical data through a knowledge base, dividing the data into small time series segments, and inputting them into an LSTM model;

[0085] Building the LSTM deep learning model includes determining the number of LSTM layers, the number of hidden units, and the size of the input and output layers, training the model using the extracted data, and adjusting hyperparameters to optimize model performance;

[0086] The optimization model performance includes finding parameter settings through cross-validation, using regularization technology to prevent overfitting, and adjusting model performance based on model prediction results; using an optimized deep learning model to monitor the performance of the equipment in real time, and providing fault warnings for the equipment based on new data.

[0087] S4: Deploy distributed intelligent monitoring nodes in the power plant to monitor equipment behavior in real time and adjust equipment parameters in different data intervals;

[0088] The equipment parameter adjustment includes deploying distributed intelligent monitoring nodes in the power plant to monitor equipment behavior in real time. When the deep learning model performs unit efficiency and energy consumption analysis, when 0≤η<0.7 or E eff <-0.1, the equipment fails, the system immediately stops the operation of the equipment with low unit efficiency and energy consumption, and performs maintenance and equipment parameter adjustment. After adjustment, continue monitoring and unit efficiency and energy consumption calculation until the normal operating level is reached; when 0.7≤η≤1 and E eff ≥0, the equipment operates normally, continues to maintain the current operation and parameters, and continues to monitor the equipment in real time; when η>1 or -0.1≤E eff <0, the monitoring point continues to perform real-time monitoring, re-extracts data, and continues to calculate the unit efficiency and energy consumption through the deep learning model, and adjusts the equipment parameters based on the calculation results.

[0089] By deploying distributed intelligent monitoring nodes, comprehensive and real-time monitoring of equipment behavior is achieved. This method breaks through the limitations of traditional centralized monitoring and improves the flexibility and robustness of the system. Especially in terms of data interval division and equipment parameter adjustment, it combines advanced machine learning algorithms and deep data analysis technology to dynamically adjust parameters according to the actual operation of the equipment, thereby optimizing equipment performance and improving the overall operation efficiency of the power plant. The academic nature of the invention is reflected in its in-depth research and application of complex industrial system monitoring and control theory; its professionalism is reflected in its precise grasp of power plant equipment characteristics and the formulation of parameter adjustment strategies; its creativity is reflected in its combination of distributed monitoring, intelligent data analysis and dynamic adjustment of equipment parameters to form a set of efficient and adaptive power plant equipment monitoring system.

[0090] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0091] Example 2

[0092] The second embodiment of the present invention is different from the previous embodiment in that:

[0093] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0094] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0095] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0096] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0097] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0098] 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 claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0099] 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 the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for intelligent management and monitoring of a power plant, characterized in that: include, Collect data information from equipment in the power plant in real time, pre-process the collected data, and use the pre-processed data information to build an integrated three-dimensional model; Extract data information from the integrated 3D model to establish a knowledge base, and include the knowledge base in the full life cycle power plant smart management system; Establish a production period energy audit model in the power plant smart management system to perform unit efficiency analysis and energy consumption analysis, use unit efficiency and energy consumption analysis to build a deep learning model, and use the deep learning model to perform fault detection and fault warning; Deploy distributed intelligent monitoring nodes in the power plant to monitor equipment behavior in real time and adjust equipment parameters in different data ranges.

2. A power plant intelligent management and monitoring method according to claim 1, characterized in that: The real-time data information collection includes collecting geometric data, physical parameters, electrical data, environmental data, safety data, maintenance and operation data, sensor and monitoring equipment data of power plant equipment; The geometric data includes equipment size, equipment layout and relative position, and geometric parameters of buildings and infrastructure; the physical parameters include temperature data of each part, pressure data in pipes and containers, and vibration frequency and amplitude of equipment; the electrical data includes operating data of the electrical system, distribution of power supply and load, and layout and status of cables and connectors; the environmental data includes air quality, humidity level, and lighting conditions; the safety data includes the status of the fire detection system, and the location and status of safety protection devices; the maintenance and operation data includes equipment operating time, maintenance and repair history, and activity records of operators; the sensor and monitoring equipment data includes sensor location and type, and data output of monitoring equipment.

3. A power plant intelligent management and monitoring method as claimed in claim 2, characterized in that: The preprocessing includes cleaning, denoising, standardizing and data fusion of the collected data; The data cleaning includes removing invalid, erroneous and incomplete data; The data standardization includes minimum-maximum standardization, that is, converting the data by applying the following formula according to the minimum and maximum values ​​of the data: Among them, X is the original collected data, X min To collect the minimum value of data, X max To collect the maximum value of data, X std is the standardized data; The data fusion includes selecting a machine learning algorithm to fuse feature values ​​from different sources, and generating optimized data through voting and weighted averaging; The preprocessed optimized data is used to construct an integrated three-dimensional model, and the data in the integrated three-dimensional model is extracted to establish a knowledge base.

4. A power plant intelligent management and monitoring method as claimed in claim 3, characterized in that: The establishment of the knowledge base includes conducting a demand analysis on the power plant smart management system, establishing long-term and short-term goals, classifying the extracted data according to the demand analysis, constructing a knowledge system structure, and selecting technology according to the knowledge system to operate and maintain the knowledge base; Analyze the data extracted from the integrated three-dimensional model, form knowledge items, build a knowledge base system, and incorporate the knowledge base system into the power plant intelligent management system for integration.

5. A power plant intelligent management and monitoring method as claimed in claim 4, characterized in that: The unit efficiency analysis includes calculating the unit efficiency using the data information extracted from the knowledge base in the production audit model, and distinguishing the equipment status of different unit efficiency intervals. The formula is as follows: Among them, η is the comprehensive efficiency index of the unit, t0 is the start time of the audit cycle, t f is the end time of the audit cycle, m is the number of units, P j (t) is the power output of the jth unit at time t, E j (t) is the energy input of the jth unit at time t, E total (t) is the total energy input at time t, λ j is the energy attenuation coefficient of the jth unit; The value range of η is [0, +∞). When 0≤η<0.7, it is determined that the unit efficiency is lower than the normal operating level and the equipment fails. Parameter adjustment and equipment maintenance are required. After adjustment, the unit efficiency is calculated until the calculated η after adjustment reaches the normal operating level. When 0.7≤η≤1, the unit efficiency is normal and the equipment is operating normally. The current operation and equipment parameters are maintained, and the equipment status is monitored in real time. When η>1, it means that the unit efficiency exceeds the normal operating level and the monitoring equipment has a detection error, which requires re-detection and recalculation.

6. A power plant intelligent management and monitoring method as claimed in claim 5, characterized in that: The energy consumption analysis includes extracting knowledge base data, performing energy consumption analysis in the production audit model, and adjusting the equipment status according to different energy consumption intervals. The energy consumption calculation formula is as follows: Among them, E eff is the power plant energy efficiency index, which indicates the ability to convert input energy into useful output energy in the entire cycle, t s is the start time of the audit cycle, t l is the end time of the audit cycle, n is the number of different energy consumption systems in the power plant, E i (t) is the energy consumption of the ith system at time t, E z (t) is the total energy consumption at time t, E i，base is the baseline energy consumption of the ith system; When E eff When ≥0, it is the normal operating range, indicating that the equipment is in normal operation and continues to maintain the current operation and maintenance process; When -0.1≤E eff <0, it is a warning interval, indicating that the equipment is abnormal and needs to be checked and maintained. The system with energy consumption higher than the normal operating level needs to be adjusted, and the energy consumption needs to be recalculated after adjustment until E eff Reach normal operating range; When E eff When <-0.1, it is the fault interval, indicating that the equipment has failed. The equipment should be stopped immediately, the fault should be checked, the maintenance plan should be updated, and E should be recalculated after the update. eff , until it reaches the normal range.

7. A power plant intelligent management and monitoring method as claimed in claim 6, characterized in that: The construction of the deep learning model includes extracting pre-processed unit efficiency and energy consumption historical data through a knowledge base, dividing the data into time series segments, and inputting them into an LSTM model; Building an LSTM deep learning model includes determining the number of LSTM layers, the number of hidden units and the input and output layers, training the model using the extracted data, and adjusting hyperparameters to optimize model performance; optimizing model performance includes obtaining parameter settings through cross-validation, using regularization technology to prevent overfitting, adjusting model performance based on model prediction results, and using the optimized deep learning model to monitor the performance of the equipment in real time, and issuing fault warnings for the equipment based on new data.

8. A power plant intelligent management and monitoring method as claimed in claim 7, characterized in that: The equipment parameter adjustment includes deploying distributed intelligent monitoring nodes in the power plant to monitor equipment behavior in real time. When the deep learning model performs unit efficiency and energy consumption analysis, when 0≤η<0.7 or E eff <-0.1, the equipment fails, the system issues an immediate shutdown order for the equipment whose unit efficiency and energy consumption are lower than the normal operating level, and performs maintenance and equipment parameter adjustment. After adjustment, monitoring and unit efficiency and energy consumption calculations continue until the normal operating level is reached; when 0.7≤η≤1 and E eff ≥0, the equipment operates normally, continues to maintain the current operation and equipment parameters, and continues to monitor the equipment in real time; when η>1 or -0.1≤E eff <0, the monitoring point continues to perform real-time monitoring, re-extracts data, and continues to calculate the unit efficiency and energy consumption through the deep learning model, and adjusts the equipment parameters based on the calculation results.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images