Multi-agent operation and maintenance method for compressed air energy storage system

Abstract

The invention relates to the technical field of novel energy, in particular to a multi-agent operation and maintenance method for a compressed air energy storage system, which mainly comprises the following steps: detecting key operation parameters of a target compressed air energy storage system to obtain real-time operation data of the target compressed air energy storage system, and generating historical operation data of the target compressed air energy storage system; performing data analysis on the real-time operation data to identify an abnormal condition of the target compressed air energy storage system, and performing fault positioning on the abnormal condition to obtain fault position information; key operation parameters are adjusted according to the abnormal condition and the fault position information; and analyzing the historical operation data and the real-time operation data of the target compressed air energy storage system to predict a maintenance plan of the target compressed air energy storage system. Therefore, the problems that operation and maintenance management of an existing CAES system mostly depends on traditional manual inspection and regular maintenance, the operation and maintenance efficiency is low, the response speed is low, fault processing is not timely and the like are solved.

Description

Technical Field

[0001] The present invention relates to the field of new energy technologies, and in particular to a multi-agent operation and maintenance method for a compressed air energy storage system. Background Art

[0002] With the transformation of the global energy mix and the large-scale integration of renewable energy, power system supply and demand balance and grid stability face new challenges. Compressed Air Energy Storage (CAES), as a large-scale, efficient, and low-cost energy storage technology, can effectively address the intermittent and unstable nature of renewable energy sources such as wind and solar power, improving the grid's peak-shaving capacity and emergency response speed. CAES systems store energy in compressed air during periods of low electricity demand and release it during peak hours, achieving peak-shaving and valley-filling in the power system.

[0003] However, existing CAES system operations and management rely heavily on traditional manual inspections and scheduled maintenance, resulting in low efficiency, slow response times, and untimely troubleshooting. This makes it difficult to meet the modern power grid's demand for fast, accurate, and intelligent O&M of energy storage systems. Furthermore, efficient CAES system operation requires precise control of every step—compression, storage, and expansion—to optimize overall system performance and economic efficiency.

[0004] Therefore, there is an urgent need for an integrated and intelligent CAES operation and maintenance system, which is of great significance for improving the reliability, safety and economy of system operation. Summary of the Invention

[0005] The present invention provides a multi-agent operation and maintenance device and method for a compressed air energy storage system to solve the problems of low operation and maintenance efficiency, slow response speed, and untimely fault handling in the existing CAES system operation and maintenance management, which mostly relies on traditional manual inspections and regular maintenance.

[0006] A first embodiment of the present invention provides a multi-agent operation and maintenance device for a compressed air energy storage system, comprising:

[0007] A monitoring agent, configured to detect key operating parameters of a target compressed air energy storage system to obtain real-time operating data of the target compressed air energy storage system and generate historical operating data of the target compressed air energy storage system;

[0008] a fault diagnosis agent, configured to perform data analysis on the real-time operating data to identify abnormal conditions of the target compressed air energy storage system, and to locate the faults of the abnormal conditions to obtain fault location information;

[0009] an optimization control agent, configured to adjust the key operating parameters according to the abnormal condition and the fault location information;

[0010] A predictive maintenance agent is used to analyze historical operating data and real-time operating data of the target compressed air energy storage system to predict a maintenance plan for the target compressed air energy storage system.

[0011] Optionally, the key operating parameters include the operating point of the compressor, the operating point of the expander, the pressure point of the air storage tank and the generator bearing position of the target compressed air energy storage system.

[0012] Optionally, the monitoring agent includes:

[0013] a data acquisition module, configured to acquire sensor signals from a plurality of measurement point sensors on the target compressed air energy storage system and convert the sensor signals into digital signals to obtain the real-time operation data and the historical operation data;

[0014] The anomaly detection module is used to detect whether the real-time operating data exceeds a preset value range, and automatically trigger an alarm mechanism if it exceeds the range.

[0015] Optionally, the fault diagnosis agent includes:

[0016] Constructing a knowledge base module for obtaining multiple fault types and characteristics of the target compressed air energy storage system to construct a dynamically updated fault knowledge base;

[0017] A model building module is used to build a fault diagnosis model based on the fault knowledge base containing a dynamic update;

[0018] A fault diagnosis module is used to perform data analysis on the real-time operating data using the fault diagnosis model to identify abnormal conditions of the target compressed air energy storage system, locate the fault of the abnormal condition, and obtain fault location information.

[0019] Optionally, the optimization control agent includes:

[0020] an acquisition module, configured to acquire a current grid demand and a current energy price of the target compressed air energy storage system;

[0021] An adjustment module is used to adjust the key operating parameters according to the abnormal condition, the fault location information, the real-time operating data and the maintenance plan.

[0022] Optionally, the predictive maintenance agent includes:

[0023] a wear assessment module, configured to perform a wear assessment on the target compressed air energy storage system based on the historical operating data and the real-time operating data based on a preset machine learning algorithm to obtain a current health status;

[0024] A prediction module is used to predict the potential failure time according to the current health status and generate the maintenance plan according to the potential failure time.

[0025] Optionally, it also includes:

[0026] A communication module is used for collaboratively transmitting data between the monitoring agent, the fault diagnosis agent, the optimization control agent and the predictive maintenance agent.

[0027] Optionally, dynamic weights are assigned among the monitoring agent, the fault diagnosis agent, the optimization control agent and the predictive maintenance agent according to different operating conditions and system states of the target compressed air energy storage system to optimize the collaboration among the monitoring agent, the fault diagnosis agent, the optimization control agent and the predictive maintenance agent.

[0028] A second embodiment of the present invention provides a multi-agent operation and maintenance method for a compressed air energy storage system, comprising:

[0029] Detecting key operating parameters of a target compressed air energy storage system to obtain real-time operating data of the target compressed air energy storage system and generating historical operating data of the target compressed air energy storage system;

[0030] performing data analysis on the real-time operating data to identify an abnormal condition of the target compressed air energy storage system, and locating a fault of the abnormal condition to obtain fault location information;

[0031] adjusting the key operating parameters according to the abnormal condition and the fault location information;

[0032] Analyze historical operating data and real-time operating data of the target compressed air energy storage system to predict a maintenance plan for the target compressed air energy storage system.

[0033] An embodiment of the third aspect of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the multi-agent operation and maintenance method for a compressed air energy storage system as described in the above embodiment.

[0034] The multi-agent operation and maintenance device and method for a compressed air energy storage system proposed in the embodiments of the present invention implements real-time monitoring, fault diagnosis, performance optimization, and predictive maintenance of the CAES system through intelligent operation and maintenance management. Through efficient communication modules, real-time information exchange is achieved to jointly complete system operation and maintenance tasks. This significantly improves the operating efficiency of the CAES system, reduces operation and maintenance costs, and enhances the stability and safety of the system. The device and method are suitable for the intelligent operation and maintenance requirements of large-scale energy storage systems.

[0035] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0037] Figure 1 A block diagram of a multi-agent operation and maintenance device for a compressed air energy storage system provided by an embodiment of the present invention;

[0038] Figure 2 A framework diagram of a multi-agent operation and maintenance device for a compressed air energy storage system provided by an embodiment of the present invention;

[0039] Figure 3 A flow chart of a multi-agent operation and maintenance method for a compressed air energy storage system provided by an embodiment of the present invention;

[0040] Figure 4 This is a schematic structural diagram of an electronic device provided by an embodiment of the present invention.

[0041] Description of reference numerals:

[0042] 10-Multi-agent operation and maintenance device of compressed air energy storage system, 101-monitoring agent, 102-fault diagnosis agent, 103-optimization control agent, 104-predictive maintenance agent and 105-communication module. DETAILED DESCRIPTION

[0043] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0044] The following describes a multi-agent operation and maintenance device and method for a compressed air energy storage system according to an embodiment of the present invention with reference to the accompanying drawings.

[0045] Figure 1A block diagram of a multi-agent operation and maintenance device for a compressed air energy storage system provided by an embodiment of the present invention.

[0046] like Figure 1 As shown, the multi-agent operation and maintenance device 10 of the compressed air energy storage system includes: a monitoring agent 101, a fault diagnosis agent 102, an optimization control agent 103 and a predictive maintenance agent 104.

[0047] The monitoring agent 101 is used to monitor key operating parameters of the target compressed air energy storage system, such as gas storage pressure, compressor outlet pressure, turbine expander inlet pressure, temperature, flow rate, compression and turbine expansion efficiency, etc., to obtain real-time operating data of the target compressed air energy storage system and generate historical operating data for the target compressed air energy storage system. The fault diagnosis agent 102 is used to analyze the real-time operating data from distributed measurement points to identify abnormal conditions in the target compressed air energy storage system, such as abnormal pressure, temperature, flow rate, equipment failure, gas quality, and energy storage efficiency. It also locates the fault location of the abnormal condition, such as the location of the compressor, expander, and heat exchanger, to obtain fault location information. The optimization control agent 103 is used to adjust key operating parameters such as pressure, temperature, flow rate, and vibration frequency based on the detected abnormal conditions and fault location information. The predictive maintenance agent 104 is used to analyze the historical and real-time operating data of the target compressed air energy storage system to predict the maintenance plan for the target compressed air energy storage system, taking into account factors such as changes in gas quality and changes in cavern structure stability that may occur during long-term compressed air storage.

[0048] In some embodiments, the monitoring agent 101 includes:

[0049] A data acquisition module is used to collect sensor signals from multiple measurement point sensors on the target compressed air energy storage system and convert the sensor signals into digital signals to obtain real-time operation data and historical operation data;

[0050] The anomaly detection module is used to detect whether the real-time operation data exceeds the preset value range, and automatically trigger the alarm mechanism if it exceeds the range.

[0051] In some embodiments, the key operating parameters include the operating point of the compressor, the operating point of the expander, the pressure point of the air storage tank, and the generator bearing position of the target compressed air energy storage system.

[0052] Specifically, in the context of intelligent operation and maintenance requirements for large-scale energy storage systems, this device deploys a large number of measurement points, distributed across key components of the target compressed air energy storage system, including the compressor unit, gas storage chamber, turbine generator unit, and heat exchanger. This allows real-time acquisition of key operating parameters such as pressure, temperature, flow rate, and vibration frequency, generating a vast amount of real-time operational data. The system also stores long-term, accumulated historical operational data. Monitoring Agent 101 is the data collection core and foundation for the multi-agent operation and maintenance system for the compressed air energy storage system. It connects to the distributed measurement points. Specific implementation involves installing high-precision sensors at multiple measurement points within the CAES system, enabling high-precision and high-frequency data acquisition to ensure data accuracy and integrity. The collected data is then transmitted via a stable communication module to other CAES system agents, such as the compressor intake, gas storage tank pressure point, expander outlet, and generator bearings. Monitoring Agent 101 is responsible for real-time monitoring of key operating parameters of the CAES system, such as pressure, temperature, and flow rate, providing intuitive data support for the system's health status.

[0053] It should be noted that distributed measurement points include pressure measurement points, temperature measurement points, liquid level measurement points and flow measurement points. Among them, the pressure measurement points are on the main body of the pressure storage equipment (such as pressure vessels, energy storage tanks, etc.), and pressure sensors are usually installed at key locations on the top, bottom and side walls to measure the internal pressure. Temperature measurement points are also distributed in different parts of the pressure storage equipment, such as positions close to heat sources (if there is an external heating device or there is a heat reaction inside), the center of the equipment, and the boundaries. Common liquid level measurement points include static pressure level gauges, radar level gauges, ultrasonic level gauges and other types, which are generally installed at appropriate locations on the top or side of the pressure storage container. Flow measurement points install flow meters at appropriate straight pipe sections on the feed and discharge pipes. Common flow meters such as electromagnetic flow meters and turbine flow meters have their corresponding optimal installation requirements. Generally, a certain length of straight pipe section must be ensured before and after to reduce the impact of flow field disturbances on flow measurement accuracy.

[0054] Furthermore, the data acquisition module converts the collected sensor signals into digital signals and transmits them to the central monitoring system via a wireless or wired network. In the central monitoring system, the data is further processed, stored, and displayed in real time on the user interface. Furthermore, the monitoring agent 101 includes an anomaly detection module. When the monitored data falls outside the normal range, the system automatically triggers an alarm mechanism and notifies maintenance personnel via text message, email, or app so that timely countermeasures can be taken. This monitoring agent 101 ensures the real-time and accuracy of system status information, providing the necessary data support for subsequent fault diagnosis and optimized control.

[0055] During normal operation, the data of each measuring point should fluctuate within a relatively stable small range. For example, the pressure fluctuation is within the set safety pressure range and the amplitude is very small, the temperature is maintained within a certain range above and below the constant temperature suitable for the stored material, and the liquid level changes smoothly in accordance with the feeding and discharging plan.

[0056] In some embodiments, the fault diagnosis agent 102 includes:

[0057] Build a knowledge base module to obtain various fault types and characteristics of the target compressed air energy storage system to build a dynamically updated fault knowledge base;

[0058] A model building module is used to build a fault diagnosis model based on a dynamically updated fault knowledge base;

[0059] The fault diagnosis module is used to analyze real-time operating data using a fault diagnosis model to identify abnormal conditions of the target compressed air energy storage system, locate the faults of the abnormal conditions, and obtain fault location information.

[0060] Specifically, in the context of intelligent operation and maintenance requirements for large-scale energy storage systems, the core function of the fault diagnosis agent 102 is to analyze the data collected by the real-time monitoring agent at distributed measurement points to quickly and accurately diagnose potential system faults. Therefore, the fault diagnosis agent 102 includes a dynamically updated fault knowledge base. This fault knowledge base can use Siemens MindSphere to collect various possible fault types and their characteristics. It uses data analysis and machine learning algorithms and a dynamically updated fault knowledge base to build a fault diagnosis model. The fault diagnosis model is then used to analyze the real-time operating data provided by the real-time monitoring agent to identify and learn various complex fault modes or abnormal conditions in the CAES system, locate the fault, and obtain fault location information. The fault diagnosis agent 102 has a self-learning function and can continuously optimize its diagnostic model based on historical fault cases, improving the speed and accuracy of fault detection and ensuring the safety performance of the compressed air energy storage system.

[0061] For example, a fault diagnosis model is built based on random forests and a dynamically updated fault knowledge base. By constructing multiple decision trees and combining their results, the accuracy and stability of identifying various complex fault modes or abnormal situations can be improved, and corresponding fault diagnosis suggestions can be provided.

[0062] Furthermore, once a fault is diagnosed, the fault diagnosis agent 102 generates a detailed fault report, including the fault type, impact range, recommended repair measures, and preventive strategies. Furthermore, the fault diagnosis agent 102 can automatically adjust the system's operating mode based on the severity of the fault to prevent the fault from spreading and ensure safe and stable system operation.

[0063] In some embodiments, the optimization control agent 103 includes:

[0064] an acquisition module, configured to acquire a current grid demand and a current energy price of a target compressed air energy storage system;

[0065] The adjustment module is used to adjust key operating parameters based on abnormal conditions, fault location information, real-time operating data and maintenance plans.

[0066] Specifically, in the context of intelligent operation and maintenance requirements for large-scale energy storage systems, the optimization control agent 103 uses an acquisition module to pre-acquire the system's grid demand, energy prices, and the maintenance plan of the predictive maintenance agent 104 to achieve global optimal control. Based on the real-time operating data provided by the monitoring agent 101, feedback from the fault diagnosis agent 102, and pre-acquired requirements, the adjustment module uses algorithms such as particle swarm optimization to dynamically adjust the key operating parameters of the CAES system. This allows for real-time adjustment of the operating points of the compressor and expander, optimization of the gas tank's energy storage strategy, and coordination of other energy conversion equipment in the system. Furthermore, the optimization control agent 103 possesses adaptive capabilities, automatically adjusting its optimization strategy based on changes in system operation and external environmental conditions, ensuring the system always operates optimally.

[0067] The goal of this intelligent agent is to improve the overall performance of the CAES system, reduce energy consumption, and ensure stable operation under various operating conditions. Through precise control, it can precisely adjust the system output and optimize energy storage efficiency.

[0068] In some embodiments, the predictive maintenance agent 104 includes:

[0069] A wear assessment module, which is used to assess the wear of the target compressed air energy storage system based on historical and real-time operating data based on a preset machine learning algorithm to obtain the current health status;

[0070] The prediction module is used to predict the potential failure time based on the current health status and generate a maintenance plan based on the potential failure time.

[0071] Specifically, in the scenario of intelligent operation and maintenance requirements of large-scale energy storage systems, the predictive maintenance agent 104 uses machine learning algorithms such as random forests, support vector machines or neural networks to evaluate the system's historical and real-time operating data. During this evaluation process, it can identify component wear patterns to predict potential failure times, the remaining life of system components, possible future failures, possible future maintenance needs, and generate maintenance plans. The maintenance plan includes component replacement, system inspections and preventive maintenance, etc., aiming to reduce unplanned downtime and improve system availability and reliability.

[0072] For example, when identifying wear patterns, random forests identify key indicators by analyzing feature importance. Node splitting in the decision tree can display features that play a key role in classification. These key features are combined with wear-related behavior patterns (high temperature, vibration, pressure fluctuations, etc.). Fault tree analysis helps identify different types of wear patterns, thereby supporting effective fault warning and maintenance decisions.

[0073] Furthermore, the predictive maintenance agent 104 can adjust maintenance plans and optimize the allocation of maintenance resources based on component maintenance history and performance degradation trends. Using predictive maintenance algorithms, the predictive maintenance agent 104 assesses the remaining lifespan and health status of system components, providing operators with informed maintenance plans. This helps reduce unplanned downtime, proactively prevent potential failures, and lower maintenance costs.

[0074] In some embodiments, the communication module 105 is used for collaboratively transmitting data among the monitoring agent 101 , the fault diagnosis agent 102 , the optimization control agent 103 and the predictive maintenance agent 104 .

[0075] Specifically, if Figure 2 As shown, in the scenario of intelligent operation and maintenance requirements for large-scale energy storage systems, the communication module 105 is the key link connecting various intelligent agents and the user interface. Its stability and security are crucial to the entire system. The communication module utilizes a combination of wired and wireless technologies to ensure real-time data transmission and high reliability. Wired networks primarily handle data transmission between the data center and key equipment, while wireless networks are used to cover areas with long distances or where cabling is inconvenient. The communication module incorporates multi-level security measures, including data encryption, access control, and intrusion detection systems, to prevent data leaks and network attacks. Furthermore, the network utilizes a redundant design, including backup communication links and backup servers, to ensure seamless system switching in the event of a failure in the primary network, ensuring communication continuity. The communication module also integrates a network management system for monitoring network status, diagnosing network issues, and optimizing and upgrading the network. The communication module 105 serves as a link between the various intelligent agents in the system, ensuring real-time data transmission and effective collaboration between them. The communication module 105 utilizes a high-reliability design that resists external interference and data loss, ensuring the stability and security of system communications. The design of the communication module takes into account the scalability of the system, allowing for the addition of more agents or integration with other systems in the future.

[0076] In some embodiments, dynamic weights are assigned among the monitoring agent, fault diagnosis agent, optimization control agent, and predictive maintenance agent based on different operating conditions and system states of the target compressed air energy storage system to optimize the collaboration among the monitoring agent, fault diagnosis agent, optimization control agent, and predictive maintenance agent.

[0077] During the actual implementation process, the embodiment of the present invention also proposes an intelligent agent collaboration mechanism and dynamic weight distribution. According to the intelligent agent collaboration mechanism and dynamic weight distribution, the collaboration between the monitoring intelligent agent, the fault diagnosis intelligent agent, the optimization control intelligent agent and the predictive maintenance intelligent agent can be optimized.

[0078] Specifically, based on the agent collaboration mechanism, when the monitoring agent detects a parameter anomaly, it not only transmits the data to the fault diagnosis agent but also sends a warning signal to other agents. The optimization control agent can prepare and adjust its strategy based on the anomaly, while the predictive maintenance agent can immediately initiate in-depth analysis of historical data related to the anomaly.

[0079] Furthermore, based on dynamic weight allocation, the embodiment of the present invention will assign dynamic weights to various operating parameters according to the different operating conditions and system states of the target compressed air energy storage system. During the charging phase of the energy storage system, the weights of the compressor-related parameters may be higher; while during the discharging phase, the expander-related parameters are more critical. When an abnormal condition occurs, the weight is adjusted according to the type of fault and the possible scope of impact. When a temperature anomaly occurs and it is judged that it may affect the overall safety of the system, the weight of the temperature parameter is greatly increased in the comprehensive judgment, so that the system can more accurately focus on key factors according to the current situation, thereby improving the accuracy and timeliness of the judgment.

[0080] In summary, the multi-agent operation and maintenance device for a compressed air energy storage system proposed in an embodiment of the present invention realizes real-time monitoring, fault diagnosis, performance optimization, and predictive maintenance of the CAES system through intelligent operation and maintenance management. It also realizes real-time information exchange through an efficient communication module to jointly complete system operation and maintenance tasks, significantly improving the operating efficiency of the CAES system, reducing operation and maintenance costs, and enhancing the stability and safety of the system. It is therefore suitable for the intelligent operation and maintenance needs of large-scale energy storage systems.

[0081] Next, a multi-agent operation and maintenance method for a compressed air energy storage system proposed in an embodiment of the present invention will be described with reference to the accompanying drawings.

[0082] Figure 3 A flow chart of a multi-agent operation and maintenance method for a compressed air energy storage system provided in an embodiment of the present invention.

[0083] like Figure 3 As shown, the multi-agent operation and maintenance method of the compressed air energy storage system includes the following steps:

[0084] In step S301 , key operating parameters of a target compressed air energy storage system are detected to obtain real-time operating data of the target compressed air energy storage system, and historical operating data of the target compressed air energy storage system is generated.

[0085] In step S302 , data analysis is performed on the real-time operating data to identify abnormal conditions of the target compressed air energy storage system, and fault location is performed on the abnormal conditions to obtain fault location information.

[0086] In step S303, key operating parameters are adjusted according to the abnormal condition and fault location information.

[0087] In step S304 , historical operating data and real-time operating data of the target compressed air energy storage system are analyzed to predict a maintenance plan for the target compressed air energy storage system.

[0088] It should be noted that the aforementioned explanation of the embodiment of the multi-agent operation and maintenance device for the compressed air energy storage system is also applicable to the multi-agent operation and maintenance method for the compressed air energy storage system of this embodiment, and will not be repeated here.

[0089] The multi-agent operation and maintenance method for a compressed air energy storage system proposed in an embodiment of the present invention implements real-time monitoring, fault diagnosis, performance optimization, and predictive maintenance of the CAES system through intelligent operation and maintenance management. By exchanging information in real time through efficient communication modules, the system's operation and maintenance tasks are jointly completed. This significantly improves the operating efficiency of the CAES system, reduces operation and maintenance costs, and enhances system stability and security. The method is suitable for the intelligent operation and maintenance requirements of large-scale energy storage systems.

[0090] Figure 4 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device may include:

[0091] Memory 401 , processor 402 , and computer programs stored in the memory 401 and executable on the processor 402 .

[0092] When the processor 402 executes the program, the multi-agent operation and maintenance method of the compressed air energy storage system provided in the above embodiment is implemented.

[0093] Furthermore, the electronic device further includes:

[0094] The communication interface 404 is used for communication between the memory 401 and the processor 402 .

[0095] The memory 401 is used to store computer programs that can be run on the processor 402 .

[0096] The memory 401 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0097] If the memory 401, the processor 402, and the communication interface 404 are implemented independently, the communication interface 404, the memory 401, and the processor 402 can be connected to each other via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0098] Optionally, in a specific implementation, if the memory 401 , the processor 402 and the communication interface 404 are integrated on a chip, the memory 401 , the processor 402 and the communication interface 404 can communicate with each other through an internal interface.

[0099] The processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0100] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples without contradiction.

[0101] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "N" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0102] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or N executable instructions for implementing a custom logical function or step of a process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0103] The logic and / or steps represented in the flowchart or otherwise described herein may be considered, for example, as an ordered list of executable instructions for implementing logical functions, and may be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device).

Claims

1. A multi-agent operation and maintenance device for a compressed air energy storage system, characterized in that: include: A monitoring agent, used to detect key operating parameters of a target compressed air energy storage system to obtain real-time operating data of the target compressed air energy storage system and generate historical operating data of the target compressed air energy storage system; A fault diagnosis agent is used to perform data analysis on the real-time operation data to identify abnormal conditions of the target compressed air energy storage system, and to locate the faults of the abnormal conditions to obtain fault location information; An optimization control agent, used for adjusting the key operating parameters according to the abnormal condition and the fault location information; A predictive maintenance agent is used to analyze historical operating data and real-time operating data of the target compressed air energy storage system to predict a maintenance plan for the target compressed air energy storage system.

2. The multi-agent operation and maintenance device of the compressed air energy storage system according to claim 1, characterized in that: The key operating parameters include the operating point of the compressor, the operating point of the expander, the pressure point of the air storage tank and the generator bearing position of the target compressed air energy storage system.

3. The multi-agent operation and maintenance device of the compressed air energy storage system according to claim 1, characterized in that: The monitoring agent comprises: A data acquisition module, used to collect sensor signals of multiple measurement point sensors on the target compressed air energy storage system, and convert the sensor signals into digital signals to obtain the real-time operation data and the historical operation data; The abnormality detection module is used to detect whether the real-time operation data exceeds a preset value range, and automatically trigger an alarm mechanism if it exceeds the preset value range.

4. The multi-agent operation and maintenance device for a compressed air energy storage system according to claim 1, characterized in that: The fault diagnosis agent comprises: Constructing a knowledge base module, for obtaining multiple fault types and characteristics of the target compressed air energy storage system, so as to construct a dynamically updated fault knowledge base; A model building module is used to build a fault diagnosis model based on the fault knowledge base containing a dynamic update; A fault diagnosis module is used to perform data analysis on the real-time operation data using the fault diagnosis model to identify abnormal conditions of the target compressed air energy storage system, locate the fault of the abnormal condition, and obtain fault location information.

5. The multi-agent operation and maintenance device for a compressed air energy storage system according to claim 1, characterized in that: The optimization control agent comprises: An acquisition module, used to acquire the current grid demand and current energy price of the target compressed air energy storage system; An adjustment module is used to adjust the key operating parameters according to the abnormal condition, the fault location information, the real-time operating data and the maintenance plan.

6. The multi-agent operation and maintenance device of the compressed air energy storage system according to claim 1, characterized in that: The predictive maintenance agent comprises: a wear assessment module, configured to perform a wear assessment on the target compressed air energy storage system based on the historical operation data and the real-time operation data based on a preset machine learning algorithm to obtain a current health status; A prediction module is used to predict the potential failure time according to the current health status and generate the maintenance plan according to the potential failure time.

7. The multi-agent operation and maintenance device for a compressed air energy storage system according to claim 1, characterized in that: Also includes: A communication module is used for collaboratively transmitting data between the monitoring agent, the fault diagnosis agent, the optimization control agent and the predictive maintenance agent.

8. The multi-agent operation and maintenance device for a compressed air energy storage system according to claim 1, characterized in that: Dynamic weights are assigned among the monitoring agent, the fault diagnosis agent, the optimization control agent and the predictive maintenance agent according to different operating conditions and system states of the target compressed air energy storage system to optimize the collaboration among the monitoring agent, the fault diagnosis agent, the optimization control agent and the predictive maintenance agent.

9. A multi-agent operation and maintenance method for a compressed air energy storage system, characterized in that: The multi-agent operation and maintenance device of the compressed air energy storage system according to any one of claims 1 to 8 comprises the following steps: Detecting key operating parameters of a target compressed air energy storage system to obtain real-time operating data of the target compressed air energy storage system and generating historical operating data of the target compressed air energy storage system; Performing data analysis on the real-time operation data to identify abnormal conditions of the target compressed air energy storage system, and locating faults of the abnormal conditions to obtain fault location information; adjusting the key operating parameters according to the abnormal condition and the fault location information; Analyze historical operating data and real-time operating data of the target compressed air energy storage system to predict a maintenance plan of the target compressed air energy storage system.

10. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the multi-agent operation and maintenance method for a compressed air energy storage system as claimed in claim 9.

Images