Monitoring and diagnosis optimization method for air storage and heat storage links of compressed air energy storage power station

Abstract

The invention relates to the technical field of novel energy, in particular to a compressed air energy storage power station air storage and heat storage link monitoring and diagnosis optimization method, which comprises an equipment layer comprising main equipment of a compressed air energy storage power station; the sensing layer comprises sensors arranged on a plurality of devices of the compressed air energy storage power station, forms a distributed sensing network and monitors multi-modal data of air storage and heat storage links; the transmission layer is used for transmitting multi-modal data; the analysis layer is used for performing pattern recognition, correlation analysis and anomaly detection according to the received multi-modal data; and the decision-making layer is used for generating a decision-making result according to the mode recognition result and the anomaly detection result and feeding back the decision-making result to the equipment layer, and the equipment layer executes corresponding actions and optimizes the operation state of the gas storage and heat storage links. Therefore, the problems of energy efficiency loss, failure risk increase, even system shutdown and the like caused by mismatching of operation of two links of air storage and heat storage of the compressed air energy storage power station are solved.

Description

Technical Field

[0001] This application relates to the field of new energy technologies, and particularly to a method for monitoring, diagnosing, and optimizing the air storage and heat storage links of a compressed air energy storage power station. Background Art

[0002] With the advancement of the global energy transition, renewable energy, as a representative of clean energy, has received extensive attention and application. However, due to the intermittent and unstable characteristics of renewable energy, the power system faces new challenges in terms of supply-demand balance and grid stability. To address these issues, CAES (Compressed Air Energy Storage) has been widely applied as an important energy storage technology.

[0003] The CAES power station stores electrical energy as compressed air during the low-demand period of electricity and then releases the compressed air to restore it to electrical energy during the peak period, achieving peak shaving and valley filling of the power system. However, in actual operation, especially in the coordination of the air storage and heat storage links, the CAES power station faces some challenges. Specifically, the compressed air energy storage process involves two key links: air storage and heat storage. During the energy storage process, the temperature of the compressed air rises, and part of the energy is converted into heat energy. When released, the expansion of the gas will cause the temperature to drop. This requires a high degree of matching between the air storage and heat storage links to ensure the efficiency and stability of the system. If the operation of these two links is not matched, it may lead to problems such as energy efficiency loss, increased failure risk, and even system shutdown.

[0004] Currently, the operation and maintenance management of CAES power stations mainly rely on traditional manual inspections and regular maintenance methods. This method has some limitations. For example, manual inspections require a large amount of time and human resources, and the ability to monitor the real-time state of the system is limited. In addition, due to human factors, it is difficult to detect and handle system anomalies in a timely manner. These problems have led to low operation and maintenance efficiency and slow response speed, and at the same time, they have also increased the risks of system safety and reliability.

[0005] To solve these problems, researchers have gradually turned their attention to the remote monitoring and fault diagnosis technologies of compressed air energy storage power stations. In recent years, with the development of sensor technology, data acquisition technology, and intelligent analysis algorithms, some studies have attempted to achieve real-time monitoring and data acquisition of key parameters of compressed air energy storage power stations. These monitoring data mainly cover pneumatic parameters such as pressure, temperature, and flow rate, and through algorithms such as rule-based and machine learning, the diagnosis and prediction of system anomalies are carried out. These studies have laid a foundation for the development of the pneumatic monitoring and anomaly diagnosis system of compressed air energy storage power stations.

[0006] However, existing research still faces some challenges and problems. First, there are many pneumatic parameters in the gas storage and heat storage links of a CAES power station, and they are interrelated. For example, the pressure change in the gas storage system, the heat exchange efficiency in the heat storage link, etc. The correlation between these parameters is strong. How to effectively perform data fusion and analysis is a difficult point. Second, the mismatch between the gas storage and heat storage links may lead to a reduction in system efficiency and even cause failures, such as airtightness problems, insufficient heat storage, or excessive heat loss. There are still difficulties in the diagnosis and prediction of these problems. Summary of the Invention

[0007] This application provides a method for monitoring, diagnosing, and optimizing the gas storage and heat storage links of a compressed air energy storage power station to solve the problems in related technologies, such as many pneumatic parameters in the gas storage and heat storage links of a compressed air energy storage power station that are interrelated and difficult to effectively perform data fusion and analysis, with low accuracy and reliability in diagnosis.

[0008] The first aspect of the embodiments of this application provides a system for monitoring, diagnosing, and optimizing the gas storage and heat storage links of a compressed air energy storage power station, including: an equipment layer, where the equipment layer includes the main equipment of the compressed air energy storage power station; a sensing layer, where the sensing layer includes a plurality of sensors arranged on the gas storage and heat storage equipment. According to the sensors on multiple pieces of equipment, a distributed sensing network is formed. Using the distributed sensing network, the sensing layer can real-time monitor the multi-modal data in the gas storage and heat storage links of the compressed air energy storage power station. The gas storage link mainly monitors the storage and release states of compressed air, and the heat storage link monitors the storage and transfer processes of heat; a transmission layer for transmitting the multi-modal data monitored by the sensing layer; an analysis layer for performing pattern recognition and anomaly detection based on the multi-modal data obtained by the transmission layer; a decision-making layer for generating a decision result according to the pattern recognition result and anomaly detection result of the analysis layer, feedbacking the decision result to the equipment layer, and performing corresponding actions according to the decision result.

[0009] Optionally, the equipment of the compressed air energy storage power station includes a compressor, a gas storage tank, a turbine, a heat storage tank, and a heat exchanger.

[0010] Optionally, the distributed sensing network includes multiple sensor nodes. Among them, the multiple sensor nodes communicate with each other through a communication network. When an equipment anomaly is detected by the current sensor node, it sends information to other sensor nodes to jointly cooperate in anomaly diagnosis and processing.

[0011] Optionally, the sensors on multiple pieces of equipment include multiple pressure sensors, temperature sensors, flow sensors, vibration sensors, image sensors, and monitoring cameras. The multi-modal data includes multiple pressure data, temperature data, flow data, vibration data, sound data, vibration data, and image data.

[0012] Optionally, the transport layer uses a wired communication network or a wireless communication network for data transmission. Among them, the wired communication network includes at least one of Ethernet, RS-232, and CAN, and the wireless communication network includes at least one of Wi-Fi, Zigbee, LoRa, NB-IoT, and 5G.

[0013] Optionally, the analysis layer includes a central data processing unit. Among them, the central data processing unit performs data cleaning and feature extraction on the data transmitted by the sensing layer, applies distributed algorithms, and performs pattern recognition and anomaly detection.

[0014] Optionally, the data cleaning methods include at least one of removing outliers, filling in missing values, and data normalization. The features extracted include at least one of statistical features, frequency domain features, and time domain features. The distributed algorithms include at least one of support vector machines, neural networks, and decision trees.

[0015] Optionally, the central data processing unit is further configured to: after identifying that the target device is in an abnormal state, send an abnormal diagnosis request to other sensor nodes through the communication network. Among them, the abnormal diagnosis request includes the abnormal type, trigger time, and possible reasons; after receiving the abnormal diagnosis request, other sensor nodes perform data collection and analysis on the target device. Other sensor nodes compare the actually collected data with the reference data to confirm whether the target device is in an abnormal state; other sensor nodes feedback the diagnosis result to the central data processing unit. After receiving the feedback diagnosis result, the central data processing unit analyzes the abnormal cause of the target device according to the diagnosis result.

[0016] An embodiment of the second aspect of the present application provides a method for monitoring, diagnosing, and optimizing the gas storage and heat storage links of a compressed air energy storage power station. The method uses the monitoring and diagnosis system for the gas storage and heat storage links of the compressed air energy storage power station in the first aspect for monitoring and diagnosis. The method includes the following steps: based on the overall design plan of the power station and specific monitoring requirements, determine the key performance indicators of the gas storage link and heat storage link of the power station and their monitoring requirements; according to the monitoring requirements of the gas storage link and heat storage link, select appropriate sensor nodes and construct a corresponding sensor network. The sensor nodes are interconnected through a communication network to form a distributed sensor network covering the gas storage link and heat storage link; collect multi-modal data of the gas storage and heat storage links through the distributed sensor network, including key parameters such as temperature, pressure, and flow rate, and perform data cleaning, denoising, and feature extraction on the collected multi-modal data to ensure data quality; use distributed algorithms for pattern recognition and anomaly detection, and combine the dynamic characteristics of the gas storage link and heat storage link to diagnose possible deviations during the operation of the system, especially potential problems caused by the mismatch between the gas storage link and heat storage link; according to the diagnosis result, optimize the collaborative work of the gas storage and heat storage links, and timely adjust the gas storage and heat storage strategies to improve the overall operation efficiency and stability of the compressed air energy storage power station.

[0017] Therefore, the present application has the following beneficial effects:

[0018] The monitoring and diagnosis system and method for the gas storage and heat storage links of a compressed air energy storage power station proposed in the embodiments of the present application integrate the monitoring data of the two energy storage links of gas storage and heat storage to achieve more accurate system diagnosis and optimization. The system includes sensors installed on multiple devices in the gas storage and heat storage links of the compressed air energy storage power station. These sensors constitute the perception layer of the distributed sensing network and can real-time monitor the multi-modal data of the gas storage and heat storage links. Through the transmission layer, the monitoring data obtained by the perception layer is transmitted to the analysis layer, where pattern recognition, anomaly detection, and matching analysis between the gas storage and heat storage links are performed on the data, and then the operating state of the energy storage system is evaluated. The decision-making layer generates a decision-making plan based on the analysis results and feeds the decision-making results back to the device layer to guide the device to perform corresponding optimization actions. This system can real-time identify and diagnose the mismatch problem between the gas storage and heat storage links, timely detect system anomalies, and effectively diagnose and optimize the operating state of the compressed air energy storage power station. At the same time, this system can improve the accuracy and reliability of diagnosis through data fusion and intelligent analysis, thereby improving the operating efficiency and safety of the compressed air energy storage power station. Therefore, the problems of energy efficiency loss, increased failure risk, and even system shutdown caused by the mismatch between the gas storage and heat storage links of the compressed air energy storage power station are solved.

[0019] The additional aspects and advantages of the present application will be partially given in the following description, partially become obvious from the following description, or be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and / or additional aspects and advantages of the present application will become obvious and easy to understand from the following description of the embodiments in conjunction with the drawings, where:

[0021] Figure 1 is a schematic structural diagram of a monitoring, diagnosis, and optimization system for the gas storage and heat storage links of a compressed air energy storage power station provided according to an embodiment of the present application;

[0022] Figure 2 is a structural diagram of a monitoring, diagnosis, and optimization system for the gas storage and heat storage links of a compressed air energy storage power station provided according to an embodiment of the present application;

[0023] Figure 3 is a flowchart of an intelligent multi-modal distributed sensing network monitoring and diagnosis method for a compressed air energy storage power station provided according to an embodiment of the present application;

[0024] Figure 4 is a schematic flowchart of a monitoring, diagnosis, and optimization method for the gas storage and heat storage links of a compressed air energy storage power station provided according to an embodiment of the present application. Detailed implementation manners

[0025] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application, and should not be construed as a limitation to the present application.

[0026] The method for monitoring, diagnosing and optimizing the gas storage and heat storage links of a compressed air energy storage power station according to an embodiment of the present application will be described below with reference to the accompanying drawings. In the related technologies mentioned in the above background art, there are many pneumatic parameters in the gas storage and heat storage links of a compressed air energy storage power station and they are interrelated, making it difficult to effectively perform data fusion and analysis, and the accuracy and reliability of the diagnosis results are low; the matching relationship between the gas storage and heat storage links is crucial for the stability and efficiency of the power station. If the coordination between the gas storage and heat storage links is improper, it will lead to performance problems and safety hazards during the operation of the power station. The present application provides a system for monitoring, diagnosing and optimizing the gas storage and heat storage links of a compressed air energy storage power station. In this system, a perception layer of a distributed sensing network is formed by including sensors arranged on multiple devices in the power station, and multi-modal data of the gas storage and heat storage links are monitored in real time by using this layer. The monitored data is transmitted through the transmission layer, and the analysis layer combines the key performance parameters of the gas storage and heat storage links to perform comprehensive analysis of pattern recognition and anomaly detection on the data, to identify whether there is a mismatch or an abnormal situation between the gas storage and heat storage links. Finally, the system will generate a decision result through the decision layer and feedback it to the device layer to execute corresponding adjustment actions, so as to timely discover the abnormal situation of the power station and accurately diagnose the mismatch or other problems between the gas storage and heat storage links. Through the application of this system, the diagnosis accuracy and reliability of a compressed air energy storage power station can be effectively improved, especially in terms of the coordination and optimization between the gas storage and heat storage links, solving the problems of difficult diagnosis and difficult data analysis in the traditional technology, thereby improving the safety and operation efficiency of the power station. Thus, the problems such as energy efficiency loss, increased failure risk and even system shutdown caused by the mismatched operation of the gas storage and heat storage links of a compressed air energy storage power station are solved.

[0027] Specifically, Figure 1 is a schematic structural diagram of a system for monitoring, diagnosing and optimizing the gas storage and heat storage links of a compressed air energy storage power station provided by an embodiment of the present application.

[0028] As Figure 1 shown, the system for monitoring, diagnosing and optimizing the gas storage and heat storage links of the compressed air energy storage power station includes: a device layer 101, a perception layer 102, a transmission layer 103, an analysis layer 104 and a decision layer 105.

[0029] Among them, the device layer 101 includes the main devices of the compressed air energy storage power station; the sensing layer 102 includes sensors arranged on multiple devices of the compressed air energy storage power station. According to the sensors on the multiple devices, a distributed sensing network is formed. By using the distributed sensing network, the sensing layer 102 can monitor the multi-modal data of the gas storage and heat storage links in the compressed air energy storage power station in real time. The gas storage link mainly monitors the storage and release states of compressed air, and the heat storage link monitors the storage and transfer processes of heat; the transmission layer 103 is used to transmit the multi-modal data monitored by the sensing layer 102; the analysis layer 104 is used to perform pattern recognition and anomaly detection based on the multi-modal data obtained by the transmission layer 103; the decision-making layer 105 is used to generate a decision result according to the pattern recognition result and anomaly detection result of the analysis layer 104, feedback the decision result to the device layer 101, and execute corresponding actions according to the decision result.

[0030] It can be understood that the embodiment of the present application includes a device layer 101, a sensing layer 102, a transmission layer 103, an analysis layer 104, and a decision-making layer 105. The device layer 101 includes the main devices of the compressed air energy storage power station, specifically including gas storage devices, heat storage devices, and auxiliary devices related to the gas storage and heat storage links. Through the sensors on multiple devices, a distributed sensing network is formed, which is an important part of the sensing layer 102, to realize the acquisition and monitoring of multi-modal data of the compressed air energy storage power station, and monitor the multi-modal data (such as pressure, temperature, flow rate, etc.) of the gas storage and heat storage links in the compressed air energy storage power station in real time. The transmission layer 103 is used to transmit the multi-modal data monitored by the sensing layer 102 to ensure the reliable transmission and real-time performance of the data. The analysis layer 104 analyzes the data, performs pattern recognition and anomaly detection. By analyzing the operation data of the gas storage and heat storage links, the matching degree between the two is identified. If there is a mismatch or anomaly in the gas storage and heat storage links, the system can detect and identify it in time to help identify potential problems, and transmit the recognition and detection results to the decision-making layer 105. The decision-making layer 105 generates a decision result according to the pattern recognition result and anomaly detection result of the analysis layer 104. The decision-making layer 105 judges whether there is a matching problem in the gas storage and heat storage links, and feedbacks instructions to the device layer 101 according to the diagnosis result to perform necessary optimization actions, specifically including adjusting the operation parameters between gas storage and heat storage, or performing troubleshooting and maintenance. The device layer 101 executes corresponding actions according to the decision result.

[0031] In the embodiment of the present application, the devices of the compressed air energy storage power station include compressors, gas storage tanks, turbines, heat storage tanks, and heat exchangers.

[0032] Among them, the compressor is a mechanical device used to increase the gas pressure or reduce its volume; the turbine is a rotating machine that converts the energy of a fluid into mechanical energy; the heat exchanger is a device that enables two or more fluids at different temperatures to transfer heat to each other without direct mixing; the air storage tank is a device used to store compressed high-pressure air. The heat storage tank is a device used to store thermal energy.

[0033] It can be understood that the equipment of the compressed air energy storage power station in the embodiments of the present application, namely the compressor, the air storage tank, the turbine, the heat storage tank, and the heat exchanger, utilize the operation of the above-mentioned equipment to achieve the function of compressed air energy storage power generation.

[0034] In the embodiments of the present application, the distributed sensing network includes multiple sensor nodes. Among them, the multiple sensor nodes communicate with each other through a communication network. When an equipment anomaly is detected by the current sensor node, it sends information to other sensor nodes and they cooperate together for anomaly diagnosis and processing.

[0035] Among them, the communication network can choose wired or wireless communication methods, which will be described in detail below and will not be elaborated here.

[0036] It can be understood that in the distributed sensing network, the sensor nodes can communicate with each other through the communication network. When a certain sensor node detects an equipment anomaly, this sensor will immediately send this information to adjacent nodes or other specified nodes through the communication network, and multiple sensor nodes cooperate together for anomaly diagnosis and processing.

[0037] In the embodiments of the present application, the sensors on multiple devices include multiple pressure sensors, temperature sensors, flow sensors, vibration sensors, image sensors, and monitoring cameras. The multi-modal data includes multiple pressure data, temperature data, flow data, vibration data, sound data, vibration data, and image data.

[0038] It can be understood that the sensors set on multiple devices in the embodiments of the present application include pressure sensors, temperature sensors, flow sensors, vibration sensors, image sensors, etc. The appropriate type of sensor is selected according to the parameters to be monitored, and it also includes monitoring cameras; the multi-modal data includes multiple pressure data, temperature data, flow data, vibration data, sound data, vibration data, and image data, which can be obtained through the corresponding sensors.

[0039] In the embodiments of the present application, the transport layer 103 uses a wired communication network or a wireless communication network for data transmission. Among them, the wired communication network includes at least one of Ethernet, RS-232, and CAN, and the wireless communication network includes at least one of Wi-Fi, Zigbee, LoRa, NB-IoT, and 5G.

[0040] Among them, Ethernet is a local area network technology standard, commonly used to connect devices such as computers to form a local area network; RS-232 is a serial communication interface standard, which can be used for point-to-point communication; CAN is a bus standard that allows microcontrollers and devices to communicate directly without a host computer; Wi-Fi, Zigbee, LoRa, NB-IoT, and 5G are all technologies that allow devices to connect to the Internet via radio waves, suitable for data transmission requirements in different scenarios.

[0041] It can be understood that the transport layer 103 of the embodiment of the present application can use a wired communication network or a wireless communication network to transmit data. If a wired network is selected for transmission, Ethernet, RS-232, CAN, etc. can be used. If a wireless network is used for transmission, Wi-Fi, Zigbee, LoRa, NB-IoT, and 5G can be used. Which transmission method to specifically select needs to consider factors such as communication distance, bandwidth, power consumption, and cost to determine the best communication network, which is not specifically limited here.

[0042] In the embodiment of the present application, the analysis layer 104 includes a central data processing unit. Among them, the central data processing unit performs data cleaning and feature extraction on the data transmitted by the sensing layer 102, and applies a distributed algorithm for pattern recognition and anomaly detection.

[0043] It can be understood that the embodiment of the present application can perform data cleaning and feature extraction on the data collected and transmitted by the sensing layer 102 through the central processing unit of the analysis layer 104, and apply a distributed algorithm to perform pattern recognition and anomaly detection on the data. The specific method will be described in detail below and will not be elaborated here.

[0044] In the embodiment of the present application, the data cleaning methods include at least one of removing outliers, filling in missing values, and data normalization. The features for feature extraction include at least one of statistical features, frequency domain features, and time domain features. The distributed algorithms include at least one of support vector machines, neural networks, and decision trees.

[0045] Among them, the support vector machine is a supervised learning model used for classification and regression analysis; the neural network is a computational model that simulates the structure of the human brain and is widely used in pattern recognition and prediction tasks; the decision tree is a tree-structured model used for classification and regression.

[0046] It can be understood that in the embodiment of the present application, through the analysis layer 104, the data collected and transmitted by the perception layer 102 is subjected to data cleaning using methods such as removing outliers and filling missing values, and data normalization is performed on the data for preprocessing; after data preprocessing, feature extraction is carried out to extract statistical features, frequency domain features, time domain features, etc. of the data, and finally, machine learning-based methods such as support vector machines, neural networks, and decision trees are used for pattern recognition and anomaly detection to complete the analysis of the data and obtain the recognition result and the detection result.

[0047] In the embodiment of the present application, the central data processing unit is further configured to: after identifying that the target device is in an abnormal state during the gas storage link and the heat storage link, send an abnormal diagnosis request to other sensor nodes through the communication network, where the abnormal diagnosis request includes the abnormal type, the trigger time, and the possible cause; after receiving the abnormal diagnosis request, other sensor nodes perform data collection and analysis on the target device, and other sensor nodes compare the actually collected data with the reference data to confirm whether the target device is in an abnormal state during the gas storage link and the heat storage link; other sensor nodes feedback the diagnosis result to the central data processing unit, and after receiving the feedback diagnosis result, the central data processing unit analyzes the abnormal cause of the target device according to the diagnosis result and performs an optimization adjustment on the mismatch problem between the gas storage link and the heat storage link of the CAES power station.

[0048] It can be understood that when the central processing unit detects that the target device may be abnormal, it sends an abnormal diagnosis request including the abnormal type, the trigger time, and the possible cause to other sensor nodes through the communication network. The sensor nodes that receive the request immediately perform data collection and analysis on the target device, especially focusing on monitoring the matching situation between the gas storage and heat storage links, and compare the actually collected data with the preset reference data for comparative analysis to determine whether there is a matching problem between the gas storage link and the heat storage link. If the matching is improper, it may lead to an abnormal state of the device, and further analyze the coordination between the gas storage and heat storage links. After the analysis is completed, the sensor nodes feedback the diagnosis result to the central data processing unit. The central data processing unit further analyzes the specific cause of the abnormality according to the received diagnosis result, determines the matching degree between the gas storage and heat storage links, and the possible abnormal situations that may be caused. Based on these analysis results, the central processing unit will decide whether to perform subsequent processing measures such as adjusting the operating parameters of the gas storage and heat storage, and optimizing the system configuration to ensure the stable operation of the system.

[0049] The monitoring and diagnosis optimization system for the gas storage and heat storage links of a compressed air energy storage power station proposed according to the embodiments of the present application constructs a perception layer of a distributed sensing network by arranging sensors on multiple key devices of the compressed air energy storage power station, monitors multi-modal data of the two energy storage links of gas storage and heat storage. The perception layer collects and transmits multi-modal data from the gas storage and heat storage links in real time, and transmits these data to the analysis layer through the transmission layer. The analysis layer uses pattern recognition and anomaly detection technologies to deeply analyze the working states of the gas storage and heat storage links, identify potential matching problems and abnormal situations. Finally, the decision-making layer generates decisions according to the analysis results, optimizes the collaborative work of the gas storage and heat storage links, discovers and diagnoses anomalies in the power station in a timely manner, and executes corresponding adjustment and optimization actions at the device layer according to the decision results, so as to ensure the efficient operation of the compressed air energy storage power station.

[0050] The following further describes the monitoring and diagnosis system for the gas storage and heat storage links of a compressed air energy storage power station through a specific embodiment. As Figure 2 shown, this embodiment proposes a monitoring and diagnosis optimization system and method for the gas storage and heat storage links of a compressed air energy storage power station, including a CAES device layer, a perception layer, a transmission layer, an analysis layer, and a decision-making layer. The CAES device layer includes a compressor, a heat exchanger, a turbine, a gas storage chamber, and a heat storage chamber, etc.

[0051] The perception layer includes pressure sensors, temperature sensors, flow sensors, monitoring cameras, etc. installed on the equipment of the gas storage and heat storage links inside the CAES power station, and monitors the working states and operating parameters of the gas storage and heat storage links in real time. Especially the temperature, pressure, flow and other data of the gas storage chamber and the heat storage chamber. The transmission layer includes wireless transmission and wired transmission methods. The analysis layer includes distributed algorithms for pattern recognition and anomaly detection, such as machine learning-based methods like support vector machines, neural networks, decision trees, etc. This layer focuses on real-time analysis of the data of the gas storage and heat storage links, identifies problems of improper matching between the two, such as insufficient gas storage capacity or differences in heat storage effects, and predicts possible system failures or risks of efficiency decline. The decision-making layer makes decisions according to the analysis results and feeds back the results to the CAES device layer. When the gas storage and heat storage links do not match, the system can automatically adjust the operating parameters of the compressor and the heat exchanger, or adjust the working modes of the gas storage and heat storage chambers to restore system balance and improve energy utilization efficiency and safety.

[0052] Figure 3 The flowchart of an intelligent multi-modal distributed sensing network monitoring and diagnosis method for a compressed air energy storage power station proposed in this embodiment is as Figure 3 shown. This process is divided into four parts:

[0053] The first part, system requirement analysis and design planning, includes:

[0054] Step S201, System Requirement Analysis: First, it is necessary to conduct a detailed analysis of the monitoring and abnormal diagnosis requirements for the gas storage and heat storage links of the power station. Determine that the equipment to be monitored includes key equipment such as compressors, gas storage tanks, turbines, heat storage tanks, and heat exchangers. The parameters to be monitored include pressure, temperature, flow rate, vibration, sound, vibration, images, etc. The monitoring frequency should be real-time, and the sampling rate needs to be determined according to the characteristics of the monitoring object and parameters. Generally, it is required to be able to meet the rapid response to changes in the equipment state and capture the changes in the equipment state in a timely manner. Especially during the energy conversion process between the gas storage and heat storage links. The abnormal diagnosis system should ensure that it can accurately identify potential abnormal problems in the gas storage and heat storage links and control the false alarm rate to avoid misdiagnosis of the normal state. In addition, the system should have the ability to quickly respond to abnormal situations and make corresponding processing in the shortest possible time. At the same time, the system should also have diversified processing strategies, including issuing alarms, automatic shutdown, adjusting operation parameters, etc., to deal with different types and severities of abnormal situations.

[0055] Step S202, System Design Planning: Based on the results of the requirement analysis, conduct system design planning. Special consideration needs to be given to the coordinated operation and matching relationship between the gas storage and heat storage links to ensure that the sensor network can comprehensively cover the key parts of these two links. Select appropriate sensor types, such as pressure sensors, temperature sensors, flow sensors, vibration sensors, image sensors, etc.; and design a reasonable sensor layout according to the specific requirements of the gas storage and heat storage processes. Design the communication network architecture, select appropriate transmission methods and data processing algorithms to ensure the stable transmission and analysis of monitoring data, especially the identification and processing of abnormal situations during the gas storage and heat storage processes.

[0056] The second part, Sensor Node Installation and Communication Network Construction, includes:

[0057] Step S203, Sensor Node Installation: Determine the installation locations of the sensors according to the equipment structure and working characteristics, such as the inlets and outlets of compressors, turbines, gas storage tanks, heat storage tanks, and heat exchangers, as well as other key parts of the compressed air energy storage power station, especially the inlets and outlets during the gas storage and heat storage processes. Reasonably select the installation locations to ensure that the sensor nodes can accurately and stably collect the key parameters of the equipment, monitor the state changes of the gas storage and heat storage processes in real time, and identify potential abnormal problems such as poor matching or energy loss.

[0058] Step S204, Communication network construction: Design a suitable communication network architecture according to the monitoring requirements of the gas storage and heat storage links. The communication between sensor nodes can choose wired or wireless communication methods. Wired communication can choose Ethernet, RS-232, CAN, etc.; wireless communication can choose Wi-Fi, Zigbee, LoRa, NB-IoT, 5G, etc. Considering the distance and environmental conditions of the gas storage and heat storage links, select a suitable communication solution to ensure the stability and real-time of data transmission. The network architecture should support high-frequency data transmission, meet the requirements of real-time monitoring and anomaly diagnosis, and ensure the security and confidentiality of data.

[0059] Part Three, Multimodal data acquisition and transmission, including:

[0060] Step S205, Multimodal data acquisition and transmission: Sensor nodes should collect pneumatic parameters (such as pressure, temperature, flow rate) and multimodal data such as vibration, sound, and image of the gas storage and heat storage links at regular intervals or event-driven. Since the gas storage and heat storage processes are closely related, the collected data should cover the state changes of the gas storage tank and the heat storage tank, and timely reflect the matching situation between the two. Through data preprocessing, such as filtering, calibration, etc., ensure the quality of the collected data. During the data transmission process, transmit the collected data to the central data processing unit through the communication network to ensure the integrity, accuracy, and security of the data, especially support for measures such as anomaly detection and fault restart during the gas storage and heat storage processes.

[0061] Part Four, Multimodal data fusion analysis and anomaly diagnosis, including:

[0062] Step S206, Central data processing unit: The central data processing unit receives the multimodal data transmitted from the sensor nodes, and preprocesses, cleans, and extracts features from the data. Pay special attention to the state changes of the gas storage and heat storage links, and analyze the matching problems of the gas storage and heat storage processes through the extracted statistical features, time-domain features, and frequency-domain features. Conduct anomaly detection through distributed algorithms and machine learning methods (such as support vector machines, neural networks, etc.) to identify potential matching problems or anomalies such as energy loss between the gas storage and heat storage links. At the same time, in the face of complex and changing gas storage and heat storage environments, supervised learning or unsupervised learning methods should be used to continuously optimize the accuracy of the model.

[0063] Step S207, Abnormal Diagnosis and Handling: When a matching problem or other abnormal situation in the gas storage and heat storage links is detected, the central data processing unit sends a diagnosis request to other relevant sensor nodes to further confirm information such as the type and cause of the abnormality. The sensor nodes analyze the data according to the local model or rules and feedback the results to the central processing unit. Based on the feedback from multiple sensor nodes, the central unit comprehensively analyzes to determine the cause of the abnormality and takes countermeasures, such as adjusting the operation parameters of gas storage or heat storage, issuing an alarm, or starting an emergency plan. In addition, equipment maintenance personnel can quickly respond and solve problems through the real-time monitoring and alarm function provided by the system to ensure the coordinated operation of the gas storage and heat storage links.

[0064] Next, a method for monitoring and diagnosing and optimizing the gas storage and heat storage links of a compressed air energy storage power station according to an embodiment of the present application will be described with reference to the accompanying drawings.

[0065] Figure 4 It is a flowchart of a method for monitoring and diagnosing and optimizing the gas storage and heat storage links of a compressed air energy storage power station according to an embodiment of the present application.

[0066] As Figure 4 shown, the method for monitoring and diagnosing and optimizing the gas storage and heat storage links of a compressed air energy storage power station includes the following steps:

[0067] In step S301, based on the overall design plan and specific monitoring requirements of the compressed air energy storage power station, the key performance indicators and their monitoring requirements of the gas storage link and the heat storage link of the compressed air energy storage power station are determined.

[0068] Among them, the design plan and monitoring requirements of the compressed air energy storage power station are obtained through specific project plans, etc.; the gas storage link mainly monitors the storage and release states of compressed air, and the heat storage link monitors the storage and transfer processes of heat.

[0069] It can be understood that the embodiments of the present application can clarify the key performance indicators of the gas storage link and the heat storage link according to the overall design plan and specific monitoring requirements of the compressed air energy storage power station, and accordingly formulate corresponding monitoring schemes, including but not limited to real-time monitoring of parameters such as gas storage pressure, temperature, volume change, and the thermal efficiency and heat loss rate of the heat storage system, to ensure the safe and stable operation of the system and achieve the expected energy storage effect.

[0070] In step S302, according to the monitoring requirements of the gas storage link and the heat storage link, appropriate sensor nodes are selected and a corresponding sensor network is constructed. Among them, the sensor nodes are interconnected through a communication network to form a distributed sensing network covering the gas storage link and the heat storage link.

[0071] Among them, determine the layout of the sensor network, select appropriate sensor types according to the monitoring parameters. For example, if the parameters to be monitored include pressure, temperature, flow rate, vibration, image, etc., then select pressure sensors, temperature sensors, flow sensors, vibration sensors, image sensors, etc., and determine the number of sensors according to the number of monitoring objects and key parts to form a distributed sensing network.

[0072] It can be understood that the embodiments of the present application can determine sensor nodes according to the design plan and monitoring requirements. For example, if the parameters to be monitored include pressure, temperature, flow rate, vibration, image, etc., then select pressure sensors, temperature sensors, flow sensors, vibration sensors, image sensors, etc., and determine the number of sensors according to the number of monitoring objects and key parts to form a distributed sensing network.

[0073] In step S303, collect multi-modal data of the gas storage link and the heat storage link through the distributed sensing network, including key parameters such as temperature, pressure, and flow rate, and perform data cleaning, denoising, and feature extraction on the collected multi-modal data to ensure data quality.

[0074] It can be understood that after the embodiments of the present application construct a distributed sensing network, use the distributed sensing network to collect multi-modal data of the gas storage and heat storage links of the compressed air energy storage power station, including data of multiple modalities such as pressure, temperature, flow rate, vibration, and image, and use the analysis layer to perform data cleaning and feature extraction on the multi-modal data, apply distributed algorithms and perform pattern recognition and anomaly detection to obtain recognition results and detection results.

[0075] In step S304, use distributed algorithms for pattern recognition and anomaly detection, combine the dynamic characteristics of the gas storage link and the heat storage link, and diagnose possible deviations during the operation of the system, especially the potential problems caused by the mismatch between the gas storage link and the heat storage link.

[0076] It can be understood that the embodiments of the present application use distributed algorithms to analyze the data of the gas storage and heat storage links in the compressed air energy storage power station, discover normal operation modes through pattern recognition technology, and then use anomaly detection methods to identify any behavior deviating from the normal mode, especially paying attention to the coordination between the gas storage and heat storage links, so as to give early warnings and solve potential problems to ensure the efficient and stable operation of the system.

[0077] In step S305, according to the diagnosis results, optimize the collaborative work of the gas storage link and the heat storage link, and adjust the gas storage and heat storage strategies.

[0078] It can be understood that the embodiments of the present application can, according to the diagnosis results, adjust the gas storage and heat storage strategies by optimizing the collaborative work mechanism of the gas storage link and the heat storage link to improve the overall efficiency and stability of the system.

[0079] It should be noted that the foregoing explanation of the monitoring and diagnosis optimization system embodiment for the gas storage and heat storage link of the compressed air energy storage power station is also applicable to the monitoring and diagnosis optimization method for the gas storage and heat storage link of the compressed air energy storage power station in this embodiment, and will not be elaborated here.

[0080] According to the monitoring and diagnosis method for the gas storage and heat storage link of the compressed air energy storage power station proposed in the embodiments of the present application, a distributed sensing network is formed by sensors arranged on multiple devices in the gas storage and heat storage link of the compressed air energy storage power station to monitor multi-modal data in the gas storage and heat storage link of the compressed air energy storage power station. Then, the monitored data is analyzed, pattern recognition and anomaly detection are performed. Finally, a decision result is generated using the pattern recognition result and the anomaly detection result, the decision result is fed back to the device layer, and corresponding actions are executed according to the decision result, which can timely detect abnormal situations in the power station and accurately diagnose the problems.

[0081] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms is not necessarily directed 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, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0082] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0083] Any process or method description shown in the flowchart or described in other ways herein can be understood as representing a module, segment, or part of code including one or N executable instructions for implementing a customized logical function or process. The scope of the preferred embodiments of the present application includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in a reverse order according to the involved functions, rather than in the order shown or discussed, which should be understood by those skilled in the art of the embodiments of the present application.

[0084] It should be understood that each part of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, the steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following techniques well known in the art or a combination thereof can be used: discrete logic circuits having logic gate circuits for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays, field programmable gate arrays, and the like.

[0085] Those of ordinary skill in the art can understand that all or part of the steps carried by the methods for implementing the above embodiments can be completed by instructing relevant hardware through a program. The above program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0086] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A monitoring and diagnostic optimization system for the gas and heat storage link of a compressed air energy storage power station, characterized in that: include: Equipment layer, wherein the equipment layer includes the main equipment of the compressed air energy storage power station; A sensing layer, wherein the sensing layer includes sensors disposed on a plurality of devices of the compressed air energy storage power station, and a distributed sensing network is formed according to the sensors on the plurality of devices. By utilizing the distributed sensing network, the sensing layer can monitor in real time the multimodal data of the gas storage link and the heat storage link in the compressed air energy storage power station, wherein the gas storage link mainly monitors the storage and release state of compressed air, and the heat storage link monitors the storage and transfer process of heat; A transmission layer, used for transmitting the multimodal data monitored by the perception layer; An analysis layer, used for performing pattern recognition and anomaly detection based on the multimodal data obtained by the transmission layer; The decision layer is used to generate a decision result based on the pattern recognition result and the anomaly detection result of the analysis layer, feed the decision result back to the device layer, and perform corresponding actions according to the decision result.

2. The compressed air energy storage power station gas storage and heat storage link monitoring and diagnosis optimization system according to claim 1 is characterized in that: The equipment of the compressed air energy storage power station includes a compressor, an air storage tank, a turbine, a heat storage tank and a heat exchanger.

3. The compressed air energy storage power station gas storage and heat storage link monitoring and diagnosis optimization system according to claim 1 is characterized in that: The distributed sensor network includes a plurality of sensor nodes, wherein the plurality of sensor nodes communicate with each other through a communication network. When a current sensor node detects an abnormality in a device, the sensor nodes send information to other sensor nodes to jointly perform abnormality diagnosis and processing.

4. The compressed air energy storage power station gas storage and heat storage link monitoring and diagnosis optimization system according to claim 1 or 3 is characterized in that: The sensors on the multiple devices include multiple pressure sensors, temperature sensors, flow sensors, vibration sensors, image sensors and surveillance cameras, and the multimodal data includes multiple pressure data, temperature data, flow data, vibration data, sound data, vibration data and image data.

5. The compressed air energy storage power station gas storage and heat storage link monitoring and diagnosis optimization system according to claim 1 is characterized in that: The transmission layer uses a wired communication network or a wireless communication network for data transmission, wherein the wired communication network includes at least one of Ethernet, RS-232 and CAN, and the wireless communication network includes at least one of Wi-Fi, Zigbee, LoRa, NB-IoT and 5G.

6. The compressed air energy storage power station gas storage and heat storage link monitoring and diagnosis optimization system according to claim 1 is characterized in that: The analysis layer includes a central data processing unit, wherein the central data processing unit performs data cleaning and feature extraction on the data transmitted by the perception layer, and applies a distributed algorithm to perform pattern recognition and anomaly detection.

7. The compressed air energy storage power station gas storage and heat storage link monitoring and diagnosis optimization system according to claim 6 is characterized in that: The data cleaning method includes at least one of removing outliers, filling missing values ​​and data normalization, the features extracted include at least one of statistical features, frequency domain features and time domain features, and the distributed algorithm includes at least one of a support vector machine, a neural network and a decision tree.

8. The compressed air energy storage power station gas storage and heat storage link monitoring and diagnosis optimization system according to claim 6 is characterized in that: The central data processing unit is also used for: After identifying that the target device is in an abnormal state in the gas storage link and the heat storage link, an abnormal diagnosis request is sent to other sensor nodes through the communication network, wherein the abnormal diagnosis request includes the abnormal type, trigger time and possible cause; After receiving the abnormal diagnosis request, the other sensor nodes collect and analyze data on the target device, and compare the collected actual data with the reference data to confirm whether the gas storage link and the heat storage link are in an abnormal state; The other sensor nodes feed back the diagnosis results to the central data processing unit shown. After receiving the feedback diagnosis results, the central data processing unit analyzes the abnormal cause of the target equipment according to the diagnosis results, and optimizes and adjusts the mismatch problem between the gas storage link and the heat storage link of the CAES power station.

9. A method for monitoring and diagnosing the optimization of the gas and heat storage links of a compressed air energy storage power station, characterized in that: The method uses the compressed air energy storage power station gas storage and heat storage link monitoring and diagnosis optimization system according to any one of claims 1 to 8 for monitoring and diagnosis, wherein the method comprises the following steps: Based on the overall design plan and specific monitoring requirements of the compressed air energy storage power station, determine the key performance indicators and monitoring requirements of the gas storage link and heat storage link of the compressed air energy storage power station; According to the monitoring requirements of the gas storage link and the heat storage link, appropriate sensor nodes are selected and a corresponding sensor network is constructed, wherein the sensor nodes are interconnected through a communication network to form a distributed sensor network covering the gas storage link and the heat storage link; Collect multimodal data of the gas storage link and the heat storage link through a distributed sensor network, including key parameters such as temperature, pressure, flow, etc., and perform data cleaning, denoising and feature extraction on the collected multimodal data to ensure data quality; Using distributed algorithms for pattern recognition and anomaly detection, combined with the dynamic characteristics of the gas storage link and the heat storage link, to diagnose possible deviations during system operation, especially potential problems caused by the mismatch between the gas storage link and the heat storage link; According to the diagnosis results, the coordinated work of the gas storage link and the heat storage link is optimized, and the gas storage and heat storage strategies are adjusted.

Images