Compressed air energy storage power station intelligent fault diagnosis device and maintenance method

Abstract

The invention discloses an intelligent fault diagnosis device and maintenance method for a compressed air energy storage power station, and the method comprises the following steps: S1, data collection: deploying a plurality of sensors in the compressed air energy storage power station to monitor the operation state and performance parameters of equipment in real time, and uploading the collected data to a central monitoring system; s2, data processing: preprocessing the data acquired in the S1; s3, a time sequence database is established, the time sequence database is used for storing historical operation data, and the data are stored in the time sequence database; s4, respectively establishing a fault diagnosis model and a fault prediction model, and meanwhile, collecting historical fault data including a fault type and equipment state parameters before and after the fault; s5, establishing an equipment performance degradation model according to the operation history and the current state of the equipment; according to the scheme, the comprehensive operation state monitoring and fault prediction maintenance system is established by integrating the Internet of Things, the sensor technology, the machine learning algorithm and the data analysis tool.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy storage power stations, and particularly relates to an intelligent fault diagnosis device and maintenance method for a compressed air energy storage power station. Background Art

[0002] As an advanced energy storage technology, the compressed air energy storage power station has a relatively complex working principle and process, involving the coordinated operation of multiple systems and components. Therefore, in the operation and maintenance process of the power station, the need for fault diagnosis and predictive maintenance is particularly urgent. Traditional fault diagnosis and maintenance methods often rely on manual inspections and experience judgments, which are not only inefficient but also difficult to accurately determine the type and location of faults. With the continuous development of intelligent technologies, applying intelligent fault diagnosis and predictive maintenance methods to compressed air energy storage power stations has become an inevitable trend. A compressed air energy storage power station is a technology that uses compressed air to store and release energy. Its working principle is generally as follows: during the energy storage stage, air is compressed by a compressor and stored in a high-pressure air storage device, while the heat generated during the compression process is recovered; during the energy release stage, the high-pressure air is released and heated, and then drives a turbine expander to generate electricity. This energy storage method has the advantages of high efficiency, environmental protection, and sustainability, and has received extensive attention and research in recent years.

[0003] With the rapid development of smart grids and renewable energy, as one of the important energy storage technologies, the operating stability and reliability of compressed air energy storage power stations are of great significance for the safe and stable operation of the power system. Therefore, intelligent fault diagnosis and predictive maintenance of compressed air energy storage power stations have become a current research hotspot. The defects of the existing technologies are as follows:

[0004] 1. Most of the existing fault diagnosis methods are based on traditional signal processing technologies and machine learning algorithms, and their diagnostic accuracy and precision need to be improved for the complex and variable fault modes of compressed air energy storage power stations.

[0005] 2. Due to the complex operating environment of compressed air energy storage power stations and the suddenness and uncertainty of fault occurrences, existing fault diagnosis methods often have difficulty in diagnosing the type and location of faults accurately and in real time.

[0006] 3. Most of the existing fault diagnosis methods rely on manual experience and professional knowledge, with a low degree of intelligence, and it is difficult to achieve automatic identification and diagnosis of faults.

[0007] 4. Most of the existing predictive maintenance methods are based on historical data and statistical models, and insufficient consideration is given to the complex operating process and fault mechanism of compressed air energy storage power stations, resulting in inaccurate prediction models and low reliability of prediction results.

[0008] 5. Existing predictive maintenance methods often only formulate maintenance strategies for specific fault types or equipment, lacking flexibility and adaptability, and it is difficult to meet the actual maintenance needs of compressed air energy storage power stations.

[0009] 6. The operation data of compressed air energy storage power stations has characteristics such as being massive, heterogeneous, and high-dimensional, making it difficult to obtain and process data,

[0010] posing great challenges to predictive maintenance.

[0011] Therefore, the present invention provides an intelligent fault diagnosis device and maintenance method for a compressed air energy storage power station to solve the technical problems raised in the above background art. Summary of the Invention

[0012] Aiming at the problems raised in the above background art, the object of the present invention is: aiming at the complex operating conditions of the compressed air energy storage power station (CAES) system, to provide an intelligent fault diagnosis device and maintenance method for a compressed air energy storage power station, by integrating the Internet of Things, sensor technology, machine learning algorithms, and data analysis tools, to establish a comprehensive operating status monitoring and fault prediction maintenance system.

[0013] To achieve the above technical objectives, the technical solutions adopted by the present invention are as follows:

[0014] An intelligent fault diagnosis device and maintenance method for a compressed air energy storage power station, including the following steps:

[0015] S1: Data acquisition, deploying multiple sensors in the compressed air energy storage power station to monitor the operating status and performance parameters of the equipment in real time, and uploading the collected data to the central monitoring system;

[0016] S2: Data processing, preprocessing the data collected in S1;

[0017] S3: Establish a time series database, which is used to store historical operation data, and store the data in the time series database;

[0018] S4: Establish a fault diagnosis model and a fault prediction model respectively. At the same time, collect historical fault data, including fault types and equipment status parameters before and after the occurrence of faults;

[0019] Specifically, the fault diagnosis model and the fault prediction model respectively use machine learning algorithms to train the fault diagnosis model so that it can automatically identify and classify faults;

[0020] S5: According to the operation history and current status of the equipment, establish an equipment performance degradation model, which is used to predict the performance change trend of the equipment in the future for a period of time;

[0021] S6: Generate a maintenance plan and intelligent maintenance suggestions based on the prediction results of the equipment performance degradation model;

[0022] S7: Establish a real-time monitoring and early warning system. When the equipment status parameters deviate from the normal range or potential failure risks are predicted, the real-time monitoring and early warning system will automatically send out early warning information to remind maintenance personnel to take measures in a timely manner.

[0023] Further defined, the sensors in S1 are arranged at the compressors, gas storage systems, and heat exchangers of the compressed air energy storage power station.

[0024] Further defined, the objects of the operation data collected by the sensors include the air compression module, gas storage module, thermal energy management module, and power generation module.

[0025] Further defined, the sensors are used to collect the pressure, temperature, flow rate, and power of the air compression module, the gas pressure, temperature, and leakage rate of the gas storage module, the temperature difference and heat flow of the heat exchanger in the thermal energy management module, and the rotational speed and electric power of the power generation module.

[0026] Further defined, the data in S1 is uploaded to the central monitoring system through the industrial Internet transmission protocol data.

[0027] Further defined, the industrial Internet transmission protocol includes MODBUS and OPC-UA.

[0028] Further defined, the data preprocessing in S2 includes cleaning, denoising, and normalization.

[0029] Further defined, the fault diagnosis model in S4 combines support vector machines and random forest classification algorithms to achieve abnormal condition identification. The fault prediction model uses long short-term memory networks or variational autoencoder time series prediction algorithms to predict the possible fault trends of key equipment.

[0030] Further defined, when the real-time monitored data in S4 matches the fault characteristics, the fault diagnosis model and the fault prediction model will send out fault early warning or alarm information.

[0031] Further defined, the maintenance plan in S6 includes maintenance time, maintenance content, and maintenance personnel. The intelligent maintenance suggestions in S6 include optimizing the maintenance plan, prompting the abnormal status and possible fault causes of specific equipment, and providing operation parameter optimization suggestions.

[0032] Advantages of the present invention:

[0033] 1. Improve system reliability

[0034] Real-time Monitoring and Diagnosis: Through the sensor network and intelligent algorithms, key parameters of the system are monitored in real time, faults are quickly diagnosed and located to ensure the stable operation of the system.

[0035] Early Warning: The fault prediction function can identify potential problems before faults occur, reducing the risks of system downtime and failures.

[0036] 2. Improve Maintenance Efficiency

[0037] Intelligent Maintenance Decision-making: Based on the diagnosis and prediction results, accurate maintenance suggestions are provided, reducing unnecessary manual intervention and maintenance time.

[0038] Optimize Maintenance Plan: Dynamically adjust the maintenance cycle and strategy to reduce resource waste and risks caused by over-maintenance or under-maintenance of equipment.

[0039] 3. Reduce Operation and Maintenance Costs

[0040] Reduce Unexpected Downtime: By detecting problems in advance and adjusting operating parameters, economic losses caused by unexpected downtime are avoided.

[0041] Efficient Resource Allocation: For critical components and high-risk areas, maintenance resources are preferentially allocated to maximize the maintenance benefits.

[0042] 4. High Data Utilization Rate

[0043] Deep Data Mining: Make full use of big data analysis technology to convert multi-variable data into useful diagnostic and predictive information.

[0044] Knowledge Accumulation and Expansion: Continuously supplement the fault diagnosis results and operation experience to the expert knowledge base to improve the system's ability to respond to new fault modes.

[0045] 5. Improve the Level of Intelligence

[0046] Real-time Decision Feedback: Realize online data analysis and intelligent decision-making functions, reduce manual intervention, and improve the degree of automation.

[0047] Strong Adaptive Ability: Can adaptively adjust parameters under changing working conditions to meet the operation requirements of complex systems.

[0048] The technical solution of the present invention integrates advanced monitoring, diagnosis, prediction, and decision-making technologies to provide intelligent and comprehensive fault diagnosis and maintenance means for compressed air energy storage power stations. It not only improves the reliability and economy of system operation but also promotes the intelligent upgrade of energy storage technologies. Description of the Drawings

[0049] The present invention can be further illustrated by the non-limiting embodiments given in the drawings;

[0050] Figure 1 This is a flowchart of the steps of an embodiment of an intelligent fault diagnosis device and maintenance method for a compressed air energy storage power station according to the present invention. Specific implementation manner

[0051] In order to enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be further described below in conjunction with the drawings and embodiments. The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0052] It should be noted that all directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the drawings). If the specific posture changes, the directional indications will also change accordingly.

[0053] In addition, the descriptions involving "first", "second", etc. in the present invention are only for descriptive purposes, and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions appears to be contradictory or unable to be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the protection scope required by the present invention. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0054] As Figure 1 shown, an intelligent fault diagnosis device and maintenance method for a compressed air energy storage power station according to the present invention includes the following steps:

[0055] S1: Data acquisition. Deploy multiple sensors in the compressed air energy storage power station to monitor the operating status and performance parameters of the equipment in real time, and upload the collected data to the central monitoring system;

[0056] S2: Data processing. Preprocess the data collected in S1;

[0057] S3: Establish a time series database. The time series database is used to store historical operation data, and store the data in the time series database;

[0058] Specifically, the time series database also supports high-frequency real-time data query.

[0059] S4: Establish a fault diagnosis model and a fault prediction model respectively. Meanwhile, collect historical fault data, including fault types and equipment status parameters before and after the occurrence of faults.

[0060] Specifically, the fault diagnosis model and the fault prediction model respectively use machine learning algorithms to train the fault diagnosis model so that it can automatically identify and classify faults.

[0061] S5: Establish an equipment performance degradation model based on the operation history and current status of the equipment. The equipment performance degradation model is used to predict the performance change trend of the equipment in a future period of time.

[0062] Specifically, such a design enables the equipment performance degradation model to detect potential fault risks in advance.

[0063] S6: Generate a maintenance plan and intelligent maintenance suggestions based on the prediction results of the equipment performance degradation model.

[0064] S7: Establish a real-time monitoring and warning system. When the equipment status parameters deviate from the normal range or potential fault risks are predicted, the real-time monitoring and warning system will automatically send out warning information to remind the maintenance personnel to take measures in time.

[0065] In the application of this embodiment, the sensors in S1 are arranged at the compressors, gas storage systems and heat exchangers of the compressed air energy storage power station.

[0066] In the application of this embodiment, the objects of the operation data collected by the sensors include the air compression module, the gas storage module, the thermal energy management module and the power generation module.

[0067] In the application of this embodiment, the sensors are used to collect the pressure, temperature, flow rate and power of the air compression module, the gas pressure, temperature and leakage rate of the gas storage module, the temperature difference and heat flow rate of the heat exchanger of the thermal energy management module, and the rotational speed and electric power of the power generation module.

[0068] Specifically, this embodiment uses information fusion technology to integrate and analyze the data of multiple sensors to extract more comprehensive fault feature information.

[0069] In the application of this embodiment, the data in S1 is uploaded to the central monitoring system through the industrial Internet transmission protocol data.

[0070] In the application of this embodiment, the industrial Internet transmission protocol includes MODBUS and OPC-UA.

[0071] In the application of this embodiment, the data preprocessing in S2 includes cleaning, denoising and normalization.

[0072] Specifically, preprocessing can ensure data quality.

[0073] In the application of this embodiment, the fault diagnosis model in S4 combines the support vector machine (SVM) and random forest (RF) classification algorithms to achieve abnormal condition recognition, and the fault prediction model uses the long short-term memory network (LSTM) or variational autoencoder (VAE) time series prediction algorithm to predict the possible fault trends of key equipment.

[0074] In the application of this embodiment, when the data monitored in real time in S4 matches the fault characteristics, the fault diagnosis model and the fault prediction model will issue a fault warning or alarm message.

[0075] In the application of this embodiment, the maintenance plan in S6 includes maintenance time, maintenance content, and maintenance personnel, and the intelligent maintenance suggestions in S6 include optimizing the maintenance plan, prompting the abnormal status and possible fault causes of specific equipment, and providing suggestions for optimizing operating parameters. Such a design can ensure the reliability and economy of the equipment.

[0076] Specifically, this embodiment adopts a CAES system, that is, a compressed air energy storage system, which is a system that can achieve large-capacity and long-term energy storage; the CAES system mainly includes key components such as a generator, a compressor, a combustion chamber, a gas storage chamber, an expander, and a motor. The system is divided into two processes: energy storage and energy release. During the energy storage process, renewable energy power such as wind power and photovoltaic power is used to drive the compressor to compress air, and the high-pressure air is stored in the gas storage chamber; during the energy release process, the high-pressure air in the gas storage chamber is released to drive the expander to do work for power generation. The CAES system has the following advantages: large-capacity energy storage: the single-unit power can reach hundreds of megawatts, and the power can be adjusted in real time during actual operation. Long-cycle energy storage: long-cycle energy storage that can achieve daily scheduling, weekly scheduling, or even quarterly scheduling. Long-time power supply: long-time power supply can be achieved by adjusting the output power. Multi-energy combined energy storage and supply: it can be combined with solar thermal, geothermal, and industrial waste heat to serve as an energy hub for a clean energy system. Strong geological adaptability: underground gas storage compressed air energy storage can use existing underground salt caverns or rock formations as gas storage reservoirs, with good geological adaptability and scalability. Flexible response: it can quickly respond to grid demands, and the process from gas storage to energy release can be completed in a short time, which is conducive to regulating the power supply and demand balance.

[0077] With the rapid development of renewable energy and the increasing demand for energy transformation, compressed air energy storage has received more attention and research. The CAES system can be used as a peak shaving power source to balance the contradiction between power supply and demand in the power grid, and can also be applied to distributed energy systems, microgrids and other fields as an energy storage unit or backup power source. In addition, CAES technology can also be combined with intermittent energy sources such as wind energy and solar energy to smoothly inject intermittent energy into the power grid and improve the utilization rate and reliability of renewable energy.

[0078] The technical solution of the present invention provides intelligent and comprehensive fault diagnosis and maintenance means for compressed air energy storage power stations by integrating advanced monitoring, diagnosis, prediction and decision-making technologies, which not only improves the reliability and economy of system operation, but also promotes the intelligent upgrade of energy storage technology.

[0079] The above embodiments are only used to exemplarily illustrate the principles and effects of the present invention, rather than to limit the present invention. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or changes completed by those with ordinary knowledge in the technical field without departing from the spirit and technical idea disclosed by the present invention should still be covered by the claims of the present invention.

Claims

1. An intelligent fault diagnosis device and maintenance method for a compressed air energy storage power station, characterized in that It includes the following steps: S1: Data collection. Deploy multiple sensors at a compressed air energy storage power station to monitor the operating status and performance parameters of the equipment in real time, and upload the collected data to the central monitoring system; S2: Data processing. Preprocess the data collected in S1; S3: Establish a time series database, which is used to store historical operation data, and store the data in the time series database; S4: Establish a fault diagnosis model and a fault prediction model respectively. At the same time, collect historical fault data, including fault types and equipment status parameters before and after the occurrence of faults; Specifically, the fault diagnosis model and the fault prediction model respectively use machine learning algorithms to train the fault diagnosis model so that it can automatically identify and classify faults; S6: Based on the prediction results of the equipment performance degradation model, generate a maintenance plan and intelligent maintenance suggestions; S7: Establish a real-time monitoring and early warning system, which is used to automatically send out early warning information when the equipment status parameters deviate from the normal range or potential fault risks are predicted, reminding the maintenance personnel to take measures in time. The sensors in S1 are arranged at the compressor, gas storage system and heat exchanger of the compressed air energy storage power station.

2. The intelligent fault diagnosis device and maintenance method for a compressed air energy storage power station according to claim 1, wherein: The objects of the operation data collected by the sensors include the air compression module, the gas storage module, the thermal energy management module and the power generation module.

3. The intelligent fault diagnosis device and maintenance method for a compressed air energy storage power station according to claim 2, characterized in that: The sensors are used to collect the pressure, temperature, flow rate and power of the air compression module, the gas pressure, temperature and leakage rate of the gas storage module, the heat exchanger temperature difference and heat flow rate of the thermal energy management module, and the rotational speed and electric power of the power generation module.

4. The intelligent fault diagnosis device and maintenance method for a compressed air energy storage power station according to claim 3, characterized in that: The data in S1 is uploaded to the central monitoring system through the industrial Internet transmission protocol data.

5. The intelligent fault diagnosis device and maintenance method for a compressed air energy storage power station according to claim 1, wherein: The industrial Internet transmission protocol includes MODBUS and OPC-UA.

6. The intelligent fault diagnosis device and maintenance method for a compressed air energy storage power station according to claim 1, characterized in that: The data preprocessing in S2 includes cleaning, denoising and normalization.

7. An intelligent fault diagnosis device and maintenance method for a compressed air energy storage power station according to claim 1, characterized in that: The fault diagnosis model in S4 combines the support vector machine and the random forest classification algorithm to realize the identification of abnormal working conditions. The fault prediction model uses the long short-term memory network or the variational autoencoder time series prediction algorithm to predict the possible fault trends of key equipment.

8. An intelligent fault diagnosis device and maintenance method for a compressed air energy storage power station according to claim 1, characterized in that: When the real-time monitored data in S4 matches the fault characteristics, the fault diagnosis model and the fault prediction model will issue fault early warning or alarm information.

9. The intelligent fault diagnosis device and maintenance method for a compressed air energy storage power station according to claim 1, characterized in that: The maintenance plan in S6 includes the maintenance time, maintenance content and maintenance personnel. The intelligent maintenance suggestions in S6 include optimizing the maintenance plan, prompting the abnormal status and possible fault reasons of specific equipment, and providing suggestions for optimizing operation parameters.

10. The intelligent fault diagnosis device and maintenance method for a compressed air energy storage power station according to claim 1, characterized in that: ​

Images