CN-121984224-A - Multi-perception collaborative inspection method and system for compressed air energy storage power station

CN121984224ACN 121984224 ACN121984224 ACN 121984224ACN-121984224-A

Abstract

The invention relates to the technical field of compressed air energy storage power station inspection, and provides a multi-perception collaborative inspection method and a system of a compressed air energy storage power station, wherein the method comprises the steps of arranging a plurality of sensors in each core monitoring area of the compressed air energy storage power station to form a sensor network for collaborative monitoring; the method comprises the steps of carrying out feature extraction on sensor monitoring data, fusing sensor features of the same equipment, calculating the state credibility of the equipment based on the fused features, packing historical monitoring data, feature fusion results and credibility calculation results of the equipment within a preset duration range to form an enhanced data packet when the credibility exceeds a state early warning threshold range, constructing a three-dimensional digital twin model, mapping real-time sensor data and the enhanced data packet of related equipment into the three-dimensional digital twin model, and carrying out analysis calculation based on the real-time sensor data and the enhanced data packet to obtain an equipment data analysis calculation result. The invention can obviously improve the safety and reliability of the power station.

Inventors

WANG HONGJIE
WEI ZHUANGZHUANG
DONG CHEN
CHEN LIYA
CHEN LU
YANG MINGHUA
HUANG XING
LIU WANSHUANG
YU JIN
LIU WENCHAO
LIU WENJIE
WAN JIANGUO

Assignees

北京洛斯达科技发展有限公司

Dates

Publication Date: 20260505
Application Date: 20260123

Claims (9)

1. The multi-perception collaborative inspection method for the compressed air energy storage power station is characterized by comprising the following steps of: S1, dividing a compressed air energy storage power station into a plurality of core monitoring areas according to the physical structure and functional logic of the compressed air energy storage power station, arranging a plurality of sensors in each core monitoring area to form a sensor network, and carrying out cooperative monitoring on equipment in each core monitoring area through the sensor network; S2, carrying out data preprocessing and feature extraction on the sensor monitoring data, fusing the sensor features of the same device in each extracted core monitoring area, calculating the reliability of the device state based on the fused features, and packaging the historical monitoring data, the feature fusion result and the reliability calculation result of the device in a preset duration range to form an enhanced data packet when the reliability exceeds a preset state early warning threshold range; S3, constructing a three-dimensional digital twin model of the compressed air energy storage power station, mapping real-time sensor data and enhanced data packets of relevant equipment in each core monitoring area into the three-dimensional digital twin model of the compressed air energy storage power station, analyzing and calculating based on the real-time sensor data and the enhanced data packets to obtain and display data analysis and calculation results of the relevant equipment, and realizing collaborative inspection of the system.
2. The compressed air energy storage power station multi-perception collaborative inspection method according to claim 1, wherein the core monitoring area comprises a gas storage area, a compression side, a heat storage area, an expansion side and an electrical control area; The gas storage area is provided with distributed optical fiber acoustic sensors for sensing microseismic and deformation of cave surrounding rock, is provided with micro-power consumption wireless pressure sensors arranged along the pipeline, is provided with laser methane/gas concentration sensors at possible leakage points, and is provided with a wide-angle high-definition camera for macroscopic monitoring of the surface environment; the compression side deployment sensor comprises a high-frequency vibration acceleration sensor and an acoustic emission sensor which are arranged on a compressor bearing and a gear box, a PT100 platinum resistance temperature sensor and a piezoresistive pressure sensor which are arranged in front of and behind an inlet and outlet and an interstage cooler, a fixed infrared thermal imager which is used for scanning the temperature fields of a compressor cylinder body and the cooler; The method comprises the steps that a partial discharge sensor is arranged on the expansion side to monitor the insulation state of a generator, and an online oil monitoring sensor is used for monitoring a lubrication system; respectively carrying out temperature/flow monitoring and electric parameter/temperature monitoring on the heat storage area and the electric control area; the gas storage area, the compression side, the heat storage area, the expansion side and the electric control area are further provided with an adjustable cradle head camera, an inspection robot and an intelligent gateway for controlling the sampling rate of the sensor.
3. The compressed air energy storage power station multi-perception collaborative inspection method according to claim 1, wherein the step S2 comprises: When the sensor monitoring data exceeds a preset threshold range, judging that corresponding equipment in a corresponding core monitoring area fails, then carrying out data preprocessing and feature extraction on the sensor monitoring data exceeding the threshold range, fusing sensor features of the same equipment in each extracted core monitoring area, calculating the reliability of equipment failure based on the fused features, and packaging historical monitoring data, feature fusion results and reliability calculation results of the equipment within a preset duration range to form an enhanced data packet when the reliability exceeds a preset state early warning threshold range.
4. The compressed air energy storage power station multi-perception collaborative inspection method according to claim 1, wherein the step S3 comprises: The method comprises the steps of constructing a three-dimensional digital twin model of the compressed air energy storage power station combining a BIM model of the compressed air energy storage power station and an AI analysis server, mapping real-time sensor data and an enhanced data packet of relevant equipment in each core monitoring area into the three-dimensional digital twin model of the compressed air energy storage power station, analyzing and calculating based on the real-time sensor data and the enhanced data packet through an AI algorithm integrated in the AI analysis server to obtain a data analysis and calculation result of the relevant equipment, and displaying the monitoring result of each core monitoring area in real time through the BIM model of the compressed air energy storage power station to realize collaborative inspection of the system.
5. The compressed air energy storage power station multi-perception collaborative inspection method according to claim 1, wherein the performing data preprocessing and feature extraction on sensor monitoring data comprises: Performing fast Fourier transform and envelope demodulation analysis on the vibration signal, and extracting the amplitude of the characteristic frequency and the passing frequency of the bearing; Graying, filtering and noise reduction are carried out on the infrared thermal image, and the characteristics of the highest temperature, the average temperature, the temperature gradient and the like are extracted; and (3) performing target detection on the visible light image by using a lightweight convolutional neural network, and extracting the opening degree of a valve, the reading of an instrument and whether foreign body characteristics exist.
6. The compressed air energy storage power station multi-perception collaborative inspection method according to any one of claims 1-5, wherein different sensor features from the same device are fused using D-S evidence theory or fuzzy logic algorithms.
7. Multi-perception collaborative inspection system of compressed air energy storage power station, which is characterized by comprising: the sensing execution module divides the compressed air energy storage power station into a plurality of core monitoring areas according to the physical structure and the functional logic of the compressed air energy storage power station, and lays a plurality of sensors in each core monitoring area to form a sensor network, and the sensor network is used for carrying out cooperative monitoring on equipment in each core monitoring area; The edge cooperation module is used for carrying out data preprocessing and feature extraction on the sensor monitoring data, fusing the sensor features of the same equipment in each extracted core monitoring area, calculating the reliability of the equipment state based on the fused features, and packing the historical monitoring data, the feature fusion result and the reliability calculation result of the equipment in a preset duration range to form an enhanced data packet when the reliability exceeds a preset state early warning threshold range; The central intelligent module is used for constructing a three-dimensional digital twin model of the compressed air energy storage power station, mapping real-time sensor data and enhanced data packets of relevant equipment in each core monitoring area into the three-dimensional digital twin model of the compressed air energy storage power station, analyzing and calculating based on the real-time sensor data and the enhanced data packets to obtain and display data analysis and calculation results of the relevant equipment, and realizing collaborative inspection of the system.
8. Electronic device, characterized by comprising a processor, a memory and a computer program stored on the memory and executable on the processor, which when executed by the processor implements a compressed air energy storage plant multi-perception collaborative inspection method according to any of claims 1-6.
9. A computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and when the computer program is executed by a processor, the computer program realizes the multi-perception collaborative inspection method of the compressed air energy storage power station of any one of claims 1-6.

Description

Multi-perception collaborative inspection method and system for compressed air energy storage power station Technical Field The invention relates to the technical field of compressed air energy storage power station inspection, in particular to a multi-perception collaborative inspection method and system for a compressed air energy storage power station. Background Currently, the equipment status monitoring and inspection of Compressed Air Energy Storage (CAES) power stations mainly relies on periodic manual inspection and stationary on-line inspection. The regular manual inspection is carried out by operation and maintenance personnel according to a preset route and period, and key equipment such as a gas storage cave, a compressor, an expansion machine, a heat exchanger and the like are subjected to naked eye observation, ear hearing abnormal sound, hand touch vibration, a point temperature meter, a hand-held vibration meter and the like for measurement. The data obtained is recorded in a paper or simple electronic form, depending on the experience and responsibility of the person. Fixed on-line monitoring means that a single sensor such as a temperature sensor and a pressure sensor is installed on part of key equipment, continuous data acquisition is carried out, and the data are transmitted to a monitoring system. However, these systems are often "islanded" independent of each other, lacking collaborative analysis capabilities. For example, the vibration monitoring system is independent of the temperature monitoring system alarm logic and cannot be analyzed in association to diagnose a composite fault. In combination with the above, the conventional inspection scheme has the following objective technical problems: The real-time performance and the early warning capability are poor, the manual inspection is discrete and periodic, the uninterrupted monitoring at 7x24 hours can not be realized, and the early signs of sudden and intermittent faults are difficult to capture. And the data are isolated and lack of fusion, namely each sensor system works independently, and the data are lack of correlation analysis. When the compressor outlet temperature is slightly raised, it may not be possible to accurately determine whether the equipment efficiency is lowered or the cooling capacity is insufficient without combining the changes in the pressure and flow rate of the cooling water system. The monitoring blind area is formed, the manual inspection path is fixed, and dangerous areas such as high altitude, narrow, high temperature and high pressure are not inspected in place. The coverage range of the fixed sensor is limited, and panoramic monitoring of the whole area (such as a large-scale gas storage) cannot be realized. The intelligent degree is low, fault diagnosis seriously depends on expert experience, an intelligent diagnosis model based on multi-source data fusion is lacking, and the crossing from 'monitoring' to 'diagnosis' and 'early warning' cannot be realized. The resource allocation is inflexible, namely the inspection resources and the monitoring strategies are static, and the inspection frequency and the key point cannot be dynamically adjusted according to the real-time health state of the equipment, so that the resource waste or the key point monitoring is insufficient. Disclosure of Invention The invention aims to solve at least one technical problem in the background art and provides a multi-perception collaborative inspection method and system for a compressed air energy storage power station. In order to achieve the above purpose, the invention provides a multi-perception collaborative inspection method of a compressed air energy storage power station, comprising the following steps: S1, dividing a compressed air energy storage power station into a plurality of core monitoring areas according to the physical structure and functional logic of the compressed air energy storage power station, arranging a plurality of sensors in each core monitoring area to form a sensor network, and carrying out cooperative monitoring on equipment in each core monitoring area through the sensor network; S2, carrying out data preprocessing and feature extraction on the sensor monitoring data, fusing the sensor features of the same device in each extracted core monitoring area, calculating the reliability of the device state based on the fused features, and packaging the historical monitoring data, the feature fusion result and the reliability calculation result of the device in a preset duration range to form an enhanced data packet when the reliability exceeds a preset state early warning threshold range; S3, constructing a three-dimensional digital twin model of the compressed air energy storage power station, mapping real-time sensor data and enhanced data packets of relevant equipment in each core monitoring area into the three-dimensional digital twin model of the compressed air energy storage power station,