Multi-scene intelligent thermal imaging abnormal state integrated management system

Abstract

The invention relates to the technical field of power data processing, and provides a multi-scene intelligent thermal imaging abnormal state comprehensive management system which integrates artificial intelligence and thermal imaging technologies and is used for monitoring temperature distribution of power equipment in real time and early warning abnormal states. The system comprises a data acquisition module, an equipment monitoring module, a fault classification module, a fault equipment determination module and a fault inspection unit. The device state is predicted by training the random forest model, the infrared detector is used for capturing the infrared radiation on the surface of the device, the fault device is rapidly positioned and detected, the system can also identify the fault sensor and continuously monitor the fault device, the stable operation of the power system is improved, and the power supply reliability is improved. The method effectively solves the problems that the number of devices in the new energy power plant is large, and the fault is difficult to locate, and improves the safety of the devices.

Description

Technical Field

[0001] The present invention relates to the technical field of power data processing, and in particular to a multi-scenario intelligent thermal imaging abnormal state integrated management system. Background Art

[0002] The multi-scenario intelligent thermal imaging abnormal state integrated management system integrates artificial intelligence technology and thermal imaging technology. Based on the principle of thermal radiation of objects, the system uses infrared detectors to capture infrared radiation emitted by target objects and converts it into electrical signals. By analyzing the electrical signals through algorithms, the system can monitor and accurately measure the temperature distribution on the surface of objects in real time and generate thermal images.

[0003] The multi-scenario intelligent thermal imaging abnormal state integrated management system plays a role in the power system. The system uses advanced thermal imaging technology to monitor the temperature distribution on the surface of power equipment in real time, quickly discover abnormal conditions such as equipment overheating and partial discharge, and issue early warning signals in time. It not only greatly improves the safety of power equipment, but also effectively reduces the risk of power outages caused by equipment failure. The system can also monitor the operating status of power equipment around the clock and uninterruptedly, providing a strong guarantee for the stable operation of the power system.

[0004] The multi-scenario intelligent thermal imaging abnormal state comprehensive management system has the following technical pain points in the power application scenario: real-time monitoring of the temperature distribution of power equipment and warning of abnormal conditions. There are many power equipment in new energy power plants. When a new energy power plant fails during operation, it is necessary to quickly locate the problem equipment in massive data. To solve this technical pain point, the present invention provides a multi-scenario intelligent thermal imaging abnormal state comprehensive management system. Summary of the invention

[0005] In view of the shortcomings of the existing technology, the present invention provides a multi-scenario intelligent thermal imaging abnormal state comprehensive management system to solve the problem of a large number of power equipment in new energy power plants. When a failure occurs in the operation of new energy power plants, it is necessary to quickly locate the problematic equipment in massive data.

[0006] In order to solve the above technical problems, the specific technical solutions of the present invention are as follows: The present invention provides a multi-scenario intelligent thermal imaging abnormal state integrated management system, comprising: A data acquisition module, which acquires historical power equipment surface temperature distribution data, historical power equipment identity information, and historical power operation status data, and uses the historical power equipment surface temperature distribution data, historical power equipment identity information, and historical power operation status data to train a random forest model to obtain a power equipment operation status prediction model; The equipment monitoring module collects real-time power equipment operation data, substitutes the real-time power equipment operation data into the power equipment operation status prediction model, and obtains the real-time power equipment operation monitoring results. The real-time power equipment operation monitoring results include normal power equipment operation and abnormal power equipment operation; The fault classification module retrieves the power equipment identity information and the power equipment temperature safety value corresponding to the power equipment operation abnormality, uses the power equipment identity information corresponding to the power equipment operation abnormality as the identity information of the device to be detected, determines the device to be detected according to the identity information of the device to be detected, retrieves the real-time temperature data of the device to be detected, compares the real-time temperature data of the device to be detected with the power equipment temperature safety value, and if the real-time temperature data of the device to be detected exceeds the power equipment temperature safety value, marks the device to be detected that exceeds the power equipment temperature safety value as a suspected faulty device; The faulty equipment determination module obtains the location data of the suspected faulty equipment and the location information of the inspection equipment, substitutes the location data of the suspected faulty equipment and the location information of the inspection equipment into the preset inspection path generation model, and obtains the inspection path of the suspected faulty equipment; The fault inspection unit transmits the inspection path of the suspected faulty equipment to the inspection device. The inspection device executes the inspection path of the suspected faulty equipment and moves to the location of the suspected faulty equipment. The inspection device captures the infrared radiation on the surface of the suspected faulty equipment in real time through the infrared detector, and converts it into an electrical signal to generate temperature distribution data of the suspected faulty equipment. The temperature distribution data of the suspected faulty equipment is substituted into a preset power equipment detection model to obtain the detection result of the temperature distribution data of the suspected faulty equipment. If the detection result of the temperature distribution data of the suspected faulty equipment is abnormal, the suspected faulty equipment is determined to be a faulty equipment.

[0007] Furthermore, in the multi-scenario intelligent thermal imaging abnormal state integrated management system of the present invention, the data acquisition module is also used for: Collect real-time operating data of power equipment, which includes current parameters, voltage parameters, power parameters and temperature data on the surface of the equipment. Input the real-time operating data of the power equipment into a power equipment operating status prediction model. Through calculation of the power equipment operating status prediction model, output the real-time power equipment operating monitoring results. The real-time power equipment operating monitoring results include whether the power equipment is in a normal operating state or an abnormal state.

[0008] Furthermore, in the multi-scenario intelligent thermal imaging abnormal state integrated management system of the present invention, the equipment monitoring module is also used for: If the equipment operating status is predicted to be abnormal, the system will feed back the real-time power equipment operation monitoring results to the corresponding monitoring system of the management personnel. The equipment monitoring module will continuously collect real-time power equipment operation data and monitor the power equipment operating status in real time. All collected real-time power equipment operation data and the results output by the power equipment operation status prediction model will be recorded and saved by the system.

[0009] Furthermore, in the multi-scenario intelligent thermal imaging abnormal state integrated management system of the present invention, the fault classification module is also used for: Retrieve the device identity information and temperature safety value corresponding to the abnormal operation of the power equipment, determine the device to be detected according to the device identity information corresponding to the abnormal operation of the power equipment, retrieve the real-time temperature data of the device to be detected, and compare the real-time temperature data of the device to be detected with the temperature safety value of the power equipment; If the real-time temperature data of the device to be detected exceeds the temperature safety value of the power equipment, the device to be detected will be marked as a suspected faulty device.

[0010] Furthermore, in the multi-scenario intelligent thermal imaging abnormal state integrated management system of the present invention, the faulty equipment determination module is also used for: The location data of the suspected faulty device and the location information of the current inspection device are substituted into the preset inspection path generation model. The inspection path generation model calculates the optimal inspection path based on the geographical location of the device, the current location of the inspection device and the path obstacles. The inspection path generation model calculates the optimal path from the current location of the inspection device to the location of the suspected faulty device through the path optimization algorithm, and outputs the calculated inspection path. The inspection device will move to the location of the suspected faulty device according to the inspection path.

[0011] Furthermore, in the multi-scenario intelligent thermal imaging abnormal state integrated management system of the present invention, the fault inspection unit is also used for: The inspection path of the suspected faulty equipment is transmitted to the inspection device. The inspection device moves to the location of the suspected faulty equipment according to the path, and uses an infrared detector to capture the infrared radiation on the surface of the suspected faulty equipment in real time, and converts the infrared radiation on the surface of the suspected faulty equipment into an electrical signal to generate temperature distribution data of the suspected faulty equipment. The temperature distribution data is substituted into a preset power equipment detection model. The preset power equipment detection model processes the temperature distribution data and outputs the detection result to determine whether there is an abnormality in the detection result. If the detection result is abnormal, the suspected faulty equipment is faulty and the suspected faulty equipment is determined to be a faulty equipment.

[0012] Furthermore, in the multi-scenario intelligent thermal imaging abnormal state integrated management system of the present invention, the fault inspection unit is also used for: Receive temperature data collected by a sensor installed on the suspected faulty device, compare the temperature data collected by the sensor on the suspected faulty device with the temperature distribution data of the suspected faulty device, and obtain temperature error data of the suspected faulty device; Retrieve the temperature safety range value corresponding to the suspected faulty device, and compare the temperature safety range value corresponding to the suspected faulty device with the temperature error data of the suspected faulty device. If the temperature error data of the suspected faulty device exceeds the temperature safety range value corresponding to the suspected faulty device, determine the sensor installed on the suspected faulty device as a faulty sensor. Use inspection equipment to continuously collect temperature data of equipment installed with fault sensors, obtain temperature data of equipment corresponding to the fault sensors, collect operating equipment status data of equipment corresponding to the fault sensors, train a neural network model with the operating equipment status data of equipment corresponding to the fault sensors and the temperature data of equipment corresponding to the fault sensors, obtain a fault equipment prediction model, use the fault equipment prediction model to continuously monitor the faulty equipment, use inspection equipment to continue collecting temperature data of equipment corresponding to the fault sensors, obtain temperature data to be processed, transmit the temperature data to be processed to the fault equipment prediction model, output the fault equipment prediction result, and if the fault equipment prediction result is that a fault exists, generate fault equipment warning information.

[0013] Beneficial effects of the present invention: The present invention can quickly discover abnormal conditions such as overheating and partial discharge of equipment by real-time monitoring and accurate measurement of the temperature distribution on the surface of power equipment, and issue early warning signals in time, thereby greatly improving the safety of power equipment and reducing the risk of power outages caused by equipment failures. Secondly, the system can monitor the operating status of power equipment around the clock and uninterruptedly, providing a strong guarantee for the stable operation of the power system. In addition, in new energy power plants, the present invention can effectively solve the problems of large number of power equipment and large amount of data, and realize efficient fault location. Through the preset inspection path generation model, the system can calculate the optimal inspection path, improve inspection efficiency, and reduce inspection time and cost. At the same time, an infrared detector is used to capture the infrared radiation on the surface of the equipment in real time, and it is converted into an electrical signal to generate temperature distribution data. Combined with the preset power equipment detection model, the accuracy of fault detection is significantly improved. In addition, the intelligent management function of the present invention integrates artificial intelligence technology and thermal imaging technology, which improves management efficiency and level. The large amount of real-time power equipment operation data collected and saved by the system provides strong data support for subsequent troubleshooting, equipment maintenance and management decisions. The system architecture of the present invention is flexible and easy to expand, and can adapt to the management needs of power equipment of different scales and different scenarios. Finally, through automation and intelligent means, the present invention reduces manual intervention, improves operation and maintenance efficiency, and reduces operation and maintenance costs.

[0014] In summary, the multi-scenario intelligent thermal imaging abnormal state comprehensive management system of the present invention has significant beneficial effects in improving the safety of power equipment, reducing the risk of power outages, optimizing inspection paths, and improving the accuracy of fault detection, and is of great significance to the stable operation and efficient management of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on the drawings without paying any creative labor.

[0016] Figure 1 A schematic diagram of the functional modules in the multi-scenario intelligent thermal imaging abnormal state integrated management system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. The technical solutions provided by the embodiments of the present invention are described in detail below in conjunction with the drawings.

[0018] In order to better understand the purpose of the present invention, the present invention is described in further detail below.

[0019] The present invention provides a multi-scenario intelligent thermal imaging abnormal state integrated management system, comprising: A data acquisition module, which acquires historical power equipment surface temperature distribution data, historical power equipment identity information, and historical power operation status data, and uses the historical power equipment surface temperature distribution data, historical power equipment identity information, and historical power operation status data to train a random forest model to obtain a power equipment operation status prediction model; In the data acquisition module, the temperature distribution data on the surface of historical power equipment is collected. The temperature distribution data on the surface of historical power equipment records the temperature distribution of the surface of the equipment under different operating conditions. At the same time, the data acquisition module also collects the identity information of historical power equipment. The identity information of historical power equipment includes basic information such as the model, location, and manufacturer of the equipment, as well as historical power operation status data. The historical power operation status data includes parameters such as current, voltage, and power, which reflect the operating status of the equipment. Then, the collected data is used to train the random forest model. The random forest model is an integrated learning method that improves the accuracy of the model by constructing multiple decision trees and combining their prediction results. After training, the model can learn the relationship between the operating status of the equipment and the temperature distribution, thereby generating a prediction model for the operating status of the power equipment. The model can predict the temperature distribution of the equipment under a given operating state, and then determine whether the equipment is operating normally.

[0020] The equipment monitoring module collects real-time power equipment operation data, substitutes the real-time power equipment operation data into the power equipment operation status prediction model, and obtains the real-time power equipment operation monitoring results. The real-time power equipment operation monitoring results include normal power equipment operation and abnormal power equipment operation; In the equipment monitoring module, the real-time operation data of the power equipment is collected. The real-time operation data of the power equipment includes current parameters, voltage parameters, power parameters and temperature data on the surface of the equipment. The collected real-time data will be input into the pre-trained power equipment operation status prediction model. The power equipment operation status prediction model is based on the historical power equipment surface temperature distribution data, historical power equipment identity information and historical power operation status data, and is trained by the random forest algorithm, with high accuracy. Through the calculation of the power equipment operation status prediction model, the equipment monitoring module will output the real-time power equipment operation monitoring results, clearly indicating whether the power equipment is in normal operation or abnormal state. If the equipment operation status is predicted to be abnormal, the system will immediately feedback this result to the management personnel or the corresponding monitoring system so that timely countermeasures can be taken. At the same time, the equipment monitoring module will continuously collect real-time power equipment operation data and monitor the power equipment operation status in real time. All collected data and the results of the model output will be recorded and saved by the system for subsequent analysis and troubleshooting.

[0021] The fault classification module retrieves the power equipment identity information and the power equipment temperature safety value corresponding to the power equipment operation abnormality, uses the power equipment identity information corresponding to the power equipment operation abnormality as the identity information of the device to be detected, determines the device to be detected according to the identity information of the device to be detected, retrieves the real-time temperature data of the device to be detected, compares the real-time temperature data of the device to be detected with the power equipment temperature safety value, and if the real-time temperature data of the device to be detected exceeds the power equipment temperature safety value, marks the device to be detected that exceeds the power equipment temperature safety value as a suspected faulty device; In the fault classification module, the specific steps for marking suspected faulty equipment are as follows: first, the fault classification module retrieves the power equipment identity information corresponding to the abnormal operation of the power equipment and the power equipment temperature safety value, and uses the power equipment identity information corresponding to the abnormal operation of the power equipment as the identity information of the device to be detected, and determines the device to be detected based on this information; then, the module retrieves the real-time temperature data of the device to be detected, and compares this data with the temperature safety value of the power equipment. Finally, if the real-time temperature data of the device to be detected exceeds the temperature safety value of the power equipment, then the device will be marked as a suspected faulty device.

[0022] The faulty equipment determination module obtains the location data of the suspected faulty equipment and the location information of the inspection equipment, substitutes the location data of the suspected faulty equipment and the location information of the inspection equipment into the preset inspection path generation model, and obtains the inspection path of the suspected faulty equipment; In the faulty equipment determination module, the location data of the suspected faulty equipment and the location information of the inspection equipment are obtained. The location data and information are used as input and substituted into the preset inspection path generation model. The inspection path generation model is calculated based on the geographical location of the equipment, the current location of the inspection equipment, and possible path obstacles. Through the path optimization algorithm, the inspection path generation model can calculate the optimal path from the current location of the inspection equipment to the location of the suspected faulty equipment. The optimal path of the suspected faulty equipment location considers multiple factors such as path length, time cost, and safety. Then, the inspection path generation model outputs the calculated inspection path, and the inspection equipment will move to the location of the suspected faulty equipment along this path. During the movement process, the inspection equipment may also need to update its location information in real time so that the inspection equipment can accurately reach the target location. Finally, after arriving at the location of the suspected faulty equipment, the inspection equipment captures the infrared radiation on the surface of the equipment in real time through an infrared detector, and converts it into an electrical signal to generate temperature distribution data, and then substitutes the data into the preset power equipment detection model to determine whether the equipment has a fault.

[0023] The fault inspection unit transmits the inspection path of the suspected faulty equipment to the inspection device. The inspection device executes the inspection path of the suspected faulty equipment and moves to the location of the suspected faulty equipment. The inspection device captures the infrared radiation on the surface of the suspected faulty equipment in real time through the infrared detector, and converts it into an electrical signal to generate temperature distribution data of the suspected faulty equipment. The temperature distribution data of the suspected faulty equipment is substituted into a preset power equipment detection model to obtain the detection result of the temperature distribution data of the suspected faulty equipment. If the detection result of the temperature distribution data of the suspected faulty equipment is abnormal, the suspected faulty equipment is determined to be a faulty equipment.

[0024] In the fault inspection unit, the inspection path information of the suspected faulty equipment is transmitted to the inspection device. After receiving the path, the inspection device moves to the location of the suspected faulty equipment according to the instructions of the path. After arriving at the location, the inspection device will use its infrared detector to capture the infrared radiation on the surface of the suspected faulty equipment in real time, and then convert these infrared radiations into electrical signals to generate temperature distribution data of the suspected faulty equipment. Next, the temperature distribution data will be substituted into the preset power equipment detection model, which processes the data and outputs the detection results. Finally, according to the detection results, if it is judged that there is an abnormality, the suspected faulty equipment will be determined as a faulty equipment.

[0025] Specifically, in the multi-scenario intelligent thermal imaging abnormal state integrated management system of the present invention, the data acquisition module is also used for: Collect real-time operating data of power equipment, which includes current parameters, voltage parameters, power parameters and temperature data on the surface of the equipment. Input the real-time operating data of the power equipment into a power equipment operating status prediction model. Through calculation of the power equipment operating status prediction model, output the real-time power equipment operating monitoring results. The real-time power equipment operating monitoring results include whether the power equipment is in a normal operating state or an abnormal state.

[0026] In the data acquisition module, the real-time operation data of the power equipment is collected. The real-time operation data of the power equipment covers the current parameters, voltage parameters, power parameters and the temperature data on the surface of the equipment, which can fully reflect the real-time operation status of the power equipment. The collected real-time data will be input into the trained power equipment operation status prediction model. The power equipment operation status prediction model is based on the historical power equipment surface temperature distribution data, historical power equipment identity information and historical power operation status data, and is trained using the random forest model. The power equipment operation status prediction model calculates the input real-time operation data and deeply analyzes the operation status of the equipment through its internal algorithms and logic. The power equipment operation status prediction model will output the real-time power equipment operation monitoring results, clearly indicating whether the power equipment is in normal operation or abnormal state. If the equipment operation status is predicted to be abnormal, the system will immediately feedback this result to the management personnel or the corresponding monitoring system. Finally, all the collected real-time power equipment operation data and the results output by the power equipment operation status prediction model will be recorded and saved by the system for subsequent analysis and reference.

[0027] Specifically, the multi-scenario intelligent thermal imaging abnormal state integrated management system of the present invention, the equipment monitoring module is also used for: If the equipment operating status is predicted to be abnormal, the system will feed back the real-time power equipment operation monitoring results to the corresponding monitoring system of the management personnel. The equipment monitoring module will continuously collect real-time power equipment operation data and monitor the power equipment operating status in real time. All collected real-time power equipment operation data and the results output by the power equipment operation status prediction model will be recorded and saved by the system.

[0028] In the equipment monitoring module, if the equipment operation status is predicted to be abnormal, the system will immediately feed back the real-time power equipment operation monitoring results to the management personnel or the corresponding monitoring system to ensure that potential problems can be dealt with in a timely manner. At the same time, the equipment monitoring module will continue to collect real-time power equipment operation data and monitor the operation status of the power equipment in real time. In this process, all the collected real-time power equipment operation data and the results output by the power equipment operation status prediction model will be recorded and saved by the system. Through continuous data collection and monitoring, the system can maintain a comprehensive understanding of the equipment status and ensure that it can be discovered and handled in time when the equipment fails. In addition, the system also pays attention to the integrity of the data, ensuring that all collected data and model output results are intact, so that accurate data analysis and decision-making can be carried out when needed. These steps together constitute the complete workflow of the equipment monitoring module when the equipment operation status is predicted to be abnormal, thereby ensuring the accuracy of the system.

[0029] Specifically, in the multi-scenario intelligent thermal imaging abnormal state integrated management system of the present invention, the fault classification module is also used for: Retrieve the device identity information and temperature safety value corresponding to the abnormal operation of the power equipment, determine the device to be detected according to the device identity information corresponding to the abnormal operation of the power equipment, retrieve the real-time temperature data of the device to be detected, and compare the real-time temperature data of the device to be detected with the temperature safety value of the power equipment; If the real-time temperature data of the device to be detected exceeds the temperature safety value of the power equipment, the device to be detected will be marked as a suspected faulty device.

[0030] In the fault classification module, when an abnormality occurs in the operation of the power equipment, the fault classification module will first retrieve the power equipment identity information and temperature safety value corresponding to the abnormality. Based on this information, the fault classification module can determine the specific equipment to be detected, and then retrieve the real-time temperature data of the equipment. Then, the fault classification module compares the real-time temperature data of the equipment to be detected with the temperature safety value of the power equipment to determine whether the equipment is in an abnormally high temperature state.

[0031] If the real-time temperature data of the device to be detected exceeds the temperature safety value of the power equipment, the fault classification module marks the device as a suspected faulty device, indicating that the device may have a fault or abnormality.

[0032] Specifically, in the multi-scenario intelligent thermal imaging abnormal state integrated management system of the present invention, the faulty equipment determination module is also used for: The location data of the suspected faulty device and the location information of the current inspection device are substituted into the preset inspection path generation model. The inspection path generation model calculates the optimal inspection path based on the geographical location of the device, the current location of the inspection device and the path obstacles. The inspection path generation model calculates the optimal path from the current location of the inspection device to the location of the suspected faulty device through the path optimization algorithm, and outputs the calculated inspection path. The inspection device will move to the location of the suspected faulty device according to the inspection path.

[0033] In the faulty equipment determination module, the location data of the suspected faulty equipment and the location information of the current inspection equipment are first passed as input parameters to the inspection path generation model. The inspection path generation model is calculated based on the geographical location of the equipment, the current location of the inspection equipment, and the path obstacles, and uses the path optimization algorithm to calculate the optimal path from the current location of the inspection equipment to the location of the suspected faulty equipment. During the calculation process, the model will consider the obstacles, distance, and possible time consumption in the path to ensure the effectiveness and efficiency of the path. Then, the inspection path generation model outputs the calculated optimal inspection path, which will serve as a moving guide for the inspection equipment. After receiving the optimal inspection path, the inspection equipment will move to the location of the suspected faulty equipment according to the path. During the movement, factors such as real-time traffic conditions and equipment status may also need to be considered. After arriving at the location of the suspected faulty equipment, the inspection equipment will capture the infrared radiation on the surface of the suspected faulty equipment in real time through the infrared detector, and convert it into electrical signals to generate temperature distribution data, and then substitute these data into the preset power equipment detection model for processing to determine whether there is an abnormality and take corresponding fault handling measures.

[0034] Specifically, in the multi-scenario intelligent thermal imaging abnormal state integrated management system of the present invention, the fault inspection unit is also used for: The inspection path of the suspected faulty equipment is transmitted to the inspection device. The inspection device moves to the location of the suspected faulty equipment according to the path, and uses an infrared detector to capture the infrared radiation on the surface of the suspected faulty equipment in real time, and converts the infrared radiation on the surface of the suspected faulty equipment into an electrical signal to generate temperature distribution data of the suspected faulty equipment. The temperature distribution data is substituted into a preset power equipment detection model. The preset power equipment detection model processes the temperature distribution data and outputs the detection result to determine whether there is an abnormality in the detection result. If the detection result is abnormal, the suspected faulty equipment is faulty and the suspected faulty equipment is determined to be a faulty equipment.

[0035] In the fault inspection unit, the inspection path of the suspected faulty equipment is first transmitted to the inspection device, and the inspection device moves to the location of the suspected faulty equipment according to the received path information. After arriving at the location, the inspection device uses an infrared detector to capture the infrared radiation on the surface of the suspected faulty equipment in real time, and converts it into an electrical signal to generate temperature distribution data of the suspected faulty equipment. Next, these temperature distribution data are substituted into the preset power equipment detection model, and the power equipment detection model processes the data and outputs the detection results. Finally, it is determined whether there is an abnormality based on the detection results. If the detection result shows that there is an abnormality, it is determined that the suspected faulty equipment is faulty and it is officially marked as a faulty device.

[0036] Specifically, in the multi-scenario intelligent thermal imaging abnormal state integrated management system of the present invention, the fault inspection unit is also used for: Receive temperature data collected by a sensor installed on the suspected faulty device, compare the temperature data collected by the sensor on the suspected faulty device with the temperature distribution data of the suspected faulty device, and obtain temperature error data of the suspected faulty device; Retrieve the temperature safety range value corresponding to the suspected faulty device, and compare the temperature safety range value corresponding to the suspected faulty device with the temperature error data of the suspected faulty device. If the temperature error data of the suspected faulty device exceeds the temperature safety range value corresponding to the suspected faulty device, determine the sensor installed on the suspected faulty device as a faulty sensor. Use inspection equipment to continuously collect temperature data of equipment installed with fault sensors, obtain temperature data of equipment corresponding to the fault sensors, collect operating equipment status data of equipment corresponding to the fault sensors, train a neural network model with the operating equipment status data of equipment corresponding to the fault sensors and the temperature data of equipment corresponding to the fault sensors, obtain a fault equipment prediction model, use the fault equipment prediction model to continuously monitor the faulty equipment, use inspection equipment to continue collecting temperature data of equipment corresponding to the fault sensors, obtain temperature data to be processed, transmit the temperature data to be processed to the fault equipment prediction model, output the fault equipment prediction result, and if the fault equipment prediction result is that a fault exists, generate fault equipment warning information.

[0037] In the fault inspection unit, the temperature data collected by the sensor installed on the suspected faulty device is received, and the data is compared with the temperature distribution data of the suspected faulty device to obtain the temperature error data of the suspected faulty device. Then, the temperature safety range values ​​corresponding to the suspected faulty device are retrieved, and these values ​​are compared with the temperature error data of the suspected faulty device. If the temperature error data of the suspected faulty device exceeds the corresponding temperature safety range value, the sensor installed on the suspected faulty device is determined to be a faulty sensor.

[0038] Subsequently, the inspection equipment is used to continuously collect the temperature data of the equipment where the fault sensor is installed and the status data of the running equipment. These data are used to train the neural network model to obtain the fault equipment prediction model. Using the fault equipment prediction model, the faulty equipment can be continuously monitored. At the same time, the inspection equipment continues to collect the temperature data of the equipment corresponding to the fault sensor, obtains the temperature data to be processed, and transmits it to the fault equipment prediction model to output the fault equipment prediction result. If the prediction result shows that there is a fault, a fault equipment warning information is generated.

[0039] The technical solution of the present invention solves the problem that there are many power equipment in the new energy power plant. When the new energy power plant fails, it is necessary to quickly locate the problem equipment in the massive data. First, the data acquisition module collects the temperature distribution data on the surface of the historical power equipment, the identity information of the historical power equipment and the historical power operation status data, and uses these data to train the random forest model to obtain the power equipment operation status prediction model. Then, the equipment monitoring module will collect the real-time power equipment operation data and substitute it into the power equipment operation status prediction model to obtain the real-time power equipment operation monitoring results, including the normal operation of the power equipment and the abnormal operation of the power equipment. When an abnormality is detected, the fault classification module will retrieve the corresponding power equipment identity information and the power equipment temperature safety value, compare the real-time temperature data of the abnormal equipment with the temperature safety value, and if it exceeds the safety value, the equipment is marked as a suspected faulty device. Then, the faulty equipment determination module will obtain the location data of the suspected faulty equipment and the inspection equipment location information, substitute them into the preset inspection path generation model, calculate the optimal inspection path, and quickly locate the suspected faulty equipment. Finally, the fault inspection unit will move the inspection equipment to the location of the suspected faulty equipment according to the provided inspection path, and use the infrared detector to capture the infrared radiation on the surface of the equipment in real time, generate temperature distribution data, and substitute it into the preset power equipment detection model for abnormality detection. If the detection result is abnormal, the suspected faulty equipment is determined to be a faulty equipment. The present invention can efficiently and accurately locate and handle faulty equipment in new energy power plants.

Claims

1. A multi-scenario intelligent thermal imaging abnormal state integrated management system, characterized in that: include: A data acquisition module, which acquires historical power equipment surface temperature distribution data, historical power equipment identity information, and historical power operation status data, and uses the historical power equipment surface temperature distribution data, historical power equipment identity information, and historical power operation status data to train a random forest model to obtain a power equipment operation status prediction model; The equipment monitoring module collects real-time power equipment operation data, substitutes the real-time power equipment operation data into the power equipment operation status prediction model, and obtains the real-time power equipment operation monitoring results. The real-time power equipment operation monitoring results include normal power equipment operation and abnormal power equipment operation; The fault classification module retrieves the power equipment identity information and the power equipment temperature safety value corresponding to the power equipment operation abnormality, uses the power equipment identity information corresponding to the power equipment operation abnormality as the identity information of the device to be detected, determines the device to be detected according to the identity information of the device to be detected, retrieves the real-time temperature data of the device to be detected, compares the real-time temperature data of the device to be detected with the power equipment temperature safety value, and if the real-time temperature data of the device to be detected exceeds the power equipment temperature safety value, marks the device to be detected that exceeds the power equipment temperature safety value as a suspected faulty device; The faulty equipment determination module obtains the location data of the suspected faulty equipment and the location information of the inspection equipment, substitutes the location data of the suspected faulty equipment and the location information of the inspection equipment into the preset inspection path generation model, and obtains the inspection path of the suspected faulty equipment; The fault inspection unit transmits the inspection path of the suspected faulty equipment to the inspection device. The inspection device executes the inspection path of the suspected faulty equipment and moves to the location of the suspected faulty equipment. The inspection device captures the infrared radiation on the surface of the suspected faulty equipment in real time through the infrared detector, and converts it into an electrical signal to generate temperature distribution data of the suspected faulty equipment. The temperature distribution data of the suspected faulty equipment is substituted into a preset power equipment detection model to obtain the detection result of the temperature distribution data of the suspected faulty equipment. If the detection result of the temperature distribution data of the suspected faulty equipment is abnormal, the suspected faulty equipment is determined to be a faulty equipment.

2. The multi-scenario intelligent thermal imaging abnormal state integrated management system according to claim 1, characterized in that: The data acquisition module is further used for: Collect real-time operating data of power equipment, which includes current parameters, voltage parameters, power parameters and temperature data on the surface of the equipment. Input the real-time operating data of the power equipment into a power equipment operating status prediction model. Through calculation of the power equipment operating status prediction model, output the real-time power equipment operating monitoring results. The real-time power equipment operating monitoring results include whether the power equipment is in a normal operating state or an abnormal state.

3. The multi-scenario intelligent thermal imaging abnormal state integrated management system according to claim 1, characterized in that: The equipment monitoring module is also used for: If the equipment operating status is predicted to be abnormal, the system will feed back the real-time power equipment operation monitoring results to the corresponding monitoring system of the management personnel. The equipment monitoring module will continuously collect real-time power equipment operation data and monitor the power equipment operating status in real time. All collected real-time power equipment operation data and the results output by the power equipment operation status prediction model will be recorded and saved by the system.

4. The multi-scenario intelligent thermal imaging abnormal state integrated management system according to claim 1, characterized in that: The fault classification module is further used for: Retrieve the device identity information and temperature safety value corresponding to the abnormal operation of the power equipment, determine the device to be detected according to the device identity information corresponding to the abnormal operation of the power equipment, retrieve the real-time temperature data of the device to be detected, and compare the real-time temperature data of the device to be detected with the temperature safety value of the power equipment; If the real-time temperature data of the device to be detected exceeds the temperature safety value of the power equipment, the device to be detected will be marked as a suspected faulty device.

5. The multi-scenario intelligent thermal imaging abnormal state integrated management system according to claim 1, characterized in that: The faulty device determination module is further used for: The location data of the suspected faulty device and the location information of the current inspection device are substituted into the preset inspection path generation model. The inspection path generation model calculates the optimal inspection path based on the geographical location of the device, the current location of the inspection device and the path obstacles. The inspection path generation model calculates the optimal path from the current location of the inspection device to the location of the suspected faulty device through the path optimization algorithm, and outputs the calculated inspection path. The inspection device will move to the location of the suspected faulty device according to the inspection path.

6. The multi-scenario intelligent thermal imaging abnormal state integrated management system according to claim 1, characterized in that: The fault inspection unit is also used for: The inspection path of the suspected faulty equipment is transmitted to the inspection device. The inspection device moves to the location of the suspected faulty equipment according to the path, and uses an infrared detector to capture the infrared radiation on the surface of the suspected faulty equipment in real time, and converts the infrared radiation on the surface of the suspected faulty equipment into an electrical signal to generate temperature distribution data of the suspected faulty equipment. The temperature distribution data is substituted into a preset power equipment detection model. The preset power equipment detection model processes the temperature distribution data and outputs the detection result to determine whether there is an abnormality in the detection result. If the detection result is abnormal, the suspected faulty equipment is faulty and the suspected faulty equipment is determined to be a faulty equipment.

7. The multi-scenario intelligent thermal imaging abnormal state integrated management system according to claim 6, characterized in that: The fault inspection unit is also used for: Receive temperature data collected by a sensor installed on the suspected faulty device, compare the temperature data collected by the sensor on the suspected faulty device with the temperature distribution data of the suspected faulty device, and obtain temperature error data of the suspected faulty device; Retrieve the temperature safety range value corresponding to the suspected faulty device, and compare the temperature safety range value corresponding to the suspected faulty device with the temperature error data of the suspected faulty device. If the temperature error data of the suspected faulty device exceeds the temperature safety range value corresponding to the suspected faulty device, determine the sensor installed on the suspected faulty device as a faulty sensor. Use inspection equipment to continuously collect temperature data of equipment installed with fault sensors, obtain temperature data of equipment corresponding to the fault sensors, collect operating equipment status data of equipment corresponding to the fault sensors, train a neural network model with the operating equipment status data of equipment corresponding to the fault sensors and the temperature data of equipment corresponding to the fault sensors, obtain a fault equipment prediction model, use the fault equipment prediction model to continuously monitor the faulty equipment, use inspection equipment to continue collecting temperature data of equipment corresponding to the fault sensors, obtain temperature data to be processed, transmit the temperature data to be processed to the fault equipment prediction model, output the fault equipment prediction result, and if the fault equipment prediction result is that a fault exists, generate fault equipment warning information.

Images