Comprehensive risk monitoring method and system for transformer substation

Abstract

The invention relates to the technical field of computer platform load balancing, and discloses a comprehensive risk monitoring method and system for a transformer substation, and the method comprises the steps: collecting first feature data of target equipment; performing anomaly detection on the first feature data, and triggering a dynamic acquisition mechanism according to an anomaly detection result to obtain supplementary data; and constructing an anomaly evaluation model based on the first feature information and the supplementary data, performing quantitative evaluation on the target equipment, and outputting a risk monitoring report. According to the method, feature data of target equipment are collected in real time, anomaly detection is carried out, a dynamic collection strategy is triggered based on a detection result, and supplementary collection is carried out on appearance and environment data of the target equipment. The dynamic acquisition strategy adjusts the acquisition priority and frequency in real time according to the risk level, so that the acquired data is more accurate and targeted, the comprehensiveness and timeliness of equipment state monitoring are ensured, and the accuracy of risk assessment and the efficiency and safety of substation operation and maintenance are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid security monitoring, and in particular to a comprehensive risk monitoring method and system for a substation. Background Art

[0002] With the continuous expansion of the scale of power systems and the increase in the complexity of power grid operation, substations, as important nodes of power systems, have a direct impact on the safety and stability of the power grid through their operating status. Traditional substation monitoring methods mainly rely on manual inspections and regular maintenance. However, with the increase in the number and types of substation equipment, manual inspections can no longer meet the requirements of modern power grids for real-time monitoring and rapid response to faults. At the same time, traditional methods are difficult to achieve in-depth analysis of the operating status of equipment and cannot accurately predict the potential risks of equipment. In recent years, with the rapid development of sensor technology, communication technology, data mining and artificial intelligence technology, substation management systems based on comprehensive monitoring have gradually become a hot topic in research and application. Many scholars have proposed solutions to use sensor networks to collect equipment operating data and combine big data analysis technology to evaluate the health status of equipment. These technologies have achieved certain results in improving monitoring efficiency and data accuracy.

[0003] Although the existing technology has improved the monitoring and management level of substations to a certain extent, there are still many shortcomings. For example, the existing technology focuses on the monitoring of a single parameter of the equipment and lacks the ability to comprehensively analyze multiple parameters, resulting in low accuracy of abnormal detection and common false alarms and missed reports. In addition, traditional monitoring systems pay less attention to environmental parameters, while environmental changes have a significant impact on the operation of substation equipment. For example, excessive humidity may cause the insulation performance of equipment to decline, and abnormal temperature may cause equipment overload or even failure. However, the existing monitoring technology is still not perfect in the research of equipment and environment coordinated monitoring, risk warning, and intelligent inspection. In addition, although video surveillance technology has been applied in substation management, it is mostly limited to post-analysis and has not been fully combined with real-time risk monitoring. Therefore, it is difficult for existing technologies to fully meet the needs of modern substations for comprehensive risk monitoring. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: due to the complexity of the substation operating environment and the diversity of equipment, manual inspection of substations has low inspection efficiency and is prone to inspection blind spots or missed inspections, making it difficult to meet efficient and accurate monitoring needs.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a comprehensive risk monitoring method for a substation, comprising: collecting first characteristic data of a target device; performing anomaly detection on the first characteristic data, triggering a dynamic collection mechanism according to the anomaly detection result, and obtaining supplementary data; constructing an anomaly assessment model based on the first characteristic information and the supplementary data, performing quantitative assessment on the target device, and outputting a risk monitoring report.

[0007] As a preferred solution of the comprehensive risk monitoring method for substations described in the present invention, wherein: the first characteristic data includes real-time operation data, historical operation data and design data of the target equipment.

[0008] As a preferred solution of the comprehensive risk monitoring method for substations described in the present invention, the dynamic collection mechanism includes collecting supplementary data of the target device through a dynamic collection device; the supplementary data includes real-time monitoring information of the appearance of the target device and environmental data around the target device.

[0009] As a preferred solution of the comprehensive risk monitoring method for substations described in the present invention, the abnormality assessment model includes an operating status model constructed based on the first characteristic data and an environmental impact model constructed based on the supplementary data; the abnormality assessment model is formed by fusing the operating status model with the environmental impact model.

[0010] As a preferred solution of the comprehensive risk monitoring method for substations described in the present invention, the abnormal detection results are also used to generate a dynamic collection strategy; the dynamic collection strategy includes the collection priority sorting of the target device and the adjustment of the collection frequency of the supplementary data; the dynamic collection strategy is updated in real time according to the risk level of the target device.

[0011] As a preferred solution of the comprehensive risk monitoring method for substations described in the present invention, the abnormality detection includes but is not limited to setting a normal operating threshold through the historical operating data and design data of the target equipment; comparing the real-time operating data with the normal operating threshold for abnormality detection, and judging the abnormality level according to the degree of deviation of the real-time operating data from the normal operating threshold.

[0012] As a preferred solution of the comprehensive risk monitoring method for substations described in the present invention, the dynamic collection mechanism also includes: using dynamic collection equipment to carry out targeted collection of environmental data around the target equipment; associating the collected environmental data with the first characteristic data of the target equipment; based on the associated data, analyzing the degree of influence of environmental factors on the operating status of the target equipment; when the degree of influence exceeds a preset threshold, triggering an environmental risk warning, and marking it in the risk monitoring report.

[0013] A comprehensive risk monitoring system for a substation using any of the methods described in the present invention, wherein: an acquisition module acquires first characteristic data of a target device through a fixed sensor, pre-processes the first characteristic data and uploads it to an anomaly detection module; an anomaly detection module performs anomaly detection on the first characteristic data, triggers a dynamic acquisition mechanism according to the anomaly detection result, and acquires supplementary data of the target device through a dynamic acquisition device; an evaluation module constructs an anomaly evaluation model based on the first characteristic data and the supplementary data, performs quantitative evaluation on the target device, determines the risk level of the target device according to the quantitative evaluation result, and outputs a risk monitoring report.

[0014] A computer device comprises: a memory and a processor; the memory stores a computer program, comprising: the steps of implementing any one of the methods of the present invention when the processor executes the computer program.

[0015] A computer-readable storage medium stores a computer program, comprising: when the computer program is executed by a processor, the steps of implementing any one of the methods of the present invention are implemented.

[0016] Beneficial effects of the present invention: The method of the present invention collects the characteristic data of the target equipment in real time and performs anomaly detection. The dynamic collection strategy is triggered based on the detection results to supplement the collection of the appearance and environmental data of the target equipment. The dynamic collection strategy adjusts the collection priority and frequency in real time according to the risk level, making the collected data more accurate and targeted, ensuring the comprehensiveness and timeliness of equipment status monitoring, thereby improving the accuracy of risk assessment and the efficiency and safety of substation operation and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0018] Figure 1 An overall flow chart of a comprehensive risk monitoring method for a substation provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0020] Example 1, reference Figure 1 , as an embodiment of the present invention, provides a comprehensive risk monitoring method for a substation, comprising:

[0021] S1: Collect first characteristic data of the target device.

[0022] The target device is a key object whose operation data can be collected and coupled with environmental data, such as industrial equipment, power equipment, transportation facilities, etc. In this embodiment, the target device is a device in a substation, and the first characteristic data includes real-time operation data, historical operation data and design data of the target device.

[0023] Specifically, high-precision sensors are used to collect real-time operating data of equipment in the substation, including but not limited to key parameters such as voltage, current, temperature, and vibration frequency, to reflect the immediate operating status of the target equipment; historical data is based on the long-term operating records of the target equipment, and key indicator data from historical operations are extracted; design data includes basic information such as the rated power, insulation level, mechanical structure characteristics, and design life of the target equipment, which is used to clarify the upper limit and design goals of the equipment design capability.

[0024] Perform preprocessing such as data denoising to ensure the accuracy and reliability of the data, use efficient and reliable wireless or wired communication methods to transmit the preprocessed data to the system terminal in real time, and classify and store the data.

[0025] In an optional embodiment, the first characteristic information may also be data of rotating mechanical equipment (such as centrifugal pumps and compressors). Specifically, real-time operation data includes speed, bearing temperature, and vibration amplitude; historical operation data includes past fault records and maintenance data; design data includes characteristic parameters such as equipment power and rotor mass. Data is collected through vibration sensors, temperature sensors, and speed sensors, and pre-processed in conjunction with edge computing units.

[0026] S2: Perform anomaly detection on the first feature data, trigger a dynamic collection mechanism according to the anomaly detection result, and obtain supplementary data.

[0027] The anomaly detection includes setting thresholds for each monitoring parameter based on equipment design data and historical data. When a monitoring parameter exceeds or falls below the threshold, it is considered that the equipment may be abnormal; the evaluation results of each monitoring parameter, including but not limited to whether the threshold is exceeded and the degree of deviation, are weighted and summed according to weights to obtain a comprehensive score for the equipment. The higher the score, the worse the equipment status; and according to the comprehensive score, the equipment is divided into different operating status levels, including but not limited to normal, attention, warning, danger, etc.

[0028] It should be noted that anomaly detection is a key step, and its connotation lies in the real-time analysis of the operating status of the target equipment. Setting the upper and lower thresholds of the monitoring parameters has statistical and engineering rationality. Based on the statistical analysis of historical data (such as maximum value, minimum value, average value, standard deviation) and the designed operating range of the equipment, the normal range of dynamic operation can be reasonably set. The weighted sum comprehensive scoring mechanism takes into account the differences in the importance of different monitoring parameters on the equipment status by introducing weights, making the detection results more scientific.

[0029] Furthermore, an analysis is performed based on the result of the abnormality detection. Specifically, taking the four levels of normal, attention, warning, and danger as an example, when the abnormality detection result is normal, it means that the target device is normal and no additional operation is performed.

[0030] When the anomaly detection result is caution, it means that the target device data slightly deviates from the normal operating range of historical data, but is still within a reasonable range. The frequency of data collection is increased, and the dynamic collection mechanism is optionally triggered. No early warning is issued, and further analysis is performed in combination with the anomaly assessment model results.

[0031] When the anomaly detection result is a warning, it means that the target device data has deviated from the data range during normal operation, triggering the dynamic collection mechanism and issuing a warning, which is further analyzed in combination with the anomaly assessment model results.

[0032] When the abnormal detection result is dangerous, it means that the data of the target device deviates significantly from the normal operating data range, triggering the dynamic collection mechanism and taking emergency measures. If permitted, the power supply of the target device can be directly cut off to prevent further damage and an emergency alarm can be issued.

[0033] Furthermore, the anomaly detection result is also used to generate a dynamic collection strategy; the dynamic collection strategy includes collection priority sorting of the target device and adjustment of the collection frequency of the supplementary data; the dynamic collection strategy is updated in real time according to the risk level of the target device.

[0034] The dynamic collection mechanism collects supplementary data of the target device through the dynamic collection device; the supplementary data includes real-time monitoring information of the appearance of the target device and environmental data around the target device. In this embodiment, the dynamic collection mechanism is linked to the environmental sensor through the inspection robot. When the device is detected to be abnormal, the inspection robot moves to the abnormal area and collects data through the built-in sensors (such as temperature and humidity detectors, gas analyzers), and combines cameras or infrared imaging to perform regional environmental analysis.

[0035] Intelligent inspection robots automatically complete the inspection tasks of equipment in the substation, replacing manual inspections and improving inspection efficiency and safety. At the same time, the system conducts all-round video monitoring of the substation, combined with infrared imaging technology, to promptly discover and deal with potential safety hazards, thereby avoiding accidents. The environmental parameter monitoring module monitors the air oxygen content, noise, temperature, humidity and other environmental parameters in the substation in real time, making it convenient for on-duty personnel to grasp the equipment operation status and environmental parameters in a timely manner.

[0036] The dynamic collection mechanism also includes using dynamic collection equipment to carry out targeted collection of environmental data around the target device; associating the collected environmental data with the first characteristic data of the target device; based on the associated data, analyzing the degree of influence of environmental factors on the operating status of the target device; when the degree of influence exceeds a preset threshold, triggering an environmental risk warning and marking it in a risk monitoring report.

[0037] In an optional embodiment, the dynamic collection mechanism can also be a multi-point collaborative dynamic collection network, which is used to cover a wide area of ​​complex traffic scenes to achieve efficient and accurate data collection. Specifically, in an intelligent traffic environment, the dynamic collection mechanism quickly responds to abnormal traffic conditions through the collaborative work of multiple dynamic collection devices (such as drones, inspection robots, roadside units RSU, etc.) to complete real-time data collection and analysis.

[0038] S3: Build an abnormality assessment model based on the first feature information and the supplementary data, perform quantitative assessment on the target device, and output a risk monitoring report.

[0039] The construction of the abnormal assessment model includes two parts: the operating status model and the environmental impact model. The operating status model is constructed based on the first feature data (including real-time operating data, historical operating data and design data), extracts key parameters through statistical analysis, and establishes the operating status feature space of the target equipment in combination with the machine learning algorithm to accurately describe the normal operating range and abnormal change trend of the equipment.

[0040] The environmental impact model is constructed through supplementary data collected by the dynamic collection mechanism (including real-time monitoring information of equipment appearance and environmental data), and uses multivariate regression or causal analysis algorithms to quantify the impact of environmental factors (such as temperature, humidity, noise, etc.) on the operating status of the equipment.

[0041] Finally, the operation status model and the environmental impact model are combined through data fusion technology to form an abnormality assessment model.

[0042] Furthermore, based on the quantitative assessment results of the abnormal assessment model, the system generates a risk monitoring report, including a comprehensive risk score, equipment operating status classification results, abnormal parameters and environmental risk analysis, and disposal recommendations.

[0043] The content in the report not only helps the operation and maintenance personnel understand the current status of the equipment, but also provides specific handling instructions, such as equipment maintenance suggestions or environmental control solutions, which improves the efficiency and accuracy of problem solving. In an optional embodiment, the anomaly assessment model can also be combined with time series analysis technology (such as dynamic time warping algorithm or LSTM neural network) to predict the future operation trend of the equipment, thereby achieving early warning of potential risks.

[0044] Example 2, the following is an embodiment of the present invention, which provides a comprehensive risk monitoring method for a substation.

[0045] Scenario: Real-time operation monitoring of key equipment (such as transformers, circuit breakers, etc.) is required in substations to ensure that the equipment operating status meets the design requirements.

[0046] The real-time operation data of the target equipment, including key parameters such as current, voltage, temperature and vibration frequency, are collected through high-precision sensors. Combined with the historical operation data of the equipment (such as past fault records and maintenance data) and design data (such as rated power and insulation level), a complete first feature data set is formed. The collected data is denoised and classified and stored at the system terminal to provide a basis for subsequent analysis. Results: The integration of multi-dimensional equipment operation status data is completed, ensuring the accuracy of subsequent analysis.

[0047] During the operation of a substation, the operating parameters of a circuit breaker fluctuate, and it is necessary to determine whether it has a potential fault.

[0048] Rule setting:

[0049] The voltage fluctuation range is ±5% of the rated value;

[0050] The vibration amplitude is outside the normal range (based on the historical standard deviation, within 3 times is normal).

[0051] Execution process:

[0052] Based on the first characteristic data, the system sets the threshold of key parameters and analyzes the real-time operation data through the abnormal detection module. When the vibration amplitude of the circuit breaker exceeds the normal range and the voltage fluctuation deviates from the set value, the system will perform a weighted summation based on the degree of excess to generate a comprehensive score. The score shows that the risk of the equipment is at the "warning" level.

[0053] The abnormal detection results trigger a dynamic collection mechanism to collect supplementary data, including real-time monitoring information of the equipment casing temperature and humidity and noise data of the environment where the circuit breaker is located.

[0054] Furthermore, a quantitative risk assessment is conducted on the circuit breakers that trigger the anomaly, and a monitoring report is generated. The impact of humidity on insulation performance in the supplementary data is combined with real-time operation data and historical fault records, and an anomaly assessment model is constructed by integrating the operation status model with the environmental impact model. The system calculates a comprehensive risk score of 85, indicating that the equipment is in a "warning" state, and recommends that the on-duty personnel arrange an inspection immediately and cut off the power supply of the equipment if necessary to prevent the spread of the fault. The monitoring report provides detailed causes of the anomaly, including abnormal vibration amplitude, increased humidity, etc., and gives corresponding treatment suggestions.

[0055] The generated risk monitoring report helps operation and maintenance personnel to quickly locate problems and take targeted maintenance measures to avoid further damage to the equipment.

[0056] Embodiment 3: In an exemplary embodiment, a comprehensive risk monitoring system for a substation is also provided, including a collection module, an anomaly detection module and an evaluation module.

[0057] The acquisition module acquires the first characteristic data of the target device through a fixed sensor, pre-processes the first characteristic data and uploads it to the anomaly detection module.

[0058] The anomaly detection module performs anomaly detection on the first feature data, triggers a dynamic collection mechanism according to the anomaly detection result, and collects supplementary data of the target device through a dynamic collection device.

[0059] The evaluation module builds an abnormal evaluation model based on the first characteristic data and the supplementary data, performs quantitative evaluation on the target device, determines the risk level of the target device according to the quantitative evaluation result, and outputs a risk monitoring report.

[0060] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0061] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0062] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0063] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0064] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A comprehensive risk monitoring method for a substation, characterized in that: include: Collecting first characteristic data of the target device; Perform anomaly detection on the first feature data, trigger a dynamic collection mechanism according to the anomaly detection result, and obtain supplementary data; An abnormality assessment model is constructed based on the first characteristic information and supplementary data, a quantitative assessment is performed on the target device, and a risk monitoring report is output.

2. The comprehensive risk monitoring method for a substation according to claim 1, characterized in that: The first characteristic data includes real-time operation data, historical operation data and design data of the target device.

3. The comprehensive risk monitoring method for a substation according to claim 2, characterized in that: The dynamic collection mechanism includes collecting supplementary data of the target device through a dynamic collection device; The supplementary data includes real-time monitoring information of the appearance of the target device and environmental data around the target device.

4. The comprehensive risk monitoring method for a substation according to claim 3, characterized in that: The abnormality assessment model includes an operation status model constructed based on the first characteristic data and an environmental impact model constructed based on the supplementary data; An abnormality assessment model is formed by fusing the operating status model with the environmental impact model.

5. The comprehensive risk monitoring method for a substation according to claim 4, characterized in that: The anomaly detection results are also used to generate dynamic acquisition strategies; The dynamic collection strategy includes collection priority sorting of target devices and adjustment of collection frequency of supplementary data; Dynamic collection strategies are updated in real time based on the risk level of the target device.

6. The comprehensive risk monitoring method for a substation according to claim 1, characterized in that: The abnormality detection includes, but is not limited to, setting a normal operation threshold through historical operation data and design data of the target device; The real-time operation data is compared with the normal operation threshold to detect anomalies, and the anomaly level is determined based on the degree to which the real-time operation data deviates from the normal operation threshold.

7. The comprehensive risk monitoring method for a substation according to claim 6, characterized in that: The dynamic collection mechanism also includes using a dynamic collection device to perform directional collection of environmental data around the target device; Associating the collected environmental data with first characteristic data of the target device; Based on the associated data, analyze the impact of environmental factors on the operating status of the target equipment; When the impact exceeds the preset threshold, an environmental risk warning is triggered and marked in the risk monitoring report.

8. A comprehensive risk monitoring system for a substation using any of the methods of claims 1 to 7, characterized in that: include, A collection module, which collects first characteristic data of a target device through a fixed sensor, pre-processes the first characteristic data and uploads it to an anomaly detection module; an anomaly detection module, performing an anomaly detection on the first feature data, triggering a dynamic collection mechanism according to the anomaly detection result, and collecting supplementary data of the target device through a dynamic collection device; The evaluation module builds an abnormal evaluation model based on the first characteristic data and the supplementary data, performs quantitative evaluation on the target device, determines the risk level of the target device according to the quantitative evaluation result, and outputs a risk monitoring report.

9. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the comprehensive risk monitoring method for a substation as described in any one of claims 1-7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the comprehensive risk monitoring method for a substation as described in any one of claims 1 to 7 are implemented.

Images