Intelligent substation equipment monitoring and fault diagnosis system

Abstract

The invention relates to an intelligent substation equipment monitoring and fault diagnosis system which comprises a data acquisition module, an equipment operation data influence factor assignment module, a comprehensive dynamic coefficient calculation module, a threshold calculation module, an abnormal equipment information judgment output module and a user interface display module. The method fully considers the influence of external factors such as the environment on the operation of the substation equipment, can achieve the refined abnormality diagnosis according to the factors such as the equipment type and the operation environment, accurately judges the operation stability of the equipment, and facilitates the subsequent targeted maintenance measures for the substation equipment.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent substation equipment maintenance, and particularly relates to an intelligent substation equipment monitoring and fault diagnosis system. Background Art

[0002] In the power system, substation equipment is an important part of power transmission and distribution. Its normal operation is crucial for ensuring the stable operation and safe power supply of the power system. However, due to factors such as a large number of substation equipment, harsh working environments, and wear and aging caused by long-term operation, equipment failures and outages are common problems. Especially in high-voltage power grids, once an equipment failure occurs, it often leads to serious power accidents and economic losses. Therefore, it is necessary to monitor substation equipment and determine whether there are faults in power equipment.

[0003] The Chinese invention patent with the publication number CN109034424A discloses a substation equipment maintenance management method, device, and terminal equipment, which discloses a method for determining whether there are faults in power equipment, that is: obtaining the historical power consumption data of power equipment, and obtaining the predicted power consumption data of power equipment according to the historical power consumption data; subtracting the predicted power consumption data from the current equipment power consumption data to obtain a power consumption difference; if the power consumption difference is greater than a preset power consumption difference threshold, it is determined that there are faults in the power equipment.

[0004] The above-mentioned prior art has the following defects: it ignores the influence of external factors such as environmental changes, equipment startup and shutdown on power consumption fluctuations. When the equipment operating environment and conditions change, when predicting faults through historical power consumption data and predicted power consumption data, the historical power consumption model may fail, resulting in inaccurate judgments or false alarms. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to make up for the deficiencies of the prior art and provide an intelligent substation equipment monitoring and fault diagnosis system.

[0006] To solve the above technical problem, the technical solution of the present invention is as follows:

[0007] An intelligent substation equipment monitoring and fault diagnosis system, comprising

[0008] A data acquisition module: including a SCADA system and an environmental detection system. The SCADA system is used to collect the operating status, operating parameters, and operating data of each substation equipment, and the environmental detection system is used to obtain the environmental information where each substation equipment is located;

[0009] An equipment operating data influencing factor assignment module: for each substation equipment, determine the influencing factors affecting each type of its operating data, and assign a weight value W to each influencing factor j, where \(j\in[1,k]\), \(k\) is the number of influencing factors, and \(j\) represents the \(j\)th influencing factor;

[0010] Comprehensive dynamic coefficient calculation module: For each type of operation data of each substation device, calculate the comprehensive dynamic coefficient: where \(P\) s is the real-time operation data of this type of operation data of this substation device, and \(P_0\) is the average value of this type of operation data of this substation device during the normal operation stage;

[0011] Threshold calculation module: For each substation device, during its normal operation stage, for each type of operation data, collect multiple operation data within a period of time, and calculate the mean and standard deviation of these operation data; obtain the fault warning threshold \([F\) g1 , \(F\) g2 of this type of operation data of this substation device through the mean and standard deviation;

[0012] Abnormal device information judgment and output module: If the comprehensive dynamic coefficient of any type of operation data of a certain substation device y , then mark this comprehensive dynamic coefficient \(DT\) as an abnormal comprehensive dynamic coefficient \(DT\), determine that this substation device is a faulty device, and output an alarm message;

[0013] User interface display module: Used for human-computer interaction and display of the operation status, operation parameters, operation data, dynamic anomaly coefficient, and alarm information of each substation device.

[0014] Furthermore, the environmental information includes temperature, humidity, wind speed, air pressure, vibration, and noise.

[0015] Furthermore, the diagnostic method includes the following steps:

[0016] Step S1: Use the SCADA system of the data acquisition module to collect the operation status, operation parameters, and operation data of each substation device in real time, and use the environmental detection system to obtain the environmental information of each substation device in real time;

[0017] Step S2: Obtain the comprehensive dynamic coefficient \(DT\) of each type of operation data of each substation device through the comprehensive dynamic coefficient calculation module;

[0018] Step S3: Obtain the operation data mean and standard deviation of each type of operation data of each substation device during the normal operation stage through the threshold calculation module; obtain the fault warning threshold \([F\) g1 , \(F\) g2 of this type of operation data of this substation device through the mean and standard deviation;

[0019] Step S4: The device operation data influence factor assignment module assigns a weight value W to each influence factor of each operation data type of each substation device j ;

[0020] Step S5: The abnormal device information judgment output module judges that if there is a comprehensive dynamic coefficient of any operation data type of a certain substation device then mark this comprehensive dynamic coefficient DT as an abnormal comprehensive dynamic coefficient DT y , judge that this substation device is a faulty device, and output an alarm message;

[0021] Step S6: The user interface display module outputs the operation status, operation parameters, operation data, dynamic anomaly coefficient and alarm information of each substation device.

[0022] Furthermore, in step S4, the collection method of the operation data is the sliding window method, that is:

[0023] During the normal operation stage of this substation device, in chronological order, for the operation data output window of this operation data type, N windows are selected, each window includes n operation data, and each operation data is represented by x i denoted as, i ∈ [1, n]; for the g-th window, calculate the mean μ g and standard deviation S g ,

[0024] Through μ g and S g obtain the anomaly coefficient CV of this window g ,

[0025] Calculate the mean value μ of the anomaly coefficients of N windows Z and the mean value S of the standard deviations Z ,

[0026]

[0027] In the fault alarm threshold [F g1 , F g2 , F g1 = μ Z - εS Z , F g2 = μ Z + εS Z , where ε is a weighting coefficient, 1 < ε < 5.

[0028] Furthermore, it also includes a warning threshold [F y1 , Fy2 , F y1 > F g1 , F y2 < F g2 .

[0029] Further, it further includes a device fault information judgment and fault information database establishment module, which is used to record the fault information of faulty devices, and when a device in a certain substation fails, analyze the abnormal comprehensive dynamic coefficient DT y The correlation relationship between the corresponding operation data and its influencing factors; if the device in this substation fails continuously twice, and DT y is strongly correlated with the jth influencing factor continuously twice, then the weight value W j of the jth influencing factor is corrected to obtain the corrected weight value of the jth influencing factor where α is a working condition adjustment coefficient; the obtained is given to the corresponding W j in the device operation data influencing factor assignment module, so that

[0030] The beneficial effects that the present invention can achieve are as follows: By introducing the comprehensive dynamic coefficient, the influence of external factors such as the environment on the operation of substation equipment is fully considered, and refined abnormal diagnosis can be realized according to factors such as equipment type and operation environment, accurately judging the operation stability of the equipment, and helping to take maintenance measures for substation equipment in a targeted manner subsequently. Description of the Drawings

[0031] Figure 1 is the overall flow schematic diagram of this embodiment.

[0032] Figure 2 is the flow schematic diagram of the threshold calculation module in this embodiment.

[0033] Figure 3 is the flow schematic diagram of the abnormal device information output module, device fault information judgment and fault information database establishment module in this embodiment. Detailed Embodiments

[0034] The present invention will be further described in detail below with reference to the drawings and specific embodiments.

[0035] An intelligent substation equipment monitoring and fault diagnosis system includes a data acquisition module, a device operation data influencing factor assignment module, a comprehensive dynamic coefficient calculation module, a threshold calculation module, an abnormal device information judgment and output module, a device fault information judgment and fault information database establishment module, and a user interface display module.

[0036] Data acquisition module: It includes a SCADA system and an environmental detection system. The operating status, operating parameters, and operating data of each substation equipment are collected through the SCADA system. The substation equipment includes substation core equipment, high-risk equipment, and auxiliary equipment. The substation core equipment includes transformers, circuit breakers, instrument transformers, switchgear, etc.; the high-risk equipment includes old equipment, outdoor exposed equipment, high-load equipment, environment-sensitive equipment, etc., and the auxiliary equipment includes standby power supplies, cooling systems, auxiliary instruments, etc. The environmental detection system is used to obtain the environmental information where each substation equipment is located, such as temperature, humidity, wind speed, air pressure, vibration, and noise.

[0037] Equipment operation data influencing factor assignment module: For each substation equipment, determine the influencing factors affecting each type of its operation data, and assign a weight value W to each influencing factor j , j ∈ [1, k], where k is the number of influencing factors, and j represents the jth influencing factor.

[0038] First, initially determine the weight of each equipment affected by influencing factors according to the engineering standards and specifications of different equipment types and the factory information when the equipment leaves the factory (factors that affect the actual operation of the equipment provided by the equipment manufacturer or national specifications), as shown in the following table:

[0039] Table 1: Distribution table of weight values of influencing factors for the secondary side voltage of voltage transformers

[0040]

[0041]

[0042] Comprehensive dynamic coefficient calculation module: For each type of operation data of each substation equipment, calculate the comprehensive dynamic coefficient: Among them, P s is the real-time operation data of this type of operation data during the stable operation process after the commissioning acceptance of this substation equipment, and P0 is the average value of this type of operation data of this substation equipment during the normal operation stage. After the equipment fails, after the maintenance personnel calibrate the equipment, the maintenance personnel can customize a period of time according to the standard, or according to the system automatically identify the average value P0 of the data when the equipment reaches the stable operation state. That is, a new P0 is set every time the equipment is repaired after a failure.

[0043] Threshold calculation module: For each substation equipment, during its normal operation stage, for each type of operation data, collect multiple operation data within a period of time, calculate the mean and standard deviation of these operation data; obtain the fault warning threshold [F g1 , F g2 of this type of operation data of this substation equipment through the mean and standard deviation. Specifically as follows:

[0044] During the normal operation stage of the substation equipment, the sliding window method is used to collect operation data. According to the time sequence, for the operation data output window of this type of operation data, N windows are sorted out. Each window includes n operation data, and each operation data is represented by x i where i ∈ [1, n]; the size of the sliding window is determined according to the equipment standard and actual on-site experience, as shown in the following table:

[0045] Table 2: Example of data collection by the sliding window method

[0046]

[0047] For the g-th window, calculate the mean μ g and the standard deviation S g of the operation data within this window, and obtain the anomaly coefficient CV g of this window through μ g and S g .

[0048] Calculate the mean μ Z of the anomaly coefficients of the N windows and the mean S Z of the standard deviations,

[0049]

[0050] In the fault alarm threshold [F g1 , F g2 , F g1 = μ Z - εS Z , F g2 = μ Z + εS Z , where ε is a weighting coefficient and 1 < ε < 5. The value of ε should satisfy that when a fault occurs, all the corresponding comprehensive dynamic coefficients DT fall within the interval [F g1 , F g2 . For example: F g1 = μ Z - 3S Z , F g2 = μ Z + 3S Z .

[0051] It also includes the early warning threshold [F y1 , F y2 , where F y1 > F g1 , F y2 < F g2 . For example: Fy1 = μ Z - 2S Z , F y2 = μ Z + 2S Z .

[0052] Early warning threshold [F y1 , F y2 is the first - level threshold, [F g1 , F g2 is the second - level threshold, and the weighting coefficient ε can be adjusted according to the type of substation equipment.

[0053] At the same time, a dynamic adjustment strategy is adopted for the window, as follows:

[0054] 1. Adaptive adjustment based on working conditions

[0055] Load change: When the equipment is running at high load, shorten the window (for example, the transformer current monitoring window is adjusted from 5 minutes to 1 minute).

[0056] Environmental anomaly: In high - temperature and high - humidity environments, shorten the oil - temperature monitoring window (for example, from 30 minutes to 10 minutes).

[0057] Adaptive adjustment based on data distribution

[0058] 2. Abnormal coefficient CV g Trigger:

[0059] If the CV g value suddenly increases (such as exceeding 2 times the historical average), automatically shrink the subsequent window to 1 / 2 of the original size.

[0060] If the CV g value is stable (such as the CV g value fluctuates within ±10% for 10 consecutive windows), restore the original window size.

[0061] 3. Manual intervention rules

[0062] Operation and maintenance experience library: According to historical fault records, manually lock the window size for a specific period (for example, fix the shortening of the lightning arrester monitoring window during the thunderstorm season).

[0063] The window setting verification and optimization process is as follows:

[0064] 1. Historical data backtesting

[0065] Use historical data for 1 - 3 months to test the abnormal detection rate and false - alarm rate under different window sizes.

[0066] Optimization goal: Select the window size that maximizes the F1 - score (the harmonic mean of precision and recall).

[0067] 2. Real-time feedback and optimization

[0068] A / B testing: Run different window configurations in parallel and compare the detection effects (e.g., window A = 5 minutes vs window B = 10 minutes).

[0069] Dynamic weight update: Adjust the window parameters through reinforcement learning based on real-time detection results.

[0070] 3. Resource constraint check

[0071] Computing load assessment: Ensure that the system processing delay does not exceed the set threshold (e.g., <1 second) after window reduction.

[0072] Abnormal device information judgment and output module: If the comprehensive dynamic coefficient of any one type of operation data of a substation device then mark the comprehensive dynamic coefficient DT as an abnormal comprehensive dynamic coefficient DT y , determine that the substation device is a faulty device, and output an alarm message; if DT ∈ [F g1 , F g2 , but then mark the comprehensive dynamic coefficient DT as a potential abnormal comprehensive dynamic coefficient DT q , determine that the substation device is a potential faulty device, and output a warning message to attract attention. After the maintenance personnel maintain the device, the maintenance personnel can feedback the content and method of maintenance to the system.

[0073] Device fault information judgment and fault information database establishment module: Used to record the fault information of faulty devices, and can also supplement fault information manually to ensure the integrity and accuracy of the fault information database. This module also provides query and statistical analysis functions for maintenance personnel to query the fault history and fault reasons.

[0074] In addition, when a substation device fails, analyze the correlation between the corresponding operation data of the abnormal comprehensive dynamic coefficient DT y and its influencing factors; if the substation device fails continuously twice, and DT y is continuously twice strongly correlated with the jth influencing factor, then correct the weight value W j of the jth influencing factor to obtain the corrected weight value of the jth influencing factor where α is the operating condition adjustment coefficient (the α of each type of device is strictly calculated according to the GB / T and IEC standards for the operating condition adjustment coefficient. For example, for the temperature factor, follow the national standard GB50217-2018: Temperature correction coefficient of cable ampacity (Appendix D)). Assign the obtained to the corresponding W j in the device operation data influencing factor assignment module, so that

[0075] Before assigning values to the influencing factors of the device operation data in the device operation data influencing factor assignment module the system first simulates changing W in the background j while keeping the weight values of the influencing factors of the actual operation unchanged, and performs simulation calculations on the data collected later in the background (simulating according to ), so as to calculate the factor weights most suitable for the device. After the calculation is completed, the factor weights set at the beginning are replaced to ensure that the system is continuously improved during operation.

[0076] User interface display module: used for human-computer interaction and display of the operation status, operation parameters, operation data, dynamic anomaly coefficient and alarm information of each substation device.

[0077] This module is responsible for designing and displaying the user interface, enabling users to intuitively view the real-time monitoring data of the device, the dynamic anomaly coefficients of different devices, alarm information, etc. The user interface should include a device list, monitoring data charts, abnormal device lists, alarm notifications, and query statistical analysis functions, etc., to ensure that users can conveniently monitor the operation status of the device and handle abnormal situations in a timely manner. At the same time, the user interface has a permission management function to ensure that different users can only view the device information and operation functions they have permission to, guaranteeing the security of the system and the confidentiality of data.

[0078] The diagnostic method of this embodiment includes the following steps:

[0079] Step S1: Real-time collect the operation status, operation parameters and operation data of each substation device through the SCADA system of the data collection module, and the environment detection system obtains the environmental information where each substation device is located in real time;

[0080] Step S2: Assign a weight value W to each influencing factor of each operation data type of each substation device through the device operation data influencing factor assignment module j ;

[0081] Step S3: Obtain the comprehensive dynamic coefficient DT of each operation data type of each substation device through the comprehensive dynamic coefficient calculation module;

[0082] Step S4: Obtain the operation data mean and standard deviation of each operation data type of each substation device during the normal operation stage through the threshold calculation module; obtain the fault alarm threshold [F g1 , F g2 of this operation data type of this substation device from the mean and standard deviation;

[0083] Step S5: The output module for judging by abnormal device information judges that if there is a comprehensive dynamic coefficient of any operating data type of a certain substation device then mark this comprehensive dynamic coefficient DT as an abnormal comprehensive dynamic coefficient DT y , judge that this substation device is a faulty device, and output an alarm message;

[0084] Step S6: The user interface display module outputs the operating status, operating parameters, operating data, dynamic abnormal coefficient and alarm message of each substation device.

[0085] Step S7: When a certain substation device fails, analyze the abnormal comprehensive dynamic coefficient DT through the device fault information judgment and fault information database establishment module y the correlation between the corresponding operating data and its influencing factors; if this substation device fails continuously twice, and DT y is strongly correlated with the jth influencing factor twice continuously, then the weight value W j of the jth influencing factor is corrected to obtain the corrected weight value of the jth influencing factor Then the obtained is assigned to the corresponding W in the device operating data influencing factor assignment module j , so that

[0086] The above is only one implementation manner of the present invention, and the protection scope of the present invention is not limited to the above embodiments. It should be pointed out that for those of ordinary skill in the art in this technical field, several improvements and refinements made without departing from the idea of the present invention are within the protection scope of the present invention.

Claims

1. An intelligent substation equipment monitoring and fault diagnosis system, characterized in that: including Data acquisition module: including a SCADA system and an environmental detection system. The SCADA system is used to collect the operating status, operating parameters, and operating data of each substation device, and the environmental detection system is used to obtain the environmental information of each substation device; Device operation data influencing factor assignment module: For each substation device, determine the influencing factors for each type of its operation data, and assign a weight value W to each influencing factor j , j ∈ [1, k], where k is the number of influencing factors, and j represents the j-th influencing factor; Comprehensive dynamic coefficient calculation module: For each type of operation data of each substation device, calculate the comprehensive dynamic coefficient: where P s is the real-time operation data of this type of operation data of the substation device, and P0 is the average value of this type of operation data of the substation device during the normal operation stage; Threshold calculation module: For each substation device, during its normal operation phase, for each type of operation data, collect multiple operation data over a period of time, and calculate the mean and standard deviation of these operation data; obtain the fault alarm threshold for this type of operation data of this substation device through the mean and standard deviation[F g1 ,F g2 ; Abnormal device information judgment and output module: If the comprehensive dynamic coefficient of any one type of operation data of a substation device then mark the comprehensive dynamic coefficient DT as an abnormal comprehensive dynamic coefficient DT y , determine that the substation device is a faulty device, and output an alarm message; User interface display module: used for human-computer interaction and display of the operating status, operating parameters, operating data, dynamic anomaly coefficient, and alarm information of each substation device.

2. The intelligent substation equipment monitoring and fault diagnosis system according to claim 1, characterized in that: The environmental information includes temperature, humidity, wind speed, air pressure, vibration, and noise.

3. The intelligent substation equipment monitoring and fault diagnosis system according to claim 1, characterized in that: The diagnostic method includes the following steps: Step S1: The SCADA system of the data acquisition module is used to collect the operating status, operating parameters, and operating data of each substation device in real time, and the environmental detection system is used to obtain the environmental information of each substation device in real time; Step S2: The device operation data influence factor assignment module assigns a weight value W to each influence factor of each operation data type of each substation device j ; Step S3: The comprehensive dynamic coefficient calculation module is used to obtain the comprehensive dynamic coefficient DT of each operating data type of each substation device; Step S4: Obtain the mean and standard deviation of the operation data of each operation data type of each substation device during the normal operation stage through the threshold calculation module; obtain the fault alarm threshold of this operation data type of this substation device based on the mean and standard deviation[F g1 ,F g2 ; Step S5: The output module for judging by abnormal device information judges that if there is a comprehensive dynamic coefficient of any operation data type of a substation device then mark this comprehensive dynamic coefficient DT as an abnormal comprehensive dynamic coefficient DT y , judge that this substation device is a faulty device, and output an alarm message; Step S6: The user interface display module is used to output the operating status, operating parameters, operating data, dynamic anomaly coefficient, and alarm information of each substation device.

4. The intelligent substation equipment monitoring and fault diagnosis system according to claim 3, characterized in that: In step S4, the collection method of the operating data is the sliding window method, that is: During the normal operation stage of the substation equipment, according to the time sequence, N windows are sorted out for the operation data output window of this type of operation data. Each window includes n operation data, and each operation data is represented by x i where i ∈ [1, n]; for the g-th window, calculate the mean μ g and the standard deviation S g , Through μ g and S g the anomaly coefficient CV of this window is obtained g , Calculate the mean value μ of the anomaly coefficients for N windows Z and the mean value S of the standard deviation Z , Fault alarm threshold [F g1 , F g2 , where F g1 = μ Z - εS Z , F g2 = μ Z + εS Z , and ε is a weighting coefficient, 1 < ε < 5.

5. The intelligent substation equipment monitoring and fault diagnosis system according to claim 4, characterized in that: It also includes a warning threshold [F y1 , F y2 , F y1 > F g1 , F y2 < F g2 .

6. The intelligent substation equipment monitoring and fault diagnosis system according to claim 1, wherein: It further includes a device fault information judgment and fault information database establishment module, which is used to record the fault information of faulty devices, and when a device in a certain substation fails, analyze the abnormal comprehensive dynamic coefficient DT y The correlation between the corresponding operation data and its influencing factors; if the devices in this substation fail continuously twice, and DT y is strongly correlated with the j-th influencing factor both times, then the weight value W j of the j-th influencing factor is corrected to obtain the corrected weight value of the j-th influencing factor where α is the working condition adjustment coefficient; the obtained is assigned to the corresponding W j in the device operation data influencing factor assignment module, so that

Images