Power equipment fault detection method and device, equipment and storage medium
By synchronously collecting pressure and temperature parameters at multiple points on power equipment, performing differential calculations and feature extraction, the problem of low accuracy in power equipment fault detection is solved, enabling early detection and accurate location, and improving the accuracy of fault identification.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SOUTHERN POWER GRID SENSING TECHNOLOGY (GUANGDONG) CO LTD
- Filing Date
- 2025-12-31
- Publication Date
- 2026-04-17
AI Technical Summary
Existing technologies for detecting faults in power equipment have low accuracy, especially for detecting gas leaks.
By synchronously collecting pressure and temperature parameters of power equipment from multiple points, performing differential calculations and feature extraction, and using the relationship between feature parameters such as pressure deviation slope, temperature mean and variance and preset thresholds, the fault type can be determined.
It enables early detection and accurate location of power equipment faults, improves the accuracy of fault identification, and avoids blind repairs and the expansion of power outages.
Smart Images
Figure CN121878342A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of power equipment condition monitoring technology, and in particular to a method, apparatus, equipment and storage medium for power equipment fault detection. Background Technology
[0002] In the field of power equipment condition monitoring and intelligent diagnostics, power equipment (e.g., gas-insulated switchgear (GIS) or circuit breakers (CB)) may leak sulfur hexafluoride (SF6) gas, which can lead to power equipment failure.
[0003] In traditional technology, only pressure sensors are used. By comparing the absolute pressures collected by a group of adjacent pressure sensors, common-mode temperature noise is eliminated, thereby enabling early detection of single gas leak faults.
[0004] However, the above-mentioned gas leak fault detection methods suffer from low fault detection accuracy. Summary of the Invention
[0005] Therefore, it is necessary to provide a method, apparatus, equipment, and storage medium for detecting power equipment faults that can improve the accuracy of power equipment fault detection, in response to the above-mentioned technical problems.
[0006] In a first aspect, this application provides a method for detecting faults in power equipment, including:
[0007] Acquire state parameters at multiple locations of the power equipment; state parameters include pressure and temperature values.
[0008] Perform difference operations on the state parameters at multiple locations to determine the difference parameters at multiple locations;
[0009] Feature extraction is performed on the difference parameters at multiple locations to obtain the feature parameters corresponding to the difference parameters at multiple locations;
[0010] The fault type of the power equipment is determined based on the relationship between the characteristic parameters and the preset state threshold.
[0011] In one embodiment, the above-described feature extraction of the difference parameters at multiple locations to obtain feature parameters corresponding to the difference parameters at multiple locations includes:
[0012] If the state parameter is a pressure value, linear regression is performed on the difference parameters at multiple locations to obtain the pressure deviation slope of the power equipment.
[0013] If the state parameter is a temperature value, the mean value of the difference parameter at multiple locations is obtained by averaging the difference parameter at multiple locations, and the variance value of the temperature at multiple locations is obtained by variance averaging the difference parameter at multiple locations.
[0014] In one embodiment, determining the fault type of the power equipment based on the relationship between the characteristic parameters and the preset state threshold includes:
[0015] If the slope of the pressure deviation is less than the negative of the preset pressure threshold, and the absolute value of the average temperature is less than the first temperature threshold, then the fault type is determined to be gas leakage.
[0016] If the absolute value of the pressure deviation slope is less than the preset pressure threshold and the absolute value of the average temperature is greater than the first temperature threshold, then the fault type is determined to be an overheating fault type.
[0017] If the slope of the pressure deviation is less than the negative of the preset pressure threshold, and the absolute value of the average temperature is greater than the first temperature threshold, then the fault type is determined to be a composite fault type.
[0018] If the absolute value of the pressure deviation slope is less than the negative of the preset pressure threshold, and the temperature variance is greater than the second temperature threshold, then the fault type is determined to be an abnormal temperature fluctuation fault type.
[0019] In one embodiment, the method further includes:
[0020] If the slope of the pressure deviation is greater than the preset pressure threshold, the electrical equipment is determined to be in normal health condition.
[0021] In one embodiment, the method further includes:
[0022] The state parameters at multiple locations are normalized to obtain the normalized state parameters at multiple locations.
[0023] Perform difference operations on the state parameters at multiple locations to determine the difference parameters at those locations, including:
[0024] Perform difference operations on the normalized state parameters at multiple locations to determine the difference parameters at multiple locations.
[0025] In one embodiment, the above-described differential operation on the state parameters at multiple locations to determine the differential parameters at the multiple locations includes:
[0026] Obtain the average value of the state parameters at multiple locations;
[0027] For any target location at multiple locations, determine the ratio between the state parameters at the target location and the average value;
[0028] The difference parameter at the target location is determined based on the difference between the ratio and the value 1.
[0029] In one embodiment, the method further includes:
[0030] Determine multiple temperature characteristic moments;
[0031] The above-mentioned acquisition of state parameters at multiple locations of the power equipment includes:
[0032] At various temperature characteristic times, the state parameters of the power equipment at multiple locations are acquired.
[0033] Secondly, this application also provides a power equipment fault detection device, comprising:
[0034] The acquisition module is used to acquire status parameters at multiple locations of the power equipment; the status parameters include pressure and temperature values.
[0035] The first determining module is used to perform differential operations on the state parameters at multiple locations to determine the differential parameters at multiple locations;
[0036] The extraction module is used to extract features from the difference parameters at multiple locations, and obtain the feature parameters corresponding to the difference parameters at multiple locations;
[0037] The second determining module is used to determine the fault type of the power equipment based on the relationship between the characteristic parameters and the preset state threshold.
[0038] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:
[0039] Acquire state parameters at multiple locations of the power equipment; state parameters include pressure and temperature values.
[0040] Perform difference operations on the state parameters at multiple locations to determine the difference parameters at multiple locations;
[0041] Feature extraction is performed on the difference parameters at multiple locations to obtain the feature parameters corresponding to the difference parameters at multiple locations;
[0042] The fault type of the power equipment is determined based on the relationship between the characteristic parameters and the preset state threshold.
[0043] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:
[0044] Acquire state parameters at multiple locations of the power equipment; state parameters include pressure and temperature values.
[0045] Perform difference operations on the state parameters at multiple locations to determine the difference parameters at multiple locations;
[0046] Feature extraction is performed on the difference parameters at multiple locations to obtain the feature parameters corresponding to the difference parameters at multiple locations;
[0047] The fault type of the power equipment is determined based on the relationship between the characteristic parameters and the preset state threshold.
[0048] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:
[0049] Acquire state parameters at multiple locations of the power equipment; state parameters include pressure and temperature values.
[0050] Perform difference operations on the state parameters at multiple locations to determine the difference parameters at multiple locations;
[0051] Feature extraction is performed on the difference parameters at multiple locations to obtain the feature parameters corresponding to the difference parameters at multiple locations;
[0052] The fault type of the power equipment is determined based on the relationship between the characteristic parameters and the preset state threshold.
[0053] The aforementioned power equipment fault detection method, device, equipment, and storage medium, through multi-point synchronous acquisition of pressure and temperature and differential and feature extraction, enable the system to lock the fault type when the values just deviate from the threshold, achieving early fault detection and accurate fault location, avoiding power outage expansion and blind repair; in addition, compared with existing algorithms that only rely on pressure for power equipment fault identification, this application considers both pressure and temperature, greatly improving the accuracy of power equipment fault identification. Attached Figure Description
[0054] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0055] Figure 1 This is a diagram illustrating the application environment of a power equipment fault detection method in one embodiment.
[0056] Figure 2This is a flowchart illustrating a power equipment fault detection method in one embodiment;
[0057] Figure 3 This is a flowchart illustrating a power equipment fault detection method in another embodiment;
[0058] Figure 4 This is a flowchart illustrating a power equipment fault detection method in another embodiment;
[0059] Figure 5 This is a flowchart illustrating a power equipment fault detection method in another embodiment;
[0060] Figure 6 This is a flowchart illustrating a power equipment fault detection method in another embodiment;
[0061] Figure 7 This is a flowchart illustrating a power equipment fault detection method in another embodiment;
[0062] Figure 8 This is a flowchart illustrating a power equipment fault detection method in another embodiment;
[0063] Figure 9 This is a structural block diagram of a power equipment fault detection device in one embodiment;
[0064] Figure 10 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation
[0065] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0066] In the field of power equipment condition monitoring and intelligent diagnostics, power equipment (e.g., gas-insulated switchgear (GIS) or circuit breakers (CB)) may leak sulfur hexafluoride (SF6) gas, which can lead to power equipment failure.
[0067] Traditional techniques utilize only pressure sensors, comparing the absolute pressures collected by a group of adjacent sensors to eliminate common-mode temperature noise, thus enabling early detection of single gas leaks. However, these gas leak detection methods suffer from low accuracy. Therefore, this application provides a power equipment fault detection method to address these issues.
[0068] The power equipment fault detection method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, the application environment includes a data storage system 102 and a server 104. The data storage system 102 can store the data that the server 104 needs to process. The data storage system 102 can be integrated onto the server 104, or it can be located in the cloud or on other network servers. The server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.
[0069] The data storage system 102 can communicate with the server 104. For example, the server 104 can send a data request to the data storage system to retrieve data from the data storage system 102, and then process the retrieved data. It should be noted that after the server 104 retrieves multiple requests from the data storage system and processes the multiple requests in parallel, it needs to output the data in the order in which the requests were retrieved.
[0070] In other possible implementations, the power equipment fault detection method provided in this application embodiment can also be applied to a terminal. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart vehicle devices, etc. Portable wearable devices can be smartwatches, smart bracelets, head-mounted devices, etc.
[0071] In one exemplary embodiment, such as Figure 2 As shown, a method for detecting faults in power equipment is provided, which can be applied to... Figure 1 Taking server 104 as an example, the explanation includes:
[0072] S201. Obtain the status parameters at multiple locations of the power equipment; the status parameters include pressure and temperature values.
[0073] Among them, the power equipment can be a gas-insulated switchgear (GIS), and multiple sensors can be pre-installed at multiple different locations outside the corresponding pipeline of the power equipment to obtain the status parameters of the power equipment at multiple locations.
[0074] In this embodiment, when it is necessary to detect faults in power equipment, the state parameters at multiple locations of the power equipment can be obtained to obtain the pressure and temperature values at multiple locations of the power equipment.
[0075] It should be noted that pressure values at multiple locations on the power equipment can be collected at multiple times based on time series data. For example, at the initial time t0, the pressure data collected by the pressure sensor are P1(t0), P2(t0), P3(t0), ..., P... m (t0), at time t1, the collected data are P1(t1), P2(t1), P3(t1), ..., P m (t1), and so on. It should be noted that time t... n (n=0,1,2,...) should select times with different temperature characteristics. For example, in one embodiment, four time points in a day, such as 7:00, 14:00, 20:00, and 2:00 in 24-hour format, are selected as four collection times t0, t1, t2, and t3.
[0076] It is also possible to collect temperature values T at multiple different locations in a GIS simultaneously based on time series data. a (t). The subscript 'a' indicates the a-th sensor, where 'a' can be 1, 2, 3, ..., m. The time 't' should be selected based on different temperature characteristics. For example, in one embodiment, four time points in a day, such as 7:00, 14:00, 20:00, and 2:00 in 24-hour format, are selected as the four data acquisition times t0, t1, t2, and t3. It should be noted that the acquisition times for temperature and pressure values can be the same or different.
[0077] S202. Perform differential operations on the state parameters at multiple locations to determine the differential parameters at multiple locations.
[0078] In this embodiment, after obtaining the state parameters at multiple locations, a difference operation can be performed on the state parameters at multiple locations to determine the difference parameters at multiple locations.
[0079] When the state parameter is a pressure value, differential calculations are performed on the pressure values at multiple locations to determine the pressure difference parameters at multiple locations; when the state parameter is a temperature value, differential calculations are performed on the temperature values at multiple locations to determine the temperature difference parameters at multiple locations.
[0080] S203. Perform feature extraction on the difference parameters at multiple locations to obtain the feature parameters corresponding to the difference parameters at multiple locations.
[0081] In this embodiment, after obtaining the difference parameters at multiple locations, feature extraction can be performed on the difference parameters at multiple locations to obtain the feature parameters corresponding to the difference parameters at multiple locations.
[0082] When the differential parameter is a pressure differential parameter, linear regression can be performed on the pressure differential parameter at multiple locations to obtain the pressure deviation slope. Pressure deviation slope It primarily characterizes the relative gas leakage rate of the sensor.
[0083] When the difference parameter is a temperature difference parameter, the average and variance of the temperature difference parameter at multiple locations can be calculated to obtain the average temperature. and temperature variance As a temperature characteristic parameter, the average temperature and temperature variance It mainly characterizes the temperature fluctuation of the sensor unit.
[0084] S204. Determine the fault type of the power equipment based on the relationship between the characteristic parameters and the preset state threshold.
[0085] In this embodiment, after obtaining the temperature characteristic parameters and pressure characteristic parameters, the fault type of the power equipment can be determined based on the relationship between the temperature characteristic parameters, pressure characteristic parameters and preset state thresholds.
[0086] For example, if the pressure characteristic parameter is greater than the preset pressure state threshold and the temperature characteristic parameter is less than the preset temperature state threshold, the power equipment is determined to be in normal health condition. If the pressure characteristic parameter is not greater than the preset pressure state threshold and the temperature characteristic parameter is not less than the preset temperature state threshold, the power equipment is determined to be in abnormal health condition and there is a gas leakage fault.
[0087] In this embodiment, by synchronously collecting pressure and temperature data from multiple points and performing differential and feature extraction, the system can lock the fault type as soon as the values deviate from the threshold, achieving early detection and accurate location of faults, avoiding power outage expansion and blind repairs. In addition, compared with existing algorithms that only rely on pressure for power equipment fault identification, this application considers both pressure and temperature, greatly improving the accuracy of power equipment fault identification.
[0088] In this embodiment, in the above Figure 2 Based on the illustrated embodiment, the detailed process of obtaining the feature parameters corresponding to the difference parameters at multiple locations will be explained. In an exemplary embodiment, such as Figure 3 As shown, the above S203 includes:
[0089] S301. If the state parameter is a pressure value, perform linear regression on the differential parameters at multiple locations to obtain the pressure deviation slope of the power equipment.
[0090] In this embodiment, when the state parameter is the pressure value, linear regression is performed on the pressure difference parameters at multiple locations to obtain the pressure deviation slope of the power equipment.
[0091] For example, after obtaining the pressure differential parameters at each location, a rectangular coordinate system can be constructed with location as the abscissa and pressure as the ordinate. The points of the pressure differential parameters at each location can be determined in this rectangular coordinate system. Then, the points can be connected to form a curve. The slope of the curve can be determined by linear regression, and the slope of the curve can be used as the pressure deviation slope of the power equipment.
[0092] S302. If the state parameter is a temperature value, perform mean processing on the difference parameters at multiple locations to obtain the mean temperature at multiple locations, and perform variance processing on the difference parameters at multiple locations to obtain the variance temperature at multiple locations.
[0093] In this embodiment, when the state parameter is a temperature value, the temperature difference parameters at multiple locations are averaged to obtain the average temperature at multiple locations, and the temperature difference parameters at multiple locations are varianced to obtain the temperature variance at multiple locations.
[0094] In this embodiment, linear regression is used to extract the slope of pressure deviation for air pressure, which can reveal the leakage rate at a glance; mean and variance are calculated simultaneously for temperature, which can grasp the overall thermal state and capture local overheating fluctuations. The most suitable statistical quantities are used for each of the two parameters, which amplifies the speed and discrete signals of early faults at the same time, making the diagnosis faster and more accurate.
[0095] In this embodiment, in the above Figure 3 Based on the illustrated embodiment, a detailed process for determining the fault type of power equipment according to the relationship between characteristic parameters and preset state thresholds will be explained. In an exemplary embodiment, such as Figure 4 As shown, the above S204 includes:
[0096] S401. If the slope of the pressure deviation is less than the negative of the preset pressure threshold and the absolute value of the average temperature is less than the first temperature threshold, then the fault type is determined to be gas leakage.
[0097] In this embodiment, after determining the pressure deviation slope and the average temperature, if the pressure deviation slope is less than the negative of the preset pressure threshold and the absolute value of the average temperature is less than the first temperature threshold, then the fault type is determined to be a gas leak, and it is recommended to investigate the leak.
[0098] S402. If the absolute value of the pressure deviation slope is less than the preset pressure threshold and the absolute value of the average temperature is greater than the first temperature threshold, then the fault type is determined to be an overheating fault type.
[0099] In this embodiment, after determining the pressure deviation slope and the average temperature, if the absolute value of the pressure deviation slope is less than the preset pressure threshold and the absolute value of the average temperature is greater than the first temperature threshold, then the fault type is determined to be an overheating fault type, and it is recommended to immediately carry out power outage maintenance.
[0100] S403. If the slope of the pressure deviation is less than the negative of the preset pressure threshold and the absolute value of the average temperature is greater than the first temperature threshold, then the fault type is determined to be a composite fault type.
[0101] In this embodiment, after determining the pressure deviation slope and the average temperature, if the pressure deviation slope is less than the negative of the preset pressure threshold and the absolute value of the average temperature is greater than the first temperature threshold, then the fault type is determined to be a composite fault type, that is, gas leakage and overheating. This situation is extremely dangerous and requires the highest priority to handle.
[0102] S404. If the absolute value of the pressure deviation slope is less than the negative of the preset pressure threshold and the temperature variance is greater than the second temperature threshold, then the fault type is determined to be the abnormal temperature fluctuation fault type.
[0103] In this embodiment, after determining the pressure deviation slope and temperature variance, if the absolute value of the pressure deviation slope is less than the negative of the preset pressure threshold and the temperature variance is greater than the second temperature threshold, then the fault type is determined to be the abnormal temperature fluctuation fault type, and it is recommended to troubleshoot the fault.
[0104] S405. If the slope of the pressure deviation is greater than the preset pressure threshold, then the health status of the power equipment is determined to be normal.
[0105] In this embodiment, if the slope of the pressure deviation is greater than the preset pressure threshold, the health status of the power equipment is determined to be normal and without faults.
[0106] In this embodiment, the four types of faults—leakage, overheating, compounding, and temperature fluctuation—are all identified at once using three-dimensional criteria: pressure deviation slope, temperature mean, and temperature variance. Furthermore, the slope exceeding the threshold in the positive direction is automatically identified as healthy, thus avoiding both missed and false alarms and significantly improving the accuracy of GIS status assessment and operational efficiency.
[0107] In this embodiment, in the above Figure 2 Based on the illustrated embodiments, in an exemplary embodiment, such as Figure 5 As shown, the above method also includes:
[0108] S205. Normalize the state parameters at multiple locations to obtain normalized state parameters at multiple locations.
[0109] In this embodiment, after obtaining the state parameters at multiple locations of the power equipment, the state parameters at multiple locations can be normalized to obtain normalized state parameters at multiple locations.
[0110] Optionally, when the state parameter is a pressure value, time t0 can be used as a reference point to normalize the pressure values collected by each sensor at each acquisition time, i.e., P 1_norm (t n )= P1 (t n ) / P1 (t0), P 2_norm (t n )= P2 (t n ) / P2 (t0), ..., P m_norm (t n )= P m (t n ) / P m (t0), where P m_norm (t n ) indicates that the m-th sensor is at t n The normalized value at time.
[0111] Preferably, at each acquisition time t n The data value should be t n The average of multiple collected values around a given time is used as the true pressure value. For example, in one embodiment, there is a collection time of 7:00. Data is collected every 5 seconds from 6:59 to 7:01. Finally, the data collected between 6:59 and 7:01 are averaged and the average value is used as the true pressure value P1 at 7:00.
[0112] It should be noted that the above normalization process converts the absolute pressure value into a dimensionless percentage value representing the change relative to the initial state.
[0113] Furthermore, the normalization process when the state parameter is temperature is exactly the same as the process when the state parameter is pressure, so it will not be elaborated here.
[0114] The above S202 includes: performing a difference operation on the normalized state parameters at multiple locations to determine the difference parameters at multiple locations.
[0115] In this embodiment, after obtaining the normalized state parameters at multiple locations, a difference operation can be performed on the normalized state parameters at multiple locations to determine the difference parameters at multiple locations.
[0116] In this embodiment, the multi-point state parameters are first normalized and then differential calculation is performed. This can completely eliminate the baseline drift caused by the difference between the dimensions and the installation position, so that subsequent features such as slope, mean, and variance can be compared on the same scale. The fault threshold can be set once and applied to the entire station, which significantly improves the robustness and portability of GIS fault diagnosis.
[0117] In this embodiment, in the above Figure 2 Based on the illustrated embodiment, the detailed process of performing differential operations on state parameters at multiple locations to determine the differential parameters at those multiple locations will be explained. In an exemplary embodiment, such as Figure 6 As shown, the above S202 includes:
[0118] S601. Obtain the average value of the state parameters at multiple locations.
[0119] S602. For any target location at multiple locations, determine the ratio between the state parameters at the target location and the average value.
[0120] S603. Determine the difference parameter at the target location based on the difference between the ratio and the value 1.
[0121] In this embodiment, after obtaining the state parameters at multiple locations, the average value of the state parameters at multiple locations can be obtained first. Then, for any target location i at multiple locations, the ratio between the state parameters at the target location and the average value can be determined, and the difference between the ratio and the value 1 can be used as the difference parameter at the target location.
[0122] When the state parameter is a pressure value, the process of determining the pressure differential parameter at the target location i can be found in the following formula (1):
[0123]
[0124] in, This refers to the normalized pressure value at target location i. It refers to the average of the normalized pressure values at various locations. This refers to the pressure differential parameter at target location i, where... .
[0125] When the state parameter is a temperature value, the process of determining the temperature difference parameter at the target location i can be found in the following formula (2):
[0126]
[0127] in, This refers to the normalized temperature value at target location i. It refers to the average of the normalized temperature values at various locations. This refers to the temperature difference parameter at the target location i, where... It should be noted that the normalization method for temperature values is the same as that for pressure values.
[0128] In this embodiment, the difference is constructed by using the ratio between a single point and the mean and the difference between the values of 1, which directly quantifies the relative distortion of each measuring point from the overall average. This eliminates environmental drift adaptively without the need for additional reference sensors, simplifying the hardware and amplifying real anomalies, making subsequent feature extraction more sensitive to early and subtle faults.
[0129] In this embodiment, in the above Figure 2 Based on the illustrated embodiment, a detailed explanation will be given of the process for acquiring state parameters at multiple locations of the power equipment. In one exemplary embodiment, such as Figure 7 As shown, the above method also includes:
[0130] S206. Determine multiple temperature characteristic moments.
[0131] In this embodiment, when acquiring the state parameters at multiple locations of the power equipment, the state parameters at multiple locations of the power equipment can be acquired at more than one time. Therefore, multiple temperature characteristic times can be predetermined, so that the state parameters at multiple locations of the power equipment can be acquired at multiple temperature characteristic times.
[0132] For example, you can select times of day with different temperature characteristics, such as four different times of day, like 7:00, 14:00, 20:00 and 2:00 in 24-hour time format, as multiple times with temperature characteristics.
[0133] It should be noted that at each data acquisition time t n The data value should be t n The average value of multiple state parameters around a given time is used as the true state parameter. For example, in one embodiment, if there is a data collection time of 7:00, then the average value of the data collected between 6:59 and 7:01 can be used as the true state parameter for 7:00.
[0134] The above-mentioned S201 also includes: acquiring state parameters at multiple locations of the power equipment at various temperature characteristic times.
[0135] In this embodiment, after determining each temperature moment, state parameters (including temperature and pressure values) at multiple locations of the power equipment can be obtained at each temperature characteristic moment. The state parameters at multiple locations are then normalized. Subsequently, at each temperature characteristic moment, differential operations are performed on the normalized state parameters at multiple locations to determine the differential parameters at multiple locations. Feature extraction is also performed on the differential parameters at multiple locations to obtain the feature parameters corresponding to the differential parameters at multiple locations. Based on the relationship between the feature parameters and the preset state threshold, the fault type of the power equipment at each temperature characteristic moment can be determined.
[0136] Optionally, when the state parameter is a pressure value, the pressure values at multiple locations of the power equipment at various temperature characteristic times can be obtained (e.g., pressure values at multiple locations of the power equipment at time t0, pressure values at multiple locations of the power equipment at time t1, pressure values at multiple locations of the power equipment at time t2, ..., t...). m (The pressure values at multiple locations of the power equipment at time t0) can then be used as a reference point to normalize the pressure values of each sensor at each acquisition time, i.e., P 1_norm (t n )= P1 (t n ) / P1 (t0), P 2_norm (t n )= P2(t n ) / P2 (t0), ..., P m_norm (t n )= P m (t n ) / P m (t0), where P m_norm (t n ) indicates that the m-th sensor is at t n The normalized value at time.
[0137] Preferably, at each acquisition time t n The data value should be t n The average of multiple collected values around a given time is used as the true pressure value. For example, in one embodiment, there is a collection time of 7:00. Data is collected every 5 seconds from 6:59 to 7:01. Finally, the data collected between 6:59 and 7:01 are averaged and the average value is used as the true pressure value P1 at 7:00.
[0138] It should be noted that the above normalization process converts the absolute pressure value into a dimensionless percentage value representing the change relative to the initial state. Furthermore, the normalization process when the state parameter is temperature is exactly the same as the process when the state parameter is pressure, and will not be elaborated upon here.
[0139] In this embodiment, by simultaneously collecting the status parameters of multiple points of power equipment at multiple temperature characteristic moments, the coupling relationship between different temperature rise stages and operating status can be accurately captured, eliminating blind spots in single-point or single-period monitoring, significantly improving the sensitivity of latent thermal defect identification and the accuracy of fault early warning, and providing high-confidence data support for differentiated operation and maintenance and life assessment.
[0140] In this embodiment, referring to 8, a method for detecting faults in power equipment is also provided, including:
[0141] T1, determine multiple temperature characteristic moments;
[0142] T2. At various temperature characteristic moments, acquire the state parameters at multiple locations of the power equipment; the state parameters include pressure and temperature values.
[0143] T3. Normalize the state parameters at multiple locations to obtain the normalized state parameters at multiple locations.
[0144] T4. Obtain the average value of the state parameters at multiple normalized locations;
[0145] T5. For any target location at multiple locations, determine the ratio between the normalized state parameters at the target location and the average value.
[0146] T6. Determine the difference parameter at the target location based on the difference between the ratio and the value 1;
[0147] T7. If the state parameter is a pressure value, perform linear regression on the difference parameters at multiple locations to obtain the pressure deviation slope of the power equipment.
[0148] T8. If the state parameter is a temperature value, perform mean processing on the difference parameters at multiple locations to obtain the mean temperature at multiple locations, and perform variance processing on the difference parameters at multiple locations to obtain the variance temperature at multiple locations.
[0149] T9. If the slope of the pressure deviation is less than the negative of the preset pressure threshold and the absolute value of the average temperature is less than the first temperature threshold, then the fault type is determined to be gas leakage.
[0150] T10. If the absolute value of the pressure deviation slope is less than the preset pressure threshold and the absolute value of the average temperature is greater than the first temperature threshold, then the fault type is determined to be an overheating fault type.
[0151] T11. If the slope of the pressure deviation is less than the negative of the preset pressure threshold and the absolute value of the average temperature is greater than the first temperature threshold, then the fault type is determined to be a composite fault type.
[0152] T12. If the absolute value of the pressure deviation slope is less than the negative of the preset pressure threshold and the temperature variance is greater than the second temperature threshold, then the fault type is determined to be the abnormal temperature fluctuation fault type.
[0153] T13. If the pressure deviation slope is greater than the preset pressure threshold, the health status of the power equipment is determined to be normal.
[0154] It should be noted that the descriptions of T1-T13 above can be found in the relevant descriptions in the above embodiments, and their effects are similar, so they will not be repeated here.
[0155] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.
[0156] Based on the same inventive concept, this application also provides a power equipment fault detection device for implementing the power equipment fault detection method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more power equipment fault detection device embodiments provided below can be found in the limitations of the power equipment fault detection method described above, and will not be repeated here.
[0157] In one exemplary embodiment, such as Figure 9 As shown, a power equipment fault detection device is provided, comprising: an acquisition module 10, a first determination module 11, an extraction module 12, and a second determination module 13, wherein:
[0158] The acquisition module 10 is used to acquire status parameters at multiple locations of the power equipment; the status parameters include pressure values and temperature values.
[0159] The first determining module 11 is used to perform differential operations on the state parameters at multiple locations to determine the differential parameters at multiple locations.
[0160] The extraction module 12 is used to extract features from the difference parameters at multiple locations to obtain the feature parameters corresponding to the difference parameters at multiple locations.
[0161] The second determining module 13 is used to determine the fault type of the power equipment based on the relationship between the characteristic parameters and the preset state threshold.
[0162] In an exemplary embodiment, the extraction module 12 includes:
[0163] The first processing unit is specifically used to perform linear regression processing on the differential parameters at multiple locations if the state parameter is a pressure value, to obtain the pressure deviation slope of the power equipment.
[0164] The second processing unit is specifically used to perform mean processing on the difference parameters at multiple locations to obtain the mean temperature value at multiple locations, and to perform variance processing on the difference parameters at multiple locations to obtain the variance temperature value at multiple locations, if the state parameter is a temperature value.
[0165] In an exemplary embodiment, the second determining module 13 described above includes:
[0166] The first determining unit is specifically used to determine the fault type as gas leakage if the slope of the pressure deviation is less than the negative of the preset pressure threshold and the absolute value of the average temperature is less than the first temperature threshold.
[0167] The second determining unit is specifically used to determine the fault type as an overheating fault type if the absolute value of the pressure deviation slope is less than the preset pressure threshold and the absolute value of the average temperature is greater than the first temperature threshold.
[0168] The third determining unit is specifically used to determine the fault type as a composite fault type if the slope of the pressure deviation is less than the negative of the preset pressure threshold and the absolute value of the average temperature is greater than the first temperature threshold.
[0169] The fourth determining unit is specifically used to determine the fault type as abnormal temperature fluctuation fault type if the absolute value of the pressure deviation slope is less than the negative of the preset pressure threshold and the temperature variance value is greater than the second temperature threshold.
[0170] In an exemplary embodiment, the second determining module 13 further includes:
[0171] The fifth determining unit is specifically used to determine that the power equipment is in normal health status if the pressure deviation slope is greater than the preset pressure threshold.
[0172] In one exemplary embodiment, the above-described apparatus further includes:
[0173] The processing module is used to normalize the state parameters at multiple locations to obtain the normalized state parameters at multiple locations.
[0174] The aforementioned first determining module is also used to perform differential operations on the normalized state parameters at multiple locations to determine the differential parameters at multiple locations.
[0175] In an exemplary embodiment, the first determining module 11 further includes:
[0176] The acquisition unit is specifically used to acquire the average value of state parameters at multiple locations;
[0177] The sixth determining unit is specifically used to determine the ratio between the state parameters at any target location and the average value for any target location at multiple locations;
[0178] The seventh determining unit is specifically used to determine the difference parameter at the target location based on the difference between the ratio and the value 1.
[0179] In one exemplary embodiment, the above-described apparatus further includes:
[0180] The determination module is used to determine multiple temperature characteristic moments.
[0181] The aforementioned acquisition module 10 is also used to acquire state parameters at multiple locations of the power equipment at various temperature characteristic times.
[0182] Each module in the aforementioned power equipment fault detection device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.
[0183] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 10As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores status parameter data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for detecting faults in power equipment.
[0184] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0185] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:
[0186] Acquire state parameters at multiple locations of the power equipment; state parameters include pressure and temperature values.
[0187] Perform difference operations on the state parameters at multiple locations to determine the difference parameters at multiple locations;
[0188] Feature extraction is performed on the difference parameters at multiple locations to obtain the feature parameters corresponding to the difference parameters at multiple locations;
[0189] The fault type of the power equipment is determined based on the relationship between the characteristic parameters and the preset state threshold.
[0190] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0191] If the state parameter is a pressure value, linear regression is performed on the difference parameters at multiple locations to obtain the pressure deviation slope of the power equipment.
[0192] If the state parameter is a temperature value, the mean value of the difference parameter at multiple locations is obtained by averaging the difference parameter at multiple locations, and the variance value of the temperature at multiple locations is obtained by variance averaging the difference parameter at multiple locations.
[0193] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0194] If the slope of the pressure deviation is less than the negative of the preset pressure threshold, and the absolute value of the average temperature is less than the first temperature threshold, then the fault type is determined to be gas leakage.
[0195] If the absolute value of the pressure deviation slope is less than the preset pressure threshold and the absolute value of the average temperature is greater than the first temperature threshold, then the fault type is determined to be an overheating fault type.
[0196] If the slope of the pressure deviation is less than the negative of the preset pressure threshold, and the absolute value of the average temperature is greater than the first temperature threshold, then the fault type is determined to be a composite fault type.
[0197] If the absolute value of the pressure deviation slope is less than the negative of the preset pressure threshold, and the temperature variance is greater than the second temperature threshold, then the fault type is determined to be an abnormal temperature fluctuation fault type.
[0198] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0199] If the slope of the pressure deviation is greater than the preset pressure threshold, the electrical equipment is determined to be in normal health condition.
[0200] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0201] The state parameters at multiple locations are normalized to obtain the normalized state parameters at multiple locations.
[0202] Perform difference operations on the state parameters at multiple locations to determine the difference parameters at those locations, including:
[0203] Perform difference operations on the normalized state parameters at multiple locations to determine the difference parameters at multiple locations.
[0204] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0205] Obtain the average value of the state parameters at multiple locations;
[0206] For any target location at multiple locations, determine the ratio between the state parameters at the target location and the average value;
[0207] The difference parameter at the target location is determined based on the difference between the ratio and the value 1.
[0208] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0209] Determine multiple temperature characteristic moments;
[0210] Obtain status parameters at multiple locations of the power equipment, including:
[0211] At various temperature characteristic times, the state parameters of the power equipment at multiple locations are acquired.
[0212] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:
[0213] Acquire state parameters at multiple locations of the power equipment; state parameters include pressure and temperature values.
[0214] Perform difference operations on the state parameters at multiple locations to determine the difference parameters at multiple locations;
[0215] Feature extraction is performed on the difference parameters at multiple locations to obtain the feature parameters corresponding to the difference parameters at multiple locations;
[0216] The fault type of the power equipment is determined based on the relationship between the characteristic parameters and the preset state threshold.
[0217] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0218] If the state parameter is a pressure value, linear regression is performed on the difference parameters at multiple locations to obtain the pressure deviation slope of the power equipment.
[0219] If the state parameter is a temperature value, the mean value of the difference parameter at multiple locations is obtained by averaging the difference parameter at multiple locations, and the variance value of the temperature at multiple locations is obtained by variance averaging the difference parameter at multiple locations.
[0220] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0221] If the slope of the pressure deviation is less than the negative of the preset pressure threshold, and the absolute value of the average temperature is less than the first temperature threshold, then the fault type is determined to be gas leakage.
[0222] If the absolute value of the pressure deviation slope is less than the preset pressure threshold and the absolute value of the average temperature is greater than the first temperature threshold, then the fault type is determined to be an overheating fault type.
[0223] If the slope of the pressure deviation is less than the negative of the preset pressure threshold, and the absolute value of the average temperature is greater than the first temperature threshold, then the fault type is determined to be a composite fault type.
[0224] If the absolute value of the pressure deviation slope is less than the negative of the preset pressure threshold, and the temperature variance is greater than the second temperature threshold, then the fault type is determined to be an abnormal temperature fluctuation fault type.
[0225] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0226] If the slope of the pressure deviation is greater than the preset pressure threshold, the electrical equipment is determined to be in normal health condition.
[0227] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0228] The state parameters at multiple locations are normalized to obtain the normalized state parameters at multiple locations.
[0229] Perform difference operations on the state parameters at multiple locations to determine the difference parameters at those locations, including:
[0230] Perform difference operations on the normalized state parameters at multiple locations to determine the difference parameters at multiple locations.
[0231] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0232] Obtain the average value of the state parameters at multiple locations;
[0233] For any target location at multiple locations, determine the ratio between the state parameters at the target location and the average value;
[0234] The difference parameter at the target location is determined based on the difference between the ratio and the value 1.
[0235] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0236] Determine multiple temperature characteristic moments;
[0237] Obtain status parameters at multiple locations of the power equipment, including:
[0238] At various temperature characteristic times, the state parameters of the power equipment at multiple locations are acquired.
[0239] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:
[0240] Acquire state parameters at multiple locations of the power equipment; state parameters include pressure and temperature values.
[0241] Perform difference operations on the state parameters at multiple locations to determine the difference parameters at multiple locations;
[0242] Feature extraction is performed on the difference parameters at multiple locations to obtain the feature parameters corresponding to the difference parameters at multiple locations;
[0243] The fault type of the power equipment is determined based on the relationship between the characteristic parameters and the preset state threshold.
[0244] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0245] If the state parameter is a pressure value, linear regression is performed on the difference parameters at multiple locations to obtain the pressure deviation slope of the power equipment.
[0246] If the state parameter is a temperature value, the mean value of the difference parameter at multiple locations is obtained by averaging the difference parameter at multiple locations, and the variance value of the temperature at multiple locations is obtained by variance averaging the difference parameter at multiple locations.
[0247] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0248] If the slope of the pressure deviation is less than the negative of the preset pressure threshold, and the absolute value of the average temperature is less than the first temperature threshold, then the fault type is determined to be gas leakage.
[0249] If the absolute value of the pressure deviation slope is less than the preset pressure threshold and the absolute value of the average temperature is greater than the first temperature threshold, then the fault type is determined to be an overheating fault type.
[0250] If the slope of the pressure deviation is less than the negative of the preset pressure threshold, and the absolute value of the average temperature is greater than the first temperature threshold, then the fault type is determined to be a composite fault type.
[0251] If the absolute value of the pressure deviation slope is less than the negative of the preset pressure threshold, and the temperature variance is greater than the second temperature threshold, then the fault type is determined to be an abnormal temperature fluctuation fault type.
[0252] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0253] If the slope of the pressure deviation is greater than the preset pressure threshold, the electrical equipment is determined to be in normal health condition.
[0254] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0255] The state parameters at multiple locations are normalized to obtain the normalized state parameters at multiple locations.
[0256] Perform difference operations on the state parameters at multiple locations to determine the difference parameters at those locations, including:
[0257] Perform difference operations on the normalized state parameters at multiple locations to determine the difference parameters at multiple locations.
[0258] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0259] Obtain the average value of the state parameters at multiple locations;
[0260] For any target location at multiple locations, determine the ratio between the state parameters at the target location and the average value;
[0261] The difference parameter at the target location is determined based on the difference between the ratio and the value 1.
[0262] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:
[0263] Determine multiple temperature characteristic moments;
[0264] Obtain status parameters at multiple locations of the power equipment, including:
[0265] At various temperature characteristic times, the state parameters of the power equipment at multiple locations are acquired.
[0266] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.
[0267] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0268] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. A power equipment failure detection method characterized by, The method includes: Acquire state parameters at multiple locations of the power equipment; the state parameters include pressure and temperature values. Perform a difference operation on the state parameters at the multiple locations to determine the difference parameters at the multiple locations; Feature extraction is performed on the difference parameters at the multiple locations to obtain the feature parameters corresponding to the difference parameters at the multiple locations; The fault type of the power equipment is determined based on the relationship between the characteristic parameters and the preset state threshold.
2. The method of claim 1, wherein, The step of extracting features from the difference parameters at the multiple locations to obtain the feature parameters corresponding to the difference parameters at the multiple locations includes: If the state parameter is the pressure value, perform linear regression on the difference parameters at the multiple locations to obtain the pressure deviation slope of the power equipment; If the state parameter is the temperature value, the difference parameters at the multiple locations are averaged to obtain the average temperature at the multiple locations, and the difference parameters at the multiple locations are varianced to obtain the variance temperature at the multiple locations.
3. The method of claim 2, wherein, The step of determining the fault type of the power equipment based on the relationship between the characteristic parameters and the preset state threshold includes: If the slope of the pressure deviation is less than the negative of the preset pressure threshold, and the absolute value of the average temperature is less than the first temperature threshold, then the fault type is determined to be a gas leak. If the absolute value of the pressure deviation slope is less than the preset pressure threshold and the absolute value of the average temperature is greater than the first temperature threshold, then the fault type is determined to be an overheating fault type. If the slope of the pressure deviation is less than the negative of the preset pressure threshold, and the absolute value of the average temperature is greater than the first temperature threshold, then the fault type is determined to be a composite fault type. If the absolute value of the pressure deviation slope is less than the negative of the preset pressure threshold, and the temperature variance value is greater than the second temperature threshold, then the fault type is determined to be a temperature abnormal fluctuation fault type.
4. The method of claim 3, wherein, The method further includes: If the slope of the pressure deviation is greater than the preset pressure threshold, then the health status of the power equipment is determined to be normal.
5. The method of claim 1, wherein, The method further includes: The state parameters at the multiple locations are normalized to obtain the normalized state parameters at the multiple locations. The step of performing a difference operation on the state parameters at the multiple locations to determine the difference parameters at the multiple locations includes: Perform a difference operation on the normalized state parameters at multiple locations to determine the difference parameters at the multiple locations.
6. The method of claim 1, wherein, The step of performing a difference operation on the state parameters at the multiple locations to determine the difference parameters at the multiple locations includes: Obtain the average value of the state parameters at the multiple locations; For any target location among the plurality of locations, determine the ratio between the state parameter at the target location and the average value; The difference parameter at the target location is determined based on the difference between the ratio and the value 1.
7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: Determine multiple temperature characteristic moments; The acquisition of state parameters at multiple locations of the power equipment includes: At each of the aforementioned temperature characteristic times, the state parameters at multiple locations of the power equipment are acquired.
8. An electric power equipment failure detection apparatus characterized by comprising: The device includes: The acquisition module is used to acquire status parameters at multiple locations of the power equipment; the status parameters include pressure values and temperature values. The first determining module is used to perform differential operations on the state parameters at the multiple locations to determine the differential parameters at the multiple locations; The extraction module is used to extract features from the difference parameters at the multiple locations to obtain the feature parameters corresponding to the difference parameters at the multiple locations; The second determining module is used to determine the fault type of the power equipment based on the relationship between the characteristic parameters and the preset state threshold. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.
10. A computer-readable storage medium having stored thereon a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.