Ground wire insulation monitoring equipment and power monitoring system
By collecting the temperature, humidity, current and voltage data of the grounding wire and combining it with data fusion and anomaly recognition models, the problem of the grounding wire insulation monitoring device being susceptible to external interference is solved, and high-accuracy insulation monitoring and rapid fault location are achieved.
Patent Information
- Application Number
- CN202510210955.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-25
- Publication Date
- 2025-09-12
- Estimated Expiration
- 2045-02-25
AI Technical Summary
Existing ground wire insulation monitoring devices are susceptible to external interference, leading to false alarms and insufficient accuracy.
The temperature, humidity, current and voltage data at different locations of the grounding wire are obtained through the data acquisition module, the characteristic values are calculated using the data fusion module, and the anomaly is judged through the anomaly recognition module and the preset grounding wire anomaly recognition model. The anomaly position is quickly located in combination with the fault location module.
The accuracy of ground wire insulation monitoring is improved, false alarms are avoided, and the safe operation of equipment and the stability of the power system are ensured.
Smart Images
Figure CN119716432B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of measuring electrical variables, and in particular to a ground wire insulation monitoring device and a power monitoring system. Background Art
[0002] Ground wire insulation monitoring is the process of inspecting and evaluating the insulation performance of ground wires in electrical equipment or power systems. Ensuring good insulation of ground wires is crucial for preventing electric shock, protecting personnel, ensuring the proper functioning of equipment, and avoiding power system failures.
[0003] In power systems, dedicated insulation monitoring devices (IMDs) are often used to monitor the insulation resistance to ground of DC or ungrounded AC systems in real time. When the insulation resistance drops below a set threshold, the IMD issues an alarm, prompting maintenance personnel to take action to remedy the potential problem. However, this technology also has potential drawbacks and limitations. For example, external interference (such as electromagnetic interference), sensor failure, or misconfiguration can cause the system to issue false alarms. Summary of the Invention
[0004] The embodiments of the present invention provide a ground wire insulation monitoring device and a power monitoring system to avoid the influence of interference on monitoring, improve the accuracy of monitoring, and avoid false alarms.
[0005] In a first aspect, an embodiment of the present invention provides a ground wire insulation monitoring device, including: a data acquisition module, a data fusion module, an abnormality identification module and an abnormality alarm module.
[0006] The data acquisition module is used to simultaneously obtain data sets of temperature, humidity, current and voltage at different positions of the target grounding wire, and transmit multiple data sets to the data fusion module.
[0007] The data fusion module is used to calculate multiple eigenvalues based on multiple data sets and transmit the multiple eigenvalues to the anomaly recognition module.
[0008] The abnormality identification module is used to determine whether there is an abnormality in the insulating shell of the target grounding wire based on multiple characteristic values. If there is an abnormality in the insulating shell of the target grounding wire, an alarm control signal is sent to the abnormality alarm module.
[0009] The abnormal alarm module is used to issue an alarm according to the alarm control signal.
[0010] In a possible implementation, the data fusion module is specifically configured to:
[0011] For each data set, a first eigenvalue is calculated based on the temperature and humidity in the data set, and a second eigenvalue is calculated based on the current and voltage.
[0012] The plurality of first characteristic values and the plurality of second characteristic values are supplied to an abnormality identification module.
[0013] In one possible implementation, calculating the first characteristic value based on the temperature and humidity in the data set and calculating the second characteristic value based on the current and voltage include:
[0014] The first eigenvalue is calculated using the first formula.
[0015] The first formula is:
[0016]
[0017] in, represents the first eigenvalue, Indicates the temperature acquisition value. Indicates the standard value of temperature. represents the temperature coefficient, Indicates the humidity collection value. Indicates the standard value of humidity. Represents the humidity coefficient.
[0018] The second eigenvalue is calculated using the second formula.
[0019]
[0020] in, represents the second eigenvalue, Indicates the current acquisition value, Indicates the standard value of current, represents the current coefficient, Indicates the voltage acquisition value, Indicates the voltage standard value, Represents the voltage coefficient.
[0021] In one possible implementation, the anomaly identification module is specifically configured to:
[0022] The first eigenvalue and the second eigenvalue at the same position are defined as a target eigenvalue group.
[0023] Multiple target feature value groups are input into a preset grounding wire anomaly recognition model to obtain an output result of the grounding wire anomaly recognition model, and the output result is used as a target grounding wire insulation shell anomaly judgment result.
[0024] In one possible implementation, the model training process of the preset ground wire anomaly recognition model includes:
[0025] A plurality of historical characteristic value groups are obtained, wherein the historical characteristic value groups include a first characteristic value and a second characteristic value corresponding to the same historical position when the insulation of the ground wire is normal, and different historical characteristic value groups correspond to different positions.
[0026] The locations and number of cluster centers are randomly selected.
[0027] Each historical feature value group is assigned to the nearest cluster center to obtain multiple clusters.
[0028] Calculate the mean of the historical feature value group in each cluster and set the mean as the updated cluster center.
[0029] Determine whether the current number of iterations has reached the maximum number of iterations.
[0030] If the current number of iterations reaches the maximum number of iterations, the cluster center updated at this time is set as the cluster center of the preset grounding line anomaly recognition model.
[0031] If the current number of iterations has not reached the maximum number of iterations, the current number of iterations is increased by one, and the process returns to the step of "assigning each historical feature value group to the nearest cluster center to obtain multiple clusters" based on the updated cluster center to continue iterating.
[0032] The process of obtaining the output of the grounding anomaly identification model includes:
[0033] Get multiple target feature value groups of the input.
[0034] For each target eigenvalue group, multiple distances from the target eigenvalue group to multiple cluster centers of the preset grounding line anomaly identification model are calculated respectively; if the minimum value among the multiple distances is less than the preset threshold, the target eigenvalue group is considered to be a normal value; if the minimum value among the multiple distances is greater than or equal to the preset threshold, the target eigenvalue group is considered to be an anomaly.
[0035] If all target characteristic value groups are normal values, the output result is that there is no abnormality in the insulation shell of the target grounding wire; otherwise, the output result is that there is an abnormality in the insulation shell of the target grounding wire.
[0036] In one possible implementation, the hyperparameters of the preset grounding line anomaly recognition model are optimized by a particle swarm optimization algorithm or an annealing algorithm; wherein the hyperparameters include at least: the position of the randomly selected cluster center, the number of cluster centers, the maximum number of iterations, and a preset threshold.
[0037] In one possible implementation, the ground wire insulation monitoring device further includes a fault location module;
[0038] The fault location module is used to determine all abnormal values in multiple target characteristic value groups according to multiple target characteristic value groups, and determine the abnormal position of the target grounding wire insulation shell based on the positions corresponding to all abnormal values.
[0039] In one possible implementation, the data acquisition module is specifically configured to:
[0040] The temperature, humidity, current and voltage are collected synchronously, and the temperature, humidity, current and voltage at the same location are taken as a set to obtain a data set.
[0041] Transfer multiple data sets to the data fusion module.
[0042] In a possible implementation, the data acquisition module further includes a data preprocessing unit; the data preprocessing unit is specifically configured to:
[0043] The synchronously collected temperature, humidity, current and voltage are filtered and standardized.
[0044] The temperature, humidity, current and voltage at the same location are taken as a set to obtain a data set including:
[0045] The filtered and standardized temperature, humidity, current, and voltage at the same location are taken as a set to obtain a data set.
[0046] In a second aspect, an embodiment of the present invention provides a power monitoring system, characterized in that it includes at least one ground wire insulation monitoring device as described in any one of the first aspects.
[0047] The beneficial effects of the present invention are: by collecting data sets of temperature, humidity, current and voltage at different positions of the target grounding wire, as many data sets as possible can be obtained to ensure the number of calculated eigenvalues. The method of jointly identifying anomalies with multiple eigenvalues can ensure the accuracy of the anomaly recognition module in identifying anomalies, and ultimately achieve the effect of avoiding the impact of interference on monitoring, improving the accuracy of monitoring, and avoiding false alarms. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] Figure 1 It is a structural diagram of a ground wire insulation monitoring device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0049] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
[0050] See also Figure 1 , which shows a schematic structural diagram of a ground wire insulation monitoring device provided by an embodiment of the present invention, and is described in detail as follows:
[0051] An embodiment of the present invention provides a ground wire insulation monitoring device, including: a data acquisition module 101 , a data fusion module 102 , an abnormality identification module 103 and an abnormality alarm module 104 .
[0052] The data acquisition module 101 is used to simultaneously acquire data sets of temperature, humidity, current and voltage at different positions of the target ground wire, and transmit multiple data sets to the data fusion module.
[0053] The data fusion module 102 is configured to calculate multiple feature values based on multiple data sets and transmit the multiple feature values to the anomaly identification module.
[0054] The abnormality identification module 103 is used to determine whether there is an abnormality in the insulating shell of the target grounding wire based on multiple characteristic values, and if there is an abnormality in the insulating shell of the target grounding wire, send an alarm control signal to the abnormality alarm module.
[0055] The abnormality alarm module 104 is used to generate an alarm according to the alarm control signal.
[0056] In some specific embodiments, the data fusion module 102 may be used to:
[0057] For each data set, a first eigenvalue is calculated based on the temperature and humidity in the data set, and a second eigenvalue is calculated based on the current and voltage.
[0058] The plurality of first characteristic values and the plurality of second characteristic values are supplied to an abnormality identification module.
[0059] In some specific embodiments, calculating the first characteristic value based on the temperature and humidity in the data set and calculating the second characteristic value based on the current and voltage include:
[0060] The first eigenvalue is calculated using the first formula.
[0061] The first formula is:
[0062]
[0063] in, represents the first eigenvalue, Indicates the temperature acquisition value. Indicates the standard value of temperature. represents the temperature coefficient, Indicates the humidity collection value. Indicates the standard value of humidity. Represents the humidity coefficient.
[0064] The second eigenvalue is calculated using the second formula.
[0065]
[0066] in, represents the second eigenvalue, Indicates the current acquisition value, Indicates the standard value of current, represents the current coefficient, Indicates the voltage acquisition value, Indicates the voltage standard value, Represents the voltage coefficient.
[0067] In some specific embodiments, the data fusion module 102 may also be used to:
[0068] For each data set, a third eigenvalue is calculated based on the temperature, humidity, current, and voltage in the data set.
[0069] The plurality of third feature values are supplied to the abnormality identification module.
[0070] In some specific embodiments, calculating the third characteristic value based on the temperature, humidity, current, and voltage in the data set may include:
[0071]
[0072] in, represents the third eigenvalue.
[0073] In some specific embodiments, the anomaly identification module 103 may be specifically used to:
[0074] The first eigenvalue and the second eigenvalue at the same position are defined as a target eigenvalue group.
[0075] Multiple target feature value groups are input into a preset grounding wire anomaly recognition model to obtain an output result of the grounding wire anomaly recognition model, and the output result is used as a target grounding wire insulation shell anomaly judgment result.
[0076] In some specific embodiments, the model training process of the preset ground wire anomaly recognition model may include:
[0077] A plurality of historical characteristic value groups are obtained, wherein the historical characteristic value groups include a first characteristic value and a second characteristic value corresponding to the same historical position when the insulation of the ground wire is normal, and different historical characteristic value groups correspond to different positions.
[0078] The locations and number of cluster centers are randomly selected.
[0079] Each historical feature value group is assigned to the nearest cluster center to obtain multiple clusters.
[0080] Calculate the mean of the historical feature value group in each cluster and set the mean as the updated cluster center.
[0081] Determine whether the current number of iterations has reached the maximum number of iterations.
[0082] If the current number of iterations reaches the maximum number of iterations, the cluster center updated at this time is set as the cluster center of the preset grounding line anomaly recognition model.
[0083] If the current number of iterations has not reached the maximum number of iterations, the current number of iterations is increased by one, and the process returns to the step of "assigning each historical feature value group to the nearest cluster center to obtain multiple clusters" based on the updated cluster center to continue iterating.
[0084] In some specific embodiments, the process of obtaining the output result of the ground wire anomaly identification model may include:
[0085] Get multiple target feature value groups of the input.
[0086] For each target eigenvalue group, multiple distances from the target eigenvalue group to multiple cluster centers of the preset grounding line anomaly identification model are calculated respectively; if the minimum value among the multiple distances is less than the preset threshold, the target eigenvalue group is considered to be a normal value; if the minimum value among the multiple distances is greater than or equal to the preset threshold, the target eigenvalue group is considered to be an anomaly.
[0087] If all target characteristic value groups are normal values, the output result is that there is no abnormality in the insulation shell of the target grounding wire; otherwise, the output result is that there is an abnormality in the insulation shell of the target grounding wire.
[0088] In some specific embodiments, the anomaly identification module 103 may also be used to:
[0089] The third eigenvalue is defined as the target eigenvalue.
[0090] Multiple target feature values are input into a preset grounding wire anomaly recognition model to obtain an output result of the grounding wire anomaly recognition model, and the output result is used as a target grounding wire insulation shell abnormality judgment result.
[0091] In some specific embodiments, the model training process of the preset ground wire anomaly recognition model may include:
[0092] A plurality of historical characteristic values are obtained, wherein the historical characteristic values include a historical third characteristic value corresponding to when the insulation of the ground wire is normal, and different historical characteristic values correspond to different positions.
[0093] The locations and number of cluster centers are randomly selected.
[0094] Each historical feature value is assigned to the nearest cluster center to obtain multiple clusters.
[0095] Calculate the mean of the historical feature values in each cluster and set the mean as the updated cluster center.
[0096] Determine whether the current number of iterations has reached the maximum number of iterations.
[0097] If the current number of iterations reaches the maximum number of iterations, the cluster center updated at this time is set as the cluster center of the preset grounding line anomaly recognition model.
[0098] If the current number of iterations has not reached the maximum number of iterations, the current number of iterations is increased by one, and the process returns to the step of "assigning each historical feature value to the nearest cluster center to obtain multiple clusters" based on the updated cluster center to continue iterating.
[0099] In some specific embodiments, the process of obtaining the output result of the ground wire anomaly identification model may include:
[0100] Get multiple target feature values of the input.
[0101] For each target eigenvalue, multiple distances from the target eigenvalue to multiple cluster centers of the preset grounding line anomaly identification model are calculated respectively; if the minimum value among the multiple distances is less than the preset threshold, the target eigenvalue is considered to be a normal value; if the minimum value among the multiple distances is greater than or equal to the preset threshold, the target eigenvalue is considered to be an abnormal value.
[0102] If all target characteristic values are normal values, the output result is that there is no abnormality in the insulation shell of the target grounding wire; otherwise, the output result is that there is an abnormality in the insulation shell of the target grounding wire.
[0103] In some specific embodiments, the hyperparameters of the preset grounding line anomaly recognition model are optimized by a particle swarm algorithm or an annealing algorithm; wherein the hyperparameters include at least: the position of the randomly selected cluster center, the number of cluster centers, the maximum number of iterations, and a preset threshold.
[0104] Specifically, compared to conventional hyperparameters, the hyperparameters in this application also include the maximum number of model iterations and the preset threshold of the model. Because of the impact of external interference on the acquisition parameters, the traditional method of directly setting the maximum number of model iterations and the preset threshold of the model based on historical experience will cause large errors, which in turn leads to a large number of false positives. In order to reduce the occurrence of false positives, these two parameters are included in the hyperparameters of the model, and are optimized together with parameters such as the position and number of randomly selected cluster centers through a particle swarm algorithm or an annealing algorithm to obtain the optimal result.
[0105] In some specific embodiments, the ground wire insulation monitoring device further includes a fault location module;
[0106] The fault location module is used to determine all abnormal values in multiple target characteristic value groups according to multiple target characteristic value groups, and determine the abnormal position of the target grounding wire insulation shell based on the positions corresponding to all abnormal values.
[0107] The fault location module can also be used to determine all abnormal values in the multiple target characteristic values according to the multiple target characteristic values, and determine the abnormal position of the target grounding wire insulation shell based on the positions corresponding to all the abnormal values.
[0108] Specifically, after the grounding wire insulation monitoring equipment sounds an alarm, the fault location can be quickly located, which can improve the efficiency of staff in handling abnormalities, achieve timely maintenance of the grounding wire, and avoid serious losses caused by grounding wire abnormalities.
[0109] In some specific embodiments, the data acquisition module 101 is specifically used to:
[0110] The temperature, humidity, current and voltage are collected synchronously, and the temperature, humidity, current and voltage at the same location are taken as a set to obtain a data set.
[0111] Transfer multiple data sets to the data fusion module.
[0112] In some specific embodiments, the data acquisition module 101 further includes a data preprocessing unit; the data preprocessing unit is specifically configured to:
[0113] The synchronously collected temperature, humidity, current and voltage are filtered and standardized.
[0114] The temperature, humidity, current and voltage at the same location are taken as a set to obtain a data set including:
[0115] The filtered and standardized temperature, humidity, current, and voltage at the same location are taken as a set to obtain a data set.
[0116] Specifically, filtering and standardizing the collected data can improve the accuracy of the collected data and the efficiency of subsequent data processing, thereby ensuring the accuracy of monitoring and avoiding false alarms.
[0117] The above-mentioned grounding wire insulation monitoring equipment can obtain as many data sets as possible by collecting data sets of temperature, humidity, current and voltage at different positions of the target grounding wire, ensuring the number of calculated eigenvalues. The method of jointly identifying anomalies with multiple eigenvalues can ensure the accuracy of the anomaly recognition module in identifying anomalies, and ultimately avoid the impact of interference on monitoring, improve the accuracy of monitoring, and avoid false alarms.
[0118] An embodiment of the present application also provides a power monitoring system, characterized in that it includes at least any one of the above-mentioned ground wire insulation monitoring devices.
[0119] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0120] In the above embodiments, the descriptions of each embodiment have their own focus. For parts not described or recorded in detail in one embodiment, please refer to the relevant descriptions of other embodiments. Unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other. The technical features of different embodiments can be combined to form new embodiments based on their inherent logical relationships.
[0121] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.
Claims
1. A ground wire insulation monitoring device, characterized in that: include: Data acquisition module, data fusion module, anomaly recognition module and anomaly alarm module; The data acquisition module is used to simultaneously acquire data sets of temperature, humidity, current and voltage at different positions of the target ground wire, and transmit multiple data sets to the data fusion module; The data fusion module is configured to calculate a plurality of feature values based on the plurality of data sets and transmit the plurality of feature values to the anomaly identification module; The abnormality identification module is used to determine whether the target grounding wire insulation shell has an abnormality based on multiple characteristic values, and if the target grounding wire insulation shell has an abnormality, send an alarm control signal to the abnormality alarm module; The abnormal alarm module is used to issue an alarm according to the alarm control signal; The data fusion module is specifically used for: For each data set, a first eigenvalue is calculated based on the temperature and humidity in the data set, and a second eigenvalue is calculated based on the current and voltage; delivering a plurality of first feature values and a plurality of second feature values to the abnormality identification module; The calculating of the first characteristic value based on the temperature and humidity in the data set and the calculating of the second characteristic value based on the current and voltage include: Using a first formula, calculate and obtain the first eigenvalue; The first formula is: Wherein, C1 represents the first characteristic value, T represents the temperature acquisition value, Indicates the temperature standard value, a indicates the temperature coefficient, and R indicates the humidity collection value. represents the humidity standard value, and b represents the humidity coefficient; Using the second formula, calculate and obtain the second eigenvalue; Wherein, C2 represents the second characteristic value, I represents the current acquisition value, Indicates the current standard value, c indicates the current coefficient, V indicates the voltage acquisition value, represents the voltage standard value, and d represents the voltage coefficient.
2. The ground wire insulation monitoring device according to claim 1, characterized in that: The abnormality identification module is specifically used for: The first eigenvalue and the second eigenvalue at the same position are defined as a target eigenvalue group; Multiple target feature value groups are input into a preset grounding wire abnormality identification model to obtain an output result of the grounding wire abnormality identification model, and the output result is used as a target grounding wire insulation shell abnormality judgment result.
3. The ground wire insulation monitoring device according to claim 2, characterized in that: The model training process of the preset grounding wire anomaly recognition model includes: Acquire multiple historical characteristic value groups, wherein the historical characteristic value groups include a first characteristic value and a second characteristic value at the same historical position corresponding to when the insulation of the ground wire is normal, and different historical characteristic value groups correspond to different positions; Randomly select the location and number of cluster centers; Assign each historical feature value group to the nearest cluster center to obtain multiple clusters; Calculate the mean of the historical feature value group in each cluster and set the mean as the updated cluster center; Determine whether the current number of iterations has reached the maximum number of iterations; If the current number of iterations reaches the maximum number of iterations, the updated cluster center is set as the cluster center of the preset grounding line anomaly recognition model; If the current number of iterations has not reached the maximum number of iterations, the current number of iterations is increased by one, and the process returns to the step of "assigning each historical feature value group to the nearest cluster center to obtain multiple clusters" based on the updated cluster center to continue iterating; The process of obtaining the output result of the ground wire abnormality identification model includes: Get multiple target feature value groups of input; For each target feature value group, multiple distances from the target feature value group to multiple cluster centers of the preset grounding line anomaly identification model are calculated respectively; if the minimum value of the multiple distances is less than a preset threshold, the target feature value group is considered to be a normal value; if the minimum value of the multiple distances is greater than or equal to the preset threshold, the target feature value group is considered to be an abnormal value; If all target characteristic value groups are normal values, the output result is that there is no abnormality in the insulation shell of the target grounding wire; otherwise, the output result is that there is an abnormality in the insulation shell of the target grounding wire.
4. The ground wire insulation monitoring device according to claim 3, characterized in that: The hyperparameters of the preset grounding line anomaly recognition model are optimized by a particle swarm algorithm or an annealing algorithm; wherein the hyperparameters include at least: the position of the randomly selected cluster center, the number of cluster centers, the maximum number of iterations and a preset threshold.
5. The ground wire insulation monitoring device according to claim 3, characterized in that: The ground wire insulation monitoring device also includes a fault location module; The fault location module is used to determine all abnormal values in multiple target characteristic value groups according to multiple target characteristic value groups, and determine the abnormal position of the target grounding wire insulation shell based on the positions corresponding to all abnormal values.
6. The ground wire insulation monitoring device according to claim 1, characterized in that: The data acquisition module is specifically used for: synchronously collecting temperature, humidity, current, and voltage, and taking the temperature, humidity, current, and voltage at the same location as a set to obtain the data set; The plurality of data sets are transmitted to the data fusion module.
7. The ground wire insulation monitoring device according to claim 6, characterized in that: The data acquisition module further includes a data preprocessing unit; the data preprocessing unit is specifically configured to: Filter and standardize the synchronously collected temperature, humidity, current and voltage; The temperature, humidity, current and voltage at the same location are taken as a set to obtain the data set, including: The filtered and standardized temperature, humidity, current, and voltage at the same location are taken as a set to obtain the data set.
8. A power monitoring system, characterized in that: The device at least comprises the ground wire insulation monitoring device according to any one of claims 1 to 7.
Citation Information
Patent Citations
Substation cable insulation monitoring method and device
CN111679162A
Method and system for identifying development stages of GIS insulation defect partial discharge
CN113325281A