Water immersion detection method and device for power grid equipment and electronic equipment

Abstract

The invention discloses a water immersion detection method and device for power grid equipment and electronic equipment. The method comprises the steps that monitoring data are acquired, the monitoring data are obtained by monitoring the surrounding environment of the power grid equipment through multiple types of sensors, the multiple types of sensors are installed around the power grid equipment, and the multiple types of sensors comprise at least one of a temperature sensor, a liquid level sensor and an audio sensor; the monitoring data are identified, abnormal data in the monitoring data are determined, and the types of the abnormal data comprise at least one of temperature abnormal data, water level abnormal data and audio abnormal data; based on the abnormal data and the position of the sensor corresponding to the abnormal data, the position where water immersion occurs is determined; and alarm information is generated, and the alarm information comprises the position where water immersion occurs. The technical problem that it is difficult to monitor water immersion of power grid equipment in time in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of power system and power grid equipment detection, and in particular to a water immersion detection method, device and electronic equipment for power grid equipment. Background Art

[0002] In recent years, power grid equipment has become the main choice in urban construction. During urban construction, power grid equipment is usually installed outdoors, which will be affected by weather factors such as rain, causing its surface to be wet. Since the waterproof and moisture-proof performance of power grid equipment is considered to be improved when it is manufactured, people often ignore the work of preventing moisture intrusion on power grid equipment.

[0003] At present, there is still a lack of water intrusion detection for power grid equipment, and it is impossible to conduct water intrusion monitoring in a timely and effective manner. If the power grid equipment is not tested for water during use, it may cause water ingress to the power grid equipment in the long run, resulting in short circuits in the wires, which in turn causes communication interruptions and other problems, affecting the normal operation of the power system. Therefore, it is very important to conduct water intrusion detection on power grid equipment to ensure the normal operation and safety of the power system.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a method, a device and an electronic device for detecting water immersion in power grid equipment, so as to at least solve the technical problem that it is difficult to timely monitor water immersion in power grid equipment in the prior art.

[0006] According to one aspect of an embodiment of the present invention, a method for detecting water immersion in power grid equipment is provided, comprising: acquiring monitoring data, wherein the monitoring data is obtained by respectively monitoring the surrounding environment of the power grid equipment by multiple types of sensors, the multiple types of sensors are installed around the power grid equipment, and the multiple types of sensors include at least one of the following: a temperature sensor, a liquid level sensor, and an audio sensor; identifying the monitoring data, and determining abnormal data in the monitoring data, wherein the type of the abnormal data includes at least one of the following: abnormal temperature data, abnormal water level data, and abnormal audio data; determining a location where water immersion has occurred based on the abnormal data and the location of the sensor corresponding to the abnormal data; and generating alarm information, wherein the alarm information includes the location where water immersion has occurred.

[0007] Optionally, the monitoring data is identified and abnormal data in the monitoring data is determined, including: identifying the monitoring data and determining the type of the monitoring data, wherein the types of the monitoring data include: temperature monitoring data, water level monitoring data, and audio monitoring data; based on the type of the monitoring data, determining preset data corresponding to the monitoring data; comparing the monitoring data with the preset data to determine whether the monitoring data is abnormal data.

[0008] Optionally, the monitoring data is compared with preset data to determine whether the monitoring data is abnormal data, including: when the monitoring data is temperature monitoring data and the preset data is a preset temperature, if the temperature monitoring data is greater than the preset temperature, then the temperature monitoring data is determined to be temperature abnormal data; if the temperature monitoring data is less than or equal to the preset temperature, then the temperature monitoring data is determined not to be temperature abnormal data; when the monitoring data is water level monitoring data and the preset data is a preset water level, if the water level monitoring data is greater than the preset water level, then the water level monitoring data is determined to be water level abnormal data; if the water level monitoring data is less than or equal to the preset water level, then the water level monitoring data is determined not to be water level abnormal data; when the monitoring data is audio monitoring data and the preset data is water immersion audio data, if the audio monitoring data is the same as the water immersion audio data, then the audio monitoring data is determined to be audio abnormal data; if the audio monitoring data is different from the water immersion audio data, then the audio monitoring data is determined not to be audio abnormal data.

[0009] Optionally, when the monitoring data is audio monitoring data and the preset data is water immersion audio data, the method further includes: performing feature analysis on the audio monitoring data to obtain audio monitoring features of the audio monitoring data, wherein the audio monitoring features include at least one of the following: audio frequency, audio amplitude, audio waveform; determining the similarity between the audio monitoring features and the preset water immersion audio corresponding to the water immersion audio data; and based on the similarity, determining whether the audio monitoring data and the water immersion audio data are the same.

[0010] Optionally, in response to the type of abnormal data being abnormal water level data, the method further includes: controlling a camera to shoot a position corresponding to the abnormal water level data to obtain a water level video; identifying the water level in the water level video to determine the abnormal water level state.

[0011] Optionally, in response to the type of abnormal data being abnormal water level data, the method further includes: controlling a water accumulation cleaning device to pump water from a position corresponding to the abnormal water level data.

[0012] Optionally, the accumulated water cleaning device is controlled to perform pumping processing on the position corresponding to the abnormal water level data, including: controlling the accumulated water cleaning device to perform pumping processing on the position corresponding to the abnormal water level data for a first preset time period; after waiting for a second preset time period, obtaining the water level monitoring data of the position corresponding to the abnormal water level data; identifying the water level monitoring data of the position corresponding to the abnormal water level data to obtain an identification result.

[0013] Optionally, the method also includes: if the recognition result is that the water level monitoring data is abnormal water level data, then controlling the accumulated water cleaning device to perform pumping processing on the position corresponding to the water level monitoring data for a first preset time period; if the recognition result is that the water level monitoring data is not abnormal water level data, then stopping pumping processing on the position corresponding to the water level monitoring data.

[0014] According to another aspect of an embodiment of the present invention, a water immersion detection device for power grid equipment is also provided, which is used to implement the water immersion detection method for power grid equipment of the above embodiment, including: an acquisition module, used to acquire monitoring data, wherein the monitoring data is obtained by various types of sensors that monitor the surrounding environment of the power grid equipment respectively, and the various types of sensors are installed around the power grid equipment, and the various types of sensors include: temperature sensors, liquid level sensors, and audio sensors; an identification module, used to identify the monitoring data and determine abnormal data, wherein the types of abnormal data include: abnormal temperature data, abnormal water level data, and abnormal audio data; a first determination module, used to determine the location where the water immersion occurs based on the abnormal data and the location of the sensor corresponding to the abnormal data; a generation module, used to generate alarm information, wherein the alarm information includes the location where the water immersion occurs.

[0015] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the method in each embodiment of the present invention is executed when the program is running.

[0016] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0017] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0018] In an embodiment of the present invention, a method for detecting water immersion in power grid equipment is provided, including: obtaining monitoring data; identifying the monitoring data and determining abnormal data in the monitoring data; determining the location where the water immersion occurs based on the abnormal data and the location of the sensor corresponding to the abnormal data; and generating alarm information. It is easy to notice that the present application actively monitors the environmental data surrounding the power grid equipment and automatically identifies the abnormal data in the monitoring data, thereby accurately determining the location where the power grid equipment is flooded, thereby achieving the purpose of timely and accurate monitoring of the power grid equipment flooding, thereby achieving the technical effect of timely and accurate identification of the occurrence of water immersion in the power grid equipment, and thus solving the technical problem that the prior art is difficult to timely monitor the flooding of the power grid equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0020] Figure 1 is a flow chart of a method for detecting water immersion in power grid equipment according to an embodiment of the present invention;

[0021] Figure 2 is a schematic diagram of a water immersion detection device for power grid equipment according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] According to an embodiment of the present invention, a method embodiment of a water immersion detection method for power grid equipment is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] Figure 1 is a flow chart of a method for detecting water immersion in a power grid device according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0026] Step S102, obtaining monitoring data.

[0027] The monitoring data is obtained by using various types of sensors to monitor the surrounding environment of the power grid equipment respectively. The various types of sensors are installed around the power grid equipment. The various types of sensors include at least one of the following: a temperature sensor, a liquid level sensor, and an audio sensor.

[0028] The above-mentioned monitoring data can be used to characterize the ambient environment level of the location where the power grid equipment is located, for example, the temperature level, humidity level or noise level of the location where the power grid equipment is located. The monitoring data may include at least one of the following: temperature data, humidity data, water volume data, water level data, audio data. The monitoring data is not limited here and can be determined according to actual needs. The monitoring data can be monitored and sent by the sensor in real time, or it can be sent by the sensor to a cloud storage platform for storage for call. Furthermore, after the sensor monitors the data, it can generate monitoring data and synchronously generate a monitoring data identifier, which can be used to uniquely determine the monitoring data and the sensor that monitors the monitoring data. The monitoring data identifier can be generated by combining the timestamp of the generated monitoring data with a random number, or it can be generated using a unique identifier such as a universal unique identifier or a globally unique identifier. Through the monitoring data, the surrounding environment of the power grid equipment can be monitored in real time and accurately for subsequent water immersion detection.

[0029] The above-mentioned power grid equipment can be used to transmit and distribute electricity. It is the infrastructure of the power system and ensures the stable supply and safe use of electricity. Through the power grid equipment, the generated electric energy can be transmitted to the user, and the dispatching and control of electric energy can be realized during the transmission process to meet the electricity demand of different regions and users. The power grid equipment can be a power generation equipment, a transmission equipment or a distribution equipment. For example, the power grid equipment can be a substation, a power plant, a transformer, a cable or a switchgear; the above-mentioned power grid equipment can be a power transmission network, a high-voltage distribution network, a medium-voltage distribution network or a low-voltage distribution network. The type of power grid equipment is not limited here and can be determined according to actual needs.

[0030] The above-mentioned sensor is a device that can detect, sense and receive specific physical quantities or specific signals, that is, the temperature environment, humidity environment and noise environment of the power grid equipment can be monitored through the sensor. The sensor can include at least one of the following: temperature sensor, liquid level sensor, audio sensor, pressure sensor, optical sensor, and the type of sensor is not limited here and can be determined according to actual needs.

[0031] In an optional embodiment, the sensor can be fixedly installed around the power grid equipment, or can be detachably installed around the power grid equipment for easy maintenance. Optionally, the sensor can be installed around the power grid equipment when the power grid equipment leaves the factory, or can be installed after the power grid equipment is laid.

[0032] Furthermore, when installing the sensor, the location where the sensor is installed can be recorded synchronously to generate a sensor identification, which may include but is not limited to sensor information and installation location information. The sensor identification is not limited here and can be determined according to actual needs. Through the sensor identification, the sensor that monitors the monitoring data can be located, and the installation location of the sensor can also be determined. Alternatively, a data table of sensors and their installation locations can also be generated, and the installation location of each sensor can be determined through the data table.

[0033] The above-mentioned temperature sensor can be used to detect, sense and receive the temperature around the power grid equipment, and convert the temperature into an electrical signal output to be acquired and analyzed. The temperature sensor can include at least one of the following: a thermistor sensor, a thermocouple sensor, and an infrared sensor. The type of temperature sensor is not limited here and can be determined according to actual needs. Based on the historical accidents of the power grid equipment, the temperature sensor can be installed in a position where the temperature around the power grid equipment is prone to significant changes, so that when the power grid equipment is flooded or the power grid equipment is overheated, the temperature change can be monitored in time.

[0034] The above-mentioned liquid level sensor can be used to detect, sense and receive the liquid height or liquid volume around the power grid equipment, and convert the liquid height or liquid volume into an electrical signal output to be acquired and analyzed. The liquid level temperature sensor may include at least one of the following: a float-type liquid level sensor, a pressure-type liquid level sensor, and an ultrasonic liquid level sensor. The type of liquid level sensor is not limited here and can be determined according to actual needs. According to the historical flooding situation of the geographical location of the power grid equipment, the liquid level sensor can be installed in cable wells, substations and other low-lying locations prone to water accumulation, so that when the liquid level exceeds the preset threshold, the liquid level change can be monitored in time.

[0035] The above-mentioned audio sensor can be used to detect, sense and receive the sounds around the power grid equipment, and convert the sound signals into electrical signals for output, so as to be acquired and analyzed. The audio sensor may include at least one of the following: a microphone sensor, a vibration sensor, and a sound spectrum sensor. The type of the audio sensor is not limited here and can be determined according to actual needs. The audio sensor can be installed at the exposed position of the power equipment according to the weather conditions of the geographical location of the power grid equipment, so that when there is the sound of flowing water, the water flow can be monitored in time.

[0036] In an optional embodiment, the monitoring data can be directly obtained from the sensor, or from a cloud storage platform, where the monitoring data is uploaded by the sensor at regular intervals. The monitoring data can also be obtained from the monitoring system of the power system. The monitoring data can also be reported manually.

[0037] In another optional embodiment, the monitoring data may be obtained by parsing the monitoring data identifier. Optionally, the monitoring data identifier may be parsed according to the communication protocol, and corresponding operations may be performed according to the command parameters.

[0038] Step S104: Identify the monitoring data and determine abnormal data in the monitoring data.

[0039] The type of abnormal data includes at least one of the following: abnormal temperature data, abnormal water level data, and abnormal audio data.

[0040] The above-mentioned abnormal data may be data characterizing the abnormal level of the surrounding environment where the power grid equipment is located, and may specifically indicate that the power equipment is flooded, for example, the abnormal temperature level, abnormal humidity level, or abnormal noise level at the location where the power grid equipment is located. The abnormal data may include at least one of the following: abnormal temperature data, abnormal humidity data, abnormal water volume data, abnormal water level data, and abnormal audio data. The abnormal data is not limited here and can be determined according to actual needs. Through the abnormal data, the abnormal environment around the power grid equipment can be monitored in real time and accurately to indicate that the power grid equipment is abnormal.

[0041] The temperature anomaly data may be data indicating abnormal ambient temperature at the location of the power grid device. Specifically, the temperature anomaly data may be temperature data indicating that the ambient temperature at the location of the power grid device is greater than a preset temperature. The temperature anomaly data may include but is not limited to temperature. The preset temperature is a temperature value indicating that the power grid device is in normal operation. Through the temperature anomaly data, the abnormal ambient temperature of the power grid device may be accurately monitored in real time, indicating that there may be a fault.

[0042] The above-mentioned abnormal water level data may be data characterizing abnormal water levels around the location of the power grid equipment. Specifically, the abnormal water level data may be water level data indicating that the water level around the location of the power grid equipment is higher than a preset water level. The abnormal water level data may include but is not limited to water level height. The preset water level is a water level height value indicating that no flooding occurs when the power grid equipment is in normal operation. Through the abnormal water level data, the abnormal water level around the power grid equipment can be accurately monitored in real time, and there may be flooding.

[0043] The above-mentioned audio abnormality data may be data indicating that water flows around the location of the power grid equipment. Specifically, the audio abnormality data may be audio data when the monitoring data is preset water immersion audio data. The audio abnormality data may include but is not limited to the frequency and amplitude of the sound wave. The preset water immersion audio data is audio data indicating that water has occurred around the power grid equipment. Through the audio abnormality data, it is possible to accurately monitor in real time that liquid flows around the power grid equipment and there may be water accumulation.

[0044] In an optional embodiment, the monitoring data can be input into a pre-trained first recognition model for recognition to determine abnormal data. The first recognition model may include at least one of the following: logistic regression, decision tree, random forest, support vector machine. The first recognition model is not limited here and can be determined according to actual needs. Depending on the type of monitoring data, the type of the first recognition model may include but is not limited to: a first temperature recognition model, a first water level recognition model, and a first audio recognition model. It is not limited here and can be set as needed. For example, temperature data, water level data, and audio data can be used as monitoring data and input into a pre-trained first temperature recognition model, a first water level recognition model, and a first audio recognition model for recognition, respectively, to determine abnormal data in each monitoring data.

[0045] In another optional embodiment, the monitoring data can be identified by a clustering algorithm, the cluster center is initialized, and the distance between each monitoring data and the cluster center is calculated. The output clustering result can be used to identify abnormal data in the monitoring data. For example, taking three types of monitoring data as an example, the three different types of monitoring data can be divided into three data clusters respectively, or the monitoring data can be clustered according to different geographical locations. Secondly, the abnormal values ​​of each cluster are observed, for example, the data value whose distance from the cluster center is greater than a preset threshold is abnormal data. The clustering algorithm can include at least one of the following: K-means clustering algorithm, Gaussian mixture model clustering algorithm. The clustering algorithm is not limited here and can be determined according to actual needs.

[0046] In another optional embodiment, with respect to the type of monitoring data, for example, taking the example that there are three types of monitoring data, the monitoring data is divided into temperature monitoring data, water level monitoring data, and audio monitoring data. Preset normal operating data ranges corresponding to each type of monitoring data can be pre-stored, that is, a preset temperature normal operating data range corresponding to the temperature monitoring data, a preset water level normal operating data range corresponding to the water level monitoring data, and a preset audio normal operating data range corresponding to the audio monitoring data. The monitoring data are compared with the preset normal operating data ranges of the corresponding types respectively. If the monitoring data is not within the preset normal operating data range, the monitoring data is abnormal data.

[0047] Step S106: determining the location where the flooding occurs based on the abnormal data and the location of the sensor corresponding to the abnormal data.

[0048] The location of the sensor corresponding to the above abnormal data is the specific location where the sensor is installed around the power equipment in the above step S102. This location can be used to indicate that the detection data monitored by the sensor installed at this location is abnormal data, that is, the power equipment at this location has been flooded.

[0049] The above-mentioned flooding can be used to indicate that the power grid equipment is flooded. When water flows into the power equipment or on the surface of the power equipment, the power equipment may be flooded, which may cause serious consequences such as short circuit, leakage, equipment damage, and even fire in the power system. Therefore, it is necessary to monitor the flooding situation in time.

[0050] In an optional embodiment, after determining the abnormal data in the monitoring data, the monitoring data identifier corresponding to the abnormal data can be parsed to obtain the sensor corresponding to the abnormal data. Further, the corresponding sensor identifier can be determined by the sensor, and then the specific location of the sensor installed in the power system can be determined by parsing the sensor identifier, and then the location where the flooding occurs can be determined. Alternatively, the installation location corresponding to the sensor can be determined from a pre-configured data table. Optionally, the monitoring data identifier can be parsed according to the communication protocol, and the corresponding operation can be performed according to the command parameters.

[0051] Step S108, generating alarm information.

[0052] The alarm information includes the location where the flooding occurs.

[0053] The above-mentioned alarm information can be used to indicate that water flooding has occurred in the power equipment. The alarm information may include at least one of the following: the location where the water flooding occurred, the time when the water flooding occurred, and the water flooding handling strategy. The alarm information is not limited here and can be determined according to actual needs.

[0054] Furthermore, the conditions and alarm rules for generating alarm information can be pre-configured. Optionally, the conditions for generating alarm information can be when abnormal data is determined, or when the location of flooding is determined. The alarm rules for alarm information can be to upload the alarm information to the monitoring system of the power system to warn that the power equipment is flooded, or to send the alarm information to the terminal held by the operation and maintenance personnel to remind the operation and maintenance personnel of the alarm information through sound alarm, vibration alarm, text alarm, etc., so as to handle it as soon as possible.

[0055] In an embodiment of the present invention, a method for detecting water immersion in power grid equipment is provided, including: obtaining monitoring data; identifying the monitoring data and determining abnormal data in the monitoring data; determining the location where the water immersion occurs based on the abnormal data and the location of the sensor corresponding to the abnormal data; and generating alarm information. It is easy to notice that the present application actively monitors the environmental data surrounding the power grid equipment and automatically identifies the abnormal data in the monitoring data, thereby accurately determining the location where the power grid equipment is flooded, thereby achieving the purpose of timely and accurate monitoring of the power grid equipment flooding, thereby achieving the technical effect of timely and accurate identification of the occurrence of water immersion in the power grid equipment, and thus solving the technical problem that the prior art is difficult to timely monitor the flooding of the power grid equipment.

[0056] Optionally, the monitoring data is identified and abnormal data in the monitoring data is determined, including: identifying the monitoring data and determining the type of the monitoring data, wherein the types of the monitoring data include: temperature monitoring data, water level monitoring data, and audio monitoring data; based on the type of the monitoring data, determining preset data corresponding to the monitoring data; comparing the monitoring data with the preset data to determine whether the monitoring data is abnormal data.

[0057] The above-mentioned preset data can be used to characterize the normal level of the surrounding environment where the power grid equipment is located, for example, the temperature level, humidity level or noise level of the location where the power grid equipment is located. The preset data may include at least one of the following: temperature data, humidity data, water volume data, water level data, audio data, the preset data is not limited here, and can be determined according to actual needs. The preset data can be determined manually or by experts based on experience, which is not limited here; or, it can also be input into an analysis model based on historical monitoring data and analyzed by the analysis model. The analysis model may include one of the following: neural network, decision tree, support vector machine, the analysis model is not limited here, and can be determined according to actual needs. The preset data can be pre-stored in a cloud storage platform for storage and call. Through the preset data, it can be judged whether the surrounding environment where the power grid equipment is located is at a normal level and whether the power grid equipment is flooded.

[0058] The above-mentioned temperature monitoring data can be used to characterize the ambient temperature level of the location where the power grid equipment is located. The temperature monitoring data can be monitored and sent in real time by a temperature sensor, or sent by a temperature sensor to a cloud storage platform for storage and retrieval. The above-mentioned water level monitoring data can be used to characterize the surrounding liquid deposition level of the location where the power grid equipment is located. The water level monitoring data can be monitored and sent in real time by a liquid level sensor, or sent by a liquid level sensor to a cloud storage platform for storage and retrieval. The above-mentioned audio monitoring data can be used to characterize the surrounding liquid flow level of the location where the power grid equipment is located. The audio monitoring data can be monitored and sent in real time by an audio sensor, or sent by an audio sensor to a cloud storage platform for storage and retrieval.

[0059] In an optional embodiment, the monitoring data type can be identified by custom rules, such as data length or data physical unit; or, the monitoring data type can be identified by regular expressions; or, the monitoring data is input into a pre-trained second recognition model for identification to determine the type of each monitoring data. The second recognition model can include at least one of the following: logistic regression, decision tree, random forest, support vector machine, and the second recognition model is not limited here and can be determined according to actual needs.

[0060] In an optional embodiment, the monitoring data can be divided into different types of data. For example, the monitoring data can be divided into three different types of data: temperature monitoring data, water level monitoring data, and audio monitoring data. Since the indicators and physical units of different types of detection data are different, the monitoring data can be compared with the preset data according to the type of monitoring data. Furthermore, the monitoring data is compared with the preset data to determine whether the monitoring data is abnormal data. If it is abnormal data, it means that the power equipment may be flooded. Optionally, the monitoring data and the preset data are input into a comparison model, and the output value of the comparison model is used to indicate whether the monitoring data is abnormal data. The comparison model can be one of the following: support vector machine, random forest, logistic regression, neural network. The analysis model is not limited here and can be determined according to actual needs.

[0061] Optionally, the monitoring data is compared with preset data to determine whether the monitoring data is abnormal data, including: when the monitoring data is temperature monitoring data and the preset data is a preset temperature, if the temperature monitoring data is greater than the preset temperature, then the temperature monitoring data is determined to be temperature abnormal data; if the temperature monitoring data is less than or equal to the preset temperature, then the temperature monitoring data is determined not to be temperature abnormal data; when the monitoring data is water level monitoring data and the preset data is a preset water level, if the water level monitoring data is greater than the preset water level, then the water level monitoring data is determined to be water level abnormal data; if the water level monitoring data is less than or equal to the preset water level, then the water level monitoring data is determined not to be water level abnormal data; when the monitoring data is audio monitoring data and the preset data is water immersion audio data, if the audio monitoring data is the same as the water immersion audio data, then the audio monitoring data is determined to be audio abnormal data; if the audio monitoring data is different from the water immersion audio data, then the audio monitoring data is determined not to be audio abnormal data.

[0062] In an optional embodiment, depending on the type of monitoring data, the preset data corresponding to the monitoring data is different, and thus the rules for comparing the monitoring data with the preset data are different.

[0063] If the monitoring data is temperature monitoring data, then the corresponding preset data is the preset temperature. Since water ingress into the power grid equipment will cause the insulating material inside to become damp and reduce the insulation performance, thereby causing the power grid equipment to have a breakdown failure and generate local high temperature, it can be set that when the temperature monitoring data is greater than the preset temperature, the temperature monitoring data is determined to be temperature abnormality data, otherwise it is not temperature abnormality data. If the monitoring data is water level monitoring data, then the corresponding preset data is the preset water level. When rainfall increases, water may accumulate around the power grid equipment, causing the water level to rise, so it can be set that when the water level monitoring data is greater than the preset water level, the water level monitoring data is determined to be water level abnormality data, otherwise it is not water level abnormality data. If the monitoring data is audio monitoring data, then the corresponding preset data is water immersion audio data. Since the sound characteristics of different substances are different, such as the frequency and tone of the sound are different, it is possible to determine whether the audio monitoring data is water immersion audio data by identifying whether the audio monitoring data is the same as the water immersion audio data.

[0064] Optionally, when the monitoring data is audio monitoring data and the preset data is water immersion audio data, the method further includes: performing feature analysis on the audio monitoring data to obtain audio monitoring features of the audio monitoring data, wherein the audio monitoring features include at least one of the following: audio frequency, audio amplitude, audio waveform; determining the similarity between the audio monitoring features and the preset water immersion audio corresponding to the water immersion audio data; and based on the similarity, determining whether the audio monitoring data and the water immersion audio data are the same.

[0065] In an optional embodiment, the audio monitoring data can be analyzed by short-time Fourier transform (STFT) and Mel Frequency Cepstral Coefficients (MFCC) to extract audio monitoring features of the audio monitoring data. The audio monitoring features include at least one of the following: audio frequency, audio amplitude, and audio waveform. The audio monitoring features are not limited here and can be set as needed. Furthermore, based on the audio features, the audio monitoring data and the water immersion audio data are compared, and the similarity between the audio monitoring features and the preset water immersion audio can be calculated by cosine similarity, Euclidean distance or Pearson correlation coefficient. If the similarity is calculated by Euclidean distance, and the distance between the audio monitoring features and the preset water immersion audio features is less than the preset distance, it means that the similarity is high, and then it is determined that the audio monitoring data is the same as the water immersion audio data, otherwise they are different.

[0066] Optionally, in response to the type of abnormal data being abnormal water level data, the method further includes: controlling a camera to shoot a position corresponding to the abnormal water level data to obtain a water level video; identifying the water level in the water level video to determine the abnormal water level state.

[0067] In an optional embodiment, when the monitoring data is identified as abnormal water level data, the camera in the power system is further triggered to record a video of the location corresponding to the abnormal water level data, and a water level video of the location of the sensor corresponding to the abnormal data is obtained, and then the abnormal water level state is determined by identifying the water level video, so that the power equipment can be repaired according to the abnormal water level state. Optionally, the abnormal water level state is determined by inputting the water level video into a pre-trained third recognition model for recognition. The third recognition model can include at least one of the following: logistic regression, decision tree, random forest, support vector machine, and the third recognition model is not limited here and can be determined according to actual needs.

[0068] Optionally, in response to the type of abnormal data being abnormal water level data, the method further includes: controlling a water accumulation cleaning device to pump water from a position corresponding to the abnormal water level data.

[0069] The above-mentioned water cleaning device can be a device that uses gravity, air pressure, etc. to pump water. The water cleaning device can include but is not limited to a pump-suction water pump, which can be determined according to actual needs. The water cleaning device can be controlled by the control system of the power system to pump water to a specific location, clean the water around the power equipment, and avoid short circuits caused by moisture in the power equipment, thereby affecting the normal operation of the power system.

[0070] Optionally, the accumulated water cleaning device is controlled to perform pumping processing on the position corresponding to the abnormal water level data, including: controlling the accumulated water cleaning device to perform pumping processing on the position corresponding to the abnormal water level data for a first preset time period; after waiting for a second preset time period, obtaining the water level monitoring data of the position corresponding to the abnormal water level data; identifying the water level monitoring data of the position corresponding to the abnormal water level data to obtain an identification result.

[0071] In order to effectively handle the accumulated water, the duration of the water cleaning device for pumping water can be pre-configured as a first preset duration, which can be set according to user needs, and this application does not limit this. For example, the first preset duration is set to 4 minutes, wherein the first preset duration can also be set to 8 minutes or 10 minutes. The value of the first preset duration is not limited here and can be determined according to actual needs. Then, after the water pumping treatment, the position is monitored again to determine that the accumulated water treatment is completed. In order to ensure the stability of the water level and improve the accuracy of the monitoring results, the second preset duration is pre-configured as the waiting time after the accumulated water treatment is completed. The second preset duration can be set according to user needs, and this application does not limit this. For example, the second preset duration is set to 30 minutes, wherein the second preset duration can also be set to 40 minutes or 50 minutes. The value of the second preset duration is not limited here and can be determined according to actual needs. Further, the water level monitoring data of the position corresponding to the abnormal water level data is identified again to determine whether the water level monitoring data of the position is abnormal. Optionally, it is possible to determine whether the water level monitoring data is abnormal by manually determining whether the water level monitoring data is abnormal, or by identifying it through a fourth recognition model. The fourth recognition model may include at least one of the following: logistic regression, decision tree, random forest, support vector machine, and the fourth recognition model is not limited here and can be determined according to actual needs.

[0072] Optionally, the method also includes: if the recognition result is that the water level monitoring data is abnormal water level data, then controlling the accumulated water cleaning device to perform pumping processing on the position corresponding to the water level monitoring data for a first preset time period; if the recognition result is that the water level monitoring data is not abnormal water level data, then stopping pumping processing on the position corresponding to the water level monitoring data.

[0073] In order to ensure the effect of clearing the accumulated water, the water level monitoring data at the location corresponding to the abnormal water level data is identified. After obtaining the identification result, it is further determined whether to continue the pumping process based on the identification result. If the water level monitoring data is still abnormal data, the pumping process is repeated until the water level monitoring data at the location is no longer abnormal data, otherwise the pumping process will not be continued.

[0074] according to Figure 2 is a schematic diagram of a water immersion detection device for power grid equipment according to an embodiment of the present invention. Figure 2 As shown, the device includes: an acquisition module 22 , an identification module 24 , a first determination module 26 and a generation module 28 .

[0075] Among them, the acquisition module 22 is used to obtain monitoring data, wherein the monitoring data is obtained by various types of sensors that monitor the surrounding environment of the power grid equipment respectively. The various types of sensors are installed around the power grid equipment, and the various types of sensors include: temperature sensors, liquid level sensors, and audio sensors.

[0076] The identification module 24 is used to identify the monitoring data and determine abnormal data, wherein the types of abnormal data include: abnormal temperature data, abnormal water level data, and abnormal audio data.

[0077] The first determination module 26 is used to determine the location where the flooding occurs based on the abnormal data and the location of the sensor corresponding to the abnormal data.

[0078] The generating module 28 generates alarm information, wherein the alarm information includes the location where the flooding occurs.

[0079] It should be noted that the acquisition module 22, the identification module 24, the first determination module 26 and the generation module 28 correspond to steps S102 to S108 in the above embodiment, and the four modules and the corresponding steps implement the same examples and application scenarios, but are not limited to the contents disclosed in the above embodiment 1. It should be noted that the above modules or units may be hardware components or software components stored in a memory and processed by one or more processors.

[0080] Optionally, the identification module 24 is specifically used to identify the monitoring data and determine the type of the monitoring data, wherein the types of the monitoring data include: temperature monitoring data, water level monitoring data, and audio monitoring data; based on the type of the monitoring data, determine the preset data corresponding to the monitoring data; and compare the monitoring data with the preset data to determine whether the monitoring data is abnormal data.

[0081] Optionally, the identification module 24 is also specifically used for, when the monitoring data is temperature monitoring data and the preset data is a preset temperature, if the temperature monitoring data is greater than the preset temperature, then determining that the temperature monitoring data is temperature abnormality data; if the temperature monitoring data is less than or equal to the preset temperature, then determining that the temperature monitoring data is not temperature abnormality data; when the monitoring data is water level monitoring data and the preset data is a preset water level, if the water level monitoring data is greater than the preset water level, then determining that the water level monitoring data is water level abnormality data; if the water level monitoring data is less than or equal to the preset water level, then determining that the water level monitoring data is not water level abnormality data; when the monitoring data is audio monitoring data and the preset data is water immersion audio data, if the audio monitoring data is the same as the water immersion audio data, then determining that the audio monitoring data is audio abnormality data; if the audio monitoring data is different from the water immersion audio data, then determining that the audio monitoring data is not audio abnormality data.

[0082] Optionally, the device also includes: an analysis module, which is used to perform feature analysis on the audio monitoring data when the monitoring data is audio monitoring data and the preset data is water immersion audio data, so as to obtain audio monitoring features of the audio monitoring data, wherein the audio monitoring features include at least one of the following: audio frequency, audio amplitude, and audio waveform; determine the similarity between the audio monitoring features and the preset water immersion audio corresponding to the water immersion audio data; and determine whether the audio monitoring data and the water immersion audio data are the same based on the similarity.

[0083] Optionally, the device also includes: a second determination module, which is used to control the camera to shoot the position corresponding to the abnormal water level data in response to the type of abnormal data being abnormal water level data to obtain a water level video; identify the water level in the water level video to determine the abnormal water level state.

[0084] Optionally, the device further includes: a first processing module, configured to control the accumulated water cleaning device to perform water pumping processing on a position corresponding to the abnormal water level data in response to the type of the abnormal data being abnormal water level data.

[0085] Optionally, the first processing module is specifically used to control the accumulated water cleaning device to perform water pumping processing on the position corresponding to the abnormal water level data for a first preset time period; after waiting for a second preset time period, obtain the water level monitoring data of the position corresponding to the abnormal water level data; identify the water level monitoring data at the position corresponding to the abnormal water level data to obtain an identification result.

[0086] Optionally, the device also includes: a second processing module, which is used to control the accumulated water cleaning device to perform pumping processing on the position corresponding to the water level monitoring data for a first preset time period if the recognition result is that the water level monitoring data is abnormal water level data; if the recognition result is that the water level monitoring data is not abnormal water level data, then stop pumping processing on the position corresponding to the water level monitoring data.

[0087] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the method in each embodiment of the present invention is executed when the program is running.

[0088] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0089] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0090] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0091] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0092] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0093] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0094] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0095] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0096] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for detecting water immersion in power grid equipment, characterized in that: include: Acquire monitoring data, wherein the monitoring data is obtained by respectively monitoring the surrounding environment of the power grid equipment by multiple types of sensors, the multiple types of sensors are installed around the power grid equipment, and the multiple types of sensors include at least one of the following: a temperature sensor, a liquid level sensor, and an audio sensor; Identifying the monitoring data and determining abnormal data in the monitoring data, wherein the type of the abnormal data includes at least one of the following: abnormal temperature data, abnormal water level data, and abnormal audio data; Determine a location where flooding occurs based on the abnormal data and a location of a sensor corresponding to the abnormal data; Generate alarm information, wherein the alarm information includes the location where the flooding occurs.

2. The water immersion detection method for power grid equipment according to claim 1, characterized in that: Identifying the monitoring data and determining abnormal data in the monitoring data includes: Identify the monitoring data and determine the type of the monitoring data, wherein the type of the monitoring data includes: temperature monitoring data, water level monitoring data, and audio monitoring data; Based on the type of the monitoring data, determining preset data corresponding to the monitoring data; The monitoring data is compared with the preset data to determine whether the monitoring data is abnormal data.

3. The water immersion detection method for power grid equipment according to claim 2, characterized in that: Comparing the monitoring data with the preset data to determine whether the monitoring data is abnormal data includes: In the case where the monitoring data is temperature monitoring data and the preset data is a preset temperature, if the temperature monitoring data is greater than the preset temperature, it is determined that the temperature monitoring data is temperature abnormality data; if the temperature monitoring data is less than or equal to the preset temperature, it is determined that the temperature monitoring data is not temperature abnormality data; In the case where the monitoring data is water level monitoring data and the preset data is a preset water level, if the water level monitoring data is greater than the preset water level, it is determined that the water level monitoring data is abnormal water level data; if the water level monitoring data is less than or equal to the preset water level, it is determined that the water level monitoring data is not abnormal water level data; In the case where the monitoring data is audio monitoring data and the preset data is water immersion audio data, if the audio monitoring data is the same as the water immersion audio data, it is determined that the audio monitoring data is audio abnormality data; if the audio monitoring data is different from the water immersion audio data, it is determined that the audio monitoring data is not audio abnormality data.

4. The water immersion detection method for power grid equipment according to claim 3, characterized in that: In the case where the monitoring data is audio monitoring data and the preset data is water immersion audio data, the method further includes: Performing feature analysis on the audio monitoring data to obtain audio monitoring features of the audio monitoring data, wherein the audio monitoring features include at least one of the following: audio frequency, audio amplitude, and audio waveform; Determining a similarity between the audio monitoring feature and a preset water immersion audio corresponding to the water immersion audio data; Based on the similarity, it is determined whether the audio monitoring data is identical to the water immersion audio data.

5. The water immersion detection method for power grid equipment according to any one of claims 1 to 4, characterized in that: In response to the type of the abnormal data being the abnormal water level data, the method further includes: Controlling the camera to shoot the position corresponding to the abnormal water level data to obtain a water level video; The water level in the water level video is identified to determine an abnormal water level state.

6. The water immersion detection method for power grid equipment according to any one of claims 1 to 4, characterized in that: In response to the type of the abnormal data being abnormal water level data, the method further includes: The accumulated water cleaning device is controlled to pump water from the position corresponding to the abnormal water level data.

7. The method for detecting water immersion in power grid equipment according to claim 6, characterized in that: Controlling the accumulated water cleaning device to pump water from the location corresponding to the abnormal water level data includes: Controlling the accumulated water cleaning device to perform a pumping process on the location corresponding to the abnormal water level data for a first preset time period; After waiting for a second preset time, obtaining water level monitoring data of a location corresponding to the abnormal water level data; The water level monitoring data at the position corresponding to the abnormal water level data is identified to obtain an identification result.

8. The water immersion detection method for power grid equipment according to claim 7, characterized in that: The method further comprises: If the identification result is that the water level monitoring data is the abnormal water level data, controlling the accumulated water cleaning device to perform a pumping process on the position corresponding to the water level monitoring data for a first preset time period; If the identification result is that the water level monitoring data does not contain the abnormal water level data, then the pumping process for the position corresponding to the water level monitoring data is stopped.

9. A water immersion detection device for power grid equipment, used to implement the water immersion detection method for power grid equipment described in claim 1, characterized in that: include: An acquisition module, used for acquiring monitoring data, wherein the monitoring data is obtained by respectively monitoring the surrounding environment of the power grid equipment by multiple types of sensors, the multiple types of sensors are installed around the power grid equipment, and the multiple types of sensors include: temperature sensors, liquid level sensors, and audio sensors; An identification module, used to identify the monitoring data and determine abnormal data, wherein the types of the abnormal data include: abnormal temperature data, abnormal water level data, and abnormal audio data; A first determination module, configured to determine a location where flooding occurs based on the abnormal data and a location of a sensor corresponding to the abnormal data; A generating module generates alarm information, wherein the alarm information includes a location where the flooding occurs.

10. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein the program, when running, executes the water immersion detection method for power grid equipment according to any one of claims 1 to 8.

Images