Power equipment inspection method based on artificial intelligence

Abstract

The invention discloses a power equipment inspection method based on artificial intelligence, and the method comprises the steps: obtaining the inspection staying time of an inspection worker during the inspection of a target object when the inspection worker inspects the target object, then synchronously obtaining the current real-time stage of the target object, carrying out the matching of the real-time stage with a stage adaptation table, and obtaining the inspection staying time of the inspection worker during the inspection of the target object. Obtaining an approval range corresponding to the current real-time stage, if the inspection staying duration is not within the approval range, generating an abnormal signal, and marking the corresponding inspection point as an abnormal inspection point; according to the method, whether the time spent by the personnel during power equipment inspection meets the corresponding inspection requirements or not is determined in the mode, and the method is used for achieving power equipment inspection and is simple, effective and easy to use.

Description

Technical Field

[0001] The present invention belongs to the technical field of power equipment inspection, and specifically is a power equipment inspection method based on artificial intelligence. Background Art

[0002] The patent with publication number CN115273267A discloses a power equipment inspection control method, control device and power equipment inspection system. The control method includes: setting the inspection task of the power equipment according to the installation distribution of the power equipment, the inspection task includes the route inspection task and the fixed-point sampling task; controlling the first inspection device to inspect the power equipment according to the inspection task; receiving the inspection information fed back by the first inspection device when inspecting according to the route inspection task in real time, the inspection information includes the image information, location information and environmental sampling information along the inspection route; obtaining the fixed-point sampling information fed back by the first inspection device when executing the fixed-point sampling task in real time; analyzing whether each power equipment has a fault and the fault type when a fault occurs according to the inspection information and the fixed-point sampling information; classifying and alarming according to the fault type, and controlling the second inspection device to move to the fire fault location according to the positioning information to extinguish the fire when the fault type is a fire fault.

[0003] However, when inspecting power equipment, how to determine whether the inspection of the power equipment by the inspectors is reasonable is a problem. Moreover, the same standards cannot be used when inspecting power equipment at different stages. For power equipment under different working conditions, targeted inspections of different degrees should be carried out. Summary of the invention

[0004] In order to solve the problems existing in the prior art, the purpose of the present invention is to provide an artificial intelligence-based power equipment inspection method. The present invention determines whether the time spent by personnel when inspecting power equipment meets the corresponding inspection requirements. The method is simple, effective and easy to use.

[0005] The purpose of the present invention is achieved through the following technical solutions:

[0006] An artificial intelligence-based power equipment inspection method, the method specifically comprises the following steps:

[0007] When the inspectors inspect the target object, the inspection stop time is automatically obtained, and then the real-time stage of the target object is synchronously obtained, and the real-time stage is matched with the stage adaptation table to obtain the approval range corresponding to the current real-time stage. If the inspection stop time is not within the approved range, an abnormal signal is generated and the corresponding inspection point is marked as an abnormal inspection point;

[0008] Continuously monitor the inspection points on the inspection path, obtain all abnormal inspection points on the inspection path, and generate an inspection abnormality signal when there are no less than two abnormal inspection points to remind the administrator to handle it;

[0009] The stage adaptation table contains the approval stages that express the stage in which the current target object is located. Each approval stage has a corresponding approval range for the inspection of the target object that is adapted to the approval stage. The approval range represents the normal time range for the inspection personnel to inspect the target object.

[0010] Furthermore, when the inspection personnel inspect the target object, they inspect along a set inspection route, which includes a walking inspection path and inspection points that need to be inspected, and the inspection points are the locations of the target objects;

[0011] The real-time location of the inspectors is determined through the smart devices they carry with them.

[0012] Furthermore, the stage adaptation table is set by the administrator, including the approval stage of the target object and its corresponding approval scope.

[0013] Furthermore, the stage adaptation table is determined by adaptation analysis, and the specific method of adaptation analysis is as follows:

[0014] Get the target object of the inspection point;

[0015] Obtain the service life of the target object and divide it into several usage phases of equal duration, with the duration of each usage phase being consistent;

[0016] Then, according to each use stage, the number of times the corresponding target object has abnormalities is the number of abnormalities. According to the difference between the number of abnormalities, the different use stages are merged into several approval stages, thereby determining several approval stages for each target object;

[0017] For each target object in the approval stage, the time spent on several standard inspections is used to obtain several inspection times, and the approval scope is determined based on the distribution of several inspection times;

[0018] Then, carry out the same process for each of the remaining approval stages and determine the corresponding approval scope;

[0019] All target objects are processed in the same way to obtain the approval scopes of all target objects at different approval stages.

[0020] Furthermore, the service life of the target object is calculated according to the average life of the equipment of several target objects after they are scrapped.

[0021] Furthermore, the specific method for determining the approval stage is as follows:

[0022] According to the service life of the target object, it is divided into several usage stages of equal duration. The duration of each usage stage is consistent, and the specific value is preset by the administrator;

[0023] Then, the number of abnormalities of the target object in each use stage is obtained. Assuming that there are n use stages, the number of abnormalities in each stage is marked as Yi, i=1, ..., n; the number of abnormalities here is also the average of the number of abnormalities of several target objects of the same type in different use stages to determine the final number of abnormalities;

[0024] Then, let i be equal to 1 to obtain the corresponding first use stage, and then let the value of i be increased by 1 to automatically obtain the second use stage. When the difference between the number of abnormalities of the second use stage and the first use stage does not exceed the preset value X1, the first use stage and the second use stage are merged to form a new use stage, which is marked as an approved stage. Otherwise, they are not merged into a new use stage, and the first use stage is automatically treated as a separate approved stage.

[0025] After the first approval stage is determined, the next use stage is obtained in order. If at least three use stages are formed during this process, the method of determining the new approval stage after these use stages are merged is as follows:

[0026] Get the average value of the number of abnormalities in all use stages, then get the absolute value of the difference between each abnormal number and the average value, then divide the absolute value by the average value, and mark it as the judgment value. When the judgment value does not exceed X2, all use stages can be merged into a new approval stage. Otherwise, the above use stages cannot be merged into a new approval stage. X2 is a preset value.

[0027] According to the above steps, all the use stages are processed and integrated to obtain several approval stages;

[0028] The same process is performed on all target objects to obtain all approval stages of all target objects.

[0029] Furthermore, an abnormality refers to an abnormal signal appearing in the device or the need for repair or replacement due to the device itself.

[0030] Furthermore, the specific method for determining the scope of approval is as follows:

[0031] Select any target object, first obtain the target object in the first approval stage, and obtain a number of inspection durations that have been confirmed in the past T1 years, and mark them as Kj, j = 1, ..., m;

[0032] The mean value P of Kj is automatically obtained, and the degree of aggregation W of Kj is calculated according to the formula. The specific calculation formula is:

[0033]

[0034] When W≤X2, the range from the smallest duration to the largest duration in Kj here is marked as the approved range; otherwise, Kj is automatically selected in the order of |Kj-P| from large to small, and each one is deleted after being selected. After deletion, the W value of the remaining Kj is calculated. If it still exceeds X2, the next Kj is selected and deleted until W does not exceed X2, and the minimum to maximum value of the remaining Kj is marked as the approved range;

[0035] The same process is performed on the remaining approval stages of the target object to obtain the approval scope of all approval stages of the target object;

[0036] The same process is then performed on the remaining target objects to obtain the approval scope of all approval stages of each target object.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] The present invention obtains the inspection stay time of the inspection personnel when inspecting the target object, then synchronously obtains the real-time stage that the target object is currently in, matches the real-time stage with the stage adaptation table, and obtains the approval range corresponding to the current real-time stage. If the inspection stay time is not within the approved range, an abnormal signal is generated, and the corresponding inspection point is marked as an abnormal inspection point; in the above manner, it is determined whether the time spent by the personnel in inspecting the power equipment meets the corresponding inspection requirements; the present invention is used to implement the inspection of power equipment, which is simple, effective and easy to use. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A flow chart of the method provided by the present invention;

[0040] Figure 2 This is a flow chart of the method for determining the phase adaptation table mentioned in the present invention. DETAILED DESCRIPTION

[0041] The technical solution of the present invention will be described clearly and completely in conjunction with the embodiments below. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Please refer to Figure 1-Figure 2 .

[0042] Embodiment 1

[0043] An artificial intelligence-based power equipment inspection method, the method specifically comprises the following steps:

[0044] Locate the inspection route and determine whether the personnel are on the correct route based on the inspection route. Different routes have different equipment, so it is necessary to look at the inspection time of each equipment to make a rough judgment, inspection effect and inspection situation to ensure the inspection quality;

[0045] Step 1: First, obtain the established inspection route. The inspection route is planned and determined by the administrator to obtain a determined inspection route. The inspection route includes the inspection path and the inspection points on the inspection path. The inspection points are set in sequence to form an inspection point set. Each inspection route needs to be assigned a corresponding inspection personnel;

[0046] Step 2: Then track the route of the inspector. The specific method of route tracking is as follows:

[0047] When the inspectors start to inspect the power equipment, for the sake of convenience, they will be uniformly described as target objects in the following text, that is, the target objects are used to refer to the power equipment;

[0048] The real-time location of the patrol personnel is determined by the smart device they carry with them. The smart device is a smart device with a positioning function, which can be a mobile phone or other devices. According to the real-time location of the patrol personnel, it is determined whether the patrol personnel have arrived at all the patrol points in the patrol point set;

[0049] Step 3: During the inspection process, it is also necessary to determine the inspection duration. The specific determination method is:

[0050] During the inspection process, when the corresponding inspection personnel inspect any inspection point, the current real-time stage of the target object will be automatically obtained. The real-time stage is used to indicate the stage of the current target object. Then, the real-time stage of the current target object is compared with the approval stage in the stage adaptation table to obtain the approval scope of the approval stage that is consistent with the real-time stage. The stage adaptation table here is pre-set by the administrator, and specifically includes each approval stage of the target object and its corresponding approval scope;

[0051] Then, the inspection personnel's inspection stay time for the target object at the inspection point is obtained, and the inspection stay time is compared with the approved range. When the inspection stay time does not fall within the approved range, an abnormal signal is automatically generated, and the corresponding inspection point is marked as an abnormal inspection point;

[0052] The inspection points on the inspection path are continuously monitored to obtain all abnormal inspection points on the inspection path. When there are no less than two abnormal inspection points, an inspection abnormality signal is generated to remind the administrator to handle it.

[0053] Embodiment 2

[0054] As another embodiment of the present invention, this embodiment is implemented on the basis of the first embodiment, and is different from the first embodiment in that the stage adaptation table and the approval stage and approval scope contained therein are determined by adaptation analysis, and the specific method of adaptation analysis is as follows:

[0055] Get the target object of the inspection point;

[0056] Then, the service life of any target object is obtained, and the service life is calculated according to the average life of the equipment consistent with the target object after being scrapped;

[0057] According to the service life of the target object, it is divided into several equal-length usage stages. The duration of each usage stage is consistent, and the specific value is preset by the administrator;

[0058] Then, the number of abnormalities of the target object in each use stage is obtained. The abnormality refers to the abnormal signal of the equipment or the need for maintenance or replacement due to other equipment itself, which affects the power grid. It is assumed that there are n use stages, and the number of abnormalities in each stage is marked as Yi, i=1,...,n; the number of abnormalities here is also the average of the number of abnormalities of several target objects of the same type in different use stages to determine the final number of abnormalities;

[0059] Then, let i be equal to 1 to obtain the corresponding first use stage, and then let the value of i be increased by 1 to automatically obtain the second use stage. When the difference between the number of abnormalities of the second use stage and the first use stage does not exceed the preset value X1, the first use stage and the second use stage are merged to form a new use stage, which is marked as an approved stage. Otherwise, they are not merged into a new use stage, and the first use stage is automatically treated as a separate approved stage.

[0060] After the first approval stage is determined, the next use stage is obtained in order. If at least three use stages are formed during this process, whether these use stages can be integrated into a new approval stage needs to be determined by the following method, specifically:

[0061] Get the average value of the number of abnormalities in all use stages, then get the absolute value of the difference between each abnormal number and the average value, then divide the absolute value by the average value, and mark it as the judgment value. When the judgment value does not exceed X2, all use stages can be merged into a new approval stage. Otherwise, the above use stages cannot be merged into a new approval stage.

[0062] According to the above steps, all the use stages are processed and integrated to obtain several approval stages;

[0063] All target objects are processed in the same way to obtain all the approval stages of all target objects;

[0064] Step 4: Match the target object at the approval stage. The specific matching method is:

[0065] Retrieve relevant data and simulate and analyze the inspection time range of the corresponding target object through relevant data. The specific method is as follows:

[0066] Select any target object, first obtain the target object in the first approval stage, and obtain a number of inspection durations that have been confirmed in the past T1 years, and mark them as Kj, j = 1, ..., m, where m is a positive integer;

[0067] The mean value P of Kj is automatically obtained, and the degree of aggregation W of Kj is calculated according to the formula. The specific calculation formula is:

[0068]

[0069] When W≤X2, the range from the smallest duration to the largest duration in Kj here is marked as the approved range; otherwise, Kj is automatically selected in the order of |Kj-P| from large to small, and each one is deleted after being selected. After deletion, the W value of the remaining Kj is calculated. If it still exceeds X2, the next Kj is selected and deleted until W does not exceed X2, and the minimum to maximum value of the remaining Kj is marked as the approved range;

[0070] The same process is performed on the remaining approval stages of the target object to obtain the approval scope of all approval stages of the target object;

[0071] The same process is then performed on the remaining target objects to obtain the approval scope of all approval stages of each target object.

[0072] The invention is used to realize patrol inspection of electric power equipment.

[0073] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A power equipment inspection method based on artificial intelligence, characterized in that: The method specifically comprises the following steps: S1. When the inspector inspects the target object, the inspection stay time of the inspector is automatically obtained; S2. Synchronously obtain the current real-time stage of the target object, match the real-time stage with the stage adaptation table, and obtain the approval range corresponding to the current real-time stage. If the inspection stay time is not within the approved range, an abnormal signal is generated and the corresponding inspection point is marked as an abnormal inspection point. The stage adaptation table contains the approval stage that expresses the stage that the current target object is in. Each approval stage has a corresponding approval range for the inspection of the target object that is adapted to the approval stage. The approval range is the normal time range for the inspection personnel to inspect the target object. S3. Continuously monitor the inspection points on the inspection path to obtain all abnormal inspection points on the inspection path. When there are no less than two abnormal inspection points, an inspection abnormality signal is generated to remind the administrator to handle it.

2. The power equipment inspection method based on artificial intelligence according to claim 1 is characterized in that: In S1, when the inspection personnel inspect the target object, they inspect along the set inspection route. The inspection route includes the inspection path and the inspection points to be inspected. The inspection points are the locations of the target objects. The real-time location of the inspectors is determined by the smart devices they carry with them.

3. The power equipment inspection method based on artificial intelligence according to claim 1 is characterized in that: In S2, the stage adaptation table is set by the administrator, including the approval stage of the target object and its corresponding approval scope.

4. The power equipment inspection method based on artificial intelligence according to claim 1 is characterized in that: In S2, the stage adaptation table is determined by adaptation analysis, and the specific method of adaptation analysis is: 41) Get the target object of the inspection point; 42) Obtain the service life of the target object and divide it into several use stages of equal duration, with the duration of each use stage being consistent; 43) According to each use stage, the number of times the corresponding target object has abnormalities is also the number of abnormalities. According to the difference between the number of abnormalities, the different use stages are merged into several approval stages, thereby determining several approval stages for each target object; 44) For each target object in the approval stage, the time spent on several standard inspections is calculated to obtain several inspection durations, and the approval scope is determined based on the distribution of the several inspection durations; 45) Carry out the same process for each of the remaining approval stages and determine the corresponding approval scope; 46) All target objects are processed in the same way to obtain the approval scopes of all target objects at different approval stages.

5. The power equipment inspection method based on artificial intelligence according to claim 4 is characterized in that: The service life of the target object is calculated based on the average life of several target object devices after they are scrapped.

6. The power equipment inspection method based on artificial intelligence according to claim 4 is characterized in that: The specific determination method of the approval stage is as follows: 61) According to the service life of the target object, it is divided into several use stages of equal duration, and the duration of each use stage is consistent; 62) Obtain the number of abnormalities of the target object in each use stage. Assuming that there are n use stages, the number of abnormalities in each stage is marked as Yi, i=1, ..., n; the number of abnormalities here is also the average of the number of abnormalities of several target objects of the same type in different use stages to determine the final number of abnormalities; 63) Let i be equal to 1, obtain the corresponding first use stage, then let the value of i be increased by 1, automatically obtain the second use stage, when the difference between the number of abnormalities of the second use stage and the first use stage does not exceed X1, merge the first use stage and the second use stage into a new use stage, mark it as the approval stage, otherwise do not merge into a new use stage, automatically treat the first use stage as a separate approval stage, and X1 is a preset value; 64) After the first approval stage is determined, the next use stage is obtained in order. If at least three use stages are formed during this process, the method of determining the new approval stage formed by these use stages is as follows: Get the average value of the number of abnormalities in all usage stages, then get the absolute value of the difference between each abnormal number and the average value, then divide the absolute value by the average value, and mark it as the judgment value. When the judgment value does not exceed X2, all usage stages are merged into a new approval stage. Otherwise, the above usage stages cannot be merged into a new approval stage. X2 is a preset value. 65) All the use stages are processed and integrated according to the above steps to obtain several approval stages; 66) All target objects are processed in the same way to obtain all the approval stages of all target objects.

7. The power equipment inspection method based on artificial intelligence according to claim 6 is characterized in that: Abnormal means that the equipment has abnormal signals or needs to be repaired or replaced due to the equipment itself.

8. The power equipment inspection method based on artificial intelligence according to claim 1 is characterized in that: In S2, the specific method for determining the scope of approval is: Select any target object, first obtain the target object in the first approval stage, and obtain a number of inspection durations that have been confirmed in the past T1 years, and mark them as Kj, j = 1, ..., m; The mean value P of Kj is automatically obtained, and the degree of aggregation W of Kj is calculated according to the formula. The specific calculation formula is: When W≤X2, the range from the smallest duration to the largest duration in Kj here is marked as the approved range; otherwise, Kj is automatically selected in descending order according to |Kj-P|, and each one is deleted after being selected. After deletion, the W value of the remaining Kj is calculated. If it still exceeds X2, the next Kj is selected and deleted until W does not exceed X2, and the minimum to maximum value of the remaining Kj is marked as the approved range; X2 is a preset value. The same process is performed on the remaining approval stages of the target object to obtain the approval scope of all approval stages of the target object; The same process is performed on the remaining target objects to obtain the approval scope of all approval stages of each target object.

Images