AI image recognition and analysis algorithm for typical equipment failures in hydropower stations

Through the AI ​​image recognition and analysis algorithm, the problem of untimely monitoring of traditional hydropower plant equipment fault monitoring methods and major labor demand is solved, and the timely identification and elimination of equipment faults is achieved, personal safety risks are reduced, and the safe and stable operation of the equipment is ensured.

CN114997335BInactive Publication Date: 2024-11-01STATE POWER INVESTMENT CORP GUIZHOU JINYUAN WEINING ENERGY CO LTD XIANGBILING HYDROPOWER STATION
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210780189.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-07-04
Publication Date
2024-11-01
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Traditional hydropower plant equipment fault monitoring methods have problems such as untimely monitoring, personal safety risks, large manpower demand, and scientific analysis and prediction of equipment performance data, resulting in the inability to detect and eliminate equipment hidden dangers in a timely manner, affecting the safe and stable operation of the equipment.

Method used

AI image recognition and analysis algorithm is used to obtain sensor detection data through data flow mode, feature extraction and dot matrix graph generation, and AI image recognition is used to determine equipment abnormalities and operation failures, and fault locations and circuit diagrams are obtained for inspection.

Benefits of technology

It realizes the timely identification and elimination of hydropower plant equipment failures, reduces personal safety risks, reduces manpower demand, improves the scientific analysis and prediction capabilities of equipment performance data, and ensures the safe and stable operation of equipment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114997335B_ABST
    Figure CN114997335B_ABST
Patent Text Reader

Abstract

The present invention discloses an AI image recognition and analysis algorithm for typical equipment failures in a hydropower station, comprising the following steps: obtaining typical equipment operation monitoring data of a hydropower station obtained by sensor detection of typical equipment in a hydropower station; performing feature extraction to generate batch dot matrix data, integrating and analyzing the batch dot matrix data into dot matrix graphics based on operation time points and dot matrix graphics based on operation thresholds of typical equipment in a hydropower station; performing AI image recognition to find out typical equipment M in a hydropower station for which no monitoring data has been detected, performing AI image recognition to find out typical equipment N in a hydropower station for which no monitoring data has been detected; determining typical equipment M in a hydropower station for which no monitoring data has been detected as an abnormal equipment failure, and determining typical equipment N in a hydropower station for which the operation threshold has been exceeded as an operation failure. The present invention recognizes and analyzes the acquired dot matrix data as a whole through AI image recognition technology, and identifies and analyzes faulty equipment with abnormal equipment and local lines with operation failures.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to an AI image recognition and analysis algorithm for typical equipment failures in a hydropower station, belonging to the technical field of AI intelligent recognition and analysis. Background Art

[0002] Existing large-scale hydropower station equipment fault monitoring and maintenance is an important part of the work of power station personnel. At present, the method of large-scale hydropower station equipment fault monitoring and maintenance relies on power station personnel to conduct regular inspections of equipment on site, and rely on personnel to judge and record whether the equipment is operating normally. This traditional fault monitoring and maintenance method has problems such as untimely monitoring, personal safety risks, large manpower requirements, and inability to scientifically analyze and predict equipment performance data. It cannot timely discover and eliminate equipment hidden dangers and affects the safe and stable operation of equipment. Summary of the invention

[0003] The purpose of the present invention is to overcome the technical defects of the prior art, solve the above-mentioned technical problems, and propose an AI image recognition and analysis algorithm for typical equipment failures in hydropower stations.

[0004] The present invention specifically adopts the following technical solution: an AI image recognition and analysis algorithm for typical equipment failures in a hydropower station, comprising the following steps:

[0005] Step SS1: using a data stream mode, batches of typical hydropower station equipment operation monitoring data obtained by sensor detection of typical hydropower station equipment are acquired;

[0006] Step SS2: extracting features from the acquired typical equipment operation monitoring data of the hydropower station to generate batch dot matrix data, integrating and analyzing the batch dot matrix data into dot matrix graphics based on operation time points and dot matrix graphics based on operation thresholds of typical equipment of the hydropower station;

[0007] Step SS3: Perform AI image recognition on the dot pattern and the dot pattern training model of the operation time point to find out the typical hydropower station equipment M for which no monitoring data is detected, and perform AI image recognition on the dot pattern and the dot pattern training model of the operation threshold value of the typical hydropower station equipment to find out the typical hydropower station equipment N that exceeds the operation threshold value;

[0008] Step SS4: Determine the typical hydropower station equipment M for which no monitoring data is detected as having an abnormal equipment fault, determine the typical hydropower station equipment N that exceeds the operating threshold as having an operating fault, obtain the location information of the typical hydropower station equipment M with the abnormal equipment fault to perform equipment fault repair, and obtain the local line diagram of the typical hydropower station equipment N with the operating fault to perform line fault repair.

[0009] As a preferred embodiment, the typical equipment of the hydropower station includes power transformation and distribution equipment of the hydropower station, a hydro-turbine generator set, and electrical mechanical equipment affiliated with the hydro-turbine generator set.

[0010] As a preferred embodiment, the power transformation and distribution equipment of the hydropower station includes a transformer, a circuit breaker, a disconnector, a mutual inductor, a combination electrical appliance and a controller.

[0011] As a preferred embodiment, the hydro-generator set includes a hydro-turbine and a hydro-generator.

[0012] As a preferred embodiment, the auxiliary electrical mechanical equipment of the hydro-generator set includes a speed governor, an oil pressure device, an excitation device, and equipment of an automation and protection system.

[0013] As a preferred embodiment, the dot map training model is obtained by the following method: feature extraction is performed on the typical equipment operation monitoring data of the hydropower station obtained in step SS1 to generate batch dot map data, which are stored in the dot map database according to the operating sequence and the typical equipment of each hydropower station for AI image training to generate a dot map training model.

[0014] As a preferred embodiment, the typical equipment operation monitoring data of the hydropower station includes: current and voltage data of the hydropower station's power distribution equipment, speed and flow data of the hydro-generator set, and electrical and control quantity data of the electrical mechanical equipment affiliated with the hydro-generator set.

[0015] Beneficial effects achieved by the present invention: The present invention aims to solve the problems of traditional fault monitoring and maintenance methods for typical hydropower station equipment, such as untimely monitoring, personal safety risks, large manpower requirements, inability to scientifically analyze and predict equipment performance data, and inability to timely discover and eliminate equipment hidden dangers that affect the safe and stable operation of equipment. The present invention uses an AI image recognition and analysis algorithm for typical equipment failures in hydropower stations, including the following steps: Step SS1: Using a data stream mode, batches of typical equipment operation monitoring data of hydropower stations obtained by sensor detection of typical equipment in hydropower stations are obtained; Step SS2: Feature extraction is performed on the acquired typical equipment operation monitoring data of hydropower stations to generate batch dot matrix data, and the batch dot matrix data is integrated and analyzed into dot matrix graphics based on operation time points and dot matrix graphics based on operation thresholds of typical equipment in hydropower stations; Step SS3: AI image recognition is performed on the dot matrix graphics at the operation time points and the dot matrix training model to find out the hydropower stations for which no monitoring data is detected. Typical equipment M, perform AI image recognition on the dot matrix pattern of the operating threshold of the typical equipment of the hydropower station and the dot matrix training model, and find out the typical equipment N of the hydropower station that exceeds the operating threshold; step SS4: determine the typical equipment M of the hydropower station that has not detected the monitoring data as an abnormal equipment fault, and determine the typical equipment N of the hydropower station that exceeds the operating threshold as an operating fault, obtain the location information of the typical equipment M of the hydropower station with abnormal equipment fault to carry out equipment fault maintenance, obtain the local line diagram of the typical equipment N of the hydropower station with operating fault to carry out line fault maintenance, and use AI image recognition technology to identify and analyze the acquired dot matrix data as a whole, identify and analyze the faulty equipment with abnormal equipment and the local line with operating fault, solve the problems of traditional fault monitoring and maintenance methods of typical equipment of hydropower stations such as untimely monitoring, personal safety risks, large manpower requirements, and inability to scientifically analyze and predict equipment performance data, and fail to timely discover and eliminate equipment hidden dangers that affect the safe and stable operation of equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of the AI ​​image recognition and analysis algorithm of typical equipment failures in a hydropower station of the present invention.

[0017] Figure 2 It is a topological diagram of the AI ​​image recognition and analysis system for typical equipment failures in a hydropower station of the present invention.

[0018] Figure 3 It is a dot matrix graphic schematic diagram of the normal operating status of typical equipment in a hydropower station according to an embodiment of the present invention.

[0019] Figure 4 It is a schematic diagram of a dot matrix diagram of a typical hydropower station equipment when an abnormal line fault occurs in the present invention.

[0020] Figure 5 It is a schematic diagram of a dot matrix diagram of a typical hydropower station equipment when an abnormal equipment failure occurs. DETAILED DESCRIPTION

[0021] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.

[0022] Example 1: Figure 1 As shown, the present invention proposes an AI image recognition and analysis algorithm for typical equipment failures in a hydropower station, comprising the following steps:

[0023] Step SS1: using a data stream mode, batches of typical hydropower station equipment operation monitoring data obtained by sensor detection of typical hydropower station equipment are acquired;

[0024] Step SS2: extracting features from the acquired typical equipment operation monitoring data of the hydropower station to generate batch dot matrix data, integrating and analyzing the batch dot matrix data into dot matrix graphics based on operation time points and dot matrix graphics based on operation thresholds of typical equipment of the hydropower station;

[0025] Step SS3: Perform AI image recognition on the dot pattern and the dot pattern training model of the operation time point to find out the typical hydropower station equipment M for which no monitoring data is detected, and perform AI image recognition on the dot pattern and the dot pattern training model of the operation threshold value of the typical hydropower station equipment to find out the typical hydropower station equipment N that exceeds the operation threshold value;

[0026] Step SS4: Determine the typical hydropower station equipment M for which no monitoring data is detected as having an abnormal equipment fault, determine the typical hydropower station equipment N that exceeds the operating threshold as having an operating fault, obtain the location information of the typical hydropower station equipment M with the abnormal equipment fault to perform equipment fault repair, and obtain the local line diagram of the typical hydropower station equipment N with the operating fault to perform line fault repair.

[0027] As a preferred embodiment, the typical equipment of the hydropower station includes power transformation and distribution equipment of the hydropower station, a hydro-turbine generator set, and electrical mechanical equipment affiliated with the hydro-turbine generator set.

[0028] As a preferred embodiment, the power transformation and distribution equipment of the hydropower station includes a transformer, a circuit breaker, a disconnector, a mutual inductor, a combination electrical appliance and a controller.

[0029] As a preferred embodiment, the hydro-generator set includes a hydro-turbine and a hydro-generator.

[0030] As a preferred embodiment, the auxiliary electrical mechanical equipment of the hydro-generator set includes a speed governor, an oil pressure device, an excitation device, and equipment of an automation and protection system.

[0031] As a preferred embodiment, the dot map training model is obtained by the following method: feature extraction is performed on the typical equipment operation monitoring data of the hydropower station obtained in step SS1 to generate batch dot map data, which are stored in the dot map database according to the operating sequence and the typical equipment of each hydropower station for AI image training to generate a dot map training model.

[0032] As a preferred embodiment, the typical equipment operation monitoring data of the hydropower station includes: current and voltage data of the hydropower station's power distribution equipment, speed and flow data of the hydro-generator set, and electrical and control quantity data of the electrical mechanical equipment affiliated with the hydro-generator set.

[0033] Specific as Figure 3 , Figure 4 and Figure 5 The figures shown are respectively a schematic diagram of a dot matrix diagram of a normal operating state of a typical hydropower station equipment according to an embodiment of the present invention, a schematic diagram of a dot matrix diagram when a line abnormal fault occurs in a typical hydropower station equipment, and a schematic diagram of a dot matrix diagram when an abnormal equipment fault occurs in a typical hydropower station equipment. The rotation speed of the turbine, the rotation speed of the turbine generator, the voltage of the transformer, the current signal of the circuit breaker, the current signal of the disconnector, the current signal of the transformer, the voltage signal of the combined electrical appliance, the control signal of the controller, the speed regulation signal of the governor, the oil pressure signal of the oil pressure device, the excitation signal of the excitation device, and the electrical signal of the equipment of the automation and protection system are obtained to generate a dot matrix diagram, which is then identified and analyzed with the dot matrix diagram training model trained with batch monitoring data and the operation threshold range of each typical equipment of the hydropower station, such as Figure 4 The voltage signal of the combined electrical appliance and the oil pressure signal of the oil pressure device are not within the range of the dot matrix training model, and it is determined to be an operating fault, such as Figure 5 The voltage signal of the transformer and the oil pressure signal of the oil pressure device were not detected, and the monitoring data determined that the equipment was abnormal.

[0034] Beneficial effects achieved by the present invention: The present invention aims to solve the problems of traditional fault monitoring and maintenance methods for typical hydropower station equipment, such as untimely monitoring, personal safety risks, large manpower requirements, inability to scientifically analyze and predict equipment performance data, and inability to timely discover and eliminate equipment hidden dangers that affect the safe and stable operation of equipment. The present invention uses an AI image recognition and analysis algorithm for typical equipment failures in hydropower stations, including the following steps: Step SS1: Using a data stream mode, batches of typical equipment operation monitoring data of hydropower stations obtained by sensor detection of typical equipment in hydropower stations are obtained; Step SS2: Feature extraction is performed on the acquired typical equipment operation monitoring data of hydropower stations to generate batch dot matrix data, and the batch dot matrix data is integrated and analyzed into dot matrix graphics based on operation time points and dot matrix graphics based on operation thresholds of typical equipment in hydropower stations; Step SS3: AI image recognition is performed on the dot matrix graphics at the operation time points and the dot matrix training model to find out the hydropower stations for which no monitoring data is detected. Typical equipment M, perform AI image recognition on the dot matrix pattern of the operating threshold of the typical equipment of the hydropower station and the dot matrix training model, and find out the typical equipment N of the hydropower station that exceeds the operating threshold; step SS4: determine the typical equipment M of the hydropower station that has not detected the monitoring data as an abnormal equipment fault, and determine the typical equipment N of the hydropower station that exceeds the operating threshold as an operating fault, obtain the location information of the typical equipment M of the hydropower station with abnormal equipment fault to carry out equipment fault maintenance, obtain the local line diagram of the typical equipment N of the hydropower station with operating fault to carry out line fault maintenance, and use AI image recognition technology to identify and analyze the acquired dot matrix data as a whole, identify and analyze the faulty equipment with abnormal equipment and the local line with operating fault, solve the problems of traditional fault monitoring and maintenance methods of typical equipment of hydropower stations such as untimely monitoring, personal safety risks, large manpower requirements, and inability to scientifically analyze and predict equipment performance data, and fail to timely discover and eliminate equipment hidden dangers that affect the safe and stable operation of equipment.

[0035] Example 2: Figure 2 As shown, the present invention proposes an AI image recognition and analysis system for typical equipment failures in a hydropower station, comprising:

[0036] The data acquisition module specifically implements: using the data stream mode to batch acquire the operation monitoring data of typical hydropower station equipment detected by sensors of typical hydropower station equipment;

[0037] The feature extraction module specifically performs: feature extraction of the acquired typical equipment operation monitoring data of the hydropower station, generating batch dot matrix data, integrating and analyzing the batch dot matrix data into dot matrix graphics based on operation time points and dot matrix graphics based on operation thresholds of typical equipment of the hydropower station;

[0038] The image recognition module specifically performs: performing AI image recognition on the dot pattern and the dot pattern training model at the operation time point to find out the typical hydropower station equipment M for which no monitoring data is detected, performing AI image recognition on the dot pattern and the dot pattern training model of the operation threshold value of the typical hydropower station equipment to find out the typical hydropower station equipment N that exceeds the operation threshold value;

[0039] The fault judgment module specifically performs the following operations: judging the typical equipment M of the hydropower station for which no monitoring data is detected as having an abnormal equipment fault, judging the typical equipment N of the hydropower station for which the operating threshold is exceeded as having an operating fault, obtaining the location information of the typical equipment M of the hydropower station with an abnormal equipment fault to perform equipment fault repair, and obtaining the local line diagram of the typical equipment N of the hydropower station with an operating fault to perform line fault repair.

[0040] As a preferred embodiment, the typical equipment of the hydropower station includes power transformation and distribution equipment of the hydropower station, a hydro-turbine generator set, and electrical mechanical equipment affiliated with the hydro-turbine generator set.

[0041] As a preferred embodiment, the power transformation and distribution equipment of the hydropower station includes a transformer, a circuit breaker, a disconnector, a mutual inductor, a combination electrical appliance and a controller.

[0042] As a preferred embodiment, the hydro-generator set includes a hydro-turbine and a hydro-generator.

[0043] As a preferred embodiment, the auxiliary electrical mechanical equipment of the hydro-generator set includes a speed governor, an oil pressure device, an excitation device, and equipment of an automation and protection system.

[0044] As a preferred embodiment, the dot map training model is obtained in the following manner: feature extraction is performed on the operation monitoring data of typical equipment in the hydropower station to generate batch dot map data, which are stored in the dot map database according to the operating sequence and the typical equipment of each hydropower station for AI image training to generate a dot map training model.

[0045] As a preferred embodiment, the typical equipment operation monitoring data of the hydropower station includes: current and voltage data of the hydropower station's power distribution equipment, speed and flow data of the hydro-generator set, and electrical and control quantity data of the electrical mechanical equipment affiliated with the hydro-generator set.

[0046] It should be noted that the rotation speed of the turbine, the rotation speed of the hydro-generator, the voltage of the transformer, the current signal of the circuit breaker, the current signal of the isolating switch, the current signal of the transformer, the voltage signal of the combination electrical appliance, the control signal of the controller, the speed regulation signal of the governor, the oil pressure signal of the oil pressure device, the excitation signal of the excitation equipment, and the electrical signals of the equipment of the automation and protection system in the present invention are not limited to one type of data of one type of equipment, but are monitoring data of the operation of several typical equipment of the hydropower station collected according to the operation needs of the hydropower station.

[0047] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0048] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0049] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. AI image recognition and analysis algorithm for typical equipment failures in hydropower stations, characterized by: The steps include: Step SS1: using a data stream mode, batches of typical hydropower station equipment operation monitoring data obtained by sensor detection of typical hydropower station equipment are acquired; Step SS2: extracting features from the acquired typical equipment operation monitoring data of the hydropower station to generate batch dot matrix data, integrating and analyzing the batch dot matrix data into dot matrix graphics based on operation time points and dot matrix graphics based on operation thresholds of typical equipment of the hydropower station; Step SS3: Perform AI image recognition on the dot pattern and the dot pattern training model of the operation time point to find out the typical hydropower station equipment M for which no monitoring data is detected, and perform AI image recognition on the dot pattern and the dot pattern training model of the operation threshold value of the typical hydropower station equipment to find out the typical hydropower station equipment N that exceeds the operation threshold value; Step SS4: Determine the typical hydropower station equipment M for which no monitoring data is detected as having an abnormal equipment fault, determine the typical hydropower station equipment N that exceeds the operating threshold as having an operating fault, obtain the location information of the typical hydropower station equipment M with the abnormal equipment fault to perform equipment fault repair, and obtain the local line diagram of the typical hydropower station equipment N with the operating fault to perform line fault repair.

2. The AI ​​image recognition and analysis algorithm for typical equipment failures in a hydropower station according to claim 1 is characterized in that: The typical equipment of the hydropower station includes power transformation and distribution equipment of the hydropower station, hydraulic turbine generator sets, and auxiliary electrical mechanical equipment of the hydraulic turbine generator sets.

3. The AI ​​image recognition and analysis algorithm for typical equipment failures in a hydropower station according to claim 2 is characterized in that: The power transformation and distribution equipment of the hydropower station includes a transformer, a circuit breaker, a disconnector, a mutual inductor, a combined electrical appliance and a controller.

4. The AI ​​image recognition and analysis algorithm for typical equipment failures in a hydropower station according to claim 2 is characterized in that: The hydro-generator set comprises a hydro-turbine and a hydro-generator.

5. The AI ​​image recognition and analysis algorithm for typical equipment failures in a hydropower station according to claim 2 is characterized in that: The auxiliary electrical and mechanical equipment of the hydro-generator set includes a speed governor, an oil pressure device, an excitation device, and equipment of an automation and protection system.

6. The AI ​​image recognition and analysis algorithm for typical equipment failures in a hydropower station according to claim 1 is characterized in that: The dot plot training model is obtained by the following method: feature extraction is performed on the typical equipment operation monitoring data of the hydropower station obtained in step SS1 to generate batch dot plot data, which are stored in the dot plot database according to the operation sequence and the typical equipment of each hydropower station for AI image training to generate a dot plot training model.

7. The AI ​​image recognition and analysis algorithm for typical equipment failures in a hydropower station according to claim 1 is characterized in that: The typical equipment operation monitoring data of the hydropower station includes: current and voltage data of the hydropower station's power transformation and distribution equipment, speed and flow data of the hydro-generator set, and electrical quantity and control quantity data of the electrical mechanical equipment attached to the hydro-generator set.