Method and system for on-line monitoring of electrical equipment of hydropower station

Abstract

This application relates to the field of online monitoring technology, and in particular to online monitoring methods and systems for electrical equipment in hydropower stations. The solution proposed in this application achieves accurate early warning of insulation risks of electrical equipment in hydropower stations by synergistically predicting water flow disturbance, mechanical vibration and electromagnetic interference, effectively avoiding the blind spots of single-factor assessment, and significantly reducing the risk of unplanned shutdowns and accidents.

Description

Technical Field

[0001] This application relates to the field of online monitoring technology, and in particular to online monitoring methods and systems for electrical equipment in hydropower stations. Background Technology

[0002] As a crucial component of clean energy, the operational safety and reliability of hydropower stations directly impact the stability and economic benefits of the power grid. Electrical equipment (such as generator stator windings, main transformers, high-voltage switchgear, and cables) is the core of energy conversion and transmission in hydropower stations, and the health of its insulation is a key factor determining equipment lifespan and system safety.

[0003] Currently, the monitoring and assessment technologies for the insulation status of electrical equipment in hydropower stations mainly suffer from the following limitations and deficiencies: The working environment of electrical equipment in hydropower stations is extremely unique. Its insulation performance is not only affected by electrical stress, but is also subjected to the long-term interaction of the following multiple physical fields: Mechanical vibration induced by water flow: Components such as turbine guide bearings and main shafts generate continuous mechanical vibration under the impact of high-speed water flow. This vibration is transmitted through the foundation, frame, and bearings to the generator stator windings and outgoing line structure. Long-term mechanical fatigue can lead to cracking, wear, or loosening of the insulation layer. Electromagnetic interference and harmonics: Induced electromotive force, high-order harmonics, and operational overvoltages generated during generator operation can introduce additional dielectric stress and partial discharge into the insulation structure, accelerating insulation aging. The effects of environmental temperature, humidity, and water leakage: The unique high humidity, water mist, and even micro-leakage environment of hydropower stations can cause moisture on the insulation surface, shorten the creepage distance, and significantly reduce the surface insulation strength.

[0004] Existing insulation life prediction or condition assessment models mostly only consider a single factor (such as simply considering thermal aging or electric field aging), failing to model mechanical vibration caused by water flow, electrical stress generated by electromagnetic interference, and the aging characteristics of the insulation material itself. This single-factor assessment method ignores the synergistic degradation effect of multiple superimposed fields (1+1>2), resulting in a significant deviation between the prediction results and the actual operating life, and failing to truly achieve early warning and precise operation and maintenance. Summary of the Invention

[0005] In order to overcome the defects and shortcomings of the existing technology, this application proposes an online monitoring method for electrical equipment in hydropower stations.

[0006] To achieve the above objectives, this application adopts the following technical solution: Firstly, this application provides a method for online monitoring of electrical equipment in hydropower stations, including the following specific steps: S100: Obtain information on the operation of electrical equipment in the hydropower station, water flow, and interference from surrounding equipment; S200, combining the impact of water flow on the vibration of electrical equipment in hydropower stations and the operating conditions of electrical equipment in hydropower stations to predict the insulation status of electrical equipment; S300, combined with the impact of water flow on the operation of surrounding equipment and the interference of surrounding equipment, predicts the electromagnetic interference risk of surrounding equipment. S400, analyze the electrical operation of electrical equipment in conjunction with the electromagnetic interference risk of surrounding equipment and the insulation condition of electrical equipment; S500, Insulation maintenance is carried out in conjunction with the electrical operation of electrical equipment.

[0007] In one implementation of this application, the operating status of the hydropower station electrical equipment includes equipment current, voltage, equipment casing vibration amplitude and frequency, winding temperature, and insulation layer connection status; the water flow status includes the flow rate collected by flow meters at the turbine inlet and outlet; and the interference status of surrounding equipment includes the switching action time, frequency, and amplitude of radiated interference sources from surrounding equipment.

[0008] In one implementation of this application, the prediction of the insulation condition of electrical equipment includes the following specific aspects: S201. Obtain the flow rate, vibration amplitude, and frequency of the equipment casing, and predict abnormal vibration of the equipment casing based on future water flow conditions. Specifically, this involves: obtaining real-time water flow conditions, vibration amplitude, and frequency of the equipment casing; multiplying the standardized vibration amplitude and frequency of the equipment casing to obtain the vibration coefficient; dividing the future water flow condition by the current water flow coefficient and then multiplying by the vibration coefficient to obtain abnormal vibration of the equipment casing. This step enables early identification of abnormal vibration of the equipment casing that may be caused by changes in water flow (such as load adjustment and water hammer effect), transforming passive response into proactive prediction. S202. Obtain the connection status of the current device insulation layer, obtain the detachment area and detachment image of the connection layer, and obtain the detachment image anomaly by calculating the average of the standard deviation of the pixel value of each point of the detachment image from the safe pixel value range. The safe pixel value range is the pixel value range when the corresponding insulation layer is initially coated. The detachment area anomaly is obtained by dividing the detachment area by the safe detachment area. The insulation layer connection anomaly is obtained by multiplying the detachment image anomaly by the detachment area anomaly. This step realizes a quantitative composite evaluation of the insulation layer connection status, which not only identifies the geometric severity of the detachment area, but also captures early microscopic blistering, discoloration, peeling and other visual anomalies that are difficult to measure by area through image pixel deviation, avoiding the one-sidedness of relying solely on area judgment. S203. Obtain the vibration influence coefficient by multiplying the abnormal vibration of the equipment casing. Then, sum the vibration influence of the casing with the value 1 and multiply it by the insulation layer connection abnormality to obtain the insulation abnormality of the electrical equipment. Dynamically couple the additional deterioration effect of vibration on insulation (i.e., the vibration influence of the casing) with the structural state of the insulation body (connection abnormality). This reflects the positive feedback mechanism that mechanical vibration accelerates insulation damage and insulation weak points are more easily damaged under vibration, making the prediction results closer to the actual physical process.

[0009] In one implementation of this application, the prediction of electromagnetic interference risk from surrounding equipment includes the following specific aspects: S301. Obtain the equipment current, voltage, equipment casing vibration amplitude and frequency, winding temperature, switch action time, and interference frequency and amplitude of nearby equipment; simultaneously obtain the water flow rate of nearby equipment; based on historical data of nearby equipment, including equipment current, voltage, equipment casing vibration amplitude and frequency, winding temperature, switch action time, interference frequency and amplitude, and the obtained water flow rate; construct a system with the following inputs: equipment current, voltage, equipment casing vibration amplitude and frequency, winding temperature, switch action time, and water flow rate; output: interference frequency during operation. The multilayer perceptron neural network model for amplitude is constructed as follows: First, six physical quantities of nearby equipment are collected simultaneously: effective value of three-phase current, line voltage, amplitude and main frequency of shell vibration, winding temperature, and switch action timestamp. Flow data of the pipeline is also introduced to form a seven-dimensional input feature vector. Electromagnetic interference output labels are the interference center frequency and peak amplitude. The data is sliced ​​into 1-second sliding window segments (0.2-second step). After removing abnormal frames due to sensor packet loss, the seven features are standardized to form approximately 2000 sets of samples, which are then divided into training, validation, and test sets in an 8:1:1 ratio. The specific layer parameters are as follows: the input layer has 7 neurons; hidden layer 1 has 128 neurons, using the ReLU activation function, followed by a batch normalization layer and a Dropout layer (dropout rate 0.3); hidden layer 2 has 64 neurons, ReLU activation, batch normalization, and Dropout (dropout rate 0.2); hidden layer 3 has 32 neurons, ReLU activation, and L2 regularization (coefficient 0.001); the output layer has 2 linear neurons, corresponding to the frequency and amplitude regression values, respectively. The Adam optimizer is used for training, with an initial learning rate of 0.001. The learning rate is halved if the validation loss does not decrease for 5 consecutive rounds. The loss function is the mean absolute error, and R is monitored. 2Indicators; Batch size 64, maximum training rounds 300, early stop mechanism enabled; Utilizing deep learning to establish a nonlinear mapping model from multiple physical quantities to electromagnetic interference, it can automatically learn complex coupling relationships from 7-dimensional features such as equipment current, voltage, vibration, temperature, switching action time and water flow, achieving accurate and real-time prediction of interference frequency and amplitude, breaking through the limitations of traditional thresholds or empirical formulas. S302. Import the collected current equipment data into the constructed multilayer perceptron neural network model, and output the predicted interference center frequency and peak amplitude for future periods; use the trained model to infer the currently collected feature data, and can quickly output the center frequency and peak amplitude of electromagnetic interference in the future short period, providing a basis for electromagnetic stress prediction for insulation maintenance.

[0010] In one implementation of this application, the prediction of electromagnetic interference risk from surrounding equipment further includes the following specific steps: S303. Obtain the interference center frequency and peak amplitude of surrounding devices for future periods, and at the same time obtain the distance between the devices and the corresponding electrical devices. S304. Obtain the ratio of the interference center frequency to the safe frequency of each surrounding device in the future period, and at the same time obtain the ratio of the peak amplitude to the safe amplitude in the future period. Multiply the two ratios and divide by the square of the standardized distance from the surrounding device to the electrical device to obtain the electromagnetic influence of the surrounding device. This provides a normalized, dimensionless electromagnetic influence quantification index, which can intuitively characterize the electromagnetic interference contribution of a certain surrounding device to the target electrical device, and facilitates subsequent accumulation and threshold comparison. S305. Obtain the electromagnetic influence of all surrounding devices and sum them to obtain the electromagnetic interference risk of surrounding devices.

[0011] In one implementation of this application, the analysis of the electrical operation of electrical equipment includes the following specific steps: It obtains the insulation abnormality of electrical equipment and the electromagnetic interference risk of surrounding equipment; by multiplying the insulation abnormality of electrical equipment by the electromagnetic interference risk of surrounding equipment, it obtains the electrical operation risk of electrical equipment in the future cycle. It combines the insulation abnormality of the equipment body (internal state) with the electromagnetic interference risk (external pressure) to form a comprehensive electrical operation risk index, which reflects the actual failure mode of the synergistic deterioration of internal and external factors, and significantly improves the comprehensiveness and accuracy of predicting the future health status of equipment.

[0012] In one implementation of this application, the insulation maintenance based on the electrical operation of the electrical equipment includes the following specific steps: The electrical operating risk of electrical equipment in the future cycle is compared with the set electrical operating risk threshold. If the electrical operating risk of the electrical equipment is greater than or equal to the set electrical operating risk threshold, insulation maintenance is required for the electrical equipment, and an insulation maintenance warning is issued. If the electrical operating risk of the electrical equipment is less than the set electrical operating risk threshold, insulation maintenance is not required for the electrical equipment.

[0013] Secondly, this application also provides an online monitoring system for electrical equipment in hydropower stations, including the following specific modules: Acquisition module, electrical operation status prediction module, and insulation maintenance module; The acquisition module is used to acquire the operating status of the hydropower station's electrical equipment, the water flow status, and the interference status of surrounding equipment; The electrical operation prediction module combines the vibration impact of water flow on the electrical equipment of the hydropower station and the operation status of the electrical equipment to predict the insulation status of the electrical equipment. It also combines the impact of water flow on the operation of surrounding equipment and the interference of surrounding equipment to predict the electromagnetic interference risk of surrounding equipment. Finally, it combines the electromagnetic interference risk of surrounding equipment with the insulation status of the electrical equipment to analyze the electrical operation status of the electrical equipment. The insulation maintenance module performs insulation maintenance based on the electrical operating conditions of the electrical equipment.

[0014] Thirdly, this application provides an electronic device comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes an online monitoring method for electrical equipment in a hydropower station by calling the computer program stored in the memory.

[0015] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform an online monitoring method for electrical equipment in a hydropower station.

[0016] Compared with the prior art, this application has the following advantages: By coordinating the prediction of water flow disturbance, mechanical vibration and electromagnetic interference, accurate early warning of insulation risks of electrical equipment in hydropower stations is achieved, effectively avoiding the blind spots of single-factor assessment and significantly reducing the risk of unplanned shutdowns and accidents. Attached Figure Description

[0017] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a schematic diagram of the overall process structure in the method embodiments of this application; Figure 2This is a schematic diagram of the overall process of step S200 in the method embodiment of this application; Figure 3 This is a schematic diagram of the model structure in step S300 of the method embodiment of this application; Figure 4 This is a schematic diagram of the structure in the system embodiment of this application. Detailed Implementation

[0018] The technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments and specific features in the embodiments are detailed descriptions of the technical solution of this application, rather than limitations thereof. In the absence of conflict, the embodiments and technical features in the embodiments can be combined with each other.

[0019] Example Please see Figures 1 to 3 , Figure 1 This is a schematic diagram of the overall process of the online monitoring method for electrical equipment in hydropower stations provided in this application embodiment, which specifically includes the following steps: S100: Obtain information on the operation of electrical equipment in the hydropower station, water flow, and interference from surrounding equipment; In this embodiment, the operating status of the hydropower station's electrical equipment includes equipment current, voltage, equipment casing vibration amplitude and frequency, winding temperature, and insulation layer connection status; water flow status includes flow rate collected using flow meters at the turbine inlet and outlet; and interference status of surrounding equipment includes the switching action time, frequency, and amplitude of radiated interference sources from surrounding equipment. A specific example of the acquisition method is as follows: Electrical operating data: Equipment current and voltage are collected in real time using high-precision current transformers (CTs) and voltage transformers (PTs) installed on the generator outlet bus, excitation circuit, and main transformer incoming side. The signals are converted into 4-20mA standard analog quantities or IEC61850 digital messages via the secondary side and sent to the data acquisition card (sampling rate not less than 10kHz). Mechanical vibration data: Piezoelectric accelerometers (sensitivity approximately 100mV / g, frequency response range 0.5Hz-10kHz) were placed on the upper and lower frames of the generator, bearing housings, and the surface of the main transformer tank to collect the amplitude and frequency of the housing vibration; simultaneously, eddy current displacement sensors were used to monitor the spindle runout. The signals were digitized at a sampling rate of 5kHz after anti-aliasing filtering. Temperature data: Platinum resistance temperature sensors are pre-embedded in the generator stator slots, rotor magnetic poles, thrust bearings and guide bearings. A four-wire connection method is used to eliminate lead wire errors. The data is converted into a 4-20mA signal by a temperature transmitter or directly read from the digital fiber optic temperature sensor. The measurement range is 0-150℃ and the accuracy is ±0.1℃. Insulation layer connection status: Industrial high-definition cameras (resolution ≥ 5 million pixels, frame rate 30fps) are installed at key parts such as the ends of generator stator windings, slots and connecting busbars, supplemented by coaxial LED light sources to avoid reflection, to continuously capture images of the insulation layer surface. The area of ​​the detached area (pixel counting method) and pixel deviation (standard deviation of RGB channel from the safety reference image) are extracted by image recognition algorithm. Water flow conditions: Ultrasonic time-of-flight flow meters (accuracy ±0.5%FS) or electromagnetic flow meters (suitable for water flow containing impurities) are installed at the turbine casing inlet, tailrace outlet, and straight section of the intake steel pipe. The instantaneous flow value is output at a refresh rate of 1Hz, and the cumulative flow is recorded synchronously through pulse output. Interference from surrounding equipment: At the generator neutral point, bus bridge, and low-voltage side of the main transformer, a wide-bandwidth Rogowski coil (bandwidth 100Hz-30MHz) coupled with a high-frequency voltage transformer is used to collect the frequency and amplitude of electromagnetic interference signals; the switching action time is obtained through a dry contact signal acquisition module (resolution 1ms) connected to the circuit breaker auxiliary contacts, and the time, phase, and number of pulses generated for each opening and closing are recorded; All the above sensor signals are aggregated by the distributed data acquisition front end to the industrial data server (RAID storage, timestamp synchronization accuracy ≤1μs) to form a standardized structured dataset in 1-second segments, providing high-quality time series input for subsequent preprocessing and model prediction; S200, combining the impact of water flow on the vibration of electrical equipment in hydropower stations and the operating conditions of electrical equipment in hydropower stations to predict the insulation status of electrical equipment; In this embodiment, predicting the insulation condition of electrical equipment includes the following specific aspects: S201. Obtain the water flow rate, equipment casing vibration amplitude, and frequency, and predict equipment casing vibration anomalies based on future water flow rates. Specifically, this involves: obtaining real-time water flow rate, equipment casing vibration amplitude, and frequency; multiplying the standardized equipment casing vibration amplitude and frequency to obtain the vibration coefficient; dividing the future water flow rate by the current water flow coefficient and then multiplying by the vibration coefficient to obtain the equipment casing vibration anomaly. This step allows for the early identification of equipment casing vibration anomalies that may be caused by water flow changes (such as load adjustments and water hammer effects), transforming passive response into proactive prediction. In hydropower stations, water flow rate is the primary excitation source of vibration; the vibration coefficient (amplitude × frequency) comprehensively reflects the mechanical energy level. By normalizing the future flow rate and the current flow coefficient and then multiplying by the vibration coefficient, an excitation-response mapping relationship is established, conforming to the fundamental principle in mechanical vibration that the excitation intensity is proportional to the response amplitude, thus providing physical support for the prediction results. S202. Obtain the connection status of the current equipment insulation layer, including the area of ​​detachment and images of the detached layer. Anomalies in the detached image are obtained by calculating the average standard deviation of the pixel values ​​at each point in the detached image from the safe pixel value range. The safe pixel value range is the pixel value range at the initial coating of the corresponding insulation layer. Detachment area anomalies are obtained by dividing the detached area by the safe detached area. Insulation layer connection anomalies are obtained by multiplying the detached image anomaly by the detached area anomaly. This step achieves a quantitative and comprehensive assessment of the insulation layer connection status, identifying both the geometric severity of the detachment area and capturing early microscopic blistering, discoloration, and peeling—visual anomalies that are difficult to measure by area—through image pixel deviation, avoiding the one-sidedness of relying solely on area judgment. The safe pixel value range represents the standard color / texture characteristics at the initial coating of the insulation layer. The deviation of the current pixel from this range (average standard deviation) objectively reflects the degree of aging, discoloration, or structural damage to the insulation surface. The ratio of the detached area to the safe area measures the severity of the damage; multiplying the two constitutes a joint weight of geometric and microscopic features, more comprehensively representing the health status of the insulation connection. S203. The vibration impact coefficient is multiplied by the abnormal vibration of the equipment casing to obtain the casing vibration impact. The casing vibration impact is then summed with a value of 1 and multiplied by the insulation layer connection anomaly to obtain the electrical equipment insulation anomaly. The additional deterioration effect of vibration on insulation (i.e., casing vibration impact) is dynamically coupled with the structural state of the insulation body (connection anomaly), reflecting the positive feedback mechanism that mechanical vibration accelerates insulation damage and weak points in insulation are more easily damaged under vibration, making the prediction results closer to the actual physical process. Mechanical vibration is the direct external cause of insulation layer detachment, crack propagation, and interface fatigue. Multiplying the vibration anomaly by the vibration impact coefficient and summing it with a value of 1 is equivalent to treating the vibration impact as a deterioration excitation factor independent of the foundation state. Multiplying this by the insulation connection anomaly realizes the superposition model of "external excitation × internal state".

[0020] S300, combined with the impact of water flow on the operation of surrounding equipment and the interference of surrounding equipment, predicts the electromagnetic interference risk of surrounding equipment. In this embodiment, predicting the electromagnetic interference risk of surrounding equipment includes the following specific aspects: S301. Obtain the equipment current, voltage, equipment casing vibration amplitude and frequency, winding temperature, switch action time, and interference frequency and amplitude of nearby equipment; simultaneously obtain the water flow rate of nearby equipment; based on historical data of nearby equipment, including equipment current, voltage, equipment casing vibration amplitude and frequency, winding temperature, switch action time, interference frequency and amplitude, and the obtained water flow rate; construct a multilayer perceptron neural network model with the equipment current, voltage, equipment casing vibration amplitude and frequency, winding temperature, switch action time, and water flow rate as inputs; and output the interference frequency and amplitude during operation, such as... Figure 3 As shown, the construction method is as follows: First, 6-dimensional physical quantities of nearby equipment are collected synchronously: effective value of three-phase current, line voltage, vibration amplitude and main frequency of the casing, winding temperature, and switch action timestamp. The flow data of the pipeline is also introduced to form a 7-dimensional input feature vector. The electromagnetic interference output label is the interference center frequency and peak amplitude. The data is sliced ​​by a 1-second sliding window (step size 0.2 seconds). After removing abnormal frames of sensor packet loss, the 7 features are standardized to form about 2000 sets of samples, which are divided into training, validation and test sets in an 8:1:1 ratio. The specific layer parameters are as follows: the input layer has 7 neurons; hidden layer 1 has 128 neurons, using the ReLU activation function, followed by a batch normalization layer and a Dropout layer (dropout rate 0.3); hidden layer 2 has 64 neurons, ReLU activation, batch normalization, and Dropout (dropout rate 0.2); hidden layer 3 has 32 neurons, ReLU activation, and L2 regularization (coefficient 0.001); the output layer has 2 linear neurons, corresponding to the frequency and amplitude regression values, respectively. The Adam optimizer is used for training, with an initial learning rate of 0.001. The learning rate is halved if the validation loss does not decrease for 5 consecutive rounds. The loss function is the mean absolute error, and R is monitored. 2 The system features a batch size of 64, a maximum training epoch of 300, and an early stop mechanism. It utilizes deep learning to establish a nonlinear mapping model from multiple physical quantities to electromagnetic interference (EMI). This model automatically learns complex coupling relationships from seven dimensions of features, including equipment current, voltage, vibration, temperature, switching action time, and water flow, enabling accurate and real-time prediction of interference frequency and amplitude, overcoming the limitations of traditional thresholds or empirical formulas. EMI (especially interference generated by partial discharge) is influenced by electrical stress, thermal stress, mechanical stress, and humidity. The multilayer perceptron (MLP) has the ability to fit any nonlinear function, and overfitting is effectively prevented through batch normalization, Dropout, and L2 regularization. The ReLU activation function and early stop mechanism improve training efficiency and generalization. A 1-second sliding window slice (0.2-second step) ensures the temporal resolution and response sensitivity of the prediction, suitable for the real-time requirements of hydropower station scenarios. S302. Import the collected current equipment data into the constructed multilayer perceptron neural network model, and output the predicted interference center frequency and peak amplitude for future periods; use the trained model to infer the currently collected feature data, and can quickly output the center frequency and peak amplitude of electromagnetic interference in the future short period, providing a basis for electromagnetic stress prediction for insulation maintenance. S303. Obtain the interference center frequency and peak amplitude of surrounding devices for future periods, and at the same time obtain the distance between the devices and the corresponding electrical devices. S304. Obtain the ratio of the interference center frequency to the safe frequency for the future period of each surrounding device, and simultaneously obtain the ratio of the peak amplitude to the safe amplitude for the future period. Multiply these two ratios and divide by the square of the standardized distance from the surrounding device to the electrical equipment to obtain the electromagnetic influence of the surrounding device. This provides a normalized, dimensionless quantitative index of electromagnetic influence, which can intuitively characterize the electromagnetic interference contribution of a surrounding device to the target electrical equipment, facilitating subsequent accumulation and threshold comparison. The ratio of the interference center frequency to the safe frequency and the ratio of the peak amplitude to the safe amplitude represent the degree of frequency deviation and amplitude exceeding the limit, respectively. The product of the two comprehensively measures the "deviation" and "intensity" of the interference. Dividing by the square of the standardized distance simulates the inverse square decay law of electromagnetic radiation in free space, assigning spatial weights to make the calculation conform to the basic principles of electromagnetic physics. S305. Obtain the electromagnetic influence of all surrounding devices and sum them to obtain the electromagnetic interference risk of surrounding devices. S400, analyze the electrical operation of electrical equipment in conjunction with the electromagnetic interference risk of surrounding equipment and the insulation condition of electrical equipment; In this embodiment, analyzing the electrical operation of electrical equipment includes the following specific steps: It obtains the insulation abnormality of electrical equipment and the electromagnetic interference risk of surrounding equipment; by multiplying the insulation abnormality of electrical equipment by the electromagnetic interference risk of surrounding equipment, it obtains the electrical operation risk of electrical equipment in the future cycle. It combines the insulation abnormality of the equipment body (internal state) with the electromagnetic interference risk (external pressure) to form a comprehensive electrical operation risk index, which reflects the actual failure mode of the synergistic deterioration of internal and external factors, and significantly improves the comprehensiveness and accuracy of predicting the future health status of equipment. S500, Perform insulation maintenance based on the electrical operating conditions of electrical equipment; In this embodiment, insulation maintenance based on the electrical operation of electrical equipment includes the following specific steps: The electrical operating risk of electrical equipment in the future cycle is compared with the set electrical operating risk threshold. If the electrical operating risk of the electrical equipment is greater than or equal to the set electrical operating risk threshold, insulation maintenance is required for the electrical equipment, and an insulation maintenance warning is issued. If the electrical operating risk of the electrical equipment is less than the set electrical operating risk threshold, insulation maintenance is not required for the electrical equipment.

[0021] It should be noted that the advantages of this embodiment are as follows: by coordinating the prediction of water flow disturbance, mechanical vibration and electromagnetic interference, accurate early warning of insulation risks of electrical equipment in hydropower stations is achieved, effectively avoiding the blind spots of single-factor assessment and significantly reducing the risk of unplanned shutdowns and accidents.

[0022] It should be noted that the setting parameters in this embodiment are obtained by fitting historical data. The specific steps are as follows: historical data is imported into this embodiment to obtain electrical operation risk, and the judgment results of whether electromagnetic crosstalk accidents occur in the historical operation process cycle are obtained. The obtained calculation results and judgment results are imported into the linear fitting software to output the value that meets the maximum judgment accuracy.

[0023] like Figure 4 As shown in the embodiments of this application, an online monitoring system for electrical equipment in hydropower stations is also provided, including: Acquisition module, electrical operation status prediction module, and insulation maintenance module; The acquisition module is used to acquire information on the operation status of the hydropower station's electrical equipment, water flow, and interference from surrounding equipment. The electrical operation prediction module combines the vibration impact of water flow on the electrical equipment of the hydropower station and the operation status of the electrical equipment to predict the insulation status of the electrical equipment. It also combines the impact of water flow on the operation of surrounding equipment and the interference of surrounding equipment to predict the electromagnetic interference risk of surrounding equipment. Finally, it combines the electromagnetic interference risk of surrounding equipment with the insulation status of the electrical equipment to analyze the electrical operation status of the electrical equipment. The insulation maintenance module performs insulation maintenance based on the electrical operating conditions of the electrical equipment.

[0024] The parameters and steps for implementing the corresponding functions of each unit module in the online monitoring system for electrical equipment of hydropower stations described above can be referred to the parameters and steps in the embodiments of the online monitoring method for electrical equipment of hydropower stations described above, and will not be repeated here.

[0025] Embodiments of this application also provide an electronic device, including a memory, a processor, and a communication bus; the memory and the processor are connected via the communication bus. The memory stores a method for online monitoring of hydropower station electrical equipment that can be loaded by the processor and executed as provided in the above embodiments.

[0026] The memory can be used to store instructions, programs, code, code sets, or instruction sets. The memory may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing the online monitoring method for hydropower station electrical equipment provided in the above embodiments, etc.; the data storage area may store data involved in the online monitoring method for hydropower station electrical equipment provided in the above embodiments, etc.

[0027] A processor may include one or more processing cores. The processor executes instructions, programs, code sets, or instruction sets stored in memory, and calls data stored in memory to perform various functions and process data as described in this application. The processor may be at least one of a specific application-specific integrated circuit, a digital signal processor, a digital signal processing device, a programmable logic device, a field-programmable gate array, a central processing unit, a controller, a microcontroller, and a microprocessor. It is understood that, for different devices, the electronic devices used to implement the above-described processor functions may also be other types, and the embodiments of this application do not specifically limit this.

[0028] A communication bus may include a pathway for transmitting information between the aforementioned components. The communication bus can be a PCI bus or an EISA bus, etc. Communication buses can be categorized into address buses, data buses, control buses, etc.

[0029] This application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as described in the above embodiments for online monitoring of electrical equipment in hydropower stations.

[0030] In this embodiment, a computer-readable storage medium can be a tangible device that holds and stores instructions used by an instruction execution device. The computer-readable storage medium can be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, the computer-readable storage medium can be a portable computer disk, a hard disk, a USB flash drive, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), spoofing random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory stick, floppy disk, optical disk, magnetic disk, mechanical encoding device, or any combination thereof.

[0031] The term includes, or any other variation thereof, is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0032] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing application concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions claimed in this application.

Claims

1. A method for on-line monitoring of electrical equipment of a hydropower plant, characterized in that, Includes the following steps: S100: Obtain information on the operation of the hydropower station's electrical equipment, water flow, and interference from surrounding equipment; S200, combining the impact of water flow on the vibration of electrical equipment in hydropower stations and the operating conditions of electrical equipment in hydropower stations to predict the insulation status of electrical equipment; S300, combined with the impact of water flow on the operation of surrounding equipment and the interference of surrounding equipment, predicts the electromagnetic interference risk of surrounding equipment. S400, analyze the electrical operation of electrical equipment in conjunction with the electromagnetic interference risk of surrounding equipment and the insulation condition of electrical equipment; S500, Insulation maintenance is carried out in conjunction with the electrical operation of electrical equipment.

2. The method for online monitoring of electrical equipment of a hydropower station according to claim 1, characterized in that, The operating status of the electrical equipment of the hydropower station includes equipment current, voltage, vibration amplitude and frequency of equipment casing, winding temperature and insulation layer connection status; the water flow status includes the flow rate collected by flow meters at the inlet and outlet of the turbine; and the interference status of surrounding equipment includes the switching action time, frequency and amplitude of the radiating interference sources of surrounding equipment.

3. The method for online monitoring of electrical equipment of a hydropower station according to claim 1, characterized in that, The predicted insulation condition of electrical equipment includes the following specific details: S201. Obtain the flow rate of water, the vibration amplitude and frequency of the equipment casing, and predict abnormal vibration of the equipment casing based on the future flow rate of water. Specifically, obtain the real-time flow rate of water, the vibration amplitude and frequency of the equipment casing, multiply the standardized vibration amplitude and frequency of the equipment casing to obtain the vibration coefficient, and divide the future flow rate of water by the current flow coefficient of water and then multiply by the vibration coefficient to obtain the abnormal vibration of the equipment casing. S202. Obtain the connection status of the current equipment insulation layer, obtain the detachment area of ​​the connection layer and the detachment image of the connection layer, obtain the detachment image anomaly by calculating the average of the standard deviation of the pixel value of each point of the detachment image from the safe pixel value range, obtain the detachment area anomaly by dividing the detachment area by the safe detachment area, and obtain the insulation layer connection anomaly by multiplying the detachment image anomaly and the detachment area anomaly. S203. Obtain the vibration influence coefficient by multiplying the abnormal vibration of the equipment housing. Then, sum the vibration influence of the housing with the value 1 and multiply it by the insulation layer connection abnormality to obtain the insulation abnormality of the electrical equipment.

4. The method for online monitoring of electrical equipment of a hydropower station according to claim 1, characterized in that, The predicted electromagnetic interference risk from surrounding equipment includes the following specific details: S301. Obtain the equipment current, voltage, equipment casing vibration amplitude and frequency, winding temperature, switch action time, and interference frequency and amplitude of nearby equipment; simultaneously obtain the water flow rate of nearby equipment; based on historical data of nearby equipment, including equipment current, voltage, equipment casing vibration amplitude and frequency, winding temperature, switch action time, interference frequency and amplitude, and the obtained water flow rate; construct a multilayer perceptron neural network model with the equipment current, voltage, equipment casing vibration amplitude and frequency, winding temperature, switch action time, and water flow rate as inputs; and output the interference frequency and amplitude during operation. S302. Import the collected current device data into the constructed multilayer perceptron neural network model, and output the predicted interference center frequency and peak amplitude for future cycles.

5. The method for online monitoring of electrical equipment of a hydropower station according to claim 1, characterized in that, The prediction of electromagnetic interference risks from surrounding equipment also includes the following specific steps: S303. Obtain the interference center frequency and peak amplitude of surrounding devices for future periods, and at the same time obtain the distance between the devices and the corresponding electrical devices. S304. Obtain the ratio of the interference center frequency to the safe frequency of each surrounding device in the future period, and at the same time obtain the ratio of the peak amplitude to the safe amplitude in the future period. Multiply the two ratios and divide by the square of the standardized distance from the surrounding device to the electrical equipment to obtain the electromagnetic influence of the surrounding device. S305. Obtain the electromagnetic influence of all surrounding devices and sum them to obtain the electromagnetic interference risk of surrounding devices.

6. The online monitoring method for electrical equipment in a hydropower station according to claim 1, characterized in that, The analysis of the electrical operation of electrical equipment includes the following specific steps: Obtain the insulation abnormality of electrical equipment and the electromagnetic interference risk of surrounding equipment; multiply the insulation abnormality of electrical equipment by the electromagnetic interference risk of surrounding equipment to obtain the electrical operation risk of electrical equipment in the future cycle.

7. The online monitoring method for electrical equipment in a hydropower station according to claim 3, characterized in that, The insulation maintenance based on the electrical operation of electrical equipment includes the following specific steps: The electrical operating risk of electrical equipment in the future cycle is compared with the set electrical operating risk threshold. If the electrical operating risk of the electrical equipment is greater than or equal to the set electrical operating risk threshold, insulation maintenance is required for the electrical equipment, and an insulation maintenance warning is issued. If the electrical operating risk of the electrical equipment is less than the set electrical operating risk threshold, insulation maintenance is not required for the electrical equipment.

8. An online monitoring system for electrical equipment in a hydropower station, used to implement the online monitoring method for electrical equipment in a hydropower station as described in any one of claims 1-7, characterized in that, It includes an acquisition module, an electrical operation prediction module, and an insulation maintenance module; The acquisition module is used to acquire the operating status of the hydropower station's electrical equipment, the water flow status, and the interference status of surrounding equipment; The electrical operation prediction module combines the vibration impact of water flow on the electrical equipment of the hydropower station and the operation status of the electrical equipment to predict the insulation status of the electrical equipment. It also combines the impact of water flow on the operation of surrounding equipment and the interference of surrounding equipment to predict the electromagnetic interference risk of surrounding equipment. Finally, it combines the electromagnetic interference risk of surrounding equipment with the insulation status of the electrical equipment to analyze the electrical operation status of the electrical equipment. The insulation maintenance module performs insulation maintenance based on the electrical operating conditions of the electrical equipment.

9. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes the online monitoring method for electrical equipment of a hydropower station as described in any one of claims 1-7 by calling the computer program stored in the memory.

Images