Hydropower station electrical equipment state monitoring and early warning system and method

Abstract

The invention relates to the technical field of monitoring control, and discloses a hydropower station electrical equipment state monitoring and early warning system and method, and the system comprises a data acquisition module, a model construction module, and a data processing module. The data acquisition module is used for acquiring real-time equipment data and mechanism characteristics corresponding to each piece of equipment; the model construction module is used for constructing a digital twinborn model according to equipment data and mechanism characteristics; the data processing module is used for inputting the obtained real-time equipment data into a digital twinborn model for processing to obtain early warning information or alarm information and sending the early warning information or alarm information to a user terminal, the early warning information comprises an early warning area and early warning speculation, and the alarm information comprises a damaged area and fault speculation; the user terminal is used for receiving the early warning information or the alarm information and sending the corresponding maintenance information to the data processing module. By adopting the system, scientific and reasonable maintenance suggestions can be provided for maintenance personnel, the maintenance efficiency is improved, and the labor cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of monitoring and control technology, and in particular to a hydropower station electrical equipment status monitoring and early warning system and method. Background Art

[0002] Against the backdrop of ongoing optimization and adjustment of today's energy structure, hydropower, as a clean, renewable, and high-quality resource, is playing an increasingly important role in the global energy system. Hydropower stations, as the core production sites of hydropower energy, require stable and reliable operation of their electrical equipment, which is directly related to the continuous supply of electricity and the security and stability of the power grid.

[0003] However, the relevant hydropower station equipment monitoring technology has a low level of intelligence in operation and maintenance, and is unable to provide maintenance personnel with scientific and reasonable maintenance suggestions, resulting in low efficiency and high labor costs.

[0004] In view of this, there is an urgent need for a method and system that can solve the above problems. Summary of the Invention

[0005] Based on this, it is necessary to provide a hydropower station electrical equipment status monitoring and early warning system to address the above technical problems, so as to provide maintenance personnel with scientific and reasonable maintenance suggestions, improve maintenance efficiency and reduce labor costs.

[0006] In a first aspect, the present application provides a hydropower station electrical equipment condition monitoring and early warning system, the system comprising: a data acquisition module, a model building module and a data processing module;

[0007] The data acquisition module is used to obtain real-time equipment data and the corresponding mechanism characteristics of each device;

[0008] The model building module is used to build a digital twin model based on equipment data and mechanism characteristics;

[0009] The data processing module is used to input the acquired real-time equipment data into the digital twin model for processing, obtain early warning information or alarm information, and send the early warning information or alarm information to the user terminal. The early warning information includes the early warning area and early warning speculation, and the alarm information includes the damaged area and fault speculation;

[0010] The user terminal is used to receive early warning information or alarm information and send corresponding maintenance information to the data processing module.

[0011] Furthermore, the acquired real-time device data is input into the digital twin model for processing, including:

[0012] Obtaining maintenance information and device status data corresponding to the maintenance information, the device status data including device status data before maintenance and device status data after maintenance;

[0013] The following formula is used to process the maintenance information and equipment status data to obtain the maintenance assessment result:

[0014] ΔT=T post -T pre

[0015] ΔV=V post -V pre

[0016] ΔP=P post -P pre

[0017]

[0018] Where ΔT represents the temperature change before and after maintenance; T post Indicates the temperature data after maintenance T pre represents the temperature data before maintenance; ΔV represents the change in vibration data before and after maintenance; V post Indicates the vibration data after maintenance; V pre represents the vibration data before maintenance; ΔP represents the change in partial discharge before and after maintenance; P post Represents the partial discharge data after maintenance; P pre Indicates the partial discharge data before maintenance; S repair Indicates the maintenance effect score; ω T Represents the weight coefficient of temperature; ω V Represents the weight coefficient of vibration; ω P Represents the weight coefficient of partial discharge;

[0019] Use the following formula to update the warning prediction or failure prediction based on the maintenance assessment results:

[0020]

[0021] Among them, θ old is the original parameter of the digital twin model; θ new is the updated digital twin model parameter; η represents the learning rate; represents the gradient of the loss function with respect to the parameter; y post Indicates the actual equipment status after maintenance; Represents the device state predicted by the model.

[0022] Furthermore, the device data includes temperature data and vibration data;

[0023] Build a digital twin model based on equipment data and mechanism characteristics, including:

[0024] Use the following formula to process the temperature data and vibration data to obtain the correlation coefficient between the temperature data and vibration data:

[0025]

[0026] Where r represents the correlation coefficient; n represents the number of samples; i represents the sample index; T i represents the temperature value collected at the i-th time point; Represents the sample mean of temperature data; V i represents the vibration amplitude collected at the i-th time point; represents the sample mean of vibration data;

[0027] Based on the correlation coefficient and the mechanism characteristics of the corresponding device, the corresponding association rules and the corresponding initial threshold are obtained through setting.

[0028] Furthermore, building a digital twin model based on equipment data and mechanism characteristics also includes:

[0029] Processing the device data using a sliding window to obtain a first threshold value, where the first threshold value is used to indicate that the device exceeds a critical value of a normal state;

[0030] The following formula is used to compensate the first threshold according to environmental factors to obtain the second threshold:

[0031] Threshold adjusted =μ t +αT amb +pH±kσ t

[0032] Among them, Threshold adjusted represents the adjusted second threshold; μ t represents the mean value calculated based on the data in the sliding window at the time step; α represents the weight coefficient of the ambient temperature; T amb represents the ambient temperature; β represents the weight coefficient of the ambient humidity; H represents the ambient humidity; k represents the multiple coefficient of the standard deviation, which is used to determine the fluctuation range of the threshold; σ t Represents the standard deviation calculated based on the data in the sliding window at time step t.

[0033] Furthermore, the user terminal is further configured to send an access request to the data processing module.

[0034] Furthermore, the data processing module also includes an access rights screening unit;

[0035] The access permission screening unit is used to judge the obtained access request and obtain a judgment result, which includes the access rights and inaccessibility rights.

[0036] If the judgment result is that the user is allowed to access, the device data is sent to the user terminal corresponding to the access request.

[0037] Furthermore, the device data is processed using a sliding window to obtain a first threshold using the following formula:

[0038]

[0039] Among them, μ t Indicates the mean value calculated based on the data in the sliding window at the time step; W represents the size of the sliding window, that is, the number of data samples contained in the window; i represents the index of the data sample in the sliding window, from to t;x i Represents the i-th sample data in the sliding window; σ t Represents the standard deviation calculated based on the data in the sliding window at time step t.

[0040] Furthermore, building a digital twin model based on equipment data and mechanism characteristics also includes:

[0041] Use the following formula to simulate the dynamic behavior of the device:

[0042]

[0043] in, represents the rate of change of the device temperature over time t; I represents the current passing through the device; R(T) represents the device resistance; h represents the heat dissipation coefficient of the device surface; A represents the surface area of ​​heat exchange between the device and the surrounding environment; T represents the current temperature of the device; T amb Indicates the ambient temperature; C indicates the thermal capacity of the equipment.

[0044] In a second aspect, the present application further provides a method for monitoring and early warning the status of electrical equipment in a hydropower station, the method comprising:

[0045] Obtain real-time equipment data and the corresponding mechanism characteristics of each device;

[0046] Build a digital twin model based on equipment data and mechanism characteristics;

[0047] The acquired real-time device data is input into the data twin model for processing to obtain early warning information or alarm information, which is then sent to the user terminal. The early warning information includes the warning area and warning speculation, and the alarm information includes the damaged area and fault speculation.

[0048] The user terminal generates maintenance information corresponding to the early warning information or the alarm information.

[0049] In a third aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any system in the first aspect of the present application when the computer program is executed by a processor.

[0050] The technical solution provided in this application includes the following technical effects: by providing a hydropower station electrical equipment status monitoring and early warning system, including: a data acquisition module, a model construction module and a data processing module; the data acquisition module is used to obtain real-time equipment data and the corresponding mechanism characteristics of each equipment; the model construction module is used to construct a digital twin model based on the equipment data and mechanism characteristics; the data processing module is used to input the acquired real-time equipment data into the digital twin model for processing, obtain early warning information or alarm information, and send the early warning information or alarm information to the user terminal, the early warning information includes the early warning area and the early warning speculation, and the alarm information includes the damaged area and the fault speculation; the user terminal is used to receive the early warning information or the alarm information, and send the corresponding maintenance information to the data processing module, so as to provide scientific and reasonable maintenance suggestions to maintenance personnel, improve maintenance efficiency, and reduce labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 A structural diagram of a hydropower station electrical equipment status monitoring and early warning system provided in one embodiment of the present application;

[0053] Figure 2 A flowchart of a method for monitoring and early warning the status of electrical equipment in a hydropower station is provided as an embodiment of the present application. DETAILED DESCRIPTION

[0054] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is merely to provide a better understanding of the present application by illustrating the examples of the present application.

[0055] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, the elements defined by the phrase "comprising..." do not exclude the presence of other identical elements in the process, method, article, or device comprising the elements.

[0056] To solve the problems of the prior art, the present invention provides a hydropower station electrical equipment status monitoring and early warning system, method, and computer storage medium. The following first introduces the hydropower station electrical equipment status monitoring and early warning system provided by the present invention.

[0057] Firstly, Figure 1 The following is a flow chart showing a hydropower station electrical equipment status monitoring and early warning system provided by an embodiment of the present application. Figure 1 As shown, the system includes: a data acquisition module 101, a model building module 102 and a data processing module 103;

[0058] The data acquisition module 101 is used to acquire real-time device data and the corresponding mechanism characteristics of each device.

[0059] Specifically, by obtaining real-time equipment data, the system can grasp the operating status of the equipment in real time and detect abnormal situations in a timely manner; and obtaining the corresponding mechanism characteristics of each device will help to more deeply understand the operating laws of the equipment, and provide solid and reliable basic data for subsequent analysis of equipment status, fault diagnosis and construction of equipment models, thereby improving the effectiveness and accuracy of the entire system.

[0060] The model building module 102 is used to build a digital twin model based on equipment data and mechanism characteristics.

[0061] Specifically, building a digital twin model can simulate the actual operating status of the equipment in a virtual environment. Operation and maintenance personnel can use this model to predict possible equipment failures in advance, analyze the impact of changes in equipment operating parameters on its performance, and perform various tests and optimizations without affecting the actual operation of the equipment. This greatly improves the management and maintenance efficiency of the equipment, reduces maintenance costs and the risk of equipment failure, and also helps to gain a deeper understanding of the operating laws of the equipment, providing strong support for the stable operation of the hydropower station.

[0062] The data processing module 103 is used to input the acquired real-time equipment data into the digital twin model for processing, obtain early warning information or alarm information, and send the early warning information or alarm information to the user terminal 104. The early warning information includes the early warning area and the early warning speculation, and the alarm information includes the damaged area and the fault speculation.

[0063] Specifically, the data processing module 103 analyzes and processes real-time equipment data, enabling early detection of potential equipment failure risks. This early warning information allows staff ample time to take preventative measures, reducing the probability of failures, preventing them from escalating, and minimizing losses caused by equipment damage. When equipment fails, the alarm information provides the corresponding damaged area and a hypothesized fault, helping staff quickly locate the problem, improving repair efficiency and reducing equipment downtime, thereby ensuring normal power generation and stable operation of the hydropower station. Furthermore, this timely information transmission helps optimize equipment maintenance plans, reduce maintenance costs, and enhance the overall operational management of the hydropower station.

[0064] The user terminal 104 is used to receive early warning information or alarm information, and send corresponding maintenance information to the data processing module.

[0065] Specifically, user terminal 104, as part of the system, is responsible for receiving early warning or alarm information from data processing module 103. After staff develop appropriate maintenance strategies based on this information, they then feed back maintenance information to data processing module 103. This process not only enables staff to promptly understand equipment status and respond quickly, but also enables the system to improve data processing module 103 with maintenance information, creating a closed-loop information exchange between user terminal 104 and data processing module 103. This improves maintenance efficiency, reduces labor costs, and ensures stable equipment operation.

[0066] By providing a hydropower station electrical equipment status monitoring and early warning system, the data acquisition module 101 is used to obtain real-time equipment data and the corresponding mechanism characteristics of each device; the model construction module 102 is used to construct a digital twin model based on the equipment data and mechanism characteristics; the data processing module 103 is used to input the acquired real-time equipment data into the digital twin model for processing, obtain early warning information or alarm information, and send the early warning information or alarm information to the user terminal. The early warning information includes the early warning area and the early warning speculation, and the alarm information includes the damaged area and the fault speculation; the user terminal 104 is used to receive the early warning information or the alarm information, and send the corresponding maintenance information to the data processing module, so as to provide maintenance personnel with scientific and reasonable maintenance suggestions, improve maintenance efficiency, and reduce labor costs.

[0067] Furthermore, the acquired real-time device data is input into the digital twin model for processing, including:

[0068] Obtaining maintenance information and device status data corresponding to the maintenance information, the device status data including device status data before maintenance and device status data after maintenance;

[0069] The following formula is used to process the maintenance information and equipment status data to obtain the maintenance assessment result:

[0070] ΔT=T post -T pre

[0071] ΔV=V post -V pre

[0072] ΔP=P post -P pre

[0073]

[0074] Where ΔT represents the temperature change before and after maintenance; T post Indicates the temperature data after maintenance T pre represents the temperature data before maintenance; ΔV represents the change in vibration data before and after maintenance; V post Indicates the vibration data after maintenance; V pre represents the vibration data before maintenance; ΔP represents the change in partial discharge before and after maintenance; Pp ost Represents the partial discharge data after maintenance; P pre Indicates the partial discharge data before maintenance; S repair Indicates the maintenance effect score; ω T Represents the weight coefficient of temperature; ω V Represents the weight coefficient of vibration; ω P Represents the weight coefficient of partial discharge;

[0075] Use the following formula to update the warning prediction or failure prediction based on the maintenance assessment results:

[0076]

[0077] Among them, θ old is the original parameter of the digital twin model; θ new is the updated digital twin model parameter; η represents the learning rate; represents the gradient of the loss function with respect to the parameter; y post Indicates the actual equipment status after maintenance; Represents the device state predicted by the model.

[0078] Specifically, by processing maintenance information and equipment status data to generate maintenance assessment results, staff can intuitively understand the effectiveness of each maintenance, provide a scientific basis for subsequent maintenance decisions, and help optimize maintenance strategies and improve maintenance quality. Furthermore, updating the digital twin model's early warning or fault predictions based on maintenance assessment results can continuously improve the model's accuracy and reliability, enabling it to better predict potential equipment failure risks or analyze the causes of existing failures. This allows for proactive measures to prevent failures, reduce equipment downtime, lower maintenance costs, and ensure the stable and efficient operation of the hydropower station's electrical equipment.

[0079] Furthermore, the device data includes temperature data and vibration data;

[0080] Build a digital twin model based on equipment data and mechanism characteristics, including:

[0081] Use the following formula to process the temperature data and vibration data to obtain the correlation coefficient between the temperature data and vibration data:

[0082]

[0083] Where r represents the correlation coefficient; n represents the number of samples; i represents the sample index; T i represents the temperature value collected at the i-th time point; Represents the sample mean of temperature data; V i represents the vibration amplitude collected at the i-th time point; represents the sample mean of vibration data;

[0084] Based on the correlation coefficient and the mechanism characteristics of the corresponding device, the corresponding association rules and the corresponding initial threshold are obtained through setting.

[0085] Specifically, by calculating the correlation coefficient between temperature and vibration data and determining association rules and initial thresholds based on this, it is possible to deeply explore the potential relationships between equipment operating data, providing strong support for building more accurate digital twin models. In practical applications, these association rules and initial thresholds can help the system more accurately judge the operating status of equipment and promptly detect abnormalities. For example, when the correlation between temperature and vibration data deviates abnormally from the association rules, or when certain data exceeds the initial threshold, it may indicate a potential equipment failure, thereby issuing early warning information, allowing staff to take timely measures to avoid equipment failure, ensure the stable operation of the hydropower station's electrical equipment, reduce downtime and maintenance costs caused by equipment failure, and improve the overall operational efficiency of the hydropower station.

[0086] Furthermore, building a digital twin model based on equipment data and mechanism characteristics also includes:

[0087] Processing the device data using a sliding window to obtain a first threshold value, where the first threshold value is used to indicate that the device exceeds a critical value of a normal state;

[0088] The following formula is used to compensate the first threshold according to environmental factors to obtain the second threshold:

[0089] Threshold adjusted =μ t +αT amb +pH±kσ t

[0090] Among them, Threshold adjustes represents the adjusted second threshold; μ t represents the mean value calculated based on the data in the sliding window at the time step; α represents the weight coefficient of the ambient temperature; T amb represents the ambient temperature; β represents the weight coefficient of the ambient humidity; H represents the ambient humidity; k represents the multiple coefficient of the standard deviation, which is used to determine the fluctuation range of the threshold; σ t Represents the standard deviation calculated based on the data in the sliding window at time step t.

[0091] Specifically, by using a sliding window to process device data to obtain a first threshold, a preliminary normal-abnormal boundary can be determined based on the device's own data characteristics, providing a basic basis for determining the device's status. Further compensating the first threshold based on environmental factors to obtain a second threshold fully considers the impact of environmental factors on device operation, making the threshold more consistent with actual conditions. Therefore, when monitoring device status, it is possible to more accurately determine whether the device is abnormal, avoiding misjudgments or missed judgments caused by ignoring environmental factors when setting thresholds based solely on the device's own data. For example, when the ambient temperature or humidity is high, the normal operating parameter range of the device may change. In this case, the second threshold, after compensation for environmental factors, can more reasonably reflect the device's true status, thereby issuing early warnings more promptly and accurately. This helps maintenance personnel take preemptive measures to ensure the stable operation of the hydropower station's electrical equipment, reduce the risk of equipment failures caused by misjudgments or missed judgments, and improve equipment reliability and the hydropower station's operational efficiency.

[0092] Furthermore, the user terminal 104 is further configured to send an access request to the data processing module.

[0093] Specifically, in this system, in addition to receiving early warning or alarm information and sending corresponding maintenance information, user terminal 104 also has the ability to send access requests to the data processing module. This means that staff can proactively request various types of relevant information from the data processing module through user terminal 104, including equipment operating status data, analysis reports, and model parameters. This function allows staff to flexibly obtain information based on their needs and keep abreast of equipment details, allowing them to make more efficient decisions and formulate maintenance plans. It also enhances the interactivity between users and the system, allowing the system to better serve actual operation and maintenance work, improving the flexibility and pertinence of operation and maintenance, and helping to improve the management level and operating efficiency of electrical equipment in hydropower stations.

[0094] Furthermore, the data processing module 103 also includes an access rights screening unit;

[0095] The access permission screening unit is used to judge the obtained access request and obtain a judgment result, which includes the access rights and inaccessibility rights.

[0096] If the judgment result is that the user is allowed to access, the device data is sent to the user terminal corresponding to the access request.

[0097] Specifically, from a security perspective, the access rights screening unit, which verifies access requests, effectively prevents unauthorized access to device data. This protects the security and confidentiality of the hydropower station's electrical equipment operating data and mitigates potential risks associated with sensitive information leakage, such as malicious data tampering or misuse. Secondly, from a management perspective, this mechanism helps standardize data access processes, ensuring that only personnel with appropriate permissions and responsibilities can access device data, making data use more rational and organized. For example, only professional operations and maintenance personnel or relevant management personnel can access critical device data, enabling them to make accurate decisions and perform effective equipment maintenance. This improves work efficiency and avoids management chaos that can result from unauthorized data access. Furthermore, this mechanism enhances system stability and reliability, reducing the likelihood of system failures or data errors caused by improper access, and ensuring the normal operation of the hydropower station's electrical equipment condition monitoring and early warning system.

[0098] Furthermore, the device data is processed using a sliding window to obtain a first threshold using the following formula:

[0099]

[0100]

[0101] Among them, μ tIndicates the mean value calculated based on the data in the sliding window at the time step; W represents the size of the sliding window, that is, the number of data samples contained in the window; i represents the index of the data sample in the sliding window, from to t;x i Represents the i-th sample data in the sliding window; σ t Represents the standard deviation calculated based on the data in the sliding window at time step t.

[0102] Specifically, using a sliding window to process device data can dynamically capture changing trends in device data. Because the sliding window moves across the device data sequence over time, it can reflect the operating characteristics of the device in real time over different time periods, making it more flexible and accurate than fixed analysis methods. Furthermore, determining the first threshold by calculating the mean and standard deviation fully accounts for the central tendency and dispersion of the device data, making the first threshold more scientific and reasonable.

[0103] Furthermore, building a digital twin model based on equipment data and mechanism characteristics also includes:

[0104] Use the following formula to simulate the dynamic behavior of the device:

[0105]

[0106] in, represents the rate of change of the device temperature over time t; I represents the current passing through the device; R(T) represents the device resistance; h represents the heat dissipation coefficient of the device surface; A represents the surface area of ​​heat exchange between the device and the surrounding environment; T represents the current temperature of the device; T amb Indicates the ambient temperature; C indicates the thermal capacity of the equipment.

[0107] Specifically, when building a digital twin model, relevant formulas are used to simulate the dynamic behavior of the device. The rate of change of device temperature over time in this formula is affected by factors such as current, resistance, heat dissipation coefficient, surface area, current temperature, ambient temperature, and thermal capacity. Combining these factors can simulate device temperature changes and overall dynamics.

[0108] In a second aspect, the present application further provides a method for monitoring and early warning the status of electrical equipment in a hydropower station, the method comprising:

[0109] S201: Acquire real-time device data and corresponding mechanism characteristics of each device;

[0110] S202: Build a digital twin model based on equipment data and mechanism characteristics;

[0111] S203: Input the acquired real-time device data into the data twin model for processing to obtain early warning information or alarm information, and send the early warning information or alarm information to the user terminal. The early warning information includes the early warning area and early warning speculation, and the alarm information includes the damaged area and fault speculation;

[0112] S204: The user terminal generates maintenance information corresponding to the early warning information or the alarm information.

[0113] Specifically, the system first acquires real-time device data, such as operating parameters like current, voltage, and temperature, as well as the corresponding mechanical characteristics of each device, such as its operating principle and performance characteristics. This provides basic data support for subsequent analysis. Next, based on this device data and mechanical characteristics, a digital twin model is constructed. This model is a digital simulation of the actual device and reflects its operating status. The acquired real-time device data is then fed into the digital twin model for processing. The model analyzes the data and outputs warning information or alarm messages. Warning information includes warning areas for potential problems and early warning predictions for potential problems. Alarm information includes damaged areas and predicted faults. This information is then transmitted to the user terminal. Finally, upon receiving the information, the user terminal generates maintenance information corresponding to the warning or alarm information, providing guidance for equipment maintenance.

[0114] A method for monitoring and early warning of the status of electrical equipment in a hydropower station is provided, which includes: obtaining real-time equipment data and the corresponding mechanism characteristics of each device; building a digital twin model based on the equipment data and mechanism characteristics; inputting the obtained real-time equipment data into the digital twin model for processing to obtain early warning information or alarm information, and sending the early warning information or alarm information to a user terminal, wherein the early warning information includes a warning area and a warning speculation, and the alarm information includes a damaged area and a fault speculation; the user terminal generates maintenance information corresponding to the early warning information or alarm information, so as to provide maintenance personnel with scientific and reasonable maintenance suggestions, improve maintenance efficiency, and reduce labor costs.

[0115] Furthermore, the acquired real-time device data is input into the digital twin model for processing, including:

[0116] Obtaining maintenance information and device status data corresponding to the maintenance information, the device status data including device status data before maintenance and device status data after maintenance;

[0117] The following formula is used to process the maintenance information and equipment status data to obtain the maintenance assessment result:

[0118] ΔT=T post -T pre

[0119] ΔV=V post-V pre

[0120] ΔP=P post -P pre

[0121]

[0122] Where ΔT represents the temperature change before and after maintenance; T post Indicates the temperature data after maintenance T pre represents the temperature data before maintenance; ΔV represents the change in vibration data before and after maintenance; V post Indicates the vibration data after maintenance; V pre represents the vibration data before maintenance; ΔP represents the change in partial discharge before and after maintenance; P post Represents the partial discharge data after maintenance; P pre Indicates the partial discharge data before maintenance; S repair Indicates the maintenance effect score; ω T Represents the weight coefficient of temperature; ω V Represents the weight coefficient of vibration; ω P Represents the weight coefficient of partial discharge;

[0123] Use the following formula to update the warning prediction or failure prediction based on the maintenance assessment results:

[0124]

[0125] Among them, θ old is the original parameter of the digital twin model; θ new is the updated digital twin model parameter; η represents the learning rate; represents the gradient of the loss function with respect to the parameter; y post Indicates the actual equipment status after maintenance; Represents the device state predicted by the model.

[0126] Furthermore, the device data includes temperature data and vibration data;

[0127] Build a digital twin model based on equipment data and mechanism characteristics, including:

[0128] Use the following formula to process the temperature data and vibration data to obtain the correlation coefficient between the temperature data and vibration data:

[0129]

[0130] Where r represents the correlation coefficient; n represents the number of samples; i represents the sample index; T i represents the temperature value collected at the i-th time point; Represents the sample mean of temperature data; V i represents the vibration amplitude collected at the i-th time point; represents the sample mean of vibration data;

[0131] Based on the correlation coefficient and the mechanism characteristics of the corresponding device, the corresponding association rules and the corresponding initial threshold are obtained through setting.

[0132] Furthermore, building a digital twin model based on equipment data and mechanism characteristics also includes:

[0133] Processing the device data using a sliding window to obtain a first threshold value, where the first threshold value is used to indicate that the device exceeds a critical value of a normal state;

[0134] The following formula is used to compensate the first threshold according to environmental factors to obtain the second threshold:

[0135] Threshold adjusted =μ t +αT amb +βH±kσ t

[0136] Among them, Threshold adjusted represents the adjusted second threshold; μ t represents the mean value calculated based on the data in the sliding window at the time step; α represents the weight coefficient of the ambient temperature; T atmb represents the ambient temperature; β represents the weight coefficient of the ambient humidity; H represents the ambient humidity; k represents the multiple coefficient of the standard deviation, which is used to determine the fluctuation range of the threshold; σ t Represents the standard deviation calculated based on the data in the sliding window at time step t.

[0137] Furthermore, the user terminal is further configured to send an access request to the data processing module.

[0138] Furthermore, the data processing module also includes an access rights screening unit;

[0139] The access permission screening unit is used to judge the obtained access request and obtain a judgment result, which includes the access rights and inaccessibility rights.

[0140] If the judgment result is that the user is allowed to access, the device data is sent to the user terminal corresponding to the access request.

[0141] Furthermore, the device data is processed using a sliding window to obtain a first threshold using the following formula:

[0142]

[0143]

[0144] Among them, μ t Indicates the mean value calculated based on the data in the sliding window at the time step; W represents the size of the sliding window, that is, the number of data samples contained in the window; i represents the index of the data sample in the sliding window, from to t;x i Represents the i-th sample data in the sliding window; σ t Represents the standard deviation calculated based on the data in the sliding window at time step t.

[0145] Furthermore, building a digital twin model based on equipment data and mechanism characteristics also includes:

[0146] Use the following formula to simulate the dynamic behavior of the device:

[0147]

[0148] in, represents the rate of change of the device temperature over time t; I represents the current passing through the device; R(T) represents the device resistance; h represents the heat dissipation coefficient of the device surface; A represents the surface area of ​​heat exchange between the device and the surrounding environment; T represents the current temperature of the device; T amb Indicates the ambient temperature; C indicates the thermal capacity of the equipment.

[0149] In a third aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any system in the first aspect of the present application when the computer program is executed by a processor.

[0150] This application is mainly aimed at the core electrical equipment involved in power conversion, transmission and control in hydropower stations, including generators (stators, rotors and bearings), transformers (windings and cooling systems), high-voltage switchgear (circuit breakers, disconnectors), busbars, cable joints, lightning arresters and partial discharge sensitive equipment (such as insulating sleeves), etc. By real-time acquisition of key parameters such as temperature, vibration, partial discharge, combined with the mechanical characteristics of the equipment (such as the electromagnetic thermal coupling characteristics of the generator and the thermal loss model of the transformer), the operating status of the above equipment is monitored, and typical faults such as overheating, mechanical wear, and insulation degradation are warned to ensure the safe and stable operation of the power system of the hydropower station. Focusing on core equipment such as generators, transformers, high-voltage switches, cables and lightning arresters, by real-time tracking of temperature changes, vibration anomalies and partial discharge phenomena, the risks of thermal failures, mechanical wear and insulation aging in equipment operation are covered. For example, typical problems such as overheating of generator windings, loose transformer core, poor contact of circuit breaker contacts, and oxidation of cable joints can be identified. Dynamically adjust the priority of monitoring indicators according to the characteristics of different equipment, such as focusing on vibration analysis of mechanical components and strengthening discharge monitoring of weak insulation links, so as to achieve multi-dimensional health status assessment and fault warning, and effectively ensure the safe and stable operation of the hydropower station's electrical system.

[0151] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0152] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial description of the method embodiments. The device embodiments described above are merely illustrative, wherein the components described as separate parts may or may not be physically separated, and the parts displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the disclosed solution. A person of ordinary skill in the art can understand and implement it without expending creative work.

[0153] The above-described embodiments merely represent several implementation methods of the embodiments of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the concept of the embodiments of the present application, and these modifications and improvements fall within the scope of protection of the embodiments of the present application.

Claims

1. A hydropower station electrical equipment status monitoring and early warning system, characterized in that: The system includes: a data acquisition module, a model building module and a data processing module; The data acquisition module is used to obtain real-time device data and the corresponding mechanism characteristics of each device; The model building module is used to build a digital twin model based on the device data and the mechanism characteristics; The data processing module is used to input the acquired real-time device data into the digital twin model for processing to obtain early warning information or alarm information, and send the early warning information or alarm information to the user terminal. The early warning information includes a warning area and a warning speculation, and the alarm information includes a damaged area and a fault speculation; The user terminal is used to receive the early warning information or alarm information, and send corresponding maintenance information to the data processing module.

2. A hydropower station electrical equipment status monitoring and early warning system according to claim 1, characterized in that: Inputting the acquired real-time device data into the digital twin model for processing includes: Acquire the maintenance information and device status data corresponding to the maintenance information, wherein the device status data includes device status data before maintenance and device status data after maintenance; The maintenance information and the equipment status data are processed using the following formula to obtain a maintenance assessment result: ΔT=T post -T pre ΔV=V post -V pre ΔP=P post -P pre Where ΔT represents the temperature change before and after maintenance; T post Indicates the temperature data after maintenance; T pre represents the temperature data before maintenance; ΔV represents the change in vibration data before and after maintenance; V post Represents the vibration data after maintenance; V pre represents the vibration data before maintenance; ΔP represents the change in partial discharge before and after maintenance; P post Represents the partial discharge data after maintenance; P pre Indicates the partial discharge data before maintenance; S repair Indicates the maintenance effect score; ω T Represents the weight coefficient of temperature; ω V Represents the weight coefficient of vibration; ω P Represents the weight coefficient of partial discharge; The following formula is used to update the warning prediction or the fault prediction based on the maintenance evaluation result: Among them, θ old is the original parameter of the digital twin model; θ new is the updated digital twin model parameter; η represents the learning rate; Represents the gradient of the loss function with respect to the parameter; y post Indicates the actual equipment status after maintenance; Represents the device state predicted by the model.

3. A hydropower station electrical equipment status monitoring and early warning system according to claim 1, characterized in that: The device data includes temperature data and vibration data; The constructing of the digital twin model according to the device data and the mechanism characteristics includes: The temperature data and the vibration data are processed using the following formula to obtain a correlation coefficient between the temperature data and the vibration data: Where r represents the correlation coefficient; n represents the number of samples; i represents the sample index; T i represents the temperature value collected at the i-th time point; Represents the sample mean of temperature data; V i represents the vibration amplitude collected at the i-th time point; represents the sample mean of vibration data; Based on the correlation coefficient and the mechanism characteristics of the corresponding device, a corresponding association rule and a corresponding initial threshold are obtained through setting.

4. A hydropower station electrical equipment status monitoring and early warning system according to claim 3, characterized in that: The constructing of the digital twin model according to the device data and the mechanism characteristics further includes: Processing the device data using a sliding window to obtain a first threshold value, where the first threshold value is used to indicate that the device exceeds a critical value of a normal state; The following formula is used to compensate the first threshold according to environmental factors to obtain the second threshold: Threshold adjusted =μ t +αT amb +βH±kσ t Among them, Threshold adjusted represents the adjusted second threshold; μ t represents the mean value calculated based on the data in the sliding window at the time step; α represents the weight coefficient of the ambient temperature; T amb represents the ambient temperature; β represents the weight coefficient of the ambient humidity; H represents the ambient humidity; k represents the multiple coefficient of the standard deviation, which is used to determine the fluctuation range of the threshold; σ t Represents the standard deviation calculated based on the data in the sliding window at time step t.

5. A hydropower station electrical equipment status monitoring and early warning system according to claim 1, characterized in that: The user terminal is further configured to send an access request to the data processing module.

6. A hydropower station electrical equipment condition monitoring and early warning system according to claim 5, characterized in that: The data processing module also includes an access rights screening unit; The access permission screening unit is used to judge the obtained access request and obtain a judgment result, wherein the judgment result includes accessible and inaccessible persons; When the judgment result is that the user is allowed to access, the device data is sent to the user terminal corresponding to the access request.

7. A hydropower station electrical equipment status monitoring and early warning system according to claim 3, characterized in that: The device data is processed using a sliding window to obtain a first threshold using the following formula: Among them, μ t represents the mean value calculated based on the data in the sliding window at the time step; W represents the size of the sliding window, that is, the number of data samples contained in the window; i represents the index of the data sample in the sliding window, from t-W+1 to t; x i Represents the i-th sample data in the sliding window; σ t Represents the standard deviation calculated based on the data in the sliding window at time step t.

8. A hydropower station electrical equipment status monitoring and early warning system according to claim 4, characterized in that: The constructing of the digital twin model according to the device data and the mechanism characteristics further includes: Use the following formula to simulate the dynamic behavior of the device: in, represents the rate of change of the device temperature over time t; I represents the current passing through the device; R(T) represents the device resistance; h represents the heat dissipation coefficient of the device surface; A represents the surface area of ​​heat exchange between the device and the surrounding environment; T represents the current temperature of the device; T amb Indicates the ambient temperature; C indicates the thermal capacity of the equipment.

9. A method for monitoring and early warning of electrical equipment status in a hydropower station, characterized in that: The method comprises: Obtain real-time equipment data and the corresponding mechanism characteristics of each device; Building a digital twin model based on the device data and the mechanism characteristics; Input the acquired real-time device data into the data twin model for processing to obtain early warning information or alarm information, and send the early warning information or alarm information to the user terminal. The early warning information includes the early warning area and the early warning speculation, and the alarm information includes the damaged area and the fault speculation; The user terminal generates maintenance information corresponding to the early warning information or the alarm information.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a hydropower station electrical equipment condition monitoring and early warning system according to any one of claims 1 to 8 are implemented.

Images