Electric power product fault identification method, device, equipment and medium

Abstract

The invention provides an electric power product fault distinguishing method and device, equipment and a medium. The method comprises the steps that operation data information of an electric power product is acquired and sent to a data processing module; performing preprocessing operation on the operation data information to obtain to-be-analyzed data; acquiring event occurrence time information of the electric power product, constructing a time axis by an interface display module, marking the time axis according to the event occurrence time information, and drawing an oscillogram; obtaining an analysis result of the electric power product according to the time axis and the oscillogram; and when the analysis result is an abnormal operation state, obtaining a power grid topological structure and a signal source of the power product, positioning abnormal equipment, obtaining an abnormal signal of the abnormal equipment, positioning a fault point of the abnormal equipment, determining a fault type of the abnormal equipment, obtaining an abnormal evaluation result, and carrying out graded alarm according to the abnormal evaluation result. According to the technical scheme provided by the embodiment of the invention, the fault of the electric power product can be accurately identified, and the early warning action can be timely performed.

Description

Technical Field

[0001] The present invention relates to the technical field of power system debugging and maintenance, and in particular to a method, device, electronic equipment and medium for identifying faults of power products. Background Art

[0002] Current methods for identifying power product faults typically involve deploying sensors, smart meters, protection devices, and other equipment at key nodes in the power system to collect information from various data sources. This includes electrical quantity data such as voltage, current, power, and frequency, as well as non-electrical quantity data such as switch status and equipment fault signals. However, existing methods for identifying power product faults rely on manual analysis of event records and signal data, are limited to a single power product device, and lack correlation analysis of the status of equipment across the entire network. This is not only time-consuming and labor-intensive, but also requires a high level of analyst experience. This leads to an over-reliance on subjectivity in the power product fault identification process and a lack of unified diagnostic standards. This results in "same fault, different conclusions" for power products, ultimately making it impossible to accurately identify power product faults and initiate timely warning actions. Summary of the Invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention provides a method, device, equipment and medium for identifying power product faults, which can accurately identify power product faults and take timely warning actions.

[0004] In a first aspect, an embodiment of the present invention provides a method for identifying a fault in an electric product, which is applied to an electric product fault identification system. The electric product fault identification system includes a data acquisition module, a data transmission module, a data processing module, and an intelligent analysis module. The data transmission module is connected to the data acquisition module and the data processing module, respectively. The intelligent analysis module is connected to the data processing module. An interface display module is further connected between the data processing module and the intelligent analysis module. The method for identifying a fault in an electric product includes:

[0005] Acquiring the operating data information of the power product collected by the data collection module, and sending the operating data information to the data processing module through the data transmission module;

[0006] The data processing module performs preprocessing operations on the operating data information to obtain data to be analyzed;

[0007] Acquiring the event occurrence time information of the power product, the interface display module constructing a time axis according to the data to be analyzed, marking the time axis according to the event occurrence time information, and drawing a waveform diagram of the power product;

[0008] The intelligent analysis module identifies abnormal events and signal patterns of the power product according to the time axis and the waveform diagram to obtain an analysis result of the power product;

[0009] Determining the analysis result, and when the analysis result indicates an abnormal operating state, obtaining a topology of a power grid in which the power product is located and a signal source, locating an abnormal device based on the power grid topology and the signal source, and obtaining an abnormal signal of the abnormal device;

[0010] Locating the fault point of the abnormal device according to the abnormal signal and the preset associated event, and determining the fault type of the abnormal device according to the fault point;

[0011] The faulty device is evaluated to obtain an abnormal evaluation result, and the interface display module issues a graded alarm based on the abnormal evaluation result.

[0012] In some embodiments of the present invention, the data processing module performs a pre-processing operation on the operating data, including:

[0013] Cleaning the operating data to eliminate noise in the operating data, fill missing values ​​in the operating data, and identify and process abnormal values ​​of the operating noise to obtain accurate data of the power product;

[0014] Performing feature extraction on the precise data to obtain waveform, frequency and amplitude changes of the precise data;

[0015] The working state and working performance of the electric power product are determined according to the waveform, the frequency and the amplitude change.

[0016] In some embodiments of the present invention, equipment fault information and operation instructions of the power product are obtained, and information on the time when the event occurs is obtained based on the equipment fault information and operation instructions;

[0017] Confirm the product event information of the event occurrence time information, and construct the timeline according to the event occurrence time information and the product event information;

[0018] The voltage information, current information and temperature information of the electric power product are obtained, and the waveform diagram is drawn on the time axis according to the voltage information, the current information and the temperature information.

[0019] In some embodiments of the present invention, the intelligent analysis module identifies abnormal events and signal patterns of the power product based on the time axis and the waveform diagram, including:

[0020] screening the data to be analyzed to obtain screening data;

[0021] Cleaning, arranging and formatting the filtered data to confirm the events and signals to be displayed on the time axis;

[0022] The interface display module marks the occurrence moment of the time axis according to the event to be displayed and the signal to be displayed to obtain a marked time axis;

[0023] In response to the user's sliding and clicking operations on the marked timeline, the user can view the events and signal changes of the power product in different time periods.

[0024] In some embodiments of the present invention, after determining the analysis result, the method further includes:

[0025] Obtaining signal amplitude, event sequence, timing relationship and matching pattern of the power product;

[0026] When the signal amplitude is within a preset rated range, the timing relationship conforms to a preset timing rule, and the matching pattern is consistent with a historical data pattern of the power product, it is determined that the power product is in a normal operating state.

[0027] In some embodiments of the present invention, obtaining the analysis result of the power product includes:

[0028] Building a rule base based on the abnormal event and the signal pattern;

[0029] Matching the data to be analyzed with the rule base, triggering an event chain that matches the conditions of the power product, and generating a rule inference result based on the event chain;

[0030] The abnormal probability information of the power product is obtained according to a preset machine learning model, and the rule reasoning result and the abnormal probability information are weighted and fused to determine the fault type of the power product. When the abnormal probability information conflicts with the rule reasoning result, the priority of the rule base and the machine learning model is confirmed according to the preset priority.

[0031] In some embodiments of the present invention, the constructing a rule base based on the abnormal event and the signal pattern includes:

[0032] Confirming and correcting the rule reasoning result to obtain a corrected result;

[0033] Adding the correction result to the data set of the machine learning model to update the model parameters of the machine learning model;

[0034] The rule base is updated according to the correction result.

[0035] In a second aspect, an embodiment of the present invention provides an apparatus for identifying faults in electric products, comprising at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute the method for identifying faults in electric products as described in the first aspect above.

[0036] In a third aspect, an embodiment of the present invention provides an electronic device comprising the power product fault identification device as described in the second aspect above.

[0037] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the method for identifying faults of electric products as described in the first aspect above.

[0038] The power product fault identification method according to the embodiment of the present invention has at least the following beneficial effects:

[0039] The original data is transmitted to the data processing module through the data transmission module (such as wireless communication, wired network) to ensure the real-time and integrity of the data. The data processing module performs pre-processing such as filtering, denoising, and normalization on the original data to eliminate invalid or interference data and generate data to be analyzed. The interface display module constructs the data to be analyzed into a time axis according to the time series, and marks key nodes on the time axis in combination with the event occurrence information (such as the fault trigger time), and draws waveforms (such as voltage fluctuation curves, current mutation waveforms) to achieve spatiotemporal visualization of the data. The intelligent analysis module is based on the time axis and waveform graph, and uses pattern recognition algorithms or rule engines to compare the signal pattern of normal operation (such as the benchmark model trained by historical data) to identify abnormal events. When it is determined to be abnormal, the specific location of the abnormal equipment is determined in combination with the power grid topology and signal source (the physical location of the fault signal). According to the abnormal signal characteristics of the abnormal equipment (such as waveform distortion mode, parameter deviation degree) and the preset associated events (such as stored in the database), the abnormal event is detected. The system automatically detects faults and provides fault information for the operator, which is then used to identify the fault location and the fault type. The system automatically detects faults and provides fault information for the operator. The system automatically detects faults and provides fault information for the operator. The system automatically detects faults and provides fault information for the operator. The system automatically detects faults and provides fault information for the operator. The system automatically detects faults and provides fault information for the operator. The system automatically detects faults and provides fault information for the operator. The system automatically detects faults and provides fault information for the operator. The system automatically detects faults and provides fault information for the operator. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a flow chart of a method for identifying faults in power products provided by one embodiment of the present invention;

[0041] Figure 2 This is a flow chart of a data processing module according to an embodiment of the present invention performing pre-processing operations on operating data;

[0042] Figure 3 It is a flow chart of an interface display module according to an embodiment of the present invention constructing a time axis based on the data to be analyzed;

[0043] Figure 4 This is a flow chart of an intelligent analysis module according to an embodiment of the present invention for identifying abnormal events and signal patterns of power products based on a time axis and a waveform diagram;

[0044] Figure 5 This is a flow chart after determining the analysis results provided by one embodiment of the present invention;

[0045] Figure 6 This is a flow chart for obtaining analysis results of power products provided by one embodiment of the present invention;

[0046] Figure 7 This is a flow chart of building a rule base based on abnormal events and signal patterns provided by one embodiment of the present invention;

[0047] Figure 8 It is a structural diagram of an electric power product fault identification device provided by another embodiment of the present invention. DETAILED DESCRIPTION

[0048] The following describes embodiments of the present invention in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present invention and are not to be construed as limiting the present invention.

[0049] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, they cannot be understood as limitations on the present invention.

[0050] In the description of the present invention, "several" means one or more, "many" means more than two, "greater than," "less than," and "exceed" are understood to exclude the number itself, while "above," "below," and "within" are understood to include the number itself. The use of "first" and "second" in the description is solely for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance, implicitly specifying the number of the indicated technical features, or implicitly specifying the order of the indicated technical features.

[0051] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, and connecting should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0052] An embodiment of the present invention provides a method for identifying faults in electric power products, which is applied to an electric power product fault identification system. The electric power product fault identification system includes a data acquisition module, a data transmission module, a data processing module and an intelligent analysis module. The data transmission module is connected to the data acquisition module and the data processing module respectively, the intelligent analysis module is connected to the data processing module, and an interface display module is also connected between the data processing module and the intelligent analysis module.

[0053] It should be noted that the data acquisition module can collect various key data during the operation of power products in real time and comprehensively, such as current, voltage, temperature, and operating time. The data transmission module connects the data acquisition module and the data processing module to ensure the stability and reliability of data during transmission. It also adopts appropriate data transmission protocols and technologies to effectively reduce data loss and transmission errors, ensuring that the collected data can be delivered to the data processing module in a timely and accurate manner for analysis and processing. The data processing module performs pre-processing operations such as cleaning, conversion, and integration on the transmitted data to remove noise and invalid data from the operating data and convert the raw data into data to be analyzed. At the same time, the use of efficient data processing algorithms can quickly process large amounts of data, improve the response speed of the fault identification system, and promptly detect possible fault signs of power products. Based on the processed data provided by the data processing module, the intelligent analysis module uses machine learning and artificial intelligence algorithms (such as neural networks and decision trees) to conduct in-depth analysis of the power product operating data. By establishing fault models and pattern recognition, it accurately identifies various fault types of power products, such as short circuit faults, overload faults, insulation faults, etc., improving the accuracy and reliability of fault diagnosis. The interface display module connects the data processing module and the intelligent analysis module, allowing operators to view real-time information such as the power product's operating status, fault analysis results, and historical data. Furthermore, parameters can be set and queries can be performed on the power product's timeline as needed, facilitating management and maintenance. The data processing and intelligent analysis modules work together to monitor and analyze the power product's operating data in real time. When data anomalies or potential fault signs are detected, early warning signals are issued, notifying relevant personnel to take corrective measures to prevent the occurrence and escalation of faults, further improving the reliability and safety of the power product.

[0054] It should be noted that the intelligent analysis module can identify abnormal waveforms in power equipment and automatically generate reports that indicate possible fault causes and recommended solutions. The specific process of waveform abnormality determination is as follows:

[0055] Data preprocessing, denoising, and alignment: Use wavelet threshold denoising (such as Daubechies wavelet) to remove high-frequency noise. Phase alignment of multi-channel signals (such as three-phase voltage) to avoid timing errors.

[0056] Multi-dimensional feature extraction: Calculates amplitude mean, variance, peak-to-peak value, and crest factor. Detects sudden changes: Identifies amplitude jumps using a sliding window CUSUM algorithm. When the voltage drops suddenly, the mean value within the window drops by 30% and the variance increases suddenly.

[0057] Extract frequency domain features. Fast Fourier transform (FFT): Extract fundamental wave and harmonic amplitudes (such as the third and fifth harmonics). Short-time Fourier transform (STFT): Locate the time-frequency distribution of transient anomalies. When harmonic distortion occurs, the fifth harmonic amplitude accounts for more than 8%.

[0058] Waveform library comparison: The feature vector is compared with the historical fault library (such as short circuit and capacitor breakdown). When 2kHz oscillation is detected in the current waveform, the rule library matches "switch arc fault".

[0059] The control method of the embodiment of the present invention is further described below based on the accompanying drawings.

[0060] Reference Figure 1 , Figure 1 A flowchart of a method for identifying a fault in an electric power product provided by an embodiment of the present invention includes but is not limited to the following steps:

[0061] Step S11, obtaining the operating data information of the power product collected by the data collection module, and sending the operating data information to the data processing module through the data transmission module;

[0062] It should be noted that embedded devices collect various operational data and information from power products in real time. This data includes at least SOE events, telesignaling information, status changes, and power signal amplitudes. After this data is accurately delivered to the data processing module via the transmission module, advanced data analysis algorithms and models are used to accurately assess the power product's operating status and quickly determine the specific location and possible cause of the fault.

[0063] Step S12: The data processing module performs pre-processing operations on the operating data information to obtain data to be analyzed;

[0064] It should be noted that the collected operational data may contain noise, missing values, or outliers. The intelligent analysis module cleans the data to eliminate noise, fill in missing values, and identify and address outliers, ensuring the accuracy of subsequent analysis. After data cleaning, the intelligent analysis module extracts key features from the cleaned data to obtain the data to be analyzed. Key features include at least the signal waveform, frequency, and amplitude changes, which can reflect the operating status and performance of the device.

[0065] Step S13, obtaining the event occurrence time information of the power product, the interface display module constructs a time axis according to the data to be analyzed, marks the time axis according to the event occurrence time information, and draws a waveform diagram of the power product;

[0066] It should be noted that by accurately marking the moment an event occurs on the timeline, operations and maintenance personnel can quickly determine the specific time when an abnormality or fault occurs in a power product. Combined with the waveform changes before and after that moment in the waveform diagram, they can intuitively observe the changes in the power product's electrical parameters before and after the fault occurs, such as distortion and mutation of voltage and current waveforms. This allows them to accurately analyze the cause of the fault and improve the efficiency and accuracy of fault diagnosis. Based on parameters such as the shape and amplitude of the waveform diagram, they can also evaluate the performance indicators of the power product, such as output power and efficiency. At the same time, through long-term monitoring and analysis of this data, it is possible to further understand the performance degradation of power products, providing a basis for their maintenance and upgrades.

[0067] Step S14: The intelligent analysis module identifies abnormal events and signal patterns of the power product based on the time axis and waveform diagram to obtain analysis results of the power product;

[0068] It's important to note that the timeline provides a precise time reference, while the waveform diagram intuitively displays changes in the electrical parameters of power products. The intelligent analysis module, combining these two, can accurately identify the specific moment an abnormal event occurs and the corresponding waveform characteristics, precisely locating the anomaly and reducing the possibility of misjudgments and missed detections. By comprehensively analyzing the waveform diagrams at different moments on the timeline, the intelligent analysis module can capture abnormal information from multiple dimensions, such as changes in parameters such as voltage amplitude, frequency, and phase, as well as changes in waveform characteristics such as shape and symmetry, thereby more comprehensively and accurately determining the operating status of the power product. Furthermore, even if a power product hasn't yet experienced an obvious fault, the intelligent analysis module may identify potential problems or trends through long-term monitoring and analysis of the timeline and waveform diagrams. For example, gradual changes in certain parameters may indicate equipment aging or performance degradation. Early detection of these issues can help implement preventive maintenance measures and avoid failures.

[0069] Step S15, judging the analysis result, when the analysis result is an abnormal operating state, obtaining the grid topology and signal source of the power product, locating the abnormal device according to the grid topology and signal source, and obtaining the abnormal signal of the abnormal device.

[0070] It should be noted that the abnormal status of power products includes model anomalies, event conflicts, timing errors and mode deviations. Specifically, signal anomalies include voltage sag / swell (such as below 180V or above 250V), current overload (such as the rated current of the power product exceeds 120% of the rated value), and frequency deviation (such as greater than 52Hz or less than 48Hz); event conflicts represent logical contradictions in SOE events (such as the "circuit breaker tripping" event occurring earlier than the "overcurrent protection action"); mode deviations represent waveform distortion (such as glitches, oscillations) and excessive harmonic content (such as THD greater than 5%) in power products. When a power product is in an abnormal state, the power product fault identification system will trigger a system alarm (such as "insulation fault" or "overload warning"), the telesignaling signal will be inconsistent with the actual status of the power product (such as being in operation but the current is zero), and the device response will time out or dance (such as the protection action delay is greater than 50ms).

[0071] Step S16, locating the fault point of the abnormal device according to the abnormal signal and the preset associated event, and determining the fault type of the abnormal device according to the fault point;

[0072] It should be noted that by real-time monitoring of abnormal signals such as electrical quantities (voltage, current waveforms) and non-electrical quantities (temperature, vibration, oil chromatography) of power products, combined with preset related events (such as protection device action timing, switch position information, and historical fault case library), a "signal feature-equipment location" mapping relationship is established. Furthermore, different fault types (such as transformer inter-turn short circuit, motor bearing wear, and circuit breaker refusal to operate) correspond to unique signal feature combinations. By establishing a mapping library of "fault point location-signal feature-fault type" (such as 1x rotation frequency abnormality in the vibration spectrum corresponds to rotor imbalance, and 2x rotation frequency abnormality corresponds to bearing fault), the algorithm is used to automatically match the feature vectors to achieve fault type identification and improve the consistency of fault identification.

[0073] Step S17: Evaluate the faulty equipment to obtain abnormal evaluation results, and the interface display module issues graded alarms based on the abnormal evaluation results.

[0074] It should be noted that after the abnormality assessment results of the power equipment are obtained, the severity of the abnormality of the power equipment is divided into three levels according to the abnormality assessment results, including:

[0075] Level 1 alarm (emergency): Direct threat to equipment safety (such as short circuit current), triggering audible and visual alarms and automatically cutting off power.

[0076] Level 2 alarm (important): affects operation but is not urgent (such as overload), generates a pop-up prompt and records the log.

[0077] Level 3 warning (prompt): Potential risks (such as harmonics exceeding the standard) are only marked as reminders on the interface.

[0078] For example, when a sudden increase in current to 150% of the rated value is detected, a first-level alarm is triggered and the circuit breaker automatically trips.

[0079] Obtain the grid topology and locate abnormal devices (such as abnormal current in a branch) through signal tracing based on the grid topology.

[0080] Acquire abnormal signals from abnormal equipment and match them with related events (such as "insulation alarm" + "zero-sequence current mutation" to confirm the location of the grounding fault point).

[0081] For example, if a voltage sag occurs in the busbar A section, it is located as a fault in the busbar A connection equipment.

[0082] It should be noted that after identifying the fault type, maintenance personnel can more specifically prepare maintenance tools and spare parts, develop detailed maintenance plans, and repair the fault point directly, avoiding blind investigation and trial and error. This greatly shortens maintenance time, improves maintenance efficiency, reduces power product downtime, and minimizes the impact on production and life. Accurately locating the fault type can avoid unnecessary maintenance operations and replacement of non-faulty components, reducing the waste of manpower, material, and financial resources during the maintenance process, and effectively reducing maintenance costs. At the same time, it also extends the service life of non-faulty components and improves the overall service life of power products.

[0083] In addition, in one embodiment, referring to Figure 2 ,exist Figure 1 Step S12 of the illustrated embodiment also includes but is not limited to the following steps:

[0084] Step S21 , cleaning the operating data to eliminate noise in the operating data, fill in missing values ​​in the operating data, and identify and process abnormal values ​​of the operating noise to obtain accurate data of the power product;

[0085] Step S22, extracting features from the precise data to obtain waveform, frequency, and amplitude changes of the precise data;

[0086] Step S23: determining the working state and working performance of the power product according to the waveform, frequency and amplitude changes.

[0087] It should be noted that, first, embedded devices are used to collect various operational data from power products in real time, including but not limited to SOE events, telesignaling information, state changes, and power signal amplitudes. This collected operational data may include but is not limited to noise, missing values, or outliers. By cleaning this data to eliminate noise, fill missing values, and identify and process outliers, accurate data on the power products is obtained, ensuring the accuracy of subsequent analysis of the power products. After the operational data is cleaned, key features are extracted from the precise data, including but not limited to signal waveforms, frequency, and amplitude changes. These waveforms, frequency, and amplitude changes are used to reflect the operating status and performance of the power products.

[0088] In addition, in one embodiment, referring to Figure 3 ,exist Figure 1 Step S13 of the illustrated embodiment also includes but is not limited to the following steps:

[0089] Step S31, obtaining equipment fault information and operation instructions of the power product, and obtaining event occurrence time information based on the equipment fault information and operation instructions;

[0090] Step S32, confirming the product event information of the event occurrence time information, and constructing a timeline according to the event occurrence time information and the product event information;

[0091] Step S33: obtaining voltage information, current information, and temperature information of the power product, and drawing a waveform diagram on a time axis according to the voltage information, current information, and temperature information.

[0092] It should be noted that the timeline is a key tool in the interface display module, used to intuitively display the timing relationships between events and signals in power products. Specifically, the timeline is represented by time scales, event markers, and signal waveforms. The time scale represents the passage of time and can be in different time units such as seconds, minutes, hours, or days; event markers mark the time when specific events occur on the timeline, such as equipment failures and the issuance of operating instructions; and signal waveforms plot various power product signal waveforms, such as voltage, current, and temperature, on the timeline to demonstrate the trend of power product signal changes over time.

[0093] Furthermore, the timeline and waveform graph can intuitively display the relationship between equipment fault information and changes in equipment operating parameters (voltage, current, temperature). By comparing the time of the event and the waveform changes, operation and maintenance personnel can quickly locate the specific time of the fault and the parameter anomalies that may have caused the fault. This helps to more accurately diagnose the cause of the fault and improve troubleshooting efficiency. For example, when a device fails, checking the timeline reveals abnormal current fluctuations near the time of the fault. Combining the waveform graph can more clearly understand the amplitude and duration of the current fluctuations, providing a strong basis for fault diagnosis.

[0094] Complex power product fault information, operating instructions, operating parameters and other data are visualized in the form of timelines and waveforms, allowing relevant personnel to more intuitively understand the operating conditions and historical events of power products.

[0095] In addition, in one embodiment, referring to Figure 4 ,exist Figure 1 Step S14 of the illustrated embodiment also includes but is not limited to the following steps:

[0096] Step S41, filtering the data to be analyzed to obtain filtered data;

[0097] Step S42: cleaning, sorting, and formatting the filtered data to confirm the events and signals to be displayed on the time axis;

[0098] Step S43: the interface display module marks the occurrence time of the time axis according to the event to be displayed and the signal to be displayed to obtain a marked time axis;

[0099] Step S44, in response to the user's sliding and clicking operations on the marked time axis, to view the events and signal changes of the power products in different time periods.

[0100] It should be noted that filtering the data to be analyzed can extract key data relevant to fault identification from a large amount of raw data and remove irrelevant or interfering data, thereby improving the data's relevance and effectiveness and reducing the workload and complexity of subsequent processing. Performing these operations on the filtered data further improves data quality, removing noise, errors, and inconsistencies, making the data more standardized and unified, and facilitating subsequent analysis and processing. The processed data can more accurately reflect the actual operation of power products, providing a reliable data foundation for fault identification. By clearly defining the events and signals to be displayed on the timeline, key information related to power product faults can be highlighted, allowing operation and maintenance personnel to quickly focus on important events and signal changes, avoiding the distraction of a large amount of irrelevant information. This allows for more efficient detection of potential fault signs and anomalies, improving fault identification efficiency. Marking the occurrence moments on the timeline makes the occurrence times of events and signals clearer and more specific, providing operation and maintenance personnel with an accurate time reference. Marking the timeline can intuitively display the temporal sequence and distribution of events and signals, facilitating analysis of correlations and causal relationships between events and better understanding the operational state of power products.

[0101] Furthermore, in this embodiment, users can slide and click on the marked timeline to view events and signal changes of power products in different time periods. This allows users to freely browse the information on the timeline according to their needs and focus, and deeply analyze the details of a specific time period, thereby gaining a more comprehensive and in-depth understanding of the operating history and fault characteristics of the power product.

[0102] In addition, in one embodiment, referring to Figure 5 ,exist Figure 1 After step S15 in the embodiment shown, the following steps are also included but not limited to:

[0103] Step S51, obtaining the signal amplitude, event sequence, timing relationship and matching mode of the power product;

[0104] Step S52: When the signal amplitude is within the preset rated range, the timing relationship conforms to the preset timing rule, and the matching pattern is consistent with the historical data pattern of the power product, it is determined that the power product is in a normal operating state.

[0105] It should be noted that signal amplitude is used to determine whether power signals, such as power supply or current, are within the rated range, such as 200V±5% and 50Hz±0.5Hz. Event sequences are used to confirm whether SOE events (such as switch opening and closing) conform to preset operating logic, such as "protection action" followed by "circuit breaker tripping." Timing relationships are used to characterize whether events and signal changes in power products conform to timing rules, such as the current should rise within 100ms after a "start command." Matching patterns are used to characterize whether the waveform and frequency of power products are consistent with historical normal data patterns, such as the absence of distortion or excessive harmonics. When a power product is in a normal state, the power product fault identification system will have no abnormal alarms or fault codes, all telesignaling signals will be consistent with the actual status of the equipment, such as the current corresponding to "operating state" being greater than zero, and the device response time will meet design specifications, such as the protection action delay being less than 20ms.

[0106] In addition, in one embodiment, referring to Figure 6 ,exist Figure 1 Step S14 of the illustrated embodiment also includes but is not limited to the following steps:

[0107] Step S61, building a rule base based on abnormal events and signal patterns;

[0108] Step S62: matching the data to be analyzed with the rule base, triggering an event chain that matches the conditions of the power product, and generating a rule inference result based on the event chain;

[0109] Step S63: Obtain the abnormal probability information of the power product according to the preset machine learning model, weightedly fuse the rule reasoning result with the abnormal probability information, and determine the fault type of the power product. When the abnormal probability information conflicts with the rule reasoning result, the priority of the rule base and the machine learning model is confirmed according to the preset priority.

[0110] It should be noted that the fault detection is based on historical fault pattern matching (such as waveform distortion matching the "capacitor breakdown" feature) and preset rules (such as "overcurrent + temperature exceeding the limit" to determine "equipment overload").

[0111] For example, a high current harmonic content plus a "rectifier fault" rule in the rule base is inferred to be a rectifier fault.

[0112] Predefined templates are called according to the fault type (such as "fault type: overload; location: line L1; confidence: 92%"), and steps are generated based on domain knowledge (such as "1. Check the load of line L1; 2. Calibrate the protection setting").

[0113] For example, when diagnosing "circuit breaker malfunction", it is recommended to "check the protection device setting and secondary circuit wiring".

[0114] Abnormal data, diagnostic results, and treatment measures are stored in a database to form a case library. User feedback on diagnostic results (such as marking misjudgment cases) is used to iterate the machine learning model. Fault modes are added to the rule library (for example, adding a "new energy inverter harmonic anomaly" rule).

[0115] For example, when the user feedbacks "overload alarm", the system optimizes the current detection algorithm for the sensor failure.

[0116] Furthermore, when power equipment experiences an overload fault, the current continuously exceeds the limit and the temperature signal rises. This triggers a Level 2 alarm, indicating an "overload risk," and locates the outgoing line circuit of a distribution cabinet. The intelligent analysis module identifies the cause of the power equipment failure as a sudden increase in load exceeding the design capacity. It generates the following recommendations: "1. Reduce the load; 2. Upgrade the circuit breaker rating." This case is recorded and the overload threshold is optimized.

[0117] When the protection device of the power equipment malfunctions, the abnormal manifestation is the SOE event "protection action" but there is no overcurrent signal.

[0118] A Level 3 alarm, labeled "Event Logic Conflict," is triggered. The fault is located in the protection device control unit. The analysis module can only identify the cause as "setting error" or "secondary circuit interference." Recommendations are generated: "1. Verify protection settings; 2. Check control circuit shielding."

[0119] In addition, in one embodiment, referring to Figure 7 ,exist Figure 6 Step S61 of the illustrated embodiment also includes but is not limited to the following steps:

[0120] Step S71, confirming and correcting the rule inference result to obtain a corrected result;

[0121] Step S72, adding the correction result to the data set of the machine learning model to update the model parameters of the machine learning model;

[0122] Step S73: Update the rule base according to the correction result.

[0123] It should be noted that adding the correction results to the dataset of the machine learning model can enable the model to access more accurate and comprehensive data. As the dataset is continuously updated with the correction results, the machine learning model can adapt to more complex and changing actual situations. By updating the rule base based on the correction results, errors or imperfections in the original rules can be corrected. For example, when judging a certain type of fault in an electric power product, the original rule may not take into account the specific voltage fluctuation situation. After correction, this factor can be incorporated into the rule, making the rule more accurately reflect the actual fault situation. The correction results may include newly discovered fault modes or related factors, which are then added to the rule base as new rules. For example, it is discovered that electric power products will have a certain special fault under electromagnetic interference of a specific frequency. Adding this rule to the rule base can make the rule base more comprehensive and improve the coverage of rule reasoning for various fault situations.

[0124] The specific update process is as follows:

[0125] Determine the threshold rule: If the total harmonic distortion (THD) is greater than 5%, an alarm is triggered. Determine the timing logic rule: Rule 1: If the voltage does not recover within 100ms after a sudden drop, it is considered a fault. Rule 2: If the high-frequency oscillation duration is less than 1ms, it is considered noise and no alarm is triggered.

[0126] Fault analysis and suggestion generation process:

[0127] Multi-source data comparison (inherent judgment mechanism): Based on relevant technical specifications and the experience of experts in the corresponding field, a fault cause comparison database is formed. When an abnormal waveform is generated, a templated fault description and suggestions are output accordingly.

[0128] Database update: Based on the positive and negative feedback provided by users after each failure, the database is confirmed and updated in real time.

[0129] After detecting an abnormal SOE event, the system automatically analyzes the relevant signal data, determines whether the event falls within the normal operating range, and prompts the user to perform corresponding inspections or adjustments.

[0130] like Figure 8 As shown, Figure 8 This is a structural diagram of a power product fault identification device provided by an embodiment of the present invention. The present invention also provides a power product fault identification device, comprising:

[0131] The processor 801 may be implemented as a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is configured to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0132] The memory 802 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 802 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 802 and is called by the processor 801 to execute the power product fault identification method of the embodiment of this application;

[0133] Input / output interface 803, used to implement information input and output;

[0134] Communication interface 804, used to implement communication interaction between the apparatus and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.);

[0135] Bus 805 , which transmits information between various components of the device (e.g., processor 801 , memory 802 , input / output interface 803 , and communication interface 804 );

[0136] The processor 801 , the memory 802 , the input / output interface 803 and the communication interface 804 are connected to each other in communication within the device via a bus 805 .

[0137] An embodiment of the present application further provides an electronic device, comprising the power product fault identification device as described above.

[0138] An embodiment of the present application further provides a storage medium, which is a computer-readable storage medium and stores a computer program. When the computer program is executed by a processor, the above-mentioned method for identifying faults of electric products is implemented.

[0139] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory optionally includes a memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of the above-mentioned networks include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof. The device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and are located in one place, or may be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0140] Those skilled in the art will appreciate that all or some of the steps and systems in the method disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, and the computer-readable medium can include computer storage media (or non-transitory media) and communication media (or temporary media). As known to those skilled in the art, the term computer storage media is included in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data) and is volatile and non-volatile, removable, and non-removable. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory, or other memory technology, CD-ROM, digital versatile disks (DVD), or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage, or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, as is well known to those skilled in the art, communication media typically includes computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0141] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above implementation. Those skilled in the art can also make various equivalent modifications or substitutions under the shared conditions that do not violate the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A method for identifying faults in power products, characterized in that: Applied to a power product fault identification system, the power product fault identification system includes a data acquisition module, a data transmission module, a data processing module, and an intelligent analysis module. The data transmission module is connected to the data acquisition module and the data processing module respectively, the intelligent analysis module is connected to the data processing module, and an interface display module is further connected between the data processing module and the intelligent analysis module. The power product fault identification method includes: Acquiring the operating data information of the power product collected by the data collection module, and sending the operating data information to the data processing module through the data transmission module; The data processing module performs preprocessing operations on the operating data information to obtain data to be analyzed; Acquiring information on the time when an event of the power product occurs, the intelligent analysis module constructing a time axis according to the data to be analyzed and the information on the time when the event occurs, and screening the data to be analyzed to determine a display event and a display signal of the time axis; Processing the filtered data to be analyzed to obtain data to be displayed, drawing a signal waveform diagram of the power product based on the display data and the event occurrence time information, and responding to a user's sliding or clicking operation to view events and changes of the power product in different time periods; The intelligent analysis module identifies abnormal events and signal patterns of the power product based on the display event, display signal and the waveform diagram to obtain an analysis result of the power product; Determining the analysis result, and when the analysis result indicates an abnormal operating state, obtaining a topology of a power grid in which the power product is located and a signal source, locating an abnormal device based on the power grid topology and the signal source, and obtaining an abnormal signal of the abnormal device; Locating the fault point of the abnormal device according to the abnormal signal and the preset associated event, and determining the fault type of the abnormal device according to the fault point; The faulty device is evaluated to obtain an abnormal evaluation result, and the interface display module issues a graded alarm based on the abnormal evaluation result.

2. The method for identifying faults of electric power products according to claim 1, characterized in that: The data processing module performs a pre-processing operation on the operation data, including: Cleaning the operating data to eliminate noise in the operating data, fill missing values ​​in the operating data, and identify and process abnormal values ​​of the operating noise to obtain accurate data of the power product; Performing feature extraction on the precise data to obtain waveform, frequency and amplitude changes of the precise data; The working state and working performance of the electric power product are determined according to the waveform, the frequency and the amplitude change.

3. The method for identifying faults of electric power products according to claim 1, characterized in that: The interface display module constructs a time axis according to the data to be analyzed, including: Acquiring equipment fault information and operating instructions of the power product, and obtaining information on the time when the event occurred based on the equipment fault information and operating instructions; Confirm the product event information of the event occurrence time information, and construct the timeline according to the event occurrence time information and the product event information; The voltage information, current information and temperature information of the electric power product are obtained, and the waveform diagram is drawn on the time axis according to the voltage information, the current information and the temperature information.

4. The method for identifying faults of electric power products according to claim 1, characterized in that: The intelligent analysis module identifies abnormal events and signal patterns of the power product according to the time axis and the waveform diagram, including: screening the data to be analyzed to obtain screening data; Cleaning, arranging and formatting the filtered data to confirm the events and signals to be displayed on the time axis; The interface display module marks the occurrence moment of the time axis according to the event to be displayed and the signal to be displayed to obtain a marked time axis; In response to the user's sliding and clicking operations on the marked timeline, the user can view the events and signal changes of the power product in different time periods.

5. The method for identifying faults of electric power products according to claim 1, characterized in that: After determining the fault type of the electric power product according to the analysis result, the method further includes: Obtaining signal amplitude, event sequence, timing relationship and matching pattern of the power product; When the signal amplitude is within a preset rated range, the timing relationship conforms to a preset timing rule, and the matching pattern is consistent with a historical data pattern of the power product, it is determined that the power product is in a normal operating state.

6. The method for identifying faults of electric power products according to claim 1, characterized in that: Determining the fault type of the power product according to the analysis result includes: Building a rule base based on the abnormal event and the signal pattern; Matching the data to be analyzed with the rule base, triggering an event chain that matches the conditions of the power product, and generating a rule inference result based on the event chain; The abnormal probability information of the power product is obtained according to a preset machine learning model, and the rule reasoning result and the abnormal probability information are weighted and fused to determine the fault type of the power product. When the abnormal probability information conflicts with the rule reasoning result, the priority of the rule base and the machine learning model is confirmed according to the preset priority.

7. The method for identifying faults of electric power products according to claim 6, characterized in that: The constructing a rule base based on the abnormal event and the signal pattern includes: Confirming and correcting the rule reasoning result to obtain a corrected result; Adding the correction result to the data set of the machine learning model to update the model parameters of the machine learning model; The rule base is updated according to the correction result.

8. A device for identifying faults in power products, characterized in that: It includes at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to execute the power product fault identification method as described in any one of claims 1 to 7.

9. An electronic device, characterized in that: Including the power product fault identification device as described in claim 8.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the power product fault identification method according to any one of claims 1 to 7.

Images