Coal mine equipment abnormality diagnosis method, system and electronic equipment based on electrical disturbance

Abstract

The present invention belongs to the technical field of coal mine equipment fault diagnosis, and discloses a method, system, and electronic device for diagnosing coal mine equipment anomalies based on electrical disturbances. The method includes: obtaining real-time data of various electrical parameters within a current period and historical data of various electrical parameters within a historical period based on a sliding window; calculating the real-time weighted average value of the real-time data of each type of electrical parameter and the historical weighted average value of the historical data; calculating the rate of change of the real-time weighted average value of the same type of electrical parameter compared to the historical weighted average value; when it is determined that the rate of change is greater than a corresponding rate of change threshold, obtaining a disturbance waveform corresponding to the real-time disturbance data; extracting disturbance features from the disturbance waveform and inputting them into a neural network prediction model to predict the type of coal mine equipment failure. The present invention achieves abnormal prediction of coal mine equipment and reduces corresponding production costs.

Description

Technical Field

[0001] The present invention relates to the technical field of coal mine equipment fault diagnosis, and in particular to a method, system and electronic equipment for diagnosing coal mine equipment abnormality based on electrical disturbances. Background Art

[0002] The underground mining process is inseparable from the normal operation of various types of coal mining equipment. Therefore, monitoring the operating status of coal mining equipment is the key to ensuring mining safety, improving mining efficiency and reducing production losses.

[0003] Traditional coal mine equipment operation monitoring relies on periodic inspections by technicians. This is not only time-consuming and labor-intensive, but also fails to meet the current production needs of unmanned underground operations. It also fails to promptly identify various abnormalities. Therefore, the following methods are currently commonly used: Method 1: Some mines install sensors on relevant coal mine equipment, establish data transmission channels and monitoring master stations, and then use the data uploaded by these sensors to determine equipment anomalies. Method 2: Since 80% of coal mine equipment in mines is connected to the coal mine power grid, and anomalies in coal mine equipment can be reflected by the status of the grid, automated electrical monitoring of the power supply section corresponding to each coal mine equipment can determine the operating status of the corresponding coal mine equipment and make appropriate fault diagnosis.

[0004] However, with the first approach, the data uploaded by the sensors only reflects the current or historical operating status of coal mine equipment. With the second approach, electrical monitoring of coal mine equipment is still limited to detecting obvious electrical faults such as short circuits and open circuits, and therefore only reflects coal mine equipment anomalies that have already occurred. In actual production, to minimize production losses, it is necessary to predict anomalies that may occur in the future. However, neither of the above approaches can predict coal mine equipment anomalies. Summary of the Invention

[0005] The present invention aims to provide a method, system and electronic equipment for diagnosing coal mine equipment anomalies based on electrical disturbances, so as to overcome the technical problem that the existing coal mine equipment monitoring process can only obtain anomalies that have occurred but cannot predict anomalies.

[0006] To achieve the above objectives, the present invention proposes the following technical solutions:

[0007] A method for diagnosing abnormalities in coal mine equipment based on electrical disturbances, comprising:

[0008] Based on a sliding window, real-time data of various electrical parameters of coal mine equipment in a current period and historical data of various electrical parameters of coal mine equipment in a historical period before the current period are obtained; wherein the electrical parameters include line voltage, phase current, and zero-sequence current;

[0009] Calculating the real-time weighted average value of each real-time data of each type of electrical parameter and the historical weighted average value of each historical data of each type of electrical parameter; and calculating the rate of change of the real-time weighted average value corresponding to the same type of electrical parameter compared to the historical weighted average value;

[0010] When it is determined that the change rate of any electrical parameter is greater than the corresponding change rate threshold, triggering the storage of a plurality of real-time disturbance data corresponding to various disturbance parameters within a preset time period from the current moment to obtain a disturbance waveform corresponding to the real-time disturbance data;

[0011] The disturbance waveform is subjected to disturbance feature extraction to obtain the disturbance amplitude, fundamental frequency, total proportion of each harmonic, proportion of the highest harmonic and disturbance duration, and the aforementioned disturbance features are input into a neural network prediction model to predict the fault type of coal mine equipment.

[0012] Further, including:

[0013] Acquire a number of training samples based on a historical database; wherein each training sample includes various disturbance features and corresponding fault types;

[0014] The original prediction model is iteratively trained based on the training samples until a preset number of iterations is reached to obtain the neural network prediction model.

[0015] Further, including:

[0016] Sending early warning information to maintenance personnel based on the predicted fault type;

[0017] When it is determined that the number of times that the maintenance personnel's inspection results are inconsistent with the predicted fault type is greater than a preset number threshold, retraining of the neural network prediction model is triggered.

[0018] Furthermore, sending warning information to maintenance personnel based on the predicted fault type includes:

[0019] Obtaining a fault level of the predicted fault type;

[0020] According to the fault level and preset frequency, the corresponding type of warning information is sent to the maintenance personnel until the maintenance personnel feedback the said maintenance results.

[0021] Further,

[0022] For the real-time weighted average value, the weight of the real-time data close to the current moment is greater than the weight of the real-time data far from the current moment;

[0023] For the historical weighted average value, the weight of historical data close to the current moment is greater than the weight of historical data far from the current moment.

[0024] A coal mine equipment abnormality diagnosis system based on electrical disturbances, comprising:

[0025] A first acquisition module is configured to acquire, based on a sliding window, a plurality of real-time data of various electrical parameters of coal mine equipment in a current period, and a plurality of historical data of various electrical parameters of coal mine equipment in a historical period preceding the current period; wherein the electrical parameters include line voltage, phase current, and zero-sequence current;

[0026] a second acquisition module, configured to calculate a real-time weighted average value of each real-time data of each type of electrical parameter, and a historical weighted average value of each historical data of each type of electrical parameter; and calculate a rate of change of the real-time weighted average value corresponding to the same type of electrical parameter compared to the historical weighted average value;

[0027] A third acquisition module is configured to trigger storage of a plurality of real-time disturbance data corresponding to various disturbance parameters within a preset time period from a current moment when determining that the change rate of any electrical parameter is greater than a corresponding change rate threshold, so as to obtain a disturbance waveform corresponding to the real-time disturbance data;

[0028] The abnormality prediction module is used to extract the disturbance features of the disturbance waveform to obtain the disturbance amplitude, fundamental frequency, total proportion of each harmonic, proportion of the highest harmonic and disturbance duration, and input the above-mentioned disturbance features into a neural network prediction model to predict the fault type of coal mine equipment.

[0029] Further, including:

[0030] A fourth acquisition module is used to acquire a number of training samples based on the historical database; wherein each training sample includes various disturbance features and corresponding fault types;

[0031] The first training module is used to perform iterative training of the original prediction model based on the training samples until a preset number of iterations is reached to obtain the neural network prediction model.

[0032] Further, including:

[0033] An abnormality warning module is used to send warning information to maintenance personnel based on the predicted fault type;

[0034] The second training module is used to trigger retraining of the neural network prediction model when it is determined that the number of times that the maintenance personnel's maintenance results are inconsistent with the predicted fault type is greater than a preset number threshold.

[0035] Furthermore, the abnormal warning module also includes:

[0036] a level acquisition unit, configured to acquire a fault level of the predicted fault type;

[0037] The early warning sending unit is used to send corresponding types of early warning information to maintenance personnel according to the fault level and preset frequency until the maintenance personnel feedback the maintenance results.

[0038] An electronic device, comprising:

[0039] at least one processor;

[0040] a memory communicatively coupled to the at least one processor;

[0041] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the diagnostic method.

[0042] Beneficial effects:

[0043] It can be seen from the above technical solutions that the technical solution of the present invention provides a method for diagnosing abnormalities in coal mine equipment based on electrical disturbances to improve the current technical problem of being unable to predict abnormalities when monitoring coal equipment.

[0044] In practice, the inventors discovered that fault monitoring based on electrical monitoring of coal mine equipment, compared to methods that rely on installing sensors, can be implemented using existing electrical monitoring equipment, thus minimizing the complexity of the already complex underground mine environment. Furthermore, the inventors discovered that electrical disturbances in the coal mine power grid can occur during the operation of coal mine equipment. While the coal mine equipment is currently operating normally, these disturbances are often associated with subsequent anomalies in the corresponding coal mine equipment. Therefore, the present technical solution was designed to achieve fault prediction for coal mine equipment.

[0045] In this technical solution, first, a sliding window is introduced to obtain real-time data and historical data corresponding to each electrical parameter. Then, the disturbance waveform is obtained. The disturbance waveform is obtained through the corresponding disturbance real-time data, while in this technical solution, only the disturbance real-time data is recorded and stored. Compared with indiscriminate data storage, recording and analysis (i.e., data storage, recording and analysis are also performed when there is no disturbance), the validity of the data in the subsequent disturbance waveform is improved and invalid output is avoided. In order to improve the immediacy of the recorded and stored disturbance real-time data, a trigger condition for recording the disturbance real-time data is also set. Specifically, from a micro perspective, considering the importance of data at different times, the real-time weighted average value corresponding to the real-time data and the historical weighted average value corresponding to the historical data are obtained; from a macro perspective, considering the overall trend of the electrical parameters, the change rate of the real-time weighted average value compared to the historical weighted average value is obtained. At this time, the trigger condition for recording the disturbance real-time data is that the change rate is greater than a preset change rate threshold. Finally, this technical solution combines traditional coal mine scenarios with a novel neural network algorithm, introducing a neural network prediction model. Using the disturbance waveform as input, this model predicts the type of fault in coal mine equipment. This not only improves the efficiency of fault type prediction, but also enhances its accuracy.

[0046] As can be seen from the above, this technical solution takes into account the complexity of underground mine hardware layout and environmental safety. It combines the electrical disturbances implicitly associated with the operating status of coal mining equipment in traditional coal mining scenarios with the neural network prediction model in the new neural network algorithm, thereby achieving efficient and accurate prediction of coal mining equipment failure types. From a global perspective, this reduces the frequency of coal mining equipment failures, improves underground mining safety, and reduces coal mining costs.

[0047] It should be appreciated that all combinations of the foregoing concepts, as well as additional concepts described in greater detail below, to the extent such concepts are not mutually inconsistent, can be considered to be part of the inventive subject matter of this disclosure.

[0048] The foregoing and other aspects, embodiments, and features of the present invention will be more fully understood from the following description in conjunction with the accompanying drawings. Other additional aspects of the present invention, such as features and / or beneficial effects of the exemplary embodiments, will become apparent from the following description or through practice of specific embodiments according to the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are not intended to be drawn to scale. In the drawings, each identical or nearly identical component shown in various figures may be represented by the same reference numeral. For clarity, not every component is labeled in every figure. Embodiments of various aspects of the present invention will now be described by way of example and with reference to the accompanying drawings, in which:

[0050] Figure 1 This is a flow chart of the method for diagnosing abnormalities in coal mine equipment based on electrical disturbances according to this embodiment;

[0051] Figure 2 for Figure 1 Flowchart of preprocessing the disturbance waveform described in;

[0052] Figure 3 for Figure 1 The training flow chart of the neural network prediction model described in ;

[0053] Figure 4 for Figure 1 Flowchart for subsequent processing of prediction results;

[0054] Figure 5 for Figure 4 A flow chart of sending the warning information described in . DETAILED DESCRIPTION

[0055] To further clarify the objectives, technical solutions, and advantages of the embodiments of the present invention, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only a portion of the embodiments of the present invention, not all of them. Based on the described embodiments of the present invention, all other embodiments derived by persons of ordinary skill in the art without requiring creative effort are within the scope of protection of the present invention. Unless otherwise defined, technical or scientific terms used herein shall have the ordinary meanings understood by persons of ordinary skill in the field to which the present invention pertains.

[0056] The words "first", "second" and similar terms used in the patent application specification and claims of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, unless the context clearly indicates otherwise, the singular forms of "a", "an" or "the" and similar terms do not indicate a quantitative limitation, but rather indicate the presence of at least one. Words such as "include" or "comprise" mean that the elements or objects appearing before "include" or "comprise" include the features, wholes, steps, operations, elements and / or components listed after "include" or "comprise", and do not exclude the existence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0057] Existing technologies, whether monitoring coal mine equipment anomalies through the deployment of sensors or through electromechanical monitoring of coal equipment connected to the coal power grid, can only detect anomalies that have already occurred, but cannot comprehensively analyze real-time parameters of coal mine equipment to proactively detect potential anomalies. Consequently, there remain technical bottlenecks in reducing the frequency of coal mine equipment anomalies and minimizing the associated losses. Therefore, this embodiment aims to provide a method for diagnosing coal mine equipment anomalies based on electrical disturbances to address these shortcomings in existing coal mine equipment anomaly monitoring.

[0058] The following is a detailed introduction to the coal mine equipment abnormality diagnosis method based on electrical disturbance disclosed in this embodiment with reference to the accompanying drawings.

[0059] like Figure 1 As shown, the method includes:

[0060] Step S102: Based on the sliding window, real-time data of various electrical parameters of coal mine equipment in the current period and historical data of various electrical parameters of coal mine equipment in a historical period before the current period are respectively obtained.

[0061] In this embodiment, the electrical parameters include: line voltage, phase current and zero-sequence current.

[0062] In this step, the sliding window is a sliding window of fixed length, which includes real-time data or historical data within 10 consecutive seconds.

[0063] Preferably, the sliding window corresponding to the real-time data and the sliding window corresponding to the historical data are temporally adjacent sliding windows. As can be seen from subsequent steps S104 to S106, disturbance data recording is triggered by the rate of change associated with the weighted average of the real-time and historical data. For a segment of data within a sliding window, a single instantaneous data change can cause a significant change in the weighted average of that segment, thereby accurately triggering the timely recording of disturbance data. Therefore, the provision of adjacent sliding windows effectively prevents the omission of real-time disturbance data while also improving the integrity of the stored real-time disturbance data.

[0064] Specifically, in this embodiment, the time stamp of the foremost real-time data in the sliding window for obtaining real-time data and the time stamp of the foremost historical data in the sliding window for obtaining historical data differ by 1 second.

[0065] Step S104: Calculate the real-time weighted average value of each real-time data of each type of electrical parameter and the historical weighted average value of each historical data of each type of electrical parameter; and calculate the rate of change of the real-time weighted average value corresponding to the same type of electrical parameter compared to the historical weighted average value.

[0066] As a specific implementation method, data close to the current moment carries more valuable information for data analysis. Furthermore, in this embodiment, the presence of electrical disturbances needs to be reflected by the rate of change relative to the weighted average value; therefore, the importance of data close to the current moment also needs to be highlighted. Therefore, for the real-time weighted average value, the weight of real-time data close to the current moment is set to be greater than the weight of real-time data further away from the current moment. Similarly, for the historical weighted average value, the weight of historical data close to the current moment is set to be greater than the weight of historical data further away from the current moment.

[0067] In the specific calculation, the real-time weighted average value is recorded as V r , the historical weighted average is recorded as V h The rate of change is recorded as R. The real-time weighted average value is obtained by the following formula:

[0068]

[0069] Among them, N i is the i-th real-time data in the sliding window at the current moment; W i N i The weight of N i Compared with N i-1 Close to the current time, and W i Always greater than W i-1 .

[0070] The real-time weighted average value is obtained by the following formula:

[0071]

[0072] Among them, N i ' is the i-th historical data in the sliding window of the historical moment; W i ' is N i 'weight; N i 'Compared to N i-1 'Close to the current moment, and W i 'Always greater than W i-1 '. And W i =W i '.

[0073] The change rate is obtained by the following formula:

[0074]

[0075] Step S106: When it is determined that the change rate of any electrical parameter is greater than the corresponding change rate threshold, a plurality of real-time disturbance data corresponding to various disturbance parameters within a preset time period from the current moment is triggered to be stored to obtain a disturbance waveform corresponding to the real-time disturbance data.

[0076] In this embodiment, the preset duration corresponding to the real-time disturbance data is 30 minutes, and the recording frequency of the real-time disturbance data is 1 second / time.

[0077] The change rate threshold is 5 times the actually obtained change rate.

[0078] In this embodiment, to facilitate fault analysis and anomaly aggregation, each acquired disturbance waveform is stored in an anomaly database. During storage, each disturbance waveform is categorized based on the associated coal mining equipment. The stored information also includes the rate of change, disturbance start time, disturbance introduction time, and disturbance duration of the trigger disturbance record corresponding to each disturbance waveform.

[0079] Step S108: extract disturbance features from the disturbance waveform and input the features into a neural network prediction model to predict the fault type of the coal mine equipment.

[0080] In a specific implementation, the disturbance characteristics include: disturbance amplitude, fundamental frequency, total proportion of each harmonic, proportion of the highest harmonic and disturbance duration.

[0081] In this embodiment, in order to improve the fault prediction efficiency of the neural network prediction model, before predicting the fault type based on the disturbance waveform, the disturbance waveform is preliminarily screened based on the disturbance duration to avoid the influence of random disturbances and occasional disturbances. Figure 2As shown, before step S108, the following steps are also included:

[0082] Step S107: Obtain the number of disturbances contained in the disturbance waveform and the disturbance duration of each disturbance, and when it is determined that the number of disturbances is greater than the disturbance number threshold, or the duration of any disturbance is greater than the disturbance duration threshold, trigger the disturbance feature extraction of the disturbance waveform.

[0083] As an optional implementation method, Figure 3 As shown, the neural network prediction model described in step S108 is obtained through the following steps:

[0084] Step S108.2: Acquire a number of training samples based on the historical database; wherein each training sample includes various disturbance features and corresponding fault types.

[0085] Step S108.4: Perform iterative training of the original prediction model based on the training samples until a preset number of iterations is reached to obtain the neural network prediction model.

[0086] In this embodiment, the neural network prediction model is specifically a BP neural network prediction model.

[0087] As a specific implementation method, Figure 4 As shown, the subsequent processing of obtaining the predicted fault type is carried out through the following process:

[0088] Step S110: Sending warning information to maintenance personnel based on the predicted fault type.

[0089] In this step, in order to improve the logic of equipment maintenance based on the predicted fault type, Figure 5 As shown, including the following:

[0090] Step S110.2: Obtain the fault level of the predicted fault type.

[0091] Step S110.4: Send corresponding types of warning information to maintenance personnel according to the fault level and preset frequency until the maintenance personnel feedback the maintenance results.

[0092] At this point, based on steps S110.2 to S110.4, early warning information can be sent in a hierarchical manner based on fault type, allowing maintenance personnel to prioritize inspection and maintenance of higher-level predicted faults, further preventing abnormal losses. Furthermore, continuously sending early warning information to maintenance personnel at a preset frequency also helps urge them to conduct timely inspections and maintenance.

[0093] In a specific implementation, the fault levels are set to include: Level 1, Level 2, and Level 3. Level 1 corresponds to predicted anomalies that will cause coal mining equipment to shut down, Level 2 corresponds to predicted anomalies that will affect the stable operation of coal mining equipment, and Level 3 corresponds to predicted anomalies that will not significantly affect the operation of coal mining equipment. Furthermore, the preset frequencies corresponding to Level 1, Level 2, and Level 3 are arranged in descending order.

[0094] Step S112: When it is determined that the number of times that the maintenance personnel's inspection result is inconsistent with the predicted fault type is greater than a preset number threshold, retraining of the neural network prediction model is triggered.

[0095] Based on this step, the neural network prediction model can be further optimized to improve the reliability of fault type prediction based on it.

[0096] As can be seen from the above, this embodiment provides a new coal mine equipment diagnostic method that utilizes the implicit impact of electrical disturbances in coal mine power grids on coal mine equipment. It also introduces neural network algorithms into the traditional coal mining field, thereby effectively predicting coal mine equipment failures. It also provides corresponding measures for subsequent processing based on predicted coal mine equipment failures, such as sending corresponding early warning information to maintenance personnel, and specifically differentiating early warning information based on fault level to improve maintenance efficiency and avoid major anomalies or failures. The actual feedback from maintenance personnel is used as a reference to trigger periodic iterative optimization of the neural network prediction model, thereby further improving the reliability of fault prediction results.

[0097] The above program can be executed in a processor or stored in a memory (or computer-readable storage medium). Computer-readable media include permanent and non-permanent, removable and non-removable media that can implement information storage by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media such as modulated data signals and carrier waves.

[0098] These computer programs can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps of the functions specified in one or more blocks can be implemented by different modules corresponding to different steps.

[0099] This embodiment also provides a coal mine equipment abnormality diagnosis system based on electrical disturbances. The system includes:

[0100] The first acquisition module is used to obtain, based on a sliding window, a number of real-time data of various electrical parameters of coal mine equipment in the current time period, as well as a number of historical data of various electrical parameters of coal mine equipment in a historical period traced back from the current time period; wherein, the electrical parameters include: line voltage, phase current and zero-sequence current.

[0101] The second acquisition module is used to calculate the real-time weighted average value of each real-time data of each type of electrical parameter, and the historical weighted average value of each historical data of each type of electrical parameter; and calculate the rate of change of the real-time weighted average value corresponding to the same type of electrical parameters compared with the historical weighted average value.

[0102] The third acquisition module is used to trigger the storage of a number of real-time disturbance data corresponding to various disturbance parameters within a preset time period from the current moment when it determines that the change rate of any electrical parameter is greater than the corresponding change rate threshold, so as to obtain the disturbance waveform corresponding to the real-time disturbance data.

[0103] The abnormality prediction module is used to extract the disturbance features of the disturbance waveform to obtain the disturbance amplitude, fundamental frequency, total proportion of each harmonic, proportion of the highest harmonic and disturbance duration, and input the above-mentioned disturbance features into a neural network prediction model to predict the fault type of coal mine equipment.

[0104] The system is used to implement the steps of the above method, so those that have been described will not be repeated here.

[0105] For example, the system further includes:

[0106] The fourth acquisition module is used to acquire a number of training samples based on the historical database; wherein each training sample includes various disturbance features and corresponding fault types.

[0107] The first training module is used to perform iterative training of the original prediction model based on the training samples until a preset number of iterations is reached to obtain the neural network prediction model.

[0108] For example, the system further includes:

[0109] The abnormal warning module is used to send warning information to maintenance personnel based on the predicted fault type.

[0110] The second training module is used to trigger retraining of the neural network prediction model when it is determined that the number of times that the maintenance personnel's maintenance results are inconsistent with the predicted fault type is greater than a preset number threshold.

[0111] Preferably, the abnormal warning module specifically includes:

[0112] A level acquisition unit is used to acquire the fault level of the predicted fault type.

[0113] The early warning sending unit is used to send corresponding types of early warning information to maintenance personnel according to the fault level and preset frequency until the maintenance personnel feedback the maintenance results.

[0114] This embodiment also provides an electronic device. The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the above-described diagnostic method.

[0115] Since the system and the electronic equipment are both built based on the above-mentioned diagnostic method, in actual use, abnormality prediction of coal mine equipment can be achieved based on the electrical disturbance waveform, thereby reducing the frequency of abnormality occurrence and avoiding unnecessary production costs.

[0116] While the present invention has been disclosed above with reference to preferred embodiments, this is not intended to limit the present invention. Persons skilled in the art will readily appreciate that various modifications and variations can be made without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the claims.

Claims

1. A method for diagnosing abnormalities in coal mine equipment based on electrical disturbances, characterized in that: include: Based on a sliding window, real-time data of various electrical parameters of coal mine equipment in a current period and historical data of various electrical parameters of coal mine equipment in a historical period preceding the current period are obtained; wherein the electrical parameters include line voltage, phase current, and zero-sequence current; wherein the various electrical parameters correspond to electrical disturbances in the coal mine power grid; Calculating the real-time weighted average value of each real-time data of each type of electrical parameter and the historical weighted average value of each historical data of each type of electrical parameter; and calculating the rate of change of the real-time weighted average value corresponding to the same type of electrical parameter compared to the historical weighted average value; When it is determined that the rate of change of any type of electrical parameter is greater than the corresponding rate of change threshold, a plurality of real-time disturbance data corresponding to each type of disturbance parameter within a preset time period from the current moment is triggered to be stored, so as to obtain a disturbance waveform corresponding to the real-time disturbance data; wherein, the disturbance waveform is classified based on the coal mining equipment to which it belongs and stored in the abnormality database; wherein, when the disturbance waveform is stored in the abnormality database, the relevant stored information includes: rate of change, disturbance start time, disturbance start time, and disturbance duration; Obtaining the number of disturbances contained in the disturbance waveform and the disturbance duration of each disturbance, and determining that the number of disturbances is greater than a disturbance number threshold, or the duration of any disturbance is greater than a disturbance duration threshold, then determining that the disturbance waveform is a non-random disturbance or an occasional disturbance, thereby triggering disturbance feature extraction of the disturbance waveform; The disturbance waveform is subjected to disturbance feature extraction to obtain the disturbance amplitude, fundamental frequency, total proportion of each harmonic, proportion of the highest harmonic and disturbance duration, and the aforementioned disturbance features are input into a neural network prediction model to predict the fault type of coal mine equipment.

2. The method for diagnosing abnormalities in coal mine equipment based on electrical disturbances according to claim 1, characterized in that: The method includes training the neural network prediction model, including: Acquire a plurality of training samples based on a historical database; wherein each training sample includes the disturbance characteristics and the corresponding fault type; The original prediction model is iteratively trained based on the training samples until a preset number of iterations is reached to obtain the neural network prediction model.

3. The method for diagnosing abnormalities in coal mine equipment based on electrical disturbances according to claim 1, characterized in that: After inputting the aforementioned disturbance features into a neural network prediction model to predict the fault type of coal mining equipment, the method includes: Sending early warning information to maintenance personnel based on the predicted fault type; When it is determined that the number of times that the maintenance personnel's inspection results are inconsistent with the predicted fault type is greater than a preset number threshold, retraining of the neural network prediction model is triggered.

4. The method for diagnosing abnormalities in coal mine equipment based on electrical disturbances according to claim 3, characterized in that: The sending of warning information to maintenance personnel based on the predicted fault type includes: Obtaining a fault level of the predicted fault type; According to the fault level and preset frequency, the corresponding type of warning information is sent to the maintenance personnel until the maintenance personnel feedback the said maintenance results.

5. The method for diagnosing abnormalities in coal mine equipment based on electrical disturbances according to claim 1, characterized in that: For the real-time weighted average value, the weight of the real-time data close to the current moment is greater than the weight of the real-time data far from the current moment; For the historical weighted average value, the weight of historical data close to the current moment is greater than the weight of historical data far from the current moment.

6. A coal mine equipment abnormality diagnosis system based on electrical disturbance, characterized in that: include: A first acquisition module is configured to acquire, based on a sliding window, a plurality of real-time data of various electrical parameters of coal mine equipment in a current period, and a plurality of historical data of various electrical parameters of coal mine equipment in a historical period preceding the current period; wherein the electrical parameters include line voltage, phase current, and zero-sequence current; wherein the various electrical parameters correspond to electrical disturbances in the coal mine power grid; a second acquisition module, configured to calculate a real-time weighted average value of each real-time data of each type of electrical parameter, and a historical weighted average value of each historical data of each type of electrical parameter; and calculate a rate of change of the real-time weighted average value corresponding to the same type of electrical parameter compared to the historical weighted average value; A third acquisition module is configured to trigger storage of a plurality of real-time disturbance data corresponding to various types of disturbance parameters within a preset time period from the current moment when determining that the change rate of any type of electrical parameter is greater than a corresponding change rate threshold, so as to obtain a disturbance waveform corresponding to the real-time disturbance data; The abnormality prediction module is used to extract the disturbance features of the disturbance waveform to obtain the disturbance amplitude, fundamental frequency, total proportion of each harmonic, proportion of the highest harmonic and disturbance duration, and input the above-mentioned disturbance features into a neural network prediction model to predict the fault type of coal mine equipment.

7. The coal mine equipment abnormality diagnosis system based on electrical disturbance according to claim 6, characterized in that: include: A fourth acquisition module is used to acquire a number of training samples based on the historical database; wherein each training sample includes various disturbance features and corresponding fault types; The first training module is used to perform iterative training of the original prediction model based on the training samples until a preset number of iterations is reached to obtain the neural network prediction model.

8. The coal mine equipment abnormality diagnosis system based on electrical disturbance according to claim 6, characterized in that: include: An abnormality warning module is used to send warning information to maintenance personnel based on the predicted fault type; The second training module is used to trigger retraining of the neural network prediction model when it is determined that the number of times that the maintenance personnel's maintenance results are inconsistent with the predicted fault type is greater than a preset number threshold.

9. The coal mine equipment abnormality diagnosis system based on electrical disturbance according to claim 8, characterized in that: The abnormal warning module also includes: a level acquisition unit, configured to acquire a fault level of the predicted fault type; The early warning sending unit is used to send corresponding types of early warning information to maintenance personnel according to the fault level and preset frequency until the maintenance personnel feedback the maintenance results.

10. An electronic device, characterized in that: include: at least one processor; a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the diagnostic method according to any one of claims 1 to 5.

Images