Coal mining machine fault diagnosis method and system

Abstract

The invention provides a coal mining machine fault diagnosis method and system, and relates to the technical field of coal mining machine fault diagnosis, and the coal mining machine fault diagnosis method comprises the steps: obtaining the real-time working data of a coal mining machine; calculating an effective value of the coal mining machine in a preset time period based on the real-time working data; calculating a fault value of the coal mining machine based on the effective value of the coal mining machine; comparing the fault value with a preset alarm threshold value, and if the fault value is greater than the preset alarm threshold value, storing the real-time working data corresponding to the fault value as fault working data; inputting the fault working data into a preset fault diagnosis model to judge whether the coal mining machine has a fault or not; and if the coal mining machine has a fault, outputting a fault type and fault location, and if the coal mining machine does not have the fault, stopping running the preset fault diagnosis model. According to the coal mining machine fault diagnosis method, the technical problems that the calculated amount is large and misjudgment is easy to occur due to environmental influence during coal mining machine fault diagnosis in related technologies are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of shearer fault diagnosis, and particularly relates to a shearer fault diagnosis method and system. Background Art

[0002] The normal operation of the shearer ensures the production efficiency of the fully mechanized coal mining face. However, the underground working environment is extremely harsh. When the shearer is operating, it is not only subjected to huge impact loads from coal, rocks, etc., but also polluted by coal dust, gas, etc. Moreover, various key components of the shearer will inevitably experience wear and damage during long-term operation, resulting in faults of the shearer. Due to the noisy underground environment, faults such as bearing wear and fracture are difficult to detect in the early stage. Once the fault develops to a serious stage, it will not only cause the shearer to stop, but also have a serious impact on the production line and even lead to safety accidents. Therefore, the research on shearer fault diagnosis technology has important practical significance and economic value.

[0003] Currently, the shearer fault diagnosis method mainly monitors various parameters of the shearer (such as temperature, vibration, noise, etc.), and judges whether the shearer has a fault by setting thresholds. Or, an artificial intelligence method is adopted to obtain a large amount of sensor information to train a deep learning model.

[0004] However, during the operation of the shearer, when cutting hard objects such as rocks or when large coal seams collapse, the vibration and noise will be enhanced. Judging whether the shearer has a fault by monitoring various parameters of the shearer is likely to cause misjudgment; and by the artificial intelligence method, it is usually necessary to obtain and store a large amount of information. Moreover, the data used in general fault diagnosis methods are obtained in a relatively stable environment and directly applied to the shearer, which is also likely to cause misjudgment.

[0005] Since the vibration characteristics of the shearer are significantly different from those in other fields (such as aerospace, automobiles, machine tools, wind power generation, etc.), which are mainly reflected in aspects such as vibration sources, working environments, load characteristics, frequency ranges, monitoring methods, and safety requirements, although the deep learning model has achieved certain results in shearer fault diagnosis, there are still problems such as complex models and large computational amounts to a certain extent. This results in slow operation on resource-constrained devices during real-time applications. Moreover, during non-fault periods, the long-term operation of the deep learning model will also cause waste of resources.

[0006] Therefore, the existing technology needs to be further developed. Summary of the Invention

[0007] The purpose of the present invention is to overcome the above technical deficiencies and provide a shearer fault diagnosis method and system to solve the technical problems of large computational amount and easy misjudgment affected by the environment during shearer fault diagnosis in related technologies.

[0008] To achieve the above technical objectives, the present invention adopts the following technical solutions: A fault diagnosis method for a shearer is provided, including: obtaining the real-time working data of the shearer; calculating the effective value of the shearer within a preset time period based on the real-time working data; calculating the fault value of the shearer based on the effective value of the shearer; comparing the size of the fault value with a preset alarm threshold, if the fault value is greater than the preset alarm threshold, then storing the real-time working data corresponding to the fault value as fault working data; inputting the fault working data into a preset fault diagnosis model to determine whether the shearer has a fault; if the shearer has a fault, then outputting the fault type and fault location, if the shearer does not have a fault, then stopping the operation of the preset fault diagnosis model.

[0009] Further, the real-time working data includes vibration raw data and noise raw data. The vibration raw data includes the acceleration values of the shearer in the X, Y, and Z axis directions collected by vibration sensors, and the noise raw data includes the analog voltage values collected by noise sensors.

[0010] Further, the effective value of the shearer includes the effective value of speed, the effective value of displacement, and the effective value of noise decibels.

[0011] Further, the method for calculating the effective value of the shearer within a preset time period based on the real-time working data includes: calculating the effective value of speed of the shearer based on the vibration raw data; calculating the effective value of displacement of the shearer based on the effective value of speed of the shearer.

[0012] Further, the method for calculating the effective value of speed of the shearer is: ; wherein, v’(t) is the instantaneous value of speed, a(t) is the shearer at X, Y, Z the instantaneous acceleration values in the three-axis directions, v is the effective value of speed, T is the preset time period; The method for calculating the effective value of displacement of the shearer is: x = v * T ; wherein, x is the effective value of displacement, v is the effective value of speed, T is the preset time period.

[0013] Further, the method for calculating the effective value of the shearer within a preset time period based on the real-time working data includes: calculating the effective value of noise based on the noise raw data, wherein the calculation method of the effective value of noise is: ; wherein, p is the sound pressure,u(t) is the analog voltage value collected by the noise sensor, S is the sensitivity of the noise sensor, L is the effective value of the noise decibel, p 0 is the reference sound pressure, in air, p 0 =2×10 -5 pa .

[0014] Furthermore, the method for calculating the fault value based on the effective value of the shearer includes: K = a(x + v) + bW + cL ; wherein, K is the fault value, a is the vibration response coefficient, b is the temperature response coefficient, c is the noise decibel response coefficient, 0< a<1 and 0<b<1 and 0<c<1 and a + b + c = 1 , x is the effective value of displacement, v is the effective value of velocity, W is the real-time temperature of the shearer, L is the effective value of the noise decibel.

[0015] Furthermore, if the fault value is greater than the preset alarm threshold, record the real-time working data corresponding to the fault value; if the fault value is less than or equal to the preset alarm threshold, discard the real-time working data corresponding to the fault value.

[0016] On the other hand, a shearer fault diagnosis system is provided. The shearer fault diagnosis system includes: a data acquisition unit for acquiring the real-time working data of the shearer; a first calculation unit for calculating the effective value of the shearer within a preset time period based on the real-time working data; a second calculation unit for calculating the fault value of the shearer based on the effective value of the shearer; a fault monitoring unit for comparing the size of the fault value with the preset alarm threshold, and if the fault value is greater than the preset alarm threshold, running a preset fault diagnosis model; a fault diagnosis unit for inputting the real-time working data into the preset fault diagnosis model to determine whether the shearer has a fault; an output unit for outputting the fault type and fault location if the shearer has a fault, and stopping running the preset fault diagnosis model if the shearer has no fault.

[0017] On the other hand, a computer-readable storage medium is provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor, each step of the fault diagnosis method for a shearer is implemented.

[0018] Beneficial effects: 1. By combining the actual working environment of the shearer, the present invention assigns weights to different working parameters of the shearer, calculates multiple working parameters within a period of time into a valid value, and reduces the fluctuations in the vibration and noise data of the shearer caused by external environmental factors such as cutting hard objects such as rocks and the shedding of large coal seams during the operation of the shearer, thus avoiding misjudgment of the working state of the shearer by the fault diagnosis system.

[0019] 2. The present invention compares the valid value of the shearer with a pre-set fault threshold, screens out the data that may have a fault and then conducts specific fault diagnosis, does not store the data that does not exceed the fault threshold, reduces the data storage volume, saves hardware resources. At the same time, only the screened data is input into the fault diagnosis model for fault diagnosis, which not only reduces the computing amount of the fault diagnosis model, saves hardware resources, but also optimizes the data quality and improves the accuracy of fault diagnosis.

[0020] 3. The present invention sets up two sets of data acquisition systems. One set of data acquisition systems is used to acquire the actual working parameters of the shearer, and the other set of data acquisition systems acquires the valid value of the working parameters of the shearer based on the actual working parameters of the shearer. After the system responsible for acquiring the valid value of the working parameters screens out the data that may have a fault, the system for acquiring the actual working parameters selectively stores the actual working parameters corresponding to the data that may have a fault. In this way, not only can the data storage volume be reduced, and the system for acquiring the actual working parameters of the shearer and the fault diagnosis model are in a stopped operation state during the data screening process, but also the waste of resources caused by the long-term operation of the data acquisition system and the fault diagnosis model can be avoided, achieving the effect of quickly processing a small amount of valid data and outputting accurate diagnosis results. Description of the drawings

[0021] Figure 1 is the flow chart of the fault diagnosis method for a shearer adopted in the embodiment of the present invention; Figure 2 is the block diagram of the fault diagnosis system for a shearer adopted in the embodiment of the present invention. Detailed implementation manners

[0022] To enable those skilled in the art to better understand the solution of this application, the following will clearly and completely describe the technical solution in the embodiments of this application in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts shall fall within the scope of protection of this application.

[0023] According to an embodiment of the present invention, a fault diagnosis method for a shearer is provided. Please refer to Figure 1 , including: S100 Obtain the real-time working data of the shearer; Specifically, the real-time working data includes vibration raw data and noise raw data. The vibration raw data includes the acceleration values of the shearer in the X, Y, and Z axis directions collected by vibration sensors, and the noise raw data includes the analog voltage values collected by noise sensors.

[0024] In specific practice, the real-time working data of the shearer requires a very high sampling frequency to strongly welcome vibration and noise information. Therefore, storing these data requires a database large enough.

[0025] S200 Calculate the effective values of the shearer within a preset time period based on the real-time working data; In this embodiment, the effective values of the shearer include speed effective value, displacement effective value, and noise decibel effective value.

[0026] Specifically, the method for calculating the effective values of the shearer within a preset time period based on the real-time working data includes: Calculate the speed effective value of the shearer based on the vibration raw data. Among them, the method for calculating the speed effective value of the shearer is: ; Among them, v’(t) is the instantaneous speed value, a(t) is the instantaneous acceleration value of the shearer in the X, Y, Z three-axis directions, v is the speed effective value, T is the preset time period; The method for calculating the displacement effective value of the shearer is: x = v * T ; Among them, x is the displacement effective value, v is the speed effective value, T is the preset time period.

[0027] In specific practice, the method for calculating the effective value of a shearer within a preset time period based on real-time working data includes: calculating the effective value of noise based on the original noise data. The calculation method for the effective value of noise is as follows: ; Wherein, p is the sound pressure, u(t) is the analog voltage value collected by the noise sensor, S is the sensitivity of the noise sensor, L is the effective value of the noise decibel, p 0 is the reference sound pressure. In the air, p 0 =2×10 -5 pa .

[0028] In this way, by calculating multiple data within the preset time period T, the effective value within this time period is obtained, effectively reducing the storage amount of the shearer's working data, screening and storing the data that may cause faults, and eliminating the data that does not cause faults, saving hardware resources and avoiding resource waste.

[0029] S300 calculates the fault value of the shearer based on the effective value of the shearer; Specifically, the method for calculating the fault value based on the effective value of the shearer includes: K = a(x + v) + bW + cL ; Wherein, K is the fault value, a is the vibration response coefficient, b is the temperature response coefficient, c is the noise decibel response coefficient, 0< a<1 And 0<b<1 And 0<c<1 And a + b + c = 1 , x is the effective value of displacement, v is the effective value of velocity, W is the real-time temperature of the shearer, L is the effective value of the noise decibel.

[0030] In this embodiment, the calculation methods of a, b, and c are as follows: ; Wherein, βa , βb , βc are the average diagnostic accuracies of vibration, temperature, and noise respectively.

[0031] Specifically, the original fault and non-fault data corresponding to vibration, temperature, and noise within the same time period are respectively input into the CNN model for training to obtain the average diagnostic accuracy rates of vibration, temperature, and noise.

[0032] It should be noted that through the convolutional-pooling-fully connected hierarchical structure, the CNN model realizes a powerful modeling ability for high-dimensional data. Its core value lies in automatic feature learning and parameter efficiency. In industrial scenarios (such as shearer vibration analysis), sensor data can be converted into spectrograms or time-frequency diagrams, and then feature extraction and fault classification are performed through the CNN.

[0033] In some other embodiments, the response coefficients a, b, and c can also be respectively assigned values based on a large amount of data collected during the operation of the shearer and rich shearer operation experience, and the values of a, b, and c can be adjusted at any time according to the correct rate of fault diagnosis. Specifically, during the operation of the shearer, vibration is the data that can most directly reflect the operating state of the shearer. Therefore, according to operation experience, the vibration response coefficient (i.e., a) is usually relatively large. Secondly, temperature can also reflect the working state of the shearer, but the temperature of the shearer is easily affected by the environment, and the temperature fluctuations will also vary under different environments. Therefore, the temperature response coefficient (i.e., b) is usually determined based on the actual operation data collected by the shearer in the same or similar working environments. At the same time, noise can also indirectly reflect the operating state of the shearer, but the noise parameters of the shearer are also extremely susceptible to the environment, and environmental noise will interfere with the noise parameters of the shearer. Therefore, the noise response coefficient (i.e., c) also needs to collect data by the shearer in the same or similar noise environments to determine the noise response coefficient (i.e., c). In summary, the settings of the three response coefficients are usually a > b > c 。

[0034] Since the fault diagnosis method of the shearer mainly judges whether a fault has occurred by monitoring the vibration, temperature, and noise of the shearer, the vibration response coefficient + the temperature response coefficient + the noise response coefficient = 1 (i.e., a + b + c = 1).

[0035] Due to the significant differences in the vibration characteristics of shearers compared to those in other fields, the main vibration source of shearers is the impact load of cutting coal and rock. However, it is also affected by environmental factors (such as extreme working conditions like large coal seam blocks falling and uneven coal and rock hardness) or the superposition of mechanical transmission, cutting load, and walking mechanism vibration. Therefore, assigning values to the vibration response coefficients based on the actual working parameters of the shearer can greatly improve the applicability of the fault diagnosis model and the accuracy of the output results of the fault diagnosis model. In this way, by collecting a large amount of working parameters of the shearer during actual operation and selecting real working parameters in an environment identical or similar to the actual working environment of the shearer to determine the three response coefficients of the shearer, the calculation of the fault value can be made more in line with the actual working conditions, and thus the fault diagnosis results of the shearer can be made more accurate.

[0036] It should be noted that in this embodiment, after the shearer starts working, the values of a, b, and c can be adjusted in real time according to the accuracy of the output structure of the fault diagnosis model. Adjusting the setting of the response coefficients according to the on-site working conditions can enable the fault value to more accurately reflect the working state of the shearer and improve the accuracy of the shearer fault diagnosis model.

[0037] In some embodiments, the calculation of the effective value is related to the hardness of coal seam cutting. Specifically, the coal seam hardness parameters are obtained in real time through sensors in the cutting part of the shearer (such as cutting resistance sensors and acoustic emission sensors). H According to the cutting hardness parameters H the weight coefficients of the three-axis vibration data are calculated dynamically. a x (H) 、 a y (H) 、 a z (H) Based on the weight coefficients, the dynamically weighted vibration effective value is calculated. v 动态 (H) The calculation formula is: ; Where v 动态 (H) is the dynamically weighted vibration effective value, a x (H) 、 a y (H) 、 a z (H) are the weight coefficients of the three-axis vibration data, is the instantaneous value of the velocity of the three-axis vibration.

[0038] In this way, by dynamically correlating the cutting hardness parameter with the three-axis vibration weight, the deficiencies in vibration data processing of traditional methods under complex working conditions are solved, and the effective vibration value of the shearer can be accurately calculated when cutting coal seams of different hardnesses.

[0039] S400 compares the fault value with the preset alarm threshold. If the fault value is greater than the preset alarm threshold, the real-time working data corresponding to the fault value is stored as fault working data. Specifically, if the fault value calculated in step S300 is greater than the preset alarm threshold, it indicates that the state of the shearer may be abnormal within the preset time period T. At this time, it is necessary to record the real-time working data corresponding to the fault value, and then further analyze and judge the real-time state of the shearer. If the fault value is less than or equal to the preset alarm threshold, it indicates that the working state of the shearer is normal within the preset time period T. Therefore, the real-time working data within the preset time period T can be discarded. In this way, both the storage amount of data is reduced, the hardware resources are saved, and the accuracy rate of fault diagnosis is improved.

[0040] In specific practice, an alarm threshold K is set T , when K>K T , the preset fault diagnosis model is triggered, and the real-time working data of the shearer obtained within the preset time period T corresponding to the fault value K is input into the preset fault diagnosis model to further determine whether there is a fault. If there is no fault, the preset fault diagnosis model is stopped. At the same time, during the calculation of the fault value K, the preset fault diagnosis model does not need to run, avoiding resource waste caused by the long-term real-time operation of the fault diagnosis model.

[0041] S500 inputs the fault working data into the preset fault diagnosis model to determine whether the shearer has a fault. In specific practice, the preset fault diagnosis model is trained with a large amount of working data collected during the actual working process of the shearer. For different working environments, the corresponding normal operation data and fault data are collected. At the same time, during the working process of the shearer, some data can be collected as a test set to evaluate the performance of the trained model. Compared with the data obtained in a relatively stable environment, the working data collected during the actual working process can more accurately judge the real-time working state of the shearer and improve the accuracy rate of fault diagnosis.

[0042] In this embodiment, the real-time working data input into the fault diagnosis model is first screened, and the real-time working data corresponding to the possible faults of the shearer (i.e., the fault working data) is obtained after screening, and the fault working data is input into the trained fault diagnosis model. In this way, both the calculation amount of the fault diagnosis model is reduced, the calculation speed of the fault diagnosis model is improved, and the accuracy rate of the fault diagnosis model can be improved.

[0043] If the shearer has a fault, the fault type and fault location are output. If the shearer has no fault, the preset fault diagnosis model stops running.

[0044] In specific practice, under normal circumstances, the fault diagnosis model does not run. Only when the detected fault value is greater than the preset alarm threshold will the fault diagnosis model be started, which can avoid wasting resources caused by the long-term operation of the fault diagnosis model during non-fault periods.

[0045] In some embodiments, when the shearer is working, after the fault diagnosis model determines the fault type and fault location, the operator records and checks in a timely manner. If the output result of the fault diagnosis model is inaccurate, the operator needs to record and feedback in a timely manner, and optimize the model by adjusting the model structure (such as increasing the number of layers or neurons of the neural network), adjusting hyperparameters (such as learning rate, regularization coefficient), increasing the amount of data or re-performing feature engineering, etc., and then re-train and evaluate until satisfactory results are obtained.

[0046] This embodiment provides a shearer fault diagnosis system. The shearer fault diagnosis system includes: a data acquisition unit for acquiring real-time working data of the shearer; a first calculation unit for calculating the effective value of the shearer within a preset time period based on the real-time working data; a second calculation unit for calculating a fault value based on the effective value of the shearer; a fault monitoring unit for comparing the size of the fault value with the preset alarm threshold. If the fault value is greater than the preset alarm threshold, the real-time working data corresponding to the fault value is stored as fault working data; a fault diagnosis unit for inputting the real-time working data into a preset fault diagnosis model to determine whether the shearer has a fault; and an output unit for outputting the fault type and fault location if the shearer has a fault.

[0047] With the above settings, the first calculation unit and the second calculation unit perform data calculations on the data collected by the data acquisition unit to obtain the fault value of the shearer. The fault monitoring unit monitors the fault value of the shearer to obtain the data corresponding to the time period when the shearer may have a fault (i.e., the preset time period corresponding to the fault value being greater than the preset alarm threshold), and inputs the above data into the fault diagnosis unit to further diagnose the working state of the shearer. In this way, by inputting the screened working data of the shearer into the fault diagnosis unit and using a small amount of possible fault data for fault diagnosis, not only the load of the model is reduced and hardware resources are saved, but also the accuracy of the fault diagnosis unit in judging the faults of the shearer can be improved.

[0048] It should be noted that before the fault monitoring unit determines that the fault value is greater than the preset alarm threshold, the fault diagnosis unit is in a stopped state of operation, avoiding resource waste caused by the long-term real-time operation of the fault diagnosis model.

[0049] Embodiment 1: The shearer fault diagnosis method of this embodiment uses two sets of data acquisition systems. Among them, the first data acquisition system is used to collect the original data of vibration and noise. The original data of vibration are the acceleration values in the X, Y, and Z axis directions collected by vibration sensors, and the original data of noise are the analog voltage values collected by noise sensors. These values require a very high sampling frequency to highly restore the vibration and noise information. Therefore, storing these data requires a sufficiently large database. The second data acquisition system is used to collect the calculated values of vibration and noise, including vibration displacement, vibration velocity, noise decibels, and temperature values. These values are calculated from the acceleration values of vibration sensors and the analog voltage values of noise sensors. The calculated values are the effective values within the t period, reducing the data storage volume.

[0050] Specifically, vibration displacement thresholds, vibration velocity thresholds, temperature thresholds, and noise decibel thresholds are set through the second data acquisition system. Once any parameter is detected to exceed the threshold, the first data acquisition system is triggered, and the original data collected by the first data acquisition system is input into the preset fault diagnosis model to further determine whether there is a fault. If there is no fault, the first data acquisition system is stopped. If there is a fault, the fault type and fault location are output.

[0051] In this way, using a small amount of data that may be faulty to input into the fault diagnosis model for fault diagnosis not only reduces the load and calculation amount of the model, saves hardware resources, but also improves the diagnostic accuracy of faults.

[0052] This embodiment provides a computer-readable storage medium. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by a processor, each step of the shearer fault diagnosis method is implemented.

[0053] Those skilled in the art should understand that the technical solutions provided by the embodiments of the present application can be in the form of methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in the process Figure 1 one process or multiple processes and / or blocks Figure 1 means for implementing the functions specified in one block or multiple blocks. These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implement the functions specified in the process Figure 1 one process or multiple processes and / or blocks Figure 1 means for implementing the functions specified in one block or multiple blocks. These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the process Figure 1 one process or multiple processes and / or blocks Figure 1 means for implementing the functions specified in one block or multiple blocks.

[0054] It should be noted that the terms "first", "second", etc. in the description, claims and above-mentioned drawings of this application are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of this application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0055] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and will not be elaborated here.

[0056] The serial numbers of the above embodiments of this application are only for description and do not represent the superiority or inferiority of the embodiments.

[0057] In the above embodiments of this application, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0058] The above are only the preferred embodiments of this application. It should be noted that for those of ordinary skill in the art, without departing from the principle of this application, several improvements and refinements can still be made, and these improvements and refinements should also be regarded as the protection scope of this application.

Claims

1. A method for diagnosing coal mining machine faults, characterized in that: include: Obtain real-time working data of coal mining machines; Calculate the effective value of the coal mining machine within a preset time period based on the real-time working data; Calculating a fault value of the coal mining machine based on the effective value of the coal mining machine; Comparing the fault value with the preset alarm threshold, if the fault value is greater than the preset alarm threshold, storing the real-time working data corresponding to the fault value as the fault working data; Inputting the fault working data into the preset fault diagnosis model to determine whether the coal mining machine has a fault; If the coal mining machine has a fault, the fault type and fault location are output; if the coal mining machine does not have a fault, the preset fault diagnosis model is stopped.

2. The coal mining machine fault diagnosis method according to claim 1, characterized in that: The real-time working data includes vibration raw data and noise raw data. The vibration raw data includes the acceleration value of the coal mining machine in the three-axis directions of X, Y, and Z collected by the vibration sensor, and the noise raw data includes the analog voltage value collected by the noise sensor.

3. The coal mining machine fault diagnosis method according to claim 2, characterized in that: The effective value of the coal mining machine includes the effective value of speed, the effective value of displacement and the effective value of noise decibel.

4. The coal mining machine fault diagnosis method according to claim 3, characterized in that: The method for calculating the effective value of the coal mining machine within a preset time period based on the real-time working data includes: Calculate the effective value of the speed of the coal mining machine based on the original vibration data; The effective value of the displacement of the coal shearer is calculated based on the effective value of the velocity of the coal shearer.

5. The coal mining machine fault diagnosis method according to claim 4, characterized in that: The method for calculating the effective value of the speed of the coal mining machine is: ； in, v'(t) is the instantaneous value of speed, a(t) For the coal mining machine X,Y,Z The instantaneous value of acceleration in the three-axis direction, v is the effective value of speed, T is a preset time period; The method for calculating the effective value of the displacement of the coal mining machine is: x=v*T ； in, x is the effective value of displacement, v is the effective value of speed, T The preset time period.

6. The coal mining machine fault diagnosis method according to claim 3, characterized in that: The method for calculating the effective value of the coal mining machine within a preset time period based on the real-time working data includes: calculating the effective value of the noise based on the original noise data, wherein the method for calculating the effective value of the noise is: ； in, p is the sound pressure, u(t) is the analog voltage value collected by the noise sensor. S is the sensitivity of the noise sensor, L is the effective value of noise in decibels, p 0 is the reference sound pressure, in air, p 0 =2×10 -5 pa .

7. The coal mining machine fault diagnosis method according to claim 3, characterized in that: The method for calculating the fault value based on the effective value of the coal mining machine includes: K=a(x+v)+bW+cL ； in, K is the fault value, a is the vibration response coefficient, b is the temperature response coefficient, c is the noise decibel response coefficient, 0<a<1 and 0<b<1 and 0<c<1 and a+b+c=1 , x is the effective value of displacement, v is the effective value of speed, W is the real-time temperature of the coal mining machine, L It is the effective value of noise in decibels.

8. The coal mining machine fault diagnosis method according to claim 1, characterized in that: If the fault value is greater than the preset alarm threshold, the real-time working data corresponding to the fault value is recorded; If the fault value is less than or equal to the preset alarm threshold, the real-time working data corresponding to the fault value is discarded.

9. A coal mining machine fault diagnosis system, characterized in that: The coal mining machine fault diagnosis system comprises: A data acquisition unit, wherein the data acquisition unit is used to obtain real-time working data of the coal mining machine; A first calculation unit, the first calculation unit is used to calculate the effective value of the coal mining machine within a preset time period based on the real-time working data; a second calculation unit, the second calculation unit being used to calculate a fault value of the coal shearer based on an effective value of the coal shearer; A fault monitoring unit, the fault monitoring unit is used to compare the fault value with the preset alarm threshold, and if the fault value is greater than the preset alarm threshold, the real-time working data corresponding to the fault value is stored as the fault working data; A fault diagnosis unit, the fault diagnosis unit is used to input the fault working data into the preset fault diagnosis model to determine whether the coal mining machine has a fault; An output unit, wherein the output unit is used to output the fault type and fault location if the coal mining machine has a fault, and to stop running the preset fault diagnosis model if the coal mining machine does not have a fault.

10. A computer-readable storage medium having computer-readable instructions stored thereon, characterized in that: When the computer-readable instructions are executed by a processor, the various steps of the coal mining machine fault diagnosis method as described in any one of claims 1-8 are implemented.

Images