Monitoring method, device and system for coal mine safety operation and medium

Abstract

The invention relates to a coal mine safety operation monitoring method, device and system and a medium, and is applied to a monitoring system.The method comprises the steps that when fault data is obtained, a fault analysis component is called to process the fault data, and an estimation result corresponding to the fault data is obtained; acquiring quality data of the raw coal in the current production period, wherein the quality data at least comprises coal briquette volume, hardness and impurity content; checking the pre-estimation result based on the quality data to obtain a target fault reason and a hidden fault; generating a first troubleshooting task based on the target fault reason, and generating a shutdown instruction and a second troubleshooting task based on the hidden fault; and sending the first troubleshooting task to the corresponding fault equipment, and sending the second troubleshooting task and the shutdown instruction to target equipment corresponding to the hidden fault. By adopting the method, the operation risk of the raw coal pretreatment system can be reduced.

Description

Technical Field

[0001] The present application relates to the technical field of coal mining, and in particular to a monitoring method, device, system and medium for safe operation of coal mines. Background Art

[0002] Coal has always been an important resource in industry. The demand for coal in daily production and life is increasing day by day. At present, the raw coal mined in coal mines needs to be processed before being transported to various places by transport vehicles. Primary processing includes washing, crushing and screening. Washing is mainly to screen out impurities such as gangue in the raw coal. Crushing is to break large coal blocks into smaller particles for easy transportation and storage. Screening is to screen the particles of coal blocks. With the development of digitalization, more and more coal mines have applied systems composed of automated equipment to realize the primary processing of raw coal, which greatly improves the processing efficiency.

[0003] In the related art, when a device in a certain process fails, a trained fault analysis model is usually used to analyze the fault phenomenon, and the fault analysis results output by the fault analysis model are used to troubleshoot the fault and obtain the possible cause of the current fault phenomenon. Since the quality of coal mined in coal mines in each period of time is different, for example, the coal seams mined in some stages have a high content of gangue and large coal blocks; the coal seams mined in some stages have a low content of gangue and are mostly small coal blocks; therefore, the reasons for the same fault in the system at different stages may also be different, and there may even be some potential hidden faults that have not occurred in some stages. However, the use of a fault analysis model trained based on historical data to analyze the current fault can only predict the cause of the current fault, but it is difficult to find some potential faults, which will lead to potential operational risks when the system is running.

[0004] Therefore, how to reduce the operational risk of the raw coal pretreatment system is an issue that needs to be addressed urgently. Summary of the invention

[0005] Based on this, it is necessary to provide a monitoring method, device, system and medium for coal mine safety operations that can reduce the operating risks of the raw coal pretreatment system in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for monitoring safe operation of a coal mine, which is applied to a monitoring system, and the method comprises: When the fault data is acquired, the fault analysis component is called to process the fault data to obtain an estimation result corresponding to the fault data, wherein the fault data includes a faulty device, a fault phenomenon, and a fault occurrence time, and the estimation result includes at least one estimated cause and an estimated probability of each of the estimated causes, and the fault analysis component is pre-built based on historical fault data; Acquire quality data of raw coal in the current production cycle, wherein the quality data at least includes coal block volume, hardness and impurity content; Verifying the prediction result based on the quality data to obtain target fault causes and hidden faults; Generate a first troubleshooting task based on the target fault cause, and generate a shutdown instruction and a second troubleshooting task based on the hidden fault; The first troubleshooting task is sent to the corresponding faulty device, and the second troubleshooting task and the shutdown instruction are sent to the target device corresponding to the hidden fault, and the shutdown instruction is used to control the target device to shut down and / or switch the target device to a backup device.

[0007] In one embodiment, sending the first troubleshooting task to the corresponding faulty device, and sending the second troubleshooting task and the shutdown instruction to the target device corresponding to the hidden fault, includes: Sending the shutdown command to the target device corresponding to the hidden fault, and acquiring multiple monitoring images of the target device; Based on the multiple monitoring images, determining whether the target device is shut down; When it is determined that the target device has been shut down, the first troubleshooting task is sent to the corresponding faulty device, and the second troubleshooting task is sent to the target device corresponding to the hidden fault.

[0008] In one embodiment, the step of verifying the prediction result based on the quality data to obtain target fault causes and hidden faults includes: Determine the inducement data of the raw coal to each device based on the quality data, wherein the inducement data is the probability of causing the device to fail due to various reasons; Determine the inducement data corresponding to the faulty equipment as target inducement data, and determine the product-cause probability of each of the estimated causes from the target inducement data, wherein the product-cause probability is the probability that the faulty equipment will have the estimated cause due to the raw coal of the quality data; The estimated results are checked based on the factor probability of each estimated cause to obtain the target fault cause and hidden fault.

[0009] In one embodiment, the estimation result is verified based on the product probability of each estimated cause to obtain the target fault cause and the hidden fault, including: Matching the factor probability based on each of the estimated causes with the estimated probability of each of the estimated causes in the estimated result; Determine the target fault cause by taking the estimated cause with the highest product of the factor probability and the estimated probability; An estimated cause whose product probability and estimated probability are both greater than a target threshold is determined as a hidden fault.

[0010] In one embodiment, the method further comprises: It is determined that among the cause data of each device, the cause with the highest probability of causing the device to fail is a hidden failure.

[0011] In one embodiment, determining the inducement data of the raw coal to each device based on the quality data includes: Based on the quality data, determining the required performance parameters of each device for the raw coal; Determine the baseline performance parameters of each device based on the mapping relationship table; Obtaining the operating time of each device in the current cycle, and determining the degree of damage caused by the raw coal to each device based on the operating time of each device, the required performance parameter of the raw coal for each device, and the benchmark performance parameter of each device; Based on the degree of damage caused by the raw coal to each device, the inducement data of the raw coal to each device is determined.

[0012] In one embodiment, the method further comprises: Each of the historical fault data is used as a training sample to train the initial LSTM model to obtain a trained LSTM model, and the trained LSTM model is used as a fault analysis component.

[0013] In a second aspect, the present application also provides a monitoring device for coal mine safety operations, the device comprising a preprocessing module, a quality data acquisition module, a verification module, a task generation module and a sending module, wherein: A preprocessing module, configured to, when acquiring fault data, call a fault analysis component to process the fault data to obtain an estimated result corresponding to the fault data, wherein the fault data includes a faulty device, a fault phenomenon, and a time of occurrence of the fault, and the estimated result includes at least one estimated cause and an estimated probability of each of the estimated causes, and the fault analysis component is pre-built based on historical fault data; A quality data acquisition module, used to acquire the quality data of raw coal in the current production cycle, wherein the quality data at least includes the volume, hardness and impurity content of the coal block; A verification module, used to verify the prediction result based on the quality data to obtain target fault causes and hidden faults; A task generation module, used to generate a first troubleshooting task based on the target fault cause, and to generate a shutdown instruction and a second troubleshooting task based on the hidden fault; A sending module is used to send the first troubleshooting task to the corresponding faulty device, and send the second troubleshooting task and the shutdown instruction to the target device corresponding to the hidden fault, and the shutdown instruction is used to control the target device to shut down and / or switch the target device to a backup device.

[0014] In a third aspect, the present application further provides a monitoring system, the system comprising: Monitoring equipment, used to collect monitoring images of various devices; Data collection equipment, used to collect quality data of raw coal in the current cycle, the quality data at least including coal block volume, hardness and impurity content; A control device, the monitoring device and the data acquisition device can both exchange information with the control device; The control device is used to execute the steps of the method as described in any one of the first aspects above.

[0015] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method as described in any one of the above-mentioned first aspects are implemented.

[0016] The above-mentioned coal mine safety operation monitoring method, device, system and medium, through the fault analysis component constructed by historical fault data, can analyze the current fault data to obtain various estimated causes and probabilities, and in this scheme, the quality data of raw coal in the current production cycle is further introduced. On the one hand, the introduction of quality data makes the fault analysis no longer completely dependent on historical data, but can dynamically adjust the estimated results according to the current production conditions, which improves the accuracy of fault location, facilitates to obtain more accurate target fault causes, and makes fault handling more in line with the actual situation of the current production cycle; on the other hand, not only pay attention to the current fault data that has occurred, but also identify possible hidden faults by comparing the quality data with the estimated results, so as to generate the first troubleshooting task and the second troubleshooting task based on the target fault cause and the hidden fault cause to troubleshoot the relevant equipment, thereby reducing the probability of hidden faults hiding, reducing the risk of the raw coal pretreatment system during operation, thereby improving the safety of the raw coal pretreatment system during operation and reducing the operational risk. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 A schematic diagram of the structure of a monitoring system in one embodiment; Figure 2 A schematic diagram of a flow chart of a method for monitoring safe operation of a coal mine in one embodiment; Figure 3 A schematic diagram of a flow chart of a step of determining a verification result in one embodiment; Figure 4 A schematic diagram of a process flow for determining inducement data in one embodiment; Figure 5 It is a structural block diagram of a monitoring device for coal mine safety operation in one embodiment; Figure 6 FIG. 1 is a diagram showing the internal structure of a control device in a monitoring system in one embodiment. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0020] The monitoring method for coal mine safety operation provided in the embodiment of the present application can be applied to Figure 1 In the monitoring system shown. The monitoring system at least includes monitoring equipment, data acquisition equipment and control equipment, wherein: the monitoring equipment is used to collect monitoring images of each device; the data acquisition equipment is used to collect the quality data of raw coal in the current cycle, and the quality data at least includes the volume, hardness and impurity content of the coal block; the control equipment, the monitoring equipment and the data acquisition equipment can exchange information with the control equipment. Among them, the control equipment can be but not limited to various personal computers, laptops, smart phones, tablet computers, and can also be servers, etc.; the server can be implemented by an independent server or a server cluster composed of multiple servers.

[0021] In an exemplary embodiment, Figure 2 As shown, a method for monitoring coal mine safety operations is provided, and the method is applied to Figure 1 The monitoring system in the control system is described as an example, and the control device in the control system is executed as an example, including the following steps 01-05, wherein: Step 01. When fault data is obtained, the fault analysis component is called to process the fault data to obtain the estimated results corresponding to the fault data. The fault data includes the faulty device, fault phenomenon and fault occurrence time. The estimated results include at least one estimated cause and the estimated probability of each estimated cause. The fault analysis component is pre-built based on historical fault data.

[0022] For the embodiment of the present application, the fault data can be obtained from the fault log generated by the faulty equipment in the raw coal pretreatment system, or the fault data can be input by the user. The method for obtaining the fault data is not specifically limited in the embodiment of the present application. The fault data is usually composed of various fault codes. Therefore, after obtaining the fault data, the fault data is first parsed based on the identification form of the preset fault code, so as to obtain the faulty equipment, fault phenomenon and fault occurrence time represented by the fault data.

[0023] The fault analysis component is constructed based on the historical fault data of each device in the raw coal pretreatment system. The fault analysis component can be a trained neural network model. The fault analysis component can also be a plug-in or script configured based on a probability distribution algorithm that can call historical fault data to analyze current fault data. This is not specifically limited in the embodiments of the present application. The fault analysis component is constructed based on historical fault data. Therefore, the fault analysis component can analyze the current fault data and then determine the various estimated causes of the fault phenomenon.

[0024] Step 02: Obtain the quality data of raw coal in the current production cycle. The quality data includes at least the volume, hardness and impurity content of the coal block.

[0025] For the embodiment of the present application, since the quality of raw coal mined from different locations or each layer section is basically the same, the production cycle can be determined based on the location of the mined raw coal or the coal seam section; of course, the production cycle can also be a fixed time period, such as 1 month. The embodiment of the present application does not specifically limit the way of dividing the production cycle.

[0026] The quality data of raw coal can be obtained by the data acquisition equipment in the monitoring system. For example, by placing a dust concentration detector at the equipment used for crushing in the raw coal pretreatment system, coal blocks with lower hardness will generate more dust when they are crushed, and coal blocks with higher hardness will generate less dust when they are crushed. Therefore, the hardness of raw coal can be determined by the dust concentration. For example, it is also possible to collect coal images of coal blocks after the screening process, identify the texture features, shape features and color features of each coal image, and determine the distribution ratio of coal blocks and impurities (gangue) in each coal image through the identified features, and then determine the impurity content in each coal image according to the distribution ratio. The impurity content corresponding to multiple coal images is further averaged to determine the impurity content of the raw coal.

[0027] Of course, the quality data of the raw coal can also be input by the user, which is not specifically limited in the embodiments of the present application.

[0028] Step 03: Verify the prediction results based on the quality data to obtain the target fault causes and hidden faults.

[0029] For the embodiment of the present application, the fault analysis component constructed based on historical data can only predict the cause of the current fault, and it is difficult to discover some potential faults. The estimated results obtained by the fault analysis component are further verified by the quality data of the raw coal obtained, so as to determine the estimated cause that is more consistent with the quality of the raw coal in the current production cycle as the target fault cause; and, combined with the quality data of the raw coal in the current production cycle, some hidden faults that have not yet appeared can also be discovered.

[0030] In one possible implementation, the verification method can be implemented using an AI agent model. For example, an experience database is constructed in advance with relevant equipment and knowledge in the coal mining and raw coal preprocessing stages, and the AI ​​agent model is trained using the experience database. The estimated results and raw coal quality data are input into the AI ​​agent model, so that the AI ​​agent model outputs the target fault causes and hidden faults.

[0031] In another possible implementation, the verification method may also be implemented using a preset verification algorithm. The processing logic of the preset verification algorithm will be introduced in more detail in subsequent embodiments and will not be described here.

[0032] Step 04: Generate a first troubleshooting task based on the target fault cause, and generate a shutdown instruction and a second troubleshooting task based on the hidden fault; Step 05: Send the first troubleshooting task to the corresponding faulty device, and send the second troubleshooting task and the shutdown command to the target device corresponding to the hidden fault. The shutdown command is used to control the target device to shut down and / or switch the target device to a backup device.

[0033] For the embodiment of the present application, each fault cause corresponds to a corresponding troubleshooting process and troubleshooting position. For example, if the fault cause is that the breaker hammer of the crusher cannot move, the troubleshooting process may be whether the reciprocating mechanical structure of the breaker hammer is intact, whether there is foreign matter blocking, whether the hydraulic oil supply pipeline of the breaker hammer is unobstructed, whether the power supply voltage of the crusher is sufficient, etc. A knowledge graph may be constructed in advance for each fault cause and the corresponding troubleshooting process. After determining the target fault cause and the hidden fault, the target fault cause and the hidden fault are searched in the knowledge graph to generate the corresponding first troubleshooting task and second troubleshooting task.

[0034] Furthermore, the first troubleshooting task is sent to the corresponding faulty device, or the on-duty device corresponding to the faulty device, to guide the on-site staff to troubleshoot the faulty device based on the first troubleshooting task. The second troubleshooting task is sent to the target device corresponding to the hidden fault or the on-duty device corresponding to the target device, to guide the on-site staff to troubleshoot the target device based on the second troubleshooting task. It should be noted that the target device can be the faulty device itself or other devices that have not failed. Therefore, before sending the second troubleshooting task, a shutdown command is first sent to the target device. After determining that the target device is shut down, the second troubleshooting task for the target device is sent.

[0035] In the above-mentioned monitoring method for safe operation of coal mines, the fault analysis component constructed by historical fault data can analyze the current fault data to obtain various estimated causes and probabilities, and in the scheme of this embodiment, the quality data of raw coal in the current production cycle is further introduced. On the one hand, the introduction of quality data makes the fault analysis no longer completely dependent on historical data, but can dynamically adjust the estimated results according to the current production conditions, which improves the accuracy of fault location, facilitates to obtain more accurate target fault causes, and makes fault handling more in line with the actual situation of the current production cycle; on the other hand, not only pays attention to the current fault data that has occurred, but also identifies possible hidden faults by comparing the quality data with the estimated results, thereby generating the first troubleshooting task and the second troubleshooting task based on the target fault cause and the hidden fault cause to troubleshoot the relevant equipment, thereby reducing the probability of hidden faults hiding, reducing the risk of the raw coal pretreatment system during operation, thereby improving the safety of the raw coal pretreatment system during operation and reducing operational risks.

[0036] Furthermore, in an embodiment of the present application, the fault analysis component is a pre-trained neural network model, wherein each historical fault data is used as a training sample, and the initial LSTM (Long Short-Term Memory) model is trained to obtain a trained LSTM model, and the trained LSTM model is used as a fault analysis component. The LSTM model has a strong learning ability for time series data, so by using the LSTM model trained with historical fault data, the fault cause corresponding to the current fault data can be estimated from the perspective of the occurrence frequency corresponding to each fault type and / or fault phenomenon, thereby obtaining each estimated cause and the estimated probability corresponding to each estimated cause.

[0037] Further, in step 03, the estimated result is verified based on the quality data to obtain the target fault cause and the estimated hidden fault, and obtain the verification result, which may specifically include steps 031 to 033, such as Figure 3 As shown, where: Step 031: Determine the inducement data of the raw coal for each device based on the quality data. The inducement data is the probability of causing the equipment to fail due to various reasons.

[0038] Step 032, determine the cause data corresponding to the faulty equipment as the target cause data, and determine the product probability of each estimated cause from the target cause data, the product probability is the probability that the faulty equipment will have the estimated cause due to the raw coal of the quality data.

[0039] Different qualities of raw coal cause different degrees of damage to each device, and therefore, the resulting cause data for each device is also different. For example, when the raw coal is hard, the damage to the equipment in the crushing process is greater; when the raw coal contains more impurities, the damage to the equipment in the screening process is greater. In a possible example, when the hardness of the raw coal is high, for the crusher equipment, the probability of the reciprocating mechanical structure of the breaker breaking, the blockage of the hydraulic oil supply pipeline, and the unstable power supply voltage are reduced in turn.

[0040] Specifically, the cause data corresponding to the faulty equipment is determined as the target cause data, and then the probability corresponding to each estimated cause in the estimated result in the target cause data is determined, that is, the cause probability.

[0041] Step 033: Verify the estimated results based on the factor probability of each estimated cause to obtain the target fault cause and hidden fault.

[0042] Specifically, the product probability of each estimated cause is matched with the estimated probability of each estimated cause in the estimation result; that is, the estimated probability of each estimated cause and the product probability are weighted and multiplied together, and the estimated cause with the highest product of the product probability and the estimated probability is determined as the target fault cause. The product probability and the estimated probability of each estimated cause are screened based on the target threshold, and the estimated cause whose product probability and the estimated probability are both greater than the target threshold is determined as a hidden fault. Among them, when the estimated probability of each estimated cause and the product probability are weighted and multiplied together, the weight corresponding to the product probability is greater than the weight corresponding to the estimated probability. Furthermore, the target threshold can be 50%, of course, it can also be 70%, and it is not specifically limited in the embodiments of the present application.

[0043] The logic of the verification algorithm in the embodiment of the present application is: when a device fails, the several possible causes of the failure corresponding to the failure are fixed, but the probability of occurrence mainly depends on the quality data of the raw coal in the current production cycle. In other words, the possible estimated causes are first determined by the fault analysis component, but the weights of the estimated probabilities of several estimated causes in the estimated causes are reduced, and a larger weight is set for the product probability of each estimated cause determined based on the fault data, and then the most likely probability of each estimated cause is obtained, that is, the product of the product probability and the estimated probability; then the estimated cause with the highest product of the product probability and the estimated probability is determined as the target fault cause.

[0044] The method of the embodiment of the present application further refines the process of determining the cause of the fault by introducing quality data to verify the estimated results, and takes into account the influence of the raw coal quality on the probability of equipment failure, thereby improving the accuracy and efficiency of fault detection and making the fault analysis more in line with the actual production situation; and no matter how the quality of the raw coal changes, the method of the present embodiment can accurately judge the cause of the fault based on the quality data of the raw coal in the current production cycle, and has strong universality.

[0045] Furthermore, if the target fault cause coincides with the hidden cause, the hidden cause of the faulty device is set to 0; and further, the cause with the highest probability of the device failing is determined to be the hidden fault in the cause data of each device. That is, when the faulty device does not have a hidden fault, the hidden faults of other devices can be determined.

[0046] By calculating the probability of each estimated cause and combining it with the estimated probability, potential hidden faults can be identified. These hidden faults are often difficult to detect in conventional fault analysis, but their existence may cause potential risks to the system. Therefore, by identifying hidden faults, these hidden faults can be discovered and checked in time, thereby avoiding potential production safety accidents.

[0047] Further, refer to Figure 4 In step 031, the specific steps of determining the incentive data may include steps 0311 to 0314, wherein: 0311. Based on quality data, determine the required performance parameters of raw coal for each equipment.

[0048] 0312. Determine the baseline performance parameters of each device based on the mapping relationship table.

[0049] Specifically, determining the required performance parameters of raw coal for each device includes: collecting quality data of raw coal in the current production cycle, including coal block volume, hardness, impurity content, etc.; analyzing quality data: based on the quality data, analyzing the required performance parameters of raw coal for each device (such as crusher, screening machine, etc.). For example, raw coal with greater hardness may have higher requirements for the wear resistance and crushing force of the crusher; recording the required performance parameters, and recording the required performance parameters obtained by analysis in the first table.

[0050] An example of the first table is shown in Table 1.

[0051] Table 1 Device Name Required performance parameters Value / Range Crusher Coal hardness treatment 15Mpa Coal block volume 0.24m³ Screening Machine Coal block diameter 10cm Screening efficiency 70% … … … Specifically, according to the device type and model, a mapping relationship table of device benchmark performance parameters is established, and the table should include the device name, benchmark performance parameters and their values; for each device, its benchmark performance parameters are queried from the mapping relationship table.

[0052] 0313. Obtain the operating time of each device in the current cycle, and determine the degree of damage caused by the raw coal to each device based on the operating time of each device, the required performance parameters of the raw coal for each device, and the benchmark performance parameters of each device; Specifically, the operation log of each device in the current production cycle is obtained, and the operation time of each device in the current cycle is obtained from the operation log of each device. Based on the equipment operation time, the required performance parameters of the raw coal for the equipment, and the benchmark performance parameters of the equipment, the damage degree of the raw coal to each device is calculated, and then the calculated damage degree is recorded in the second table.

[0053] An example of the second table is shown in Table 2.

[0054] Table 2 Device Name Benchmark performance parameters Value / Range Crusher Maximum crushing hardness 13.5Mpa Maximum crushing volume 0.2m³ Screening Machine Maximum screening diameter 11cm Screening efficiency 70% … … … The degree of damage can be calculated by comparing the difference between the required performance parameters and the benchmark performance parameters and combining the simulation function of the running time. The simulation function can be a genetic algorithm function or a gradient descent function. The specific simulation function is not specifically limited in the embodiments of the present application.

[0055] 0314. Based on the degree of damage caused by raw coal to each equipment, determine the inducement data of raw coal to each equipment.

[0056] The incentive data is constructed in a table format, and the incentive data of each device is stored in a third table. An example of the third table is shown in Table 3.

[0057] Table 3 Device Name Cause Probability Crusher Breaker fracture 15% Hydraulic oil supply line is blocked 10% Unstable power supply voltage 5% Screening Machine Screen clogged 8% Vibration motor failure 2% … … … Furthermore, in order to improve the safety when executing troubleshooting tasks, step 05 may specifically include: sending a shutdown command to the target device corresponding to the hidden fault, and obtaining multiple monitoring images of the target device; based on the multiple monitoring images, determining whether the target device is shut down; when it is determined that the target device has been shut down, sending the first troubleshooting task to the corresponding faulty device, and sending the second troubleshooting task to the target device corresponding to the hidden fault.

[0058] Specifically, through multiple monitoring images, each monitoring image is grayscaled and binarized, and then each processed image is corner-recognized to mark the position data of the corner points in each image; the position data of the corner points in each image are compared for similarity, and when it is determined that the similarity of the position data of the corner points in at least a set number of images exceeds a set similarity threshold, the images are considered similar, and the equipment is determined to be shut down, that is, it is determined that the target equipment is shut down and no longer running.

[0059] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0060] Based on the same inventive concept, the embodiment of the present application also provides a monitoring device for coal mine safety operation for implementing the monitoring method for coal mine safety operation involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more monitoring devices for coal mine safety operation provided below can refer to the limitations of the monitoring method for coal mine safety operation above, and will not be repeated here.

[0061] In an exemplary embodiment, Figure 5 As shown, a monitoring device for coal mine safety operation is provided, the device includes a preprocessing module 501, a quality data acquisition module 502, a verification module 503, a task generation module 504 and a sending module 505, wherein: The preprocessing module 501 is used to call the fault analysis component to process the fault data when the fault data is acquired, and obtain the estimated result corresponding to the fault data. The fault data includes the fault device, the fault phenomenon and the fault occurrence time. The estimated result includes at least one estimated cause and the estimated probability of each estimated cause. The fault analysis component is pre-built based on the historical fault data; The quality data acquisition module 502 is used to acquire the quality data of the raw coal in the current production cycle, and the quality data at least includes the volume, hardness and impurity content of the coal block; A verification module 503 is used to verify the prediction result based on the quality data to obtain the target fault cause and hidden fault; A task generation module 504, used to generate a first troubleshooting task based on the target fault cause, and to generate a shutdown instruction and a second troubleshooting task based on the hidden fault; The sending module 505 is used to send the first troubleshooting task to the corresponding faulty device, and send the second troubleshooting task and the shutdown instruction to the target device corresponding to the hidden fault, and the shutdown instruction is used to control the target device to shut down and / or switch the target device to a backup device.

[0062] In one embodiment, when the sending module 505 sends the first troubleshooting task to the corresponding faulty device and sends the second troubleshooting task and the shutdown instruction to the target device corresponding to the hidden fault, it is specifically used to: Send a shutdown command to the target device corresponding to the hidden fault, and obtain multiple monitoring images of the target device; Determine whether the target equipment is down based on multiple monitoring images; When it is determined that the target device has been shut down, the first troubleshooting task is sent to the corresponding faulty device, and the second troubleshooting task is sent to the target device corresponding to the hidden fault.

[0063] In one embodiment, the verification module 503 verifies the prediction result based on the quality data to obtain the target fault cause and the predicted hidden fault, and when the verification result is obtained, is specifically used to: Determine the inducement data of raw coal to each device based on the quality data, where the inducement data is the probability of the equipment failing due to various reasons; Determine the cause data corresponding to the faulty equipment as the target cause data, and determine the product probability of each estimated cause from the target cause data. The product probability is the probability that the faulty equipment will have the estimated cause due to the raw coal of the quality data; The estimated results are checked based on the product probability of each estimated cause to obtain the target fault cause and hidden fault.

[0064] In one embodiment, when the verification module 503 verifies the prediction result based on the product probability of each predicted cause to obtain the target fault cause and the hidden fault, it is specifically used to: Match the factor probability based on each estimated cause with the estimated probability of each estimated cause in the estimated result; The estimated cause with the highest product of the product probability and the estimated probability is determined as the target failure cause; The estimated causes whose product probability and estimated probability are both greater than the target threshold are determined as hidden faults.

[0065] In one embodiment, the verification module 503 is further configured to: It is determined that among the cause data of each device, the cause with the highest probability of causing the device to fail is the hidden failure.

[0066] In one embodiment, when determining the inducement data of raw coal to each device based on the quality data, the verification module 503 is specifically used to: Based on the quality data, determine the performance parameters required by each equipment for raw coal; Determine the baseline performance parameters of each device based on the mapping relationship table; Obtain the operating time of each device in the current cycle, and determine the degree of damage caused by the raw coal to each device based on the operating time of each device, the required performance parameters of the raw coal for each device, and the baseline performance parameters of each device; Based on the degree of damage caused by raw coal to each equipment, determine the inducement data of raw coal to each equipment.

[0067] In one embodiment, the method further includes a training module, wherein the training module is specifically configured to: Each historical fault data is used as a training sample to train the initial LSTM model to obtain a trained LSTM model, and the trained LSTM model is used as a fault analysis component.

[0068] Each module in the above-mentioned coal mine safety operation monitoring device can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the control device in the form of hardware, or can be stored in the memory in the control device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0069] In an exemplary embodiment, a monitoring system is provided; wherein the monitoring system at least includes a monitoring device, a data acquisition device and a control device, wherein: the monitoring device is used to collect monitoring images of each device; the data acquisition device is used to collect quality data of raw coal in the current cycle, and the quality data at least includes the volume, hardness and impurity content of the coal block; the control device, the monitoring device and the data acquisition device can exchange information with the control device. Among them, the control device can be but not limited to various personal computers, laptops, smart phones, tablet computers, and can also be a server, etc.; the server can be implemented as an independent server or a server cluster composed of multiple servers.

[0070] Specifically, the internal structure diagram of the control device can be as follows: Figure 6 As shown. The control device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the control device is used to provide computing and control capabilities. The memory of the control device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the control device is used to store various data. The input / output interface of the control device is used to exchange information between the processor and an external device. The communication interface of the control device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the program steps of the monitoring method for coal mine safety operations as in any one of the above-mentioned method embodiments are implemented.

[0071] Those skilled in the art will understand that Figure 6 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the control device to which the scheme of the present application is applied. The specific control device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0072] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the program steps of the method for monitoring safe operations in a coal mine as described in any one of the above method embodiments are implemented.

[0073] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0074] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0075] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0076] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for monitoring coal mine safety operations, characterized in that: Applied to a monitoring system, the method comprises: When the fault data is acquired, the fault analysis component is called to process the fault data to obtain an estimation result corresponding to the fault data, wherein the fault data includes a faulty device, a fault phenomenon, and a fault occurrence time, and the estimation result includes at least one estimated cause and an estimated probability of each of the estimated causes, and the fault analysis component is pre-built based on historical fault data; Acquire quality data of raw coal in the current production cycle, wherein the quality data at least includes coal block volume, hardness and impurity content; Verifying the prediction result based on the quality data to obtain target fault causes and hidden faults; Generate a first troubleshooting task based on the target fault cause, and generate a shutdown instruction and a second troubleshooting task based on the hidden fault; The first troubleshooting task is sent to the corresponding faulty device, and the second troubleshooting task and the shutdown instruction are sent to the target device corresponding to the hidden fault, and the shutdown instruction is used to control the target device to shut down and / or switch the target device to a backup device.

2. The method according to claim 1, characterized in that The sending the first troubleshooting task to the corresponding faulty device, and sending the second troubleshooting task and the shutdown instruction to the target device corresponding to the hidden fault, includes: Sending the shutdown command to the target device corresponding to the hidden fault, and acquiring multiple monitoring images of the target device; Based on the multiple monitoring images, determining whether the target device is shut down; When it is determined that the target device has been shut down, the first troubleshooting task is sent to the corresponding faulty device, and the second troubleshooting task is sent to the target device corresponding to the hidden fault.

3. The method according to claim 1, characterized in that The step of verifying the prediction result based on the quality data to obtain target fault causes and hidden faults includes: Determine the inducement data of the raw coal to each device based on the quality data, wherein the inducement data is the probability of causing the device to fail due to various reasons; Determine the inducement data corresponding to the faulty equipment as target inducement data, and determine the product-cause probability of each of the estimated causes from the target inducement data, wherein the product-cause probability is the probability that the faulty equipment will have the estimated cause due to the raw coal of the quality data; The estimated results are checked based on the factor probability of each estimated cause to obtain the target fault cause and hidden fault.

4. The method according to claim 3, characterized in that: The step of verifying the estimated result based on the factor probability of each estimated cause to obtain the target fault cause and hidden fault includes: Matching the factor probability based on each of the estimated causes with the estimated probability of each of the estimated causes in the estimated result; Determine the target fault cause by taking the estimated cause with the highest product of the factor probability and the estimated probability; An estimated cause whose product probability and estimated probability are both greater than a target threshold is determined as a hidden fault.

5. The method according to claim 3, characterized in that: The method further comprises: It is determined that among the cause data of each device, the cause with the highest probability of causing the device to fail is a hidden failure.

6. The method according to any one of claims 3 to 5, characterized in that: The determining the inducement data of the raw coal to each device based on the quality data includes: Based on the quality data, determining the required performance parameters of each device for the raw coal; Determine the baseline performance parameters of each device based on the mapping relationship table; Obtaining the operating time of each device in the current cycle, and determining the degree of damage caused by the raw coal to each device based on the operating time of each device, the required performance parameter of the raw coal for each device, and the benchmark performance parameter of each device; Based on the degree of damage caused by the raw coal to each device, the inducement data of the raw coal to each device is determined.

7. The method according to any one of claims 1 to 5, characterized in that The method further comprises: Each of the historical fault data is used as a training sample to train the initial LSTM model to obtain a trained LSTM model, and the trained LSTM model is used as a fault analysis component.

8. A monitoring device for coal mine safety operation, characterized in that: The device includes a preprocessing module, a quality data acquisition module, a verification module, a task generation module and a sending module, wherein: A preprocessing module, configured to, when acquiring fault data, call a fault analysis component to process the fault data to obtain an estimated result corresponding to the fault data, wherein the fault data includes a faulty device, a fault phenomenon, and a time of occurrence of the fault, and the estimated result includes at least one estimated cause and an estimated probability of each of the estimated causes, and the fault analysis component is pre-built based on historical fault data; A quality data acquisition module, used to acquire the quality data of raw coal in the current production cycle, wherein the quality data at least includes the volume, hardness and impurity content of the coal block; A verification module, used to verify the prediction result based on the quality data to obtain target fault causes and hidden faults; A task generation module, used to generate a first troubleshooting task based on the target fault cause, and to generate a shutdown instruction and a second troubleshooting task based on the hidden fault; A sending module is used to send the first troubleshooting task to the corresponding faulty device, and send the second troubleshooting task and the shutdown instruction to the target device corresponding to the hidden fault, and the shutdown instruction is used to control the target device to shut down and / or switch the target device to a backup device.

9. A monitoring system, characterized in that: The system comprises: Monitoring equipment, used to collect monitoring images of various devices; Data collection equipment, used to collect quality data of raw coal in the current cycle, the quality data at least including coal block volume, hardness and impurity content; A control device, the monitoring device and the data acquisition device can both exchange information with the control device; The control device is used to execute the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images