A method, device, system, and medium for monitoring safe operations in coal mines.

Abstract

This application relates to a monitoring method, device, system, and medium for safe coal mine operations. Applied to a monitoring system, the method includes: upon acquiring fault data, calling a fault analysis component to process the fault data and obtain a corresponding estimated result; acquiring raw coal quality data within the current production cycle, the quality data including at least coal lump volume, hardness, and impurity content; verifying the estimated result based on the quality data to obtain the target fault cause and latent fault; generating a first investigation task based on the target fault cause, and generating a shutdown command and a second investigation task based on the latent fault; sending the first investigation task to the corresponding faulty equipment, and sending the second investigation task and shutdown command to the target equipment corresponding to the latent fault. This method can reduce the operational risks of raw coal pretreatment systems.

Description

Technical Field

[0001] This application relates to the technical field of coal mining, and in particular to a method, device, system and medium for monitoring safe operations in coal mines. Background Technology

[0002] Coal has always been an important resource in industry, and the demand for coal in daily production and life is increasing day by day. Currently, raw coal mined in coal mines needs to undergo preliminary processing before being transported to various places by vehicles. Preliminary processing includes processes such as washing, crushing, and screening. Washing mainly removes impurities such as gangue from the raw coal, crushing breaks larger coal lumps into smaller particles for easier transportation and storage, and screening separates the coal lumps into particles. With the development of digitalization, more and more coal mines are using automated systems to achieve preliminary processing of raw coal, greatly improving processing efficiency.

[0003] In related technologies, when equipment malfunctions in a particular process, a trained fault analysis model is typically used to analyze the fault phenomenon. The fault analysis results output by the model are then used to troubleshoot the problem and determine the possible causes of the current fault. However, the quality of coal mined in a coal mine varies over time. For example, some stages of mining may involve coal seams with high gangue content and large coal chunks, while others may involve coal seams with low gangue content and small coal chunks. Therefore, the causes of the same fault in a system may differ at different stages, and some stages may even contain potential, latent faults. Using a fault analysis model trained on historical data to analyze the current fault can only predict the cause of the current fault but cannot detect potential faults, leading to potential operational risks during system operation.

[0004] Therefore, how to reduce the operational risks of raw coal pretreatment systems is an urgent problem to be solved. Summary of the Invention

[0005] Therefore, it is necessary to provide a monitoring method, device, system, and medium for coal mine safety operations that can reduce the operational risks of raw coal pretreatment systems, in order to address the aforementioned technical problems.

[0006] Firstly, this application provides a method for monitoring safe operations in coal mines, applied to a monitoring system, the method comprising:

[0007] When fault data is acquired, the fault analysis component is invoked to process the fault data and obtain the prediction result corresponding to the fault data. The fault data includes the faulty equipment, the fault phenomenon and the fault occurrence time. The prediction result includes at least one predicted cause and the predicted probability of each predicted cause. The fault analysis component is pre-built based on historical fault data.

[0008] Obtain the quality data of raw coal within the current production cycle, wherein the quality data includes at least the coal lump volume, hardness, and impurity content;

[0009] The predicted results are verified based on the quality data to obtain the target fault causes and latent faults.

[0010] A first investigation task is generated based on the target fault cause, and a shutdown command and a second investigation task are generated based on the hidden fault.

[0011] The first troubleshooting task is sent to the corresponding faulty device, and the second troubleshooting task and the shutdown command are sent to the target device corresponding to the latent fault. The shutdown command is used to control the target device to shut down and / or switch the target device to a standby device.

[0012] In one embodiment, sending the first troubleshooting task to the corresponding faulty device and sending the second troubleshooting task and the shutdown command to the target device corresponding to the latent fault includes:

[0013] The shutdown command is sent to the target device corresponding to the latent fault, and multiple monitoring images of the target device are acquired.

[0014] Based on the multiple surveillance images, determine whether the target device is shut down;

[0015] 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 latent fault.

[0016] In one embodiment, the step of verifying the predicted results based on the quality data to obtain the target fault cause and latent fault includes:

[0017] Based on the quality data, the causal data of the raw coal on each piece of equipment is determined, wherein the causal data is the probability that the equipment will fail due to each cause.

[0018] The causal data corresponding to the faulty equipment is determined as the target causal data, and the causal probability of each of the estimated causes is determined from the target causal data. The causal probability is the probability that the faulty equipment will have the estimated cause due to the raw coal of the quality data.

[0019] The prediction results are verified based on the probability of each predicted cause to obtain the target fault cause and the latent fault.

[0020] In one embodiment, the step of verifying the prediction results based on the probability of each of the predicted causes to obtain the target fault cause and the latent fault includes:

[0021] The probability of each of the predicted causes is matched with the predicted probability of each of the predicted causes in the prediction results.

[0022] The predicted cause with the highest product of the product probability and the predicted probability is determined as the target fault cause;

[0023] The predicted cause where both the probability of the fault and the estimated probability are greater than the target threshold is identified as a latent fault.

[0024] In one embodiment, the method further includes:

[0025] Among the causes of each device, the cause with the highest probability of device failure is identified as a latent fault.

[0026] In one embodiment, determining the causal data of the raw coal on each piece of equipment based on the quality data includes:

[0027] Based on the quality data, the required performance parameters of the raw coal for each piece of equipment are determined;

[0028] The baseline performance parameters of each device are determined based on the mapping relationship table.

[0029] The operating time of each device in the current cycle is obtained, and the degree of damage to each device by the raw coal is determined based on the operating time of each device, the performance parameters required by the raw coal for each device, and the baseline performance parameters of each device.

[0030] Based on the degree of damage caused by the raw coal to each piece of equipment, the causal data of the raw coal to each piece of equipment are determined.

[0031] In one embodiment, the method further includes:

[0032] Each historical fault data point is used as a training sample to train the initial LSTM model, resulting in a trained LSTM model, which serves as a fault analysis component.

[0033] Secondly, this application also provides a monitoring device for safe operation in coal mines, the device comprising a preprocessing module, a quality data acquisition module, a verification module, a task generation module, and a sending module, wherein:

[0034] The preprocessing module is used to call the fault analysis component to process the fault data when the fault data is acquired, and to obtain the prediction result corresponding to the fault data. The fault data includes the faulty equipment, the fault phenomenon and the fault occurrence time. The prediction result includes at least one predicted cause and the predicted probability of each predicted cause. The fault analysis component is pre-built based on historical fault data.

[0035] The quality data acquisition module is used to acquire the quality data of raw coal within the current production cycle. The quality data includes at least the coal block volume, hardness, and impurity content.

[0036] The verification module is used to verify the predicted results based on the quality data to obtain the target fault cause and hidden fault.

[0037] The task generation module is used to generate a first investigation task based on the target fault cause, and to generate a shutdown command and a second investigation task based on the hidden fault.

[0038] The sending module is used to send the first troubleshooting task to the corresponding faulty device, and to send the second troubleshooting task and the shutdown command to the target device corresponding to the latent fault. The shutdown command is used to control the target device to shut down and / or switch the target device to a standby device.

[0039] Thirdly, this application also provides a monitoring system, the system comprising:

[0040] Monitoring equipment, used to collect monitoring images from various devices;

[0041] Data acquisition equipment is used to collect the quality data of raw coal in the current period, and the quality data includes at least the coal volume, hardness and impurity content;

[0042] The control device, the monitoring device and the data acquisition device are both capable of information interaction with the control device;

[0043] The control device is used to perform the steps of the method as described in any one of the first aspects above.

[0044] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method as described in any one of the first aspects above.

[0045] The aforementioned monitoring methods, devices, systems, and media for coal mine safety operations utilize a fault analysis component built from historical fault data. This component analyzes current fault data to obtain various estimated causes and probabilities. Furthermore, this solution incorporates raw coal quality data from the current production cycle. On one hand, the introduction of quality data allows fault analysis to move beyond solely relying on historical data, enabling dynamic adjustments to the estimated results based on current production conditions. This improves the accuracy of fault location, facilitates obtaining more precise target fault causes, and makes fault handling more aligned with the actual situation of the current production cycle. On the other hand, it not only focuses on currently occurring fault data but also identifies potential latent faults by comparing quality data with estimated results. Based on the target fault cause and the latent fault cause, it generates a first investigation task and a second investigation task to investigate related equipment. This reduces the probability of latent faults being hidden, lowers the operational risk of the raw coal pretreatment system, and thus improves the operational safety of the raw coal pretreatment system and reduces operational risks. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is a schematic diagram of the monitoring system in one embodiment;

[0048] Figure 2 This is a flowchart illustrating a method for monitoring safe operations in a coal mine, as shown in one embodiment.

[0049] Figure 3 This is a flowchart illustrating the steps for determining the verification result in one embodiment;

[0050] Figure 4 This is a flowchart illustrating the steps for determining trigger data in one embodiment;

[0051] Figure 5 This is a structural block diagram of a monitoring device for safe operation in a coal mine, as shown in one embodiment.

[0052] Figure 6 This is an internal structure diagram of the control device in a monitoring system in one embodiment. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0054] The coal mine safety operation monitoring method provided in this application embodiment can be applied to, for example, Figure 1 The monitoring system shown includes at least monitoring equipment, data acquisition equipment, and control equipment. The monitoring equipment collects images from various devices; the data acquisition equipment collects quality data of the raw coal for the current period, including at least coal volume, hardness, and impurity content; and the control equipment allows the monitoring and data acquisition equipment to interact with each other. The control equipment can be, but is not limited to, various personal computers, laptops, smartphones, tablets, or servers. The server can be a standalone server or a server cluster.

[0055] In one exemplary embodiment, such as Figure 2 As shown, a method for monitoring safe operations in coal mines is provided, which can be applied to... Figure 1 The following is an example of a monitoring system in a control system, executed by control equipment within the control system, including the following steps 01-05:

[0056] Step 01: When fault data is obtained, the fault analysis component is called to process the fault data and obtain the corresponding prediction results. The fault data includes the faulty equipment, fault phenomenon and fault occurrence time. The prediction results include at least one predicted cause and the predicted probability of each predicted cause. The fault analysis component is pre-built based on historical fault data.

[0057] In this embodiment, fault data can be obtained from fault logs generated by faulty equipment in the raw coal pretreatment system, or it can be input by the user. This embodiment does not specifically limit the method of obtaining fault data. Fault data typically consists of various fault codes. Therefore, after obtaining the fault data, it is first parsed based on a preset fault code identification form to obtain the faulty equipment, fault phenomenon, and fault occurrence time represented by the fault data.

[0058] The fault analysis component is built based on historical fault data of various equipment in the raw coal pretreatment system. The fault analysis component can be a trained neural network model, or it can be a plugin or script configured based on a probability distribution algorithm that can call historical fault data to analyze current fault data. This embodiment does not specifically limit its capabilities. Since the fault analysis component relies on historical fault data, it can analyze current fault data and thus determine various estimated causes of the fault phenomenon.

[0059] Step 02: Obtain the quality data of raw coal within the current production cycle. The quality data should include at least the coal block volume, hardness, and impurity content.

[0060] In the embodiments of this application, since the quality of raw coal mined from different locations or each seam is basically consistent, the production cycle can be determined based on the location of the mined raw coal or the seam cross section; of course, the production cycle can also be a fixed period of time, such as 1 month. In the embodiments of this application, the method of dividing the production cycle is not specifically limited.

[0061] The quality data of raw coal can be obtained by data acquisition equipment in the monitoring system. For example, by deploying dust concentration detectors at the crushing equipment in the raw coal pretreatment system, coal blocks with lower hardness will generate more dust when crushed, while coal blocks with higher hardness will generate less dust. Therefore, the hardness of the raw coal can be determined by the dust concentration. Alternatively, images of the coal blocks after screening can be acquired, and texture, shape, and color features can be identified for each image. Based on these features, the distribution ratio of coal blocks and impurities (gangue) in each image can be determined, and the impurity content in each image can be determined based on this distribution ratio. Furthermore, the impurity content of multiple images can be averaged to determine the total impurity content of the raw coal.

[0062] Of course, the quality data of raw coal can also be input by the user, and this application embodiment does not impose specific limitations.

[0063] Step 03: Verify the predicted results based on the quality data to obtain the target fault causes and latent faults.

[0064] In this embodiment of the application, the fault analysis component built based on historical data can only predict the cause of the current fault, making it difficult to discover some potential faults. However, by further verifying the predicted results obtained by the fault analysis component using the acquired raw coal quality data, the predicted cause that is more consistent with the raw coal quality within the current production cycle can be determined as the target fault cause. Furthermore, by combining the raw coal quality data within the current production cycle, some latent faults that have not yet appeared can also be discovered.

[0065] In one possible implementation, the verification can be achieved using an AI agent model. For example, an experience database can be pre-built with relevant equipment and knowledge from the coal mining and raw coal pretreatment stages, and the AI ​​agent model can be trained using this database. The predicted results and raw coal quality data are then input into the AI ​​agent model, enabling it to output the target fault causes and latent faults.

[0066] In another possible implementation, the verification method can also be implemented using a preset verification algorithm. The processing logic of the preset verification algorithm will be described in more detail in subsequent embodiments, and will not be repeated here.

[0067] Step 04: Generate the first troubleshooting task based on the cause of the target fault, and generate a shutdown command and a second troubleshooting task based on the hidden fault;

[0068] Step 05: Send the first troubleshooting task to the corresponding faulty device, and send the second troubleshooting task and shutdown command to the target device corresponding to the latent fault. The shutdown command is used to control the target device to shut down and / or switch the target device to the standby device.

[0069] In the embodiments of this application, each fault cause corresponds to a specific troubleshooting procedure and location. For example, if the fault cause is that the crusher's hammer cannot move, the troubleshooting procedures could be, in sequence, checking the integrity of the hammer's reciprocating mechanical structure, whether there are any foreign objects blocking it, whether the hydraulic oil supply line of the hammer is unobstructed, and whether the crusher's power supply voltage is sufficient. Each fault cause and its corresponding troubleshooting procedure can be pre-constructed using a knowledge graph. After determining the target fault cause and the latent fault, a search is performed in the knowledge graph based on the target fault cause and the latent fault, respectively, to generate the corresponding first and second troubleshooting tasks.

[0070] Furthermore, the first troubleshooting task is sent to the corresponding faulty device or the monitoring device corresponding to the faulty device to guide on-site personnel to troubleshoot the faulty device based on the first troubleshooting task. The second troubleshooting task is sent to the target device corresponding to the latent fault or the monitoring device corresponding to the target device to guide on-site personnel 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 experienced a fault. Therefore, before sending the second troubleshooting task, a shutdown command is first sent to the target device. After confirming that the target device is shut down, the second troubleshooting task for the target device is then sent.

[0071] In the aforementioned monitoring method for safe coal mine operations, the fault analysis component constructed from historical fault data can analyze current fault data to obtain various estimated causes and probabilities. Furthermore, in this embodiment, the quality data of raw coal within the current production cycle is introduced. On the one hand, the introduction of quality data means that fault analysis no longer relies entirely on historical data, but can dynamically adjust the estimated results according to current production conditions. This improves the accuracy of fault location, facilitates obtaining more accurate target fault causes, and makes fault handling more aligned with the actual situation of the current production cycle. On the other hand, it not only focuses on the fault data that has already occurred, but also identifies potential hidden faults by comparing quality data with estimated results. Based on the target fault cause and the hidden fault cause, a first investigation task and a second investigation task are generated to investigate the relevant equipment, thereby reducing the probability of hidden faults and lowering the risk of the raw coal pretreatment system during operation. This improves the safety of the raw coal pretreatment system during operation and reduces operational risks.

[0072] Furthermore, in this embodiment, the fault analysis component is a pre-trained neural network model. Each historical fault data point is used as a training sample to train an initial LSTM (Long Short-Term Memory) model, resulting in a trained LSTM model, which serves as the fault analysis component. The LSTM model has strong learning capabilities for time-series data. Therefore, by using an LSTM model trained with historical fault data, it is possible to predict the fault causes corresponding to the current fault data from the perspective of the frequency of occurrence of each fault type and / or fault phenomenon, thereby obtaining each predicted cause and its corresponding predicted probability.

[0073] Further, in step 03, the predicted results are verified based on the quality data to obtain the target fault cause and the predicted hidden fault, thus obtaining the verification result. This can specifically include steps 031-033, such as... Figure 3 As shown, where:

[0074] Step 031: Determine the causal data of raw coal on each piece of equipment based on the quality data. The causal data is the probability that the equipment will fail due to each cause.

[0075] Step 032: Determine the causal data corresponding to the faulty equipment as the target causal data, and determine the causal probability of each predicted cause from the target causal data. The causal probability is the probability that the faulty equipment will have a predicted cause due to the raw coal in the quality data.

[0076] Different qualities of raw coal cause varying degrees of damage to different equipment, resulting in different causal data for each piece of equipment. For example, higher hardness of raw coal leads to greater damage to equipment in the crushing process; higher impurity content in raw coal leads to greater damage to equipment in the screening process. In one possible example, when the raw coal is hard, the probability of failure for the crusher equipment is decreasing in the following order: fracture of the reciprocating mechanical structure of the breaker hammer, blockage of the hydraulic oil supply line, and unstable power supply voltage.

[0077] Specifically, the data corresponding to the faulty equipment is identified as the target cause data, and then the probability of each predicted cause in the prediction results corresponding to the target cause data is determined, which is the cause probability.

[0078] Step 033: Verify the prediction results based on the probability of each predicted cause to obtain the target fault cause and the latent fault.

[0079] Specifically, the probability of each predicted cause is matched with the predicted probability of each predicted cause in the prediction results; that is, the predicted probability and the probability of each predicted cause are multiplied by weight, and the predicted cause with the highest product of the probability of the cause and the predicted probability is determined as the target fault cause. The probability of each predicted cause and the predicted probability of the cause are then filtered based on a target threshold; predicted causes whose probability of the cause and the predicted probability are both greater than the target threshold are determined as latent faults. When multiplying the predicted probability and the probability of the cause for each predicted cause by weight, the weight corresponding to the probability of the cause is greater than the weight corresponding to the predicted probability. Further, the target threshold can be 50%, or it can be 70%, and this embodiment does not impose a specific limitation.

[0080] The logic of the verification algorithm in this embodiment is as follows: When a device malfunctions, the possible causes of the malfunction are fixed, but the probability of occurrence depends mainly on the quality data of the raw coal in the current production cycle. That is, the possible predicted causes are first determined through the fault analysis component, but the weight of the predicted probabilities of several predicted causes is reduced. By assigning a larger weight to the probability of each predicted cause determined based on the fault data, the most likely probability of each predicted cause is obtained, which is the product of the probability of the cause and the predicted probability. Then, the predicted cause with the highest product of the probability of the cause and the predicted probability is determined as the target malfunction cause.

[0081] The method in this embodiment of the application further refines the process of determining the cause of failure by introducing quality data to verify the estimated results, and considers the impact of raw coal quality on the probability of equipment failure, thereby improving the accuracy and efficiency of fault diagnosis and making the fault analysis more in line with the actual production situation; and no matter how the quality of raw coal changes, the method in this embodiment can accurately judge the cause of failure based on the quality data of raw coal in the current production cycle, and has strong universality.

[0082] Furthermore, if the target fault cause overlaps with the latent cause, the latent cause of the faulty device is set to 0; and further, the cause with the highest probability of causing the device to fail is identified from the causative data of each device as the latent fault. In other words, if the faulty device does not have a latent fault, the latent faults of other devices can be identified.

[0083] By calculating the causal probability of each predicted cause and combining it with the predicted probabilities, potential latent faults can be identified. These latent faults are often difficult to detect in conventional fault analysis, but their existence may pose potential risks to the system. Therefore, identifying latent faults allows for their timely discovery and resolution, thereby preventing potential production safety accidents.

[0084] Furthermore, referring to Figure 4 In step 031, the specific steps for determining the trigger data may include steps 0311-0314, wherein:

[0085] 0311. Based on quality data, determine the required performance parameters of raw coal for each piece of equipment.

[0086] 0312. Determine the baseline performance parameters of each device based on the mapping relationship table.

[0087] Specifically, determining the required performance parameters for each piece of equipment for raw coal includes: collecting raw coal quality data during the current production cycle, including coal lump volume, hardness, and impurity content; analyzing the quality data: based on the quality data, analyzing the required performance parameters for each piece of equipment (such as crushers, screening machines, etc.). For example, harder raw coal may require higher wear resistance and crushing force from the crusher; recording the required performance parameters, and recording the analyzed required performance parameters in the first table.

[0088] One example of the first table is shown in Table 1.

[0089] Table 1

[0090] Equipment Name Demand performance parameters Value / Range crusher Processing coal hardness 15Mpa Processing coal volume 0.24m³ Screening machine coal block diameter 10cm Screening efficiency 70% … … …

[0091] Specifically, a mapping table of equipment baseline performance parameters is established based on the equipment type and model. This table should include the equipment name, baseline performance parameters and their values. For each piece of equipment, its baseline performance parameters are queried from the mapping table.

[0092] 0313. Obtain the running time of each device in the current cycle, and determine the degree of damage to each device by the raw coal based on the running time of each device, the performance parameters required by the raw coal for each device, and the baseline performance parameters of each device.

[0093] Specifically, the operation logs of each piece of equipment during the current production cycle are obtained, and the operating time of each piece of equipment during the current cycle is obtained from the operation logs of each piece of equipment. Based on the equipment operating time, the performance parameters required by raw coal for the equipment, and the baseline performance parameters of the equipment, the degree of damage caused by raw coal to each piece of equipment is calculated, and then the calculated degree of damage is recorded in the second table.

[0094] An example of the second table is shown in Table 2.

[0095] Table 2

[0096] Equipment Name Baseline performance parameters Value / Range crusher Maximum crushing hardness 13.5 MPa Maximum crushing volume 0.2m³ Screening machine Maximum sieve diameter 11cm Screening efficiency 70% … … …

[0097] The degree of damage can be calculated by comparing the difference between the required performance parameters and the baseline performance parameters, and by combining the simulation function of the runtime. 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 this application.

[0098] 0314. Based on the degree of damage to each piece of equipment caused by raw coal, determine the causal data of raw coal on each piece of equipment.

[0099] The trigger data is constructed in tabular format, with the trigger data for each device stored in a third table. An example of the third table is shown in Table 3.

[0100] Table 3

[0101] Equipment Name Cause of the fault probability crusher Hydraulic breakage 15% Hydraulic oil supply line blockage 10% Unstable power supply voltage 5% Screening machine Screen clogging 8% Vibration motor failure 2% … … …

[0102] Furthermore, to enhance security during the execution of troubleshooting tasks, step 05 may specifically include: sending a shutdown command to the target device corresponding to the latent fault and acquiring multiple monitoring images of the target device; determining whether the target device is shut down based on the multiple monitoring images; and when it is determined that the target device is 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 latent fault.

[0103] Specifically, multiple monitoring images are processed by grayscale and binarization. Then, corner point recognition is performed on each processed image 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. 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, that is, the equipment is determined to be shut down, i.e., the target equipment is determined to be shut down and no longer running.

[0104] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0105] Based on the same inventive concept, this application also provides a coal mine safety operation monitoring device for implementing the coal mine safety operation monitoring method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more coal mine safety operation monitoring device embodiments provided below can be found in the limitations of the coal mine safety operation monitoring method described above, and will not be repeated here.

[0106] In one exemplary embodiment, such as Figure 5 As shown, a monitoring device for safe operation in a coal mine 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:

[0107] The preprocessing module 501 is used to call the fault analysis component to process the fault data when the fault data is acquired, and to obtain the prediction result corresponding to the fault data. The fault data includes the faulty equipment, the fault phenomenon and the fault occurrence time. The prediction result includes at least one predicted cause and the predicted probability of each predicted cause. The fault analysis component is pre-built based on historical fault data.

[0108] The quality data acquisition module 502 is used to acquire the quality data of raw coal in the current production cycle. The quality data includes at least the coal block volume, hardness, and impurity content.

[0109] Verification module 503 is used to verify the predicted results based on quality data to obtain the target fault causes and hidden faults;

[0110] The task generation module 504 is used to generate a first investigation task based on the cause of the target fault, and to generate a shutdown command and a second investigation task based on the hidden fault.

[0111] The sending module 505 is used to send the first troubleshooting task to the corresponding faulty device, and to send the second troubleshooting task and shutdown command to the target device corresponding to the latent fault. The shutdown command is used to control the target device to shut down and / or switch the target device to the standby device.

[0112] In one embodiment, when the sending module 505 sends the first troubleshooting task to the corresponding faulty device and the second troubleshooting task and shutdown command to the target device corresponding to the latent fault, it is specifically used for:

[0113] The shutdown command is sent to the target device corresponding to the latent fault, and multiple monitoring images of the target device are acquired.

[0114] Based on multiple surveillance images, determine whether the target device is shut down;

[0115] 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 latent fault.

[0116] In one embodiment, when the verification module 503 verifies the prediction results based on quality data to obtain the target fault cause and the predicted hidden fault, and obtains the verification result, it is specifically used for:

[0117] Based on quality data, determine the causal data of raw coal on each piece of equipment. The causal data is the probability that the equipment will fail due to various reasons.

[0118] The data corresponding to the faulty equipment is identified as the target cause data, and the probability of each predicted cause is determined from the target cause data. The probability of each cause is the probability that the faulty equipment will have a predicted cause due to the raw coal with quality data.

[0119] The prediction results are verified based on the probability of each predicted cause to obtain the target failure cause and the hidden failure.

[0120] In one embodiment, when the verification module 503 verifies the prediction results based on the probability of each predicted cause to obtain the target fault cause and the latent fault, it is specifically used for:

[0121] The probability of each predicted cause is matched with the predicted probability of each predicted cause in the prediction results.

[0122] The predicted cause with the highest product of the product probability and the predicted probability is identified as the target cause of failure.

[0123] The predicted cause, where both the probability of the fault and the estimated probability are greater than the target threshold, is identified as a latent fault.

[0124] In one embodiment, the verification module 503 is further configured to:

[0125] Among the identified causes of equipment failure, latent faults are the most likely to cause equipment malfunctions.

[0126] In one embodiment, when determining the causal data of raw coal on each piece of equipment based on quality data, the verification module 503 is specifically used for:

[0127] Based on quality data, determine the required performance parameters of raw coal for each piece of equipment;

[0128] The baseline performance parameters of each device are determined based on the mapping relationship table.

[0129] The operating time of each device in the current cycle is obtained, and the degree of damage to each device by the raw coal is determined based on the operating time of each device, the performance parameters required by the raw coal for each device, and the baseline performance parameters of each device.

[0130] Based on the degree of damage caused by raw coal to each piece of equipment, the causal data of raw coal to each piece of equipment are determined.

[0131] In one embodiment, the method further includes a training module, which is specifically used for:

[0132] Each historical fault data point is used as a training sample to train the initial LSTM model, resulting in a trained LSTM model, which is then used as a fault analysis component.

[0133] The modules in the aforementioned coal mine safety operation monitoring device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the control device in hardware form or independent of it, or stored in the memory of the control device in software form, so that the processor can call and execute the corresponding operations of each module.

[0134] In one exemplary embodiment, a monitoring system is provided; wherein the monitoring system includes at least monitoring equipment, data acquisition equipment, and control equipment, wherein: the monitoring equipment is used to acquire monitoring images from various devices; the data acquisition equipment is used to acquire quality data of raw coal within the current period, the quality data including at least coal volume, hardness, and impurity content; and the control equipment is capable of information interaction between the monitoring equipment and the data acquisition equipment. The control equipment may be, but is not limited to, various personal computers, laptops, smartphones, tablets, or servers; the server may be a standalone server or a server cluster composed of multiple servers.

[0135] Specifically, the internal structure diagram of the control equipment can be as follows: Figure 6 As shown, the control device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores various data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements the program steps of any of the coal mine safety operation monitoring methods described in the above embodiments.

[0136] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the control device to which the present application is applied. The specific control device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0137] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the program steps of any of the coal mine safety operation monitoring methods described in the above method embodiments.

[0138] 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, data stored, data displayed, 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 the relevant data must comply with relevant regulations.

[0139] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this 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), magnetic 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. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0140] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0141] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for monitoring safe operations in coal mines, characterized in that, Applied to a monitoring system, the method includes: When fault data is acquired, the fault analysis component is invoked to process the fault data and obtain the prediction result corresponding to the fault data. The fault data includes the faulty equipment, the fault phenomenon and the fault occurrence time. The prediction result includes at least one predicted cause and the predicted probability of each predicted cause. The fault analysis component is pre-built based on historical fault data. Obtain the quality data of raw coal within the current production cycle, wherein the quality data includes at least the coal lump volume, hardness, and impurity content; The predicted results are verified based on the quality data to obtain the target fault causes and latent faults. A first investigation task is generated based on the target fault cause, and a shutdown command and a second investigation task are generated based on the hidden fault. The first troubleshooting task is sent to the corresponding faulty device, and the second troubleshooting task and the shutdown command are sent to the target device corresponding to the latent fault. The shutdown command is used to control the target device to shut down and / or switch the target device to a standby device.

2. The method according to claim 1, characterized in that, The step of sending the first troubleshooting task to the corresponding faulty device and sending the second troubleshooting task and the shutdown command to the target device corresponding to the latent fault includes: The shutdown command is sent to the target device corresponding to the latent fault, and multiple monitoring images of the target device are acquired. Based on the multiple surveillance images, determine 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 latent fault.

3. The method according to claim 1, characterized in that, The step of verifying the predicted results based on the quality data to obtain the target fault causes and latent faults includes: Based on the quality data, the causal data of the raw coal on each piece of equipment is determined, wherein the causal data is the probability that the equipment will fail due to each cause. The causal data corresponding to the faulty equipment is determined as the target causal data, and the causal probability of each of the estimated causes is determined from the target causal data. The causal probability is the probability that the faulty equipment will have the estimated cause due to the raw coal of the quality data. The prediction results are verified based on the probability of each predicted cause to obtain the target fault cause and the latent fault.

4. The method according to claim 3, characterized in that, The step of verifying the prediction results based on the probability of each predicted cause to obtain the target fault cause and the latent fault includes: The probability of each of the predicted causes is matched with the predicted probability of each of the predicted causes in the prediction results. The predicted cause with the highest product of the product probability and the predicted probability is determined as the target fault cause; The predicted cause where both the probability of the fault and the estimated probability are greater than the target threshold is identified as a latent fault.

5. The method according to claim 3, characterized in that, The method further includes: Among the causes of each device, the cause with the highest probability of device failure is identified as a latent fault.

6. The method according to any one of claims 3-5, characterized in that, The determination of the causal data of the raw coal on each piece of equipment based on the quality data includes: Based on the quality data, the required performance parameters of the raw coal for each piece of equipment are determined; The baseline performance parameters of each device are determined based on the mapping relationship table. The operating time of each device in the current cycle is obtained, and the degree of damage to each device by the raw coal is determined based on the operating time of each device, the performance parameters required by the raw coal for each device, and the baseline performance parameters of each device. Based on the degree of damage caused by the raw coal to each piece of equipment, the causal data of the raw coal to each piece of equipment are determined.

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

8. A monitoring device for safe operation in a coal mine, 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: The preprocessing module is used to call the fault analysis component to process the fault data when the fault data is acquired, and to obtain the prediction result corresponding to the fault data. The fault data includes the faulty equipment, the fault phenomenon and the fault occurrence time. The prediction result includes at least one predicted cause and the predicted probability of each predicted cause. The fault analysis component is pre-built based on historical fault data. The quality data acquisition module is used to acquire the quality data of raw coal within the current production cycle. The quality data includes at least the coal block volume, hardness, and impurity content. The verification module is used to verify the predicted results based on the quality data to obtain the target fault cause and hidden fault. The task generation module is used to generate a first investigation task based on the target fault cause, and to generate a shutdown command and a second investigation task based on the hidden fault. The sending module is used to send the first troubleshooting task to the corresponding faulty device, and to send the second troubleshooting task and the shutdown command to the target device corresponding to the latent fault. The shutdown command is used to control the target device to shut down and / or switch the target device to a standby device.

9. A monitoring system, characterized in that, The system includes: Monitoring equipment, used to collect monitoring images from various devices; Data acquisition equipment is used to collect the quality data of raw coal in the current period, and the quality data includes at least the coal volume, hardness and impurity content; The control device, the monitoring device and the data acquisition device are both capable of information interaction with the control device; The control device is used to perform the steps of the method as described in any one of claims 1-7.

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

Images