Comprehensive monitoring and evaluating system for coal mining machine

Abstract

The invention belongs to the technical field of coal mining machine systems, and particularly relates to a coal mining machine comprehensive monitoring and evaluation system which comprises a multi-source sensing layer, a safe transmission layer, a dynamic geological fusion engine, a process coupling analysis module, a predictive maintenance module, a control closed loop module, a digital twinborn verification engine, a resource optimization module and an expert knowledge base module. The process coupling analysis module is used for calculating the correlation degree between the process parameters and the equipment loss; and the predictive maintenance module is used for fusing the multi-source data and outputting the residual life and the fault probability of the equipment. The dynamic geological fusion engine quantifies the geological threat coefficient in real time, and the health assessment model is dynamically adjusted through the weight adaptive unit, so that the equipment health assessment can reflect the actual geological working condition more accurately. And the process coupling analysis module establishes a regression model of the cutting speed and the wear factor, accurately associates the process parameters with the equipment loss, provides a scientific basis for optimizing the cutting strategy, and reduces the abnormal wear of the equipment.

Description

Technical Field

[0001] This invention belongs to the technical field of coal mining machine systems, specifically relating to a comprehensive monitoring and evaluation system for coal mining machines. Background Technology

[0002] In underground coal mining operations, existing coal mining machine operation status monitoring systems have many limitations. Firstly, traditional systems mostly use independent sensor networks for data acquisition, such as equipment status parameters like vibration, temperature, and oil levels, as well as geological information like coal seam hardness, fault distance, and interbedded rock thickness. This data is often stored separately, lacking an effective multi-source heterogeneous data fusion architecture. Furthermore, data transmission mainly relies on a single communication link, such as an industrial bus, which is susceptible to electromagnetic interference in the harsh underground environment, leading to unstable data transmission. Simultaneously, the raw data lacks encryption and evidence preservation mechanisms, posing a risk of tampering and compromising data reliability.

[0003] Secondly, existing systems do not adequately consider the dynamic coupling relationship between geological conditions and equipment wear. Geological information is typically treated as a static parameter, making it impossible to quantify the impact of geological threats on equipment operation and wear in real time. When encountering complex geological structures, such as interbedded rock layers or faults, the system can only trigger fixed alarm thresholds and cannot dynamically adjust the cutting strategy based on the coal seam cutability index, leading to abnormal wear of the cutting teeth or motor overload. Furthermore, the correlation analysis between process parameters and equipment health status mainly relies on manual experience, lacking precise mathematical modeling and quantitative analysis methods, making it difficult to achieve accurate equipment maintenance and fault prediction.

[0004] Finally, existing system maintenance strategies mostly rely on periodic inspections, failing to effectively consider multi-objective optimization of spare parts inventory costs and downtime losses. The data synchronization rate between digital twins and actual equipment is low, and model calibration often depends on offline manual calibration, making it impossible to guide real-time equipment parameter adjustments. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a comprehensive monitoring and evaluation system for coal mining machines. This system aims to solve the problems of reliable fusion of multi-source heterogeneous data, dynamic coupling modeling of geological conditions and equipment losses, and collaborative optimization of prediction-control closed-loop decision-making, thereby achieving adaptive regulation of the health status of coal mining machines.

[0006] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows: A comprehensive monitoring and evaluation system for coal mining machines, comprising: The multi-source sensing layer integrates equipment status sensors, geological exploration sensors, environmental sensors, and process monitoring sensors to collect data in real time on coal mining machine vibration, temperature, oil parameters, coal seam hardness, fault distance, interlayer thickness, coal seam fracture density, ambient temperature and humidity, cutting speed, and traction speed. The secure transmission layer adopts a dual-redundant architecture of industrial Ethernet and 5G private network, with a built-in blockchain data storage module and industrial firewall, and is configured with edge computing nodes to realize data encryption and preprocessing. A dynamic geological fusion engine is used to quantify geological threat coefficients, calculate coal seam cuttable indexes, and dynamically adjust health assessment weights. The system includes: a process coupling analysis module for calculating the correlation between process parameters and equipment wear; a predictive maintenance module for fusing multi-source data and outputting remaining equipment lifespan and failure probability; a control closed-loop module for dynamically adjusting coal mining machine operating parameters based on health scores; a digital twin verification engine for constructing a high-precision digital twin of the coal mining machine and calibrating the model; a resource optimization module for solving multi-objective maintenance cost optimization problems; and an expert knowledge base module for storing fault case maps and providing decision support.

[0007] The dynamic geological fusion engine includes: The geological threat coefficient generation unit is used to generate a geological threat coefficient based on a weighted summation of coal seam hardness, fault distance, and interbedded gangue thickness. The weights of each parameter are preset values. The weighted adaptive unit is used to update the base weights of the sensor data. The health score calculation unit is used to calculate the weighted sum of sensor data and multiply it by an adjustment factor, which is positively correlated with the geological threat coefficient and has an upper limit threshold.

[0008] The dynamic geological fusion engine also includes: The cutability index calculation unit is used to calculate the cutability index of a coal seam based on coal seam hardness, gangue strength, coal seam fracture density, and coal seam dip angle. The vibration threshold adjustment unit raises the vibration alarm threshold when the coal seam cutability index exceeds the preset cutting difficulty threshold.

[0009] The process coupling analysis module includes: The reference speed setting unit is used to dynamically set the reference cutting speed according to the coal seam cutability index. The reference cutting speed is negatively correlated with the coal seam cutability index. The wear factor calculation unit is used to calculate the wear factor based on the ratio function of the actual cutting speed and the reference cutting speed, and the deviation function of the actual traction speed and the optimal traction speed. The regression coefficients of each function are determined by fitting historical data.

[0010] The predictive maintenance module includes: The multi-source data fusion unit uses a graph neural network to fuse time-series data with geological GIS topological relationships. The maintenance strategy optimization unit is configured to output an emergency maintenance command and trigger a spare parts requisition process when the combined assessment value of the geological threat coefficient and the coal seam cuttable index exceeds the maintenance threshold or the failure probability exceeds the risk threshold.

[0011] The control closed-loop module includes: The health response strategy unit is configured to select full-load operation, reduced-load operation, speed-limited inspection, or shutdown maintenance control strategies based on the multi-level threshold range in which the health score is located.

[0012] The digital twin verification engine includes: The model calibration unit is used to calibrate the model online using a particle filter algorithm when the relative deviation between virtual data and actual data continuously exceeds the allowable range. The credibility report generation unit is used to generate a data credibility report based on the overall deviation rate between virtual data and actual data.

[0013] The resource optimization module is configured to minimize the following total cost: Output loss costs that are positively correlated with downtime; spare parts costs that include procurement costs and inventory holding costs; and travel costs that are positively correlated with the distance maintenance personnel travel to and from the site.

[0014] The expert knowledge base module includes a decision support unit, configured to call similar case information from the fault cause solution map when the confidence level of the prediction model is lower than the decision threshold. The control closed-loop module is communicatively connected to the mobile terminal interaction module, which includes: an augmented reality display unit for displaying the real-time health status of the equipment; and a voice control unit for receiving voice commands to adjust the parameters of the coal mining machine.

[0015] The predictive maintenance module also includes a fault probability calculation unit, which uses a Weibull distribution model to calculate the fault probability. The parameters of the model are determined by fitting historical fault data, and the input variables include the cumulative operating time of the equipment. The optimal traction speed in the process coupling analysis module is set according to the coal seam cutability index, and the optimal traction speed is negatively correlated with the coal seam cutability index.

[0016] Compared with the prior art, the beneficial effects of this invention are: The dynamic geological fusion engine quantifies the geological threat coefficient in real time and dynamically adjusts the health assessment model through weighted adaptive units, enabling equipment health assessments to more accurately reflect actual geological conditions. The process coupling analysis module establishes a regression model between cutting speed and wear factors, accurately linking process parameters with equipment wear, providing a scientific basis for optimizing cutting strategies and reducing abnormal equipment wear.

[0017] The predictive maintenance module integrates multi-source data output of the remaining lifespan and failure probability of the equipment, and drives the control closed-loop module to dynamically adjust the operating parameters of the coal mining machine, such as load reduction and speed limiting, so as to realize real-time adaptive control of the equipment status.

[0018] The digital twin verification engine improves the consistency between virtual and real data by using particle filtering to calibrate the model online, ensuring an accurate mapping of the digital twin to the actual equipment and providing reliable support for equipment operation decisions.

[0019] The resource optimization module solves for the multi-objective Pareto optimal solution for downtime losses, spare parts costs, and travel costs, thereby reducing overall maintenance costs and improving the economic efficiency of coal mining enterprises. The expert knowledge base module uses fault case graphs to assist decision-making, improving the accuracy of emergency maintenance commands, reducing the risk of misoperation, and ensuring the safe and stable operation of equipment. Attached Figure Description

[0020] Figure 1 This is a connection block diagram of the present invention. Detailed Implementation

[0021] The technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0022] like Figure 1 As shown, a comprehensive monitoring and evaluation system for coal mining machines includes a multi-source sensing layer, a secure transmission layer, a dynamic geological fusion engine, a process coupling analysis module, a predictive maintenance module, a control closed-loop module, a digital twin verification engine, a resource optimization module, and an expert knowledge base module.

[0023] The multi-source sensing layer integrates various high-precision sensors to comprehensively monitor the operating status of the coal mining machine and its surrounding environment. Equipment status sensors include vibration sensors installed in key parts of the coal mining machine, such as the cutting arm and rocker arm. Based on the piezoelectric principle, these sensors capture minute vibrations, offering a wide measurement range and high accuracy, reflecting the real-time mechanical status of the equipment. Temperature sensors are distributed in heat-prone parts such as motors and bearings, using the characteristics of thermistors to accurately measure temperature changes and provide early warnings of overheating faults. Oil parameter sensors monitor parameters such as viscosity and contamination levels of the hydraulic system oil in real time, accurately assessing oil quality through laser particle size analysis and spectral technology to ensure stable operation of the hydraulic system.

[0024] In terms of geological exploration sensors, the coal seam hardness sensor uses an ultrasonic probe to emit ultrasonic waves into the coal seam and receive the reflected waves. The hardness of the coal seam is calculated based on the wave velocity and attenuation, providing a basis for adjusting cutting parameters. The fault distance sensor uses ground-penetrating radar technology to penetrate the coal seam and detect the location of underground faults, allowing for advance planning of avoidance paths. The interbedded rock layer thickness sensor is based on the principle of gamma-ray backscattering to accurately measure the thickness of the interbedded rock layer, helping to optimize cutting strategies. The coal seam fracture density sensor uses resistivity imaging technology to construct an image of the internal structure of the coal seam, clearly presenting the fracture distribution density.

[0025] Environmental sensors monitor the temperature and humidity of the coal mining face in real time, using capacitive humidity sensing and resistance temperature sensing technologies to ensure accurate and reliable data and guarantee that the equipment operates in a suitable environment; process monitoring sensors accurately measure the cutting speed and traction speed, using laser speed measurement and encoder technology to provide real-time data support for process optimization.

[0026] The secure transmission layer adopts a dual-redundancy architecture of industrial Ethernet and 5G private network to ensure stable and reliable data transmission. The industrial Ethernet uses dedicated optical fiber to build a high-speed wired transmission channel, enabling low-latency, high-bandwidth transmission of sensor data; the 5G private network utilizes its high bandwidth and low latency characteristics to seamlessly switch in the event of wired network failure, ensuring uninterrupted data transmission.

[0027] The blockchain data storage module generates a unique hash value for each monitoring data point and stores it in the blockchain distributed ledger, ensuring data immutability, integrity, and traceability, thus enhancing data credibility. Industrial firewalls are deployed at the network boundary, employing deep packet inspection technology to monitor and block network attacks and malicious traffic in real time, maintaining system network security. Edge computing nodes are equipped with high-performance processors and storage devices to encrypt on-site collected data, using national cryptographic algorithms to ensure data security; simultaneously, data preprocessing, including filtering, compression, and feature extraction, reduces transmission burden and improves overall system efficiency.

[0028] The core of the dynamic geological fusion engine lies in quantifying the geological threat coefficient, calculating the coal seam cutability index, and dynamically adjusting the health assessment weights. The geological threat coefficient generation unit integrates data on coal seam hardness, fault distance, and interbedded rock thickness, performs a weighted summation based on preset weights, and generates a quantitative geological threat coefficient, intuitively reflecting the potential threat level of geological conditions to the coal mining machine. The weight adaptive unit analyzes the quality and correlation of sensor data in real time, and uses machine learning algorithms to dynamically update the basic weights of each parameter, making the weight allocation more consistent with actual geological conditions. The health score calculation unit weights and sums the sensor data according to the updated weights, multiplies it by an adjustment factor positively correlated with the geological threat coefficient (with an upper limit threshold set to prevent excessive amplification), and obtains an accurate health score, providing a scientific basis for equipment health status assessment.

[0029] The cutability index calculation unit combines data on coal seam hardness, gangue strength, coal seam fracture density, and coal seam dip angle to calculate the coal seam cutability index using a specific algorithm, quantifying the ease or difficulty of coal seam cutting. The vibration threshold adjustment unit compares the coal seam cutability index with a preset cutting difficulty threshold in real time. When the index exceeds the limit, it automatically raises the vibration alarm threshold to avoid false alarms caused by changes in geological conditions, ensuring the accuracy and reliability of vibration monitoring.

[0030] The process coupling analysis module aims to calculate the correlation between process parameters and equipment wear. The benchmark speed setting unit dynamically sets the benchmark cutting speed based on the coal seam cutability index and a preset mapping relationship. The two are negatively correlated; that is, the more difficult the coal seam is to cut, the lower the benchmark speed, achieving intelligent adaptation of the cutting speed. The wear factor calculation unit uses the ratio function of the actual cutting speed to the benchmark cutting speed and the deviation function of the actual traction speed from the optimal traction speed as basis, combined with regression coefficients determined by fitting historical data, to accurately calculate the wear factor, quantify the impact of process parameters on equipment wear, and provide key data support for optimizing the process and reducing wear.

[0031] The predictive maintenance module integrates multi-source data to accurately predict equipment remaining life and failure probability. The multi-source data fusion unit uses graph neural networks to deeply integrate equipment time-series data (such as vibration and temperature) with geological GIS topological relationships (such as coal seam distribution and fault location), fully exploring potential correlations between data to construct a comprehensive equipment status profile. The maintenance strategy optimization unit evaluates the combined value of the geological threat coefficient and the coal seam cutability index, as well as the failure probability, in real time. When any indicator exceeds a preset threshold, an emergency maintenance command is immediately output, and the spare parts requisition process is automatically triggered to ensure timely maintenance, reduce equipment downtime losses, and guarantee the continuity of coal mining operations.

[0032] The control closed-loop module dynamically adjusts the coal mining machine's operating parameters based on health scores. The health response strategy unit divides the health score into multiple threshold ranges, corresponding to different equipment operating states. When the health score is in the highest range, the coal mining machine operates at full load to maximize efficiency; if the score drops to the next highest range, it switches to a reduced-load operation mode to reduce equipment load and extend service life; when the score further drops to the middle range, a speed-limiting inspection strategy is implemented, limiting the operating speed and promptly arranging inspections and maintenance while ensuring safety; if the score falls to the lowest range, the machine is immediately shut down for maintenance, thoroughly investigating potential faults to ensure safe and stable equipment operation.

[0033] The digital twin verification engine constructs a high-precision digital twin of the coal mining machine and calibrates the model. The model calibration unit compares the relative deviations between virtual and actual data in real time. When the deviations continuously exceed the allowable range, the particle filter algorithm is immediately activated to calibrate the model online, dynamically correcting model parameters to ensure the digital twin accurately maps the actual state of the coal mining machine. The credibility report generation unit statistically analyzes the overall deviation rate between virtual and actual data and generates a data credibility report based on preset evaluation criteria. This provides a reliability assessment for digital twin-based decision-making, ensuring the scientific validity and accuracy of decisions.

[0034] The resource optimization module focuses on solving multi-objective maintenance cost optimization problems. By establishing a complex optimization model, it comprehensively considers the output loss cost positively correlated with downtime, the spare parts cost including procurement and inventory holding costs, and the travel cost positively correlated with the round-trip distance of maintenance personnel. It uses intelligent optimization algorithms to search for the cost-optimal solution, formulates scientific maintenance plans and resource allocation strategies, minimizes maintenance costs, and improves the economic efficiency of coal mining operations.

[0035] The expert knowledge base module stores a rich database of fault cases and provides decision support. The decision support unit monitors the confidence level of the prediction model in real time. When the confidence level falls below a preset decision threshold, it quickly retrieves similar case information from the fault cause solution database, providing reference decisions for maintenance personnel and helping them quickly locate faults and develop solutions. The control closed-loop module communicates with the mobile interaction module, which integrates an augmented reality display unit and a voice control unit. The augmented reality display unit uses the mobile device's camera and AR technology to overlay equipment health status information onto the actual equipment screen in real time, intuitively presenting the equipment's operating status. The voice control unit receives voice commands from maintenance personnel through voice recognition technology, instantly adjusting the coal mining machine parameters, achieving convenient and efficient human-machine interaction, and improving the convenience and response speed of maintenance operations.

[0036] The predictive maintenance module's failure probability calculation unit uses the Weibull distribution model to calculate failure probabilities. This model, based on historical equipment failure data, employs methods such as maximum likelihood estimation to accurately fit model parameters. It takes key variables such as cumulative equipment operating time as input and outputs the equipment failure probability at the corresponding time point, providing a strong basis for advance maintenance planning and failure prevention. Simultaneously, the optimal traction speed in the process coupling analysis module is set based on the coal seam cutability index, and the two are negatively correlated; that is, the higher the coal seam cutability index, the lower the optimal traction speed. This ensures that the coal mining machine tractions at an appropriate speed under different geological conditions, balancing operational efficiency and equipment wear, and achieving efficient and stable coal mining operations.

[0037] The above description only illustrates preferred embodiments of the present invention, but the present invention is not limited to the above embodiments.

Claims

1. A comprehensive monitoring and evaluation system for coal mining machines, characterized in that, include: The multi-source sensing layer integrates equipment status sensors, geological exploration sensors, environmental sensors, and process monitoring sensors to collect data in real time on coal mining machine vibration, temperature, oil parameters, coal seam hardness, fault distance, interlayer thickness, coal seam fracture density, ambient temperature and humidity, cutting speed, and traction speed. The secure transmission layer adopts a dual-redundant architecture of industrial Ethernet and 5G private network, with a built-in blockchain data storage module and industrial firewall, and is configured with edge computing nodes to realize data encryption and preprocessing. A dynamic geological fusion engine is used to quantify geological threat coefficients, calculate coal seam cuttable indexes, and dynamically adjust health assessment weights. The process coupling analysis module is used to calculate the correlation between process parameters and equipment losses; The predictive maintenance module is used to integrate multi-source data and output the remaining lifespan and failure probability of the equipment; the control closed-loop module is used to dynamically adjust the working parameters of the coal mining machine based on the health score. The digital twin verification engine is used to build a high-precision digital twin of the coal mining machine and calibrate the model; the resource optimization module is used to solve multi-objective maintenance cost optimization problems; and the expert knowledge base module is used to store fault case maps and provide decision support.

2. The comprehensive monitoring and evaluation system for coal mining machines according to claim 1, characterized in that, The dynamic geological fusion engine includes: The geological threat coefficient generation unit is used to generate a geological threat coefficient based on a weighted summation of coal seam hardness, fault distance, and interbedded gangue thickness. The weights of each parameter are preset values. The weighted adaptive unit is used to update the base weights of the sensor data. The health score calculation unit is used to calculate the weighted sum of sensor data and multiply it by an adjustment factor, which is positively correlated with the geological threat coefficient and has an upper limit threshold.

3. The comprehensive monitoring and evaluation system for coal mining machines according to claim 2, characterized in that, The dynamic geological fusion engine also includes: The cutability index calculation unit is used to calculate the cutability index of a coal seam based on coal seam hardness, gangue strength, coal seam fracture density, and coal seam dip angle. The vibration threshold adjustment unit raises the vibration alarm threshold when the coal seam cutability index exceeds the preset cutting difficulty threshold.

4. The comprehensive monitoring and evaluation system for coal mining machines according to claim 3, characterized in that, The process coupling analysis module includes: The reference speed setting unit is used to dynamically set the reference cutting speed according to the coal seam cutability index. The reference cutting speed is negatively correlated with the coal seam cutability index. The wear factor calculation unit is used to calculate the wear factor based on the ratio function of the actual cutting speed and the reference cutting speed, and the deviation function of the actual traction speed and the optimal traction speed. The regression coefficients of each function are determined by fitting historical data.

5. The comprehensive monitoring and evaluation system for coal mining machines according to claim 4, characterized in that, The predictive maintenance module includes: The multi-source data fusion unit uses a graph neural network to fuse time-series data with geological GIS topological relationships. The maintenance strategy optimization unit is configured to output an emergency maintenance command and trigger a spare parts requisition process when the combined assessment value of the geological threat coefficient and the coal seam cuttable index exceeds the maintenance threshold or the failure probability exceeds the risk threshold.

6. The comprehensive monitoring and evaluation system for coal mining machines according to claim 2, characterized in that, The control closed-loop module includes: The health response strategy unit is configured to select full-load operation, reduced-load operation, speed-limited inspection, or shutdown maintenance control strategies based on the multi-level threshold range in which the health score is located.

7. The comprehensive monitoring and evaluation system for coal mining machines according to claim 1, characterized in that, The digital twin verification engine includes: The model calibration unit is used to calibrate the model online using a particle filter algorithm when the relative deviation between virtual data and actual data continuously exceeds the allowable range. The credibility report generation unit is used to generate a data credibility report based on the overall deviation rate between virtual data and actual data.

8. The comprehensive monitoring and evaluation system for coal mining machines according to claim 1, characterized in that, The resource optimization module is configured to minimize the following total cost: Output loss costs that are positively correlated with downtime; spare parts costs that include procurement costs and inventory holding costs; and travel costs that are positively correlated with the distance maintenance personnel travel to and from the site.

9. The comprehensive monitoring and evaluation system for coal mining machines according to claim 1, characterized in that, The expert knowledge base module includes a decision support unit, configured to call similar case information from the fault cause solution map when the confidence level of the prediction model is lower than the decision threshold. The control closed-loop module is communicatively connected to the mobile terminal interaction module, which includes: an augmented reality display unit for displaying the real-time health status of the equipment; and a voice control unit for receiving voice commands to adjust the parameters of the coal mining machine.

10. A comprehensive monitoring and evaluation system for coal mining machines according to claim 5, characterized in that, The predictive maintenance module also includes a fault probability calculation unit, which uses a Weibull distribution model to calculate the fault probability. The parameters of the model are determined by fitting historical fault data, and the input variables include the cumulative operating time of the equipment. The optimal traction speed in the process coupling analysis module is set according to the coal seam cutability index, and the optimal traction speed is negatively correlated with the coal seam cutability index.

Images