Mining mechanical equipment type selection management control platform based on network

Abstract

The invention discloses a mining mechanical equipment type selection management control platform based on a network, and relates to the technical field of mining mechanical equipment, and the control platform comprises a data collection module, a data processing and analysis module, and a type selection recommendation module. Multi-source heterogeneous data from a mining area geological exploration department, an equipment sensor, a satellite remote sensing image and a meteorological station are ingeniously fused, and the data are effectively integrated together through normalization processing and weight distribution, so that a comprehensive and accurate information basis is provided for subsequent model selection recommendation; the data processing and analysis module further performs cleaning, classification, coding and feature extraction on the data, a quantitative relation model between working condition factors and equipment performance is established, and the intelligent data analysis and processing capability enables the platform to perform quantitative analysis according to actual working condition requirements of a mining area. And equipment models and parameters with high adaptability and lowest full life cycle cost are accurately recommended.

Description

Technical Field

[0001] The present invention relates to the technical field of mining machinery and equipment, and in particular to a network-based mining machinery and equipment selection management and control platform. Background Art

[0002] In the field of mineral mining, the selection and management of mining machinery and equipment are key links to ensure production efficiency and safety. With the advancement of science and technology and the increasing complexity of mining areas, the performance requirements for mining machinery and equipment are becoming higher and higher. Traditional selection methods often rely on experience judgment and limited data support, and it is difficult to fully consider various working conditions and the full life cycle cost of equipment, resulting in inaccurate selection results, which affects the production efficiency and economic benefits of the mining area. At the same time, during the operation of the equipment, due to the harsh working environment and large load changes, it is easy to malfunction, affecting the continuity and safety of production. Therefore, how to achieve accurate selection and efficient management of mining machinery and equipment has become a technical problem that needs to be solved urgently in the current field of mineral mining.

[0003] Traditional technologies have many shortcomings in the selection and management of mining machinery and equipment. First, in terms of selection, traditional methods often lack comprehensive and accurate data support, resulting in inaccurate selection results and difficulty in adapting to complex and changeable mining conditions. Secondly, in terms of equipment management, traditional technologies lack the ability of real-time monitoring and fault diagnosis, and cannot promptly detect and warn of equipment failures, resulting in increased maintenance costs and time, affecting the stable operation of equipment and the normal production of mining areas. In addition, traditional technologies also lack intelligent data analysis and processing capabilities, and cannot achieve full life cycle evaluation and optimization of equipment performance, limiting the improvement of mining production efficiency and economic benefits.

[0004] Therefore, developing a network-based mining machinery and equipment selection management and control platform will significantly improve the selection accuracy and management efficiency of mining machinery and equipment, and provide strong guarantees for the production efficiency and safety of mining areas. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the prior art and to provide a network-based mining machinery and equipment selection management and control platform. The platform realizes the intelligent selection and management of mining machinery and equipment through data collection, processing and analysis, selection recommendation, equipment monitoring and user interaction modules. The platform can integrate multi-source heterogeneous data, establish a quantitative relationship model between working conditions and equipment performance, and provide accurate equipment selection recommendations for mining areas. At the same time, digital twin technology and data anomaly detection are used to realize real-time monitoring and intelligent fault diagnosis of equipment, thereby improving the operating efficiency and maintenance level of the equipment. In addition, the user interaction interface can automatically optimize the display effect according to different user roles and equipment, support remote collaboration, and enhance the platform's ease of use and practicality.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a network-based mining machinery equipment selection management control platform, the control platform includes: a data acquisition module, a data processing and analysis module, a selection recommendation module, an equipment monitoring module and a user interaction interface; The data acquisition module: obtains geological conditions and mining scale data from the geological exploration department of the mining area, installs temperature, pressure, and vibration sensors on mining machinery and equipment to monitor power output and operation data in real time, cooperates with satellite data service providers and meteorological stations around the mining area to obtain remote sensing images and real-time meteorological data, and performs format conversion, normalization processing, and fusion of data from different sources; The data processing and analysis module receives data from the data acquisition module, cleans the received data, classifies and codes the cleaned mining area working condition data, classifies the geological condition data according to the nature and purpose, classifies and codes the mining scale data according to relevant factors, extracts the characteristic data from the equipment operation data, establishes a mathematical model based on the processed data, and analyzes the relationship between different working condition factors and equipment performance; The selection recommendation module: constructs a full life cycle cost model covering procurement, operating energy consumption, maintenance and scrapping costs, assuming that the equipment procurement cost is The operating energy cost is The maintenance cost is The scrapping cost is , the equipment service life is , the mining intensity coefficient of the mining area is , the device model parameter vector is , life cycle cost The calculation formula is: , combined with the equipment adaptability evaluation index, the whole life cycle cost and the matching degree with the mining area development plan, the comprehensive evaluation score is used to comprehensively evaluate the candidate equipment. The candidate equipment set is , the equipment adaptability evaluation index is The total life cycle cost is , and the matching degree with the mining area development plan is , the formula is: ,in: is the cost adjustment factor Indicates the device In the The deviation from the ideal working condition under the key working condition dimension, It is the number of key working condition dimensions, and recommends to users the equipment models and parameters with the lowest life cycle cost under the premise of meeting the current working condition requirements of the mining area, having good adaptability and matching the development plan; The equipment monitoring module: uses digital twin technology to create a virtual digital model of mining machinery and equipment, synchronizes the real-time data collected by sensors on the equipment with the digital twin model in real time, presents the real-time operating status of the equipment on the user interaction interface through three-dimensional visualization technology, detects in real time whether the data collected by the sensor is abnormal, and establishes a performance degradation model based on historical and real-time data. When data anomalies are detected or faults are predicted, Bayesian network inference formulas are used to diagnose faults. Maintenance personnel formulate maintenance plans based on the fault diagnosis results and repair the equipment; The user interaction interface automatically adjusts the interface layout and display content according to the roles and operating habits of different users. At the same time, it has an adaptive function, automatically optimizes the display effect according to different devices, and has a remote collaboration function. When encountering complex selection problems or equipment failures, experts are allowed to conduct real-time remote collaboration through the interface to share data, video and voice communication.

[0007] Furthermore, the data acquisition module is used for multi-source heterogeneous data fusion through the data fusion formula. Assume that the traditional mining area data vector is , the device sensor data vector is , the satellite remote sensing image data vector is , the meteorological data vector is , the fused data vector The calculation formula is: ,in, is the normalization factor, is the weight coefficient, is the importance weight of the corresponding data element.

[0008] Furthermore, the data processing and analysis module analyzes the variation of equipment performance under different working conditions by establishing a quantitative relationship model between working condition factors and equipment performance. Suppose the working condition factor vector is , the device performance vector is , establish the correlation function between the two, the formula is: ,in, It is the correlation coefficient obtained through training with a large amount of mining area data.

[0009] Furthermore, in the life cycle cost of the recommended module, the procurement cost The operating energy consumption cost is obtained from the quotation and purchase contract documents provided by the equipment supplier. Based on the energy consumption characteristic data of the equipment and the mining plan of the mining area, it is assumed that the equipment is The load is , for device models , its energy consumption is , the energy price is , the operating energy cost is: , where the mining intensity coefficient of the mining area is The maintenance cost is determined according to the mining volume and mining speed factors in the mining plan. Based on the equipment maintenance manual, wearing parts list, and maintenance labor cost standard information calculation, the equipment model In time The number of replacements of wearing parts within is The cost of replacing each wearing part is , maintenance man-hours are , hourly labor cost is , then the maintenance cost is: , scrapping costs According to the market price and environmental protection requirements for equipment scrapping, the weight of the equipment is , the dismantling and transportation cost per ton of equipment and materials is , environmental protection treatment costs are , then the scrapping cost is: , the service life is Determined by the mining plan of the mining area.

[0010] Furthermore, the selection recommendation module measures the matching degree between equipment selection and long-term development plan of the mining area through the matching degree formula between equipment selection and mining area development plan. Suppose the mining area development plan vector is , the equipment selection parameter vector is , the matching degree between the two for: ,in, It is the equipment selection parameter Factors affecting mining area development planning The influence function of is calculated as: ,in, is the number of equipment selection parameters, It is the equipment selection parameter. It is a factor in the planning of mining area development The influence coefficient of .

[0011] Furthermore, the selection recommendation module uses the equipment adaptability evaluation formula to evaluate the equipment adaptability index, assuming that the mining area geological complexity vector is , the mining difficulty coefficient is , Equipment adaptability index for: ,in, and The geological complexity factors are Mean and standard deviation in historically stable mining areas, The geological complexity factor The weight reflects its influence on the adaptability of the equipment and the mining difficulty coefficient. Based on comprehensive calculation of mining scale, estimated mining time and geological conditions, the formula is: It is The mining difficulty factor is the corresponding weight.

[0012] Furthermore, the equipment monitoring module detects in real time whether the sensor collected data is abnormal through a data anomaly detection formula, wherein: is the weighted mean of the weighted standard deviation of time, and the formula is: , is the weighted standard deviation of time t, and the formula is: ), is a constant determined by the allowed false alarm rate. or When the data is abnormal.

[0013] Furthermore, the device monitoring module predicts the degradation of device performance through the device performance degradation prediction formula. The sensor data vector is: , the initial performance state of the device is , the performance degradation coefficient vector is , the equipment performance degradation model is: ,in, It is a sensor The initial data value of Below the set threshold When the device is predicted to fail.

[0014] Furthermore, the performance degradation coefficient vector of the equipment performance degradation prediction formula in the equipment monitoring module is By analyzing a large amount of historical operating data of the equipment under different working conditions, it is obtained that Operate under different working conditions, each condition has Sensor data and performance evaluation data at each time point, for each working condition , at the time point , the sensor data is , the corresponding performance evaluation value is , determined by the multiple linear regression model, the formula is: ,in, is the regression coefficient, obtained by fitting the data using the least squares method. Converted into performance degradation coefficient , the formula is: ,get .

[0015] Furthermore, the equipment monitoring module diagnoses faults through the Bayesian network inference formula. Suppose the fault type set is , the device symptom set is , known prior probability and conditional probability , according to Bayes' theorem, when the symptom set is observed In case of fault type The posterior probability for: , calculate each fault type The posterior probability Finally, these probability values ​​are compared, and the fault type with the largest posterior probability is the most likely fault type under the currently observed equipment symptoms.

[0016] Compared with the existing technology, this network-based mining machinery equipment selection management and control platform has the following beneficial effects: 1. The present invention cleverly integrates multi-source heterogeneous data from geological exploration departments in mining areas, equipment sensors, satellite remote sensing images and meteorological stations through the data acquisition module. After normalization and weight allocation, these data are effectively integrated together, providing a comprehensive and accurate information basis for subsequent selection recommendations. The data processing and analysis module further cleans, classifies, encodes and extracts features from these data, and establishes a quantitative relationship model between operating factors and equipment performance. This intelligent data analysis and processing capability enables the platform to accurately recommend equipment models and parameters with strong adaptability and the lowest life cycle cost according to the actual operating conditions of the mining area, thereby greatly improving the accuracy and efficiency of selection.

[0017] 2. The present invention uses an equipment monitoring module to enable the platform to synchronize sensor data on the equipment in real time, and use digital twin technology to create a virtual digital model to intuitively present the operating status of the equipment. At the same time, the platform also uses data anomaly detection formulas and performance degradation prediction formulas to monitor and warn the equipment's operating data in real time. Once data anomalies are found or equipment performance degradation is predicted, the platform will immediately start the fault diagnosis process, use the Bayesian network reasoning formula to perform fault diagnosis, and give corresponding maintenance suggestions. This real-time monitoring and fault diagnosis capability can not only effectively prevent the occurrence of equipment failures, but also quickly locate the problem when a failure occurs, reducing maintenance costs and time, thereby ensuring the stable operation of the equipment and normal production in the mining area.

[0018] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 This is a connection architecture diagram of a network-based mining machinery equipment selection management and control platform; Figure 2 This is the flow chart of the equipment monitoring module; Figure 3 The following is a flowchart of the recommended modules for selection. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Embodiment 1: Application of the mining machinery equipment selection management control platform in an open-pit coal mine Data collection and fusion: obtain geological condition data of the open-pit coal mine from the geological exploration department of the mining area, install temperature, pressure, and vibration sensors on mining transport trucks, excavators, and loaders to collect equipment operation data, and cooperate with satellite data service providers to obtain remote sensing images of the mining area with a resolution of m, obtain real-time meteorological data from meteorological stations around the mining area, convert and normalize the above data from different sources through the data acquisition module, and use the data fusion formula to set the traditional mining area data vector as , the device sensor data vector is , the satellite remote sensing image data vector is , the meteorological data vector is , the fused data vector for: , providing a comprehensive and accurate data basis for subsequent analysis.

[0023] Data processing and analysis: receiving data from the data acquisition module, cleaning the collected data, removing outliers and erroneous data, classifying geological condition data into coal seam characteristics and roof condition categories according to their properties, and coding them; classifying and coding mining scale data according to mining plans and expected mining years; extracting characteristic data from equipment operation data; establishing a mathematical model based on the processed data; analyzing the relationship between different working conditions and equipment performance; assuming that the working condition factor vector is , the device performance vector is , establish the correlation function between the two, the formula is: For example, it is found that when the coal seam thickness When increased, the excavator's digging efficiency will increase, but when the coal seam inclination When it is too large, the stability of the excavator It will decline, affecting operational safety. By training with a large amount of mining data, the correlation coefficient in the quantitative relationship model between operating conditions and equipment performance is obtained, thereby accurately predicting the performance changes of equipment under different operating conditions.

[0024] Selection recommendation: obtain quotations and purchase contract documents of different types of transport trucks from equipment suppliers. Assume that the equipment purchase cost is , according to the energy consumption characteristic data of the equipment and the mining plan of the mining area, assuming that the equipment is at time The load is , for device models , its energy consumption is , the energy price is , the mining intensity coefficient of the mining area is , according to the mining volume and mining speed factors in the mining plan, the operating energy consumption cost is: , based on the equipment maintenance manual, wearing parts list, and maintenance labor cost standard information calculation, assuming the equipment model In time The number of replacements of wearing parts within is The cost of replacing each wearing part is , maintenance man-hours are , hourly labor cost is , the maintenance cost is; , calculated based on the market price of equipment scrapping and environmental protection requirements, assuming the weight of the equipment is , the dismantling and transportation cost per ton of equipment and materials is , environmental protection treatment costs are , then the scrapping cost is: , the equipment service life is Determined by the mining plan of the mining area, the equipment model parameter vector is , life cycle cost The calculation formula is: , for different types of excavators, evaluate their adaptability to the geological conditions of the open-pit coal mine , calculate its life cycle cost , analyze its matching degree with the long-term development plan of the mining area , the matching degree between equipment selection and mining area development plan is measured by the matching degree formula between equipment selection and mining area development plan. Suppose the mining area development plan vector is , the equipment selection parameter vector is , the matching degree between the two for: , combined with equipment adaptability evaluation indicators, life cycle cost and matching degree with mining area development plan, a comprehensive evaluation of candidate equipment is conducted. The candidate equipment set is , the equipment adaptability evaluation index is The total life cycle cost is , and the matching degree with the mining area development plan is , the comprehensive evaluation score formula is: ,in: is the cost adjustment factor, Indicates the device In the The deviation from the ideal working condition under the key working condition dimension, is the number of key working condition dimensions. Finally, the equipment model and parameters with the lowest life cycle cost are recommended to the mining area under the premise of meeting the current working condition requirements, having good adaptability and matching the development plan. For example, a certain model of excavator is recommended, and its parameters are bucket capacity. Cubic meters, engine power is Dry tiles.

[0025] Equipment monitoring uses digital twin technology to create virtual digital models of transport trucks and excavators and mining machinery. The real-time data collected by sensors on the equipment is synchronized with the digital twin model in real time. The real-time operation status of the equipment is presented on the user interface through 3D visualization technology. For example, the driving route and speed of the transport truck can be intuitively seen in the monitoring room. , Loading capacity d information, as well as the excavation action and excavation depth of the excavator , through the data anomaly detection formula to detect whether the sensor collected data is abnormal in real time, set ,when or When the engine temperature of a transport truck exceeds the normal range, the data is judged to be abnormal. Based on historical and real-time data, a performance degradation model is established to predict the performance degradation of the equipment. The sensor data vector is , the initial performance state of the device is , the performance degradation coefficient vector is , the equipment performance degradation model is: when Below the set threshold When the data is abnormal or a fault is predicted, the Bayesian network inference formula for fault diagnosis is used to diagnose the fault. Suppose the fault type set is , the device symptom set is , known prior probability and conditional probability , according to Bayes' theorem, when the symptom set is observed In case of fault type The posterior probability for: , calculate each fault type The posterior probability Finally, these probability values ​​are compared, and the fault type with the largest posterior probability is the most likely fault type under the currently observed equipment symptoms.

[0026] User interaction automatically adjusts the interface layout and display content according to different user roles and operating habits in the mining area. For example, managers can see the equipment's comprehensive operating data report and selection recommendation results, operators can see the equipment's operating guide and real-time operating status, and maintenance personnel can see the equipment's fault diagnosis information and maintenance records. At the same time, the interface has an adaptive function that automatically optimizes the display effect according to different equipment and provides clear and intuitive information display. When encountering complex selection problems or equipment failures, experts can use the remote collaboration function to view data and videos in real time, communicate with on-site personnel by voice, and jointly solve problems.

[0027] In this embodiment, the open-pit coal mine uses the mining machinery and equipment selection management and control platform to achieve accurate selection recommendations through multi-source data collection and fusion, in-depth processing and analysis, and comprehensively considers the equipment's full life cycle cost, adaptability and matching degree with the mining area planning. Equipment monitoring uses digital twins, real-time detection and intelligent diagnosis technology to ensure safe and reliable operation, and the user interaction interface improves operational convenience and coordination. The platform effectively solves the drawbacks of traditional management, significantly improves production efficiency and reduces costs, provides strong support for the sustainable development of open-pit coal mines, and also sets an example of intelligent management for related industries, helping the industry to develop in a more efficient and intelligent direction.

[0028] Embodiment 2: Application of mining machinery equipment selection management control platform in an underground metal mine Data collection and fusion: obtain the geological conditions of underground metal mines from the geological exploration department, install sensors on the drilling rig, underground transportation vehicles, and hoist equipment, and collect equipment operation data. The remote sensing images obtained can assist in analyzing the surface topography and surrounding environment of the mining area. Use the data fusion formula to fuse various types of data. Suppose the traditional mining area data vector is , the device sensor data vector is , the satellite remote sensing image data vector is , the meteorological data vector is , the fused data vector for: , providing a comprehensive and accurate data basis for subsequent analysis.

[0029] Data processing and analysis: clean the collected data to ensure data accuracy, classify and code the geological condition data according to ore characteristics and geological structure, classify and code the mining scale data according to mining methods and mining progress factors, extract the key features of equipment operation data, establish the relationship model between working condition factors and equipment performance, and set the working condition factor vector as , the device performance vector is , the correlation function between the two is established as: , for example, to find out the hardness of an ore Increase the drilling speed of the drilling rig Will reduce, drill bit wear aggravated, analyze the direction of different veins Impact on mining equipment operation path planning: Optimize equipment operating parameters through models to improve mining efficiency.

[0030] Model selection recommendation, obtain quotations and purchase contract documents of different models of rock drilling rigs, and assume that the equipment purchase cost is , calculate the operating energy consumption cost based on the energy consumption characteristic data of the equipment and the mining plan of the mining area, assuming that the equipment is at time The load is , for device models , its energy consumption is , the energy price is , the mining intensity coefficient of the mining area is , then the operating energy cost is; , calculate the maintenance cost based on the equipment maintenance manual, wearing parts list, and maintenance labor cost standard information, assuming the equipment model , at time The number of replacements of wearing parts within is The cost of replacing each wearing part is , maintenance man-hours are , hourly labor cost is , the maintenance cost is; The scrapping cost is calculated based on the market price and environmental protection requirements of the equipment scrapping. Assuming the weight of the equipment is , the dismantling and transportation cost per ton of equipment and materials is , environmental protection treatment costs are , then the scrapping cost is: , the equipment service life is The life cycle cost is determined by the mining plan of the mine area The calculation formula is: , let the candidate device set be , the equipment adaptability evaluation index is The total life cycle cost is , and the matching degree with the mining area development plan is , the comprehensive evaluation score formula is: , the matching degree between equipment selection and mining area development plan is measured by the matching degree formula between equipment selection and mining area development plan. Suppose the mining area development plan vector is , the equipment selection parameter vector is , the matching degree between the two for: , recommend equipment models and parameters that are highly adaptable, cost-effective and in line with the mining area development plan.

[0031] Equipment monitoring, creating a digital twin model of underground equipment, synchronizing sensor data in real time, and realizing visual monitoring of equipment operation status. For example, the drilling position and angle of the drilling rig can be observed in real time in the monitoring center. , the driving trajectory of the underground transport vehicle and the operating status of the hoist, and the data anomaly detection formula is used to detect in real time whether the sensor data is abnormal. ,when or When the lifting speed of the elevator suddenly drops and the current is abnormal, it is judged that the equipment may fail. A performance degradation model is established based on historical and real-time data to predict equipment performance changes. The sensor data vector is , the initial performance state of the device is , the performance degradation coefficient vector is , the equipment performance degradation model is: , when predicted When the drilling rig is close to or below the set threshold, it is prompted that the drilling rig may face performance degradation or failure risk, and the corresponding maintenance plan is arranged. If the hoist has abnormal vibration and noise, the fault type set is , the device symptom set is , known prior probability and conditional probability , according to Bayes' theorem, when the symptom set is observed (i.e. abnormal vibration and noise occur at the same time), the fault type The posterior probability for , calculate the posterior probability of each fault type, compare these probability values, and the fault type with the largest posterior probability is the most likely fault type under the currently observed equipment symptoms.

[0032] User interaction: The interface is adjusted according to the needs of different users. Managers can view equipment operation statistics and cost analysis reports, operators can obtain equipment operation guidance and real-time status feedback, and maintenance personnel can obtain detailed fault diagnosis information and maintenance history records. The interface adapts to the display characteristics of different devices to provide a good user experience. When encountering complex problems, experts can work together with on-site personnel to solve them through remote collaboration functions. For example, when remotely guiding the handling of complex elevator failures, experts can quickly and accurately locate problems and provide solutions through shared data, video and voice communication.

[0033] In this embodiment, an underground metal mine applies a mining machinery and equipment selection management and control platform to integrate geological, equipment operation, remote sensing and meteorological multi-source data in the data collection and fusion link to provide a comprehensive basis for subsequent decision-making. The mathematical model established by the data processing and analysis module accurately reveals the relationship between working conditions and equipment performance, and assists in selection recommendations. The selection recommendation comprehensively considers the full life cycle cost, adaptability and planning matching to select the optimal equipment. Equipment monitoring uses digital twins, anomaly detection, performance degradation prediction and Bayesian network diagnosis technology to achieve real-time monitoring, fault warning and accurate diagnosis to ensure reliable operation of equipment. The user interaction interface meets the needs of different users and improves operational convenience and collaborative efficiency. The application of the entire platform effectively solves traditional management problems, improves the equipment management level and production efficiency of the mining area, and provides strong support for the sustainable development of underground metal mining operations. It has important reference significance for similar mining companies. In the future, with the continuous advancement of technology, the platform is expected to be further optimized and play a greater role in the process of mine intelligence.

[0034] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A network-based mining machinery equipment selection management and control platform, characterized in that: The control platform includes: data acquisition module, data processing and analysis module, selection recommendation module, equipment monitoring module and user interaction interface; The data acquisition module: obtains geological conditions and mining scale data from the geological exploration department of the mining area, installs temperature, pressure, and vibration sensors on mining machinery and equipment to monitor power output and operation data in real time, cooperates with satellite data service providers and meteorological stations around the mining area to obtain remote sensing images and real-time meteorological data, and performs format conversion, normalization processing, and fusion of data from different sources; The data processing and analysis module receives data from the data acquisition module, cleans the received data, classifies and codes the cleaned mining area working condition data, classifies the geological condition data according to the nature and purpose, classifies and codes the mining scale data according to relevant factors, extracts the characteristic data from the equipment operation data, establishes a mathematical model based on the processed data, and analyzes the relationship between different working condition factors and equipment performance; The selection recommendation module: constructs a full life cycle cost model covering procurement, operating energy consumption, maintenance and scrapping costs, assuming that the equipment procurement cost is The operating energy cost is The maintenance cost is The scrapping cost is , the equipment service life is , the mining intensity coefficient of the mining area is , the device model parameter vector is , life cycle cost The calculation formula is: , combined with the equipment adaptability evaluation index, the whole life cycle cost and the matching degree with the mining area development plan, the comprehensive evaluation score is used to comprehensively evaluate the candidate equipment. The candidate equipment set is , the equipment adaptability evaluation index is The total life cycle cost is , and the matching degree with the mining area development plan is , the formula is: ,in: is the cost adjustment factor Indicates the device In the The deviation from the ideal working condition under the key working condition dimension, It is the number of key working condition dimensions, and recommends to users the equipment models and parameters with the lowest life cycle cost under the premise of meeting the current working condition requirements of the mining area, having good adaptability and matching the development plan; The equipment monitoring module: uses digital twin technology to create a virtual digital model of mining machinery and equipment, synchronizes the real-time data collected by sensors on the equipment with the digital twin model in real time, presents the real-time operating status of the equipment on the user interaction interface through three-dimensional visualization technology, detects in real time whether the data collected by the sensor is abnormal, and establishes a performance degradation model based on historical and real-time data. When data anomalies are detected or faults are predicted, Bayesian network inference formulas are used to diagnose faults. Maintenance personnel formulate maintenance plans based on the fault diagnosis results and repair the equipment; The user interaction interface automatically adjusts the interface layout and display content according to the roles and operating habits of different users. At the same time, it has an adaptive function, automatically optimizes the display effect according to different devices, and has a remote collaboration function. When encountering complex selection problems or equipment failures, experts are allowed to conduct real-time remote collaboration through the interface to share data, video and voice communication.

2. A network-based mining machinery equipment selection management and control platform according to claim 1, characterized in that: The data acquisition module is used for multi-source heterogeneous data fusion through the data fusion formula. Suppose the traditional mining area data vector is , the device sensor data vector is , the satellite remote sensing image data vector is , the meteorological data vector is , the fused data vector The calculation formula is: ,in, is the normalization factor, is the weight coefficient, is the importance weight of the corresponding data element.

3. A network-based mining machinery equipment selection management and control platform according to claim 1, characterized in that: In the data processing and analysis module, a quantitative relationship model between operating factors and equipment performance is established to analyze the changing law of equipment performance under different operating conditions. Suppose the operating factor vector is , the device performance vector is , establish the correlation function between the two, the formula is: ,in, It is the correlation coefficient obtained through training with a large amount of mining area data.

4. A network-based mining machinery equipment selection management and control platform according to claim 1, characterized in that: The purchase cost of the recommended module in the full life cycle cost is The operating energy consumption cost is obtained from the quotation and purchase contract documents provided by the equipment supplier. Based on the energy consumption characteristic data of the equipment and the mining plan of the mining area, it is assumed that the equipment is The load is , for device models , its energy consumption is , the energy price is , then the operating energy cost is: , where the mining intensity coefficient of the mining area is The maintenance cost is determined according to the mining volume and mining speed factors in the mining plan. Based on the equipment maintenance manual, wearing parts list, and maintenance labor cost standard information calculation, the equipment model In time The number of replacements of wearing parts within is , the cost of replacing wearing parts each time is , maintenance man-hours are , hourly labor cost is , then the maintenance cost is: , scrapping costs According to the market price and environmental protection requirements for equipment scrapping, the weight of the equipment is , the dismantling and transportation cost per ton of equipment and materials is , environmental protection treatment costs are , then the scrapping cost is: , the service life is Determined by the mining plan of the mining area.

5. A network-based mining machinery equipment selection management and control platform according to claim 1, characterized in that: The selection recommendation module measures the matching degree between equipment selection and long-term development plan of the mining area through the matching degree formula between equipment selection and mining area development plan. Suppose the mining area development plan vector is , the equipment selection parameter vector is , the matching degree between the two for: ,in, It is the equipment selection parameter Factors affecting mining area development planning The influence function of is calculated as: ,in, is the number of equipment selection parameters, It is the equipment selection parameter. It is a factor in the planning of mining area development The influence coefficient of .

6. A network-based mining machinery equipment selection management and control platform according to claim 1, characterized in that: The selection recommendation module uses the equipment adaptability evaluation formula to evaluate the equipment adaptability index. Suppose the mining area geological complexity vector is , the mining difficulty coefficient is , Equipment adaptability index for: ,in, and The geological complexity factors are Mean and standard deviation in historically stable mining areas, The geological complexity factor The weight reflects its influence on the adaptability of the equipment and the mining difficulty coefficient. Based on comprehensive calculation of mining scale, estimated mining time and geological conditions, the formula is: It is The mining difficulty factor is the corresponding weight.

7. A network-based mining machinery equipment selection management and control platform according to claim 1, characterized in that: The equipment monitoring module detects in real time whether the sensor collected data is abnormal through the data anomaly detection formula, wherein: is the weighted mean of the weighted standard deviation of time, and the formula is: , is the weighted standard deviation of time t, and the formula is: ), is a constant determined by the allowed false alarm rate. or When the data is abnormal.

8. A network-based mining machinery equipment selection management and control platform according to claim 1, characterized in that: The equipment monitoring module predicts the degradation of equipment performance through the equipment performance degradation prediction formula. The sensor data vector is: , the initial performance state of the device is , the performance degradation coefficient vector is , the equipment performance degradation model is: ,in, It is a sensor The initial data value of Below the set threshold When the device is predicted to fail.

9. A network-based mining machinery equipment selection management and control platform according to claim 8, characterized in that: The performance degradation coefficient vector of the equipment performance degradation prediction formula in the equipment monitoring module By analyzing a large amount of historical operating data of the equipment under different working conditions, it is obtained that Operate under different working conditions, each condition has Sensor data and performance evaluation data at each time point, for each working condition , at the time point , the sensor data is , the corresponding performance evaluation value is , determined by the multiple linear regression model, the formula is: ,in, is the regression coefficient, obtained by fitting the data using the least squares method. Converted into performance degradation coefficient , the formula is: ,get .

10. A network-based mining machinery equipment selection management and control platform according to claim 1, characterized in that: The equipment monitoring module diagnoses faults through the Bayesian network reasoning formula. Suppose the fault type set is , the device symptom set is , known prior probability and conditional probability , according to Bayes' theorem, when the symptom set is observed In case of fault type The posterior probability for: , calculate each fault type The posterior probability Finally, these probability values ​​are compared, and the fault type with the largest posterior probability is the most likely fault type under the currently observed equipment symptoms.

Images