LoRaWAN-based mine equipment intelligent management system and method

Abstract

The invention discloses a LoRaWAN-based mining equipment intelligent management system and method, and relates to the technical field of equipment intelligent management, and the system comprises a transport vehicle data collection module, a transport vehicle data processing module, a health index and task completion degree analysis module, a matching degree analysis module, a priority analysis module, and a transport vehicle task management module. The method comprises the following steps: collecting operation data, health data and task historical data of a transport vehicle, carrying out preprocessing and feature extraction on the data, generating standardized feature data, calculating a health index and task completion degree of the transport vehicle, establishing a matching degree model to analyze the matching degree of the transport vehicle to a target task, generating a priority, and according to a priority score, determining the task completion degree of the transport vehicle. According to the method, the vehicle task completion capability is clearly reflected through multi-dimensional data fusion and intelligent model construction, and the efficiency loss caused by blind scheduling is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent equipment management, and specifically to a LoRaWAN-based intelligent management system and method for mining equipment. Background Art

[0002] In the field of mining equipment management, traditional technologies face key challenges such as limited data collection, ambiguous equipment status assessment, and insufficient task scheduling flexibility. Early management systems for the management of vehicles used in mineral transportation relied on manual inspections and empirical judgment, making it difficult to obtain real-time critical parameters during equipment operation. They also lacked proactive early warning capabilities for potential faults such as abnormal engine operating conditions and tire pressure deviations. This led to frequent equipment failures, which not only risked transportation disruptions but also created safety hazards due to untimely maintenance. Furthermore, task allocation was primarily based on simple matching of load and mileage, ignoring differences in vehicle performance and health status. This led to resource misallocation, resulting in wasted equipment capacity and difficulty ensuring timely and quality task completion, creating a dual dilemma of extensive management and low efficiency. With the accelerated advancement of intelligent mining, the need for data-driven, precise assessments in equipment management is becoming increasingly urgent. Traditional approaches rely on manual inspections or fragmented sensor data to assess equipment health, lacking systematic quantitative models and making it difficult to formulate scientific preventive maintenance strategies. This leads to high O&M costs and shortened equipment lifespans. Task completion capability assessments also remain at the level of simple quantitative statistics, failing to dynamically reflect core indicators such as vehicle on-time delivery rates and task execution stability. This makes it difficult for management systems to distinguish differences in equipment performance during scheduling, resulting in a lack of prioritization of high-quality resources and uneven overall task execution, making it difficult to meet the requirements of efficient and reliable mine transportation operations. Responding to emergencies in complex mine environments is a significant shortcoming of traditional management systems. When transport vehicles suddenly malfunction or task requirements change, existing scheduling mechanisms often rely on manual reallocation, which is cumbersome and slow to respond, easily disrupting the transport chain and impacting mine production continuity. This static matching model lacks a coordinated analysis of the real-time status of equipment and the dynamic requirements of tasks, making it impossible to quickly generate alternative solutions. This results in weak anti-interference capabilities and makes it difficult to cope with common uncertainties in mine operations, such as equipment failures and changing road conditions, hindering the advancement of intelligent management. This invention addresses these technical pain points by constructing an intelligent management system that covers the entire process of equipment monitoring, assessment, and scheduling through multi-dimensional data fusion, intelligent model construction, and dynamic adjustment mechanisms, providing an innovative solution for efficient and safe mine transportation operations. Summary of the Invention

[0003] The purpose of the present invention is to provide a LoRaWAN-based intelligent management system and method for mining equipment to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solution: a method for intelligent management of mining equipment based on LoRaWAN, comprising the following steps:

[0005] S1. Collect the operation data, health data and mission history data of the transport vehicle;

[0006] S2, preprocessing and feature extraction of data to generate standardized feature data;

[0007] S3. Based on the standardized feature data, the health index and task completion degree of the transport vehicle are calculated using the health assessment model and the task completion degree model respectively;

[0008] S4. Establish a matching model between the transport vehicle attributes and the transport task requirements to analyze the matching degree of the transport vehicle to the target task;

[0009] S5. Based on the health index, task completion and matching degree, a priority scoring model is constructed to generate the priority of the transport vehicle;

[0010] S6. Based on the priority score, recommend the highest priority transport vehicle for the target transport task, and make real-time adjustments to abnormal tasks during the transport process.

[0011] Furthermore, in step S1, the operating data is collected in real time by onboard sensors, including driving speed v, fuel consumption f, location information p, and cargo status s, to form an operating data set {v, f, p, s}. The location information includes a timestamp and longitude and latitude, and the cargo status includes the temperature and humidity of the cargo environment and the loading status, where a loading status of 1 indicates loading and a loading status of 0 indicates unloading.

[0012] The health data is obtained based on the vehicle diagnostic interface (OBD) health data, including engine status e, tire pressure t and battery power b, to form a health data set {e, f, b};

[0013] Task history data is extracted from the task management database, including the number r of tasks received, the number m of tasks completed on time, and the number a of completed tasks, forming the task history data set {r, m, a}. This refined capture of multi-dimensional information establishes a comprehensive and three-dimensional data support system for mining equipment management. Operational data collection incorporates spatiotemporal coordinates and cargo environment monitoring to accurately restore vehicle dynamic trajectories and monitor cargo storage status in real time. This not only provides a spatiotemporal data foundation for transport route optimization, but also ensures safe cargo transportation through temperature and humidity monitoring and loading status identification, mitigating transportation risks caused by environmental anomalies or load imbalances. Health data collection focuses on the status of core components, enabling real-time tracking of engine operating conditions, tire pressure, and battery charge. This allows management to proactively identify potential equipment failures, reduce unplanned downtime through preventative maintenance, improve equipment reliability, and reduce maintenance costs. Targeted extraction of task history data creates a profile of a vehicle's task execution capabilities, clearly reflecting its task acceptance efficiency and on-time delivery levels. This provides historical performance evidence for scientific scheduling, enabling the management system to prioritize equipment with strong execution capabilities, creating a virtuous cycle of optimized resource allocation and efficient task completion.

[0014] Further, in step S2, an operation efficiency feature set {V, F} is obtained, where V is the average value of the driving speed v, and F is the ratio of the fuel consumption f to the driving distance; a health status feature set {E, T} is obtained, where E = (2e0-|e-e0|) / 2e0, e0 represents the rated speed of the engine, and T is the warning parameter obtained by comparing the tire pressure t with the standard pressure value t0, T = (1-|t-t0|) / t0; a task execution feature set {M, A} is obtained, where M represents the task on-time completion rate, which represents the ratio of the number of tasks completed on time to the number of completed tasks, and A represents the task completion rate, which represents the ratio of the number of completed tasks to the number of received tasks; the operation efficiency feature set, the health status feature set, and the task execution feature set are unified into the freight feature set {x1, x2,…, x i ,…,x I}, where I represents the number of freight features, x i Denotes the i-th freight feature, and generates the freight feature set {X1, X2,…, X i ,…,X IThis provides a precise data foundation for comprehensive assessments of mining equipment. The operational efficiency feature, based on average speed and fuel consumption / energy consumption ratio, effectively quantifies a vehicle's power performance and energy efficiency during transport. This not only provides an efficiency reference for route planning but also identifies high-energy-consuming equipment through energy consumption comparison, facilitating transport cost control and energy efficiency optimization. The health status feature dynamically correlates actual engine operating conditions and tire pressure with standard parameters to form quantifiable health warning indicators. This provides intuitive numerical representation of equipment abnormalities, enabling managers to quickly identify potential faults, plan maintenance plans in advance, and mitigate the risk of sudden failures. The task execution feature, by dually characterizing on-time completion rate and task completion rate, clearly demonstrates the vehicle's historical task execution quality, providing a performance basis for task allocation and encouraging the management system to prioritize equipment with stable execution capabilities for critical tasks. Linear normalization eliminates dimensional differences between features, establishing a unified evaluation standard for multi-dimensional indicators. This significantly improves the input quality and computational accuracy of subsequent models such as health assessment and task matching, providing reliable support for intelligent management decision-making.

[0015] Furthermore, in step S3, a health assessment model is constructed: the normalized health status feature set is input into a regression model based on a support vector machine (SVM), and a health index H is output, where 0≤H≤1;

[0016] Constructing a task completion model: Task completion is obtained by weighting and summing the normalized task execution features. The weights are obtained through historical data training and sum to 1. The normalized task execution features are input and the task completion index C is output, where 0≤C≤1. This solution achieves deep integration and precise quantification of equipment status assessment and task execution capability analysis through intelligent algorithms and data-driven mechanisms. The health assessment model introduces a support vector machine regression algorithm. Based on normalized health characteristics such as engine operating conditions and tire pressure, it constructs a nonlinear mapping relationship, effectively capturing the changing patterns of equipment health under the influence of multi-parameter coupling and outputting a standardized health index. This quantitative assessment method breaks through the ambiguity of traditional manual experience-based judgments, allowing for intuitive presentation of equipment health levels and providing a scientific basis for the formulation of preventive maintenance strategies. Managers can dynamically adjust maintenance cycles based on the health index, proactively identify hidden dangers in low-index equipment, and prevent failures from escalating into downtime accidents, significantly improving equipment availability and reducing operation and maintenance costs.

[0017] Furthermore, in step S4, the matching model between the transport vehicle attributes and the transport task requirements is established, and the matching index of the transport vehicle to the target task is calculated, including:

[0018] Each transport vehicle is analyzed to extract its attribute parameters, including load capacity (L) and maximum range (R). The required parameters for each task are then parsed: cargo weight (G), transport distance (J), and required range (Q). The matching index (S) for the vehicle to the task is then calculated: S = α1*G / L + α2*J / R + α3*Q / R. This matching model construction scheme achieves precise alignment between transport resources and task requirements by quantitatively linking equipment attributes with task requirements. The model focuses on two core equipment attributes: load capacity and range. Combining the task's cargo weight, transport distance, and range requirements, it constructs a multi-factor weighted matching mechanism, creating an intuitive quantitative mapping between vehicle performance parameters and task requirements. This data-driven matching approach transcends the limitations of traditional scheduling, which relies on manual judgment and experience. It accurately identifies whether a vehicle has the basic capabilities to complete a task, thereby avoiding the risk of mission failure due to insufficient load capacity or range, and preventing the waste of resources caused by over-matching high-quality equipment to simple tasks. The weighted calculation mechanism flexibly adjusts weights based on the priorities of different tasks in mine transportation scenarios (e.g., prioritizing heavy loads or long-distance endurance), significantly improving the model's adaptability to complex task demands. By incorporating the matching index into the subsequent priority scoring system, the model forms a multi-dimensional evaluation loop with equipment health assessments and task completion, driving scheduling decisions.

[0019] Furthermore, in step S5, the health index, task completion and matching degree are integrated to construct a priority scoring model to generate the priority of the transport vehicle, including:

[0020] Combining the health index H, task completion index C, and matching index S, a priority scoring model is constructed: S = β1*H + β2*C + β3*S, where S is the vehicle's priority score for a task, β1 is the weight of the health index on the priority score, β2 is the weight of the task completion index on the priority score, and β3 is the weight of the matching index on the priority score. β1, β2, and β3 are system settings. The health index, task completion index, and matching index are then input to output a vehicle's priority score for a task. By integrating multi-dimensional indicators, a three-dimensional evaluation system is constructed that covers equipment status, task capabilities, and demand matching. The model integrates three core elements, equipment health index, task completion, and task matching, into a unified evaluation framework, breaking the limitation of traditional scheduling that relies on a single metric. Vehicle priority determination comprehensively reflects the overall performance of the equipment and its task suitability. The system can flexibly adjust the weights of each dimension based on the actual needs of mine transportation. For example, the health index may be weighted more heavily for tasks requiring high reliability, while task completion may be emphasized for tasks requiring timeliness. This significantly enhances the model's adaptability to complex scenarios. The priority score generated through quantitative calculation provides an intuitive and clear sorting basis for scheduling decisions, enabling the management system to quickly screen out vehicles with good health, outstanding task execution capabilities and a high degree of match with demand to undertake tasks. This not only avoids the problem of inefficient and high-configuration equipment, but also improves the efficiency of task allocation through scientific sorting, forming a virtuous mechanism in which vehicles with excellent health, strong execution capabilities and high demand matching are given priority to undertake tasks, thus optimizing the overall allocation of mine transportation resources and providing core technical support for intelligent and refined scheduling management.

[0021] Furthermore, in step S6, any task is analyzed, and the priority scores of the vehicles for the tasks are sorted in descending order to generate a priority score set {S1, S2, ..., S n ,…,S N}, where N represents a total of N transport vehicles, S n Indicates the priority score of the nth transport vehicle for the task, calculates the distance the transport vehicle needs to reach the task starting point, and estimates the time it will take for the transport vehicle to arrive at the task starting point based on the average speed of the vehicles. If the estimated time to arrive at the task starting point meets the task time window, the vehicle information is placed in the set of candidate vehicles for the task, and then the transport vehicle with the highest priority score is selected from the set of candidate vehicles to match the task. If there are vehicles with the same priority score, the vehicle with the highest task completion rate is selected to match the task.

[0022] The real-time adjustment of abnormal tasks during the transportation process includes: when the recommended transport vehicle is unable to perform the task due to a sudden failure, re-execute steps S2-S6, recalculate the health index, task completion, matching score and priority score based on the real-time data of the remaining available transport vehicles, and generate a new recommendation result; build a transportation task allocation system that is both efficient and reliable. In the task matching stage, the system accurately screens out vehicles that have both high comprehensive performance and meet the task timeliness requirements based on the descending order of priority scores and time window constraints, avoiding matching deviations or time delays caused by relying solely on a single indicator. The establishment of a set of alternative vehicles and the decision logic guided by priority scores ensure that the equipment with the best overall performance is prioritized within the compliance time range, significantly improving the accuracy and execution efficiency of task allocation. In response to sudden failures during transportation, the real-time adjustment function uses a full-process dynamic recalculation mechanism to quickly generate new recommended solutions based on the latest status data of the remaining vehicles, completely changing the shortcomings of slow manual intervention and delayed data updates in traditional scheduling. This automated emergency response capability enables re-matching of tasks and equipment in record time, effectively mitigating the risk of transport chain disruptions caused by vehicle failures and ensuring the stable operation of mining production processes. This entire mechanism combines static priority assessment with dynamic, real-time adjustments, enabling efficient allocation of routine tasks while empowering the system with robustness to respond to emergencies. This provides end-to-end intelligent assurance for reliable transportation in complex mining environments.

[0023] The LoRaWAN-based intelligent management system for mining equipment includes: transport vehicle data acquisition module, transport vehicle data processing module, health index and task completion analysis module, matching analysis module, priority analysis module, and transport vehicle task management module;

[0024] The transport vehicle data acquisition module is used to collect the transport vehicle's operating data, health data and mission history data;

[0025] The transport vehicle data processing module is used to pre-process and extract features from the data to generate standardized feature data;

[0026] The health index and task completion analysis module is used to calculate the health index and task completion of the transport vehicle respectively based on the standardized feature data through the health assessment model and the task completion model;

[0027] The matching analysis module is used to establish a matching model between the transport vehicle attributes and the transport task requirements, and calculate the matching degree of the transport vehicle to the target task;

[0028] The priority analysis module is used to comprehensively consider the health index, task completion and matching scores, construct a priority scoring model, and analyze the priority of the transport vehicle;

[0029] The transport vehicle task management module is used to recommend the transport vehicle with the highest priority for the target transport task according to the priority, and to make real-time adjustments to abnormal tasks during the transport process.

[0030] Furthermore, the transport vehicle data acquisition module, transport vehicle data processing module, health index and task completion analysis module, matching analysis module, priority analysis module and transport vehicle task management module are connected to the core processor through LoRaWAN, and after a task is assigned, the real-time updated data is backed up to the core processor.

[0031] Compared with the existing technology, the beneficial effects achieved by the present invention are: on the one hand, through multi-dimensional data fusion and intelligent model construction, it brings significant benefits to mine equipment management. The system uses on-board sensors and diagnostic interfaces to collect equipment operation, health and task history information in real time, forming a complete data portrait covering equipment status and task execution. This full-time, multi-parameter monitoring mechanism enables managers to accurately grasp equipment dynamics, promptly discover potential hidden dangers such as abnormal engine speed and tire pressure imbalance, intervene in maintenance in advance, avoid transportation interruptions due to equipment failure, and improve the safety and reliability of mine transportation from the source. At the same time, in-depth analysis of historical task data can clearly reflect the vehicle's task completion capability, provide solid data support for the scientific allocation of resources, and effectively reduce efficiency losses caused by blind scheduling.

[0032] On the one hand, it enables a quantitative assessment of equipment status and task execution capabilities. The health index uses a support vector machine regression model to integrate key parameters such as engine speed and tire pressure to accurately characterize the equipment's health level, providing an intuitive basis for the development of preventive maintenance plans, extending equipment life, and reducing operating and maintenance costs. The task completion model determines weights through historical data training, scientifically measuring vehicle on-time completion rates and task completion rates. This enables the management system to dynamically adjust task allocation strategies based on actual vehicle performance, prioritizing the use of equipment with stable performance and high execution efficiency to undertake critical transportation tasks, significantly improving the overall quality of task completion and forming a virtuous management cycle of high efficiency and high utilization.

[0033] On the other hand, the dynamic matching mechanism and abnormal adjustment function give the system strong adaptability and anti-interference capabilities. The priority scoring model comprehensively considers the health status of the equipment, the ability to complete the task, and the matching degree of the task requirements, and generates vehicle priorities through multi-factor weighted calculations to ensure the optimal match between the transportation task and the equipment attributes, and maximize the efficiency of each device. What is particularly important is that when a sudden failure causes the original vehicle to be unable to perform the task, the system can quickly recalculate and evaluate based on the real-time data of the remaining equipment, automatically trigger alternative plans, and complete the secondary matching of the task and the vehicle in a short time, effectively avoiding the break of the transportation chain caused by unexpected events, and ensuring the continuity of the mine production process. This intelligent dynamic adjustment capability significantly enhances the robustness of the management system, enabling it to calmly deal with various emergencies in the complex environment of the mine, and provide a solid guarantee for efficient and stable transportation operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0035] Figure 1 This is a structural diagram of the LoRaWAN-based intelligent management system for mining equipment of the present invention;

[0036] Figure 2 It is a flow chart of the intelligent management method of mining equipment based on LoRaWAN of the present invention. DETAILED DESCRIPTION

[0037] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0038] See also Figure 1 and Figure 2 The present invention provides a technical solution: a method for intelligent management of mining equipment based on LoRaWAN, comprising the following steps:

[0039] S1. Collect the operation data, health data and mission history data of the transport vehicle;

[0040] S2, preprocessing and feature extraction of data to generate standardized feature data;

[0041] S3. Based on the standardized feature data, the health index and task completion degree of the transport vehicle are calculated using the health assessment model and the task completion degree model respectively;

[0042] S4. Establish a matching model between the transport vehicle attributes and the transport task requirements to analyze the matching degree of the transport vehicle to the target task;

[0043] S5, based on the comprehensive health index, task completion and matching degree, builds a priority scoring model to generate the priority of the transport vehicle;

[0044] S6. Based on the priority score, recommend the highest priority transport vehicle for the target transport task, and make real-time adjustments to abnormal tasks during the transport process.

[0045] In step S1, operating data is collected in real time through on-board sensors, including driving speed v, fuel consumption f, location information p, and cargo status s, forming an operating data set {v, f, p, s}. The location information includes timestamp and longitude and latitude. The cargo status includes the cargo environment temperature and humidity and loading status. The loading status is 1 when it indicates loading, and 0 when it indicates unloaded.

[0046] Health data is obtained based on the vehicle diagnostic interface (OBD), including engine status e, tire pressure t and battery power b, to form a health data set {e, f, b};

[0047] Task history data is extracted from the task management database, including the number of tasks received (r), the number of tasks completed on time (m), and the number of completed tasks (a), forming the task history data set {r, m, a}. This refined capture of multi-dimensional information builds a comprehensive and three-dimensional data support system for mining equipment management. Operational data collection incorporates spatiotemporal coordinates and cargo environment monitoring to accurately restore vehicle dynamic trajectories and monitor cargo storage status in real time. This not only provides a spatiotemporal data foundation for transport route optimization, but also ensures safe cargo transportation through temperature and humidity monitoring and loading status identification, mitigating transportation risks caused by environmental anomalies or load imbalances. Health data collection focuses on the status of core components, enabling real-time tracking of engine operating conditions, tire pressure, and battery charge. This allows management to proactively identify potential equipment failures, reduce unplanned downtime through preventive maintenance, improve equipment reliability, and reduce maintenance costs. Targeted extraction of task history data creates a profile of a vehicle's task execution capabilities, clearly reflecting its task acceptance efficiency and on-time delivery levels. This provides historical performance evidence for scientific scheduling, enabling the management system to prioritize equipment with strong execution capabilities, creating a virtuous cycle of optimized resource allocation and efficient task completion.

[0048] In step S2, the operation efficiency feature set {V, F} is obtained, where V is the average value of the driving speed v, and F is the ratio of the fuel consumption f to the driving distance; the health status feature set {E, T} is obtained, where E = (2e0-|e-e0|) / 2e0, e0 represents the rated speed of the engine, and T is the warning parameter obtained by comparing the tire pressure t with the standard pressure value t0, T = (1-|t-t0|) / t0; the task execution feature set {M, A} is obtained, where M represents the task on-time completion rate, which represents the ratio of the number of tasks completed on time to the number of completed tasks, and A represents the task completion rate, which represents the ratio of the number of completed tasks to the number of received tasks; the operation efficiency feature set, the health status feature set, and the task execution feature set are unified into the freight feature set {x1, x2,…, x i ,…,x I}, where I represents the number of freight features, x i Denotes the i-th freight feature, and generates the freight feature set {X1, X2,…, X i ,…,X I This provides a precise data foundation for comprehensive assessments of mining equipment. The operational efficiency feature, based on average speed and fuel consumption / energy consumption ratio, effectively quantifies a vehicle's power performance and energy efficiency during transport. This not only provides an efficiency reference for route planning but also identifies high-energy-consuming equipment through energy consumption comparison, facilitating transport cost control and energy efficiency optimization. The health status feature dynamically correlates actual engine operating conditions and tire pressure with standard parameters to form quantifiable health warning indicators. This provides intuitive numerical representation of equipment abnormalities, enabling managers to quickly identify potential faults, plan maintenance plans in advance, and mitigate the risk of sudden failures. The task execution feature, by dually characterizing on-time completion rate and task completion rate, clearly demonstrates the vehicle's historical task execution quality, providing a performance basis for task allocation and encouraging the management system to prioritize equipment with stable execution capabilities for critical tasks. Linear normalization eliminates dimensional differences between features, establishing a unified evaluation standard for multi-dimensional indicators. This significantly improves the input quality and computational accuracy of subsequent models such as health assessment and task matching, providing reliable support for intelligent management decision-making.

[0049] In step S3, a health assessment model is constructed: the normalized health status feature set is input into a regression model based on a support vector machine (SVM) and a health index H is output, where 0≤H≤1;

[0050] Constructing a task completion model: Task completion is obtained by weighting and summing the normalized task execution features. The weights are obtained through historical data training and sum to 1. The normalized task execution features are input and the task completion index C is output, where 0≤C≤1. This solution achieves deep integration and precise quantification of equipment status assessment and task execution capability analysis through intelligent algorithms and data-driven mechanisms. The health assessment model introduces a support vector machine regression algorithm. Based on normalized health characteristics such as engine operating conditions and tire pressure, it constructs a nonlinear mapping relationship, effectively capturing the changing patterns of equipment health under the influence of multi-parameter coupling and outputting a standardized health index. This quantitative assessment method breaks through the ambiguity of traditional manual experience-based judgments, allowing for intuitive presentation of equipment health levels and providing a scientific basis for the formulation of preventive maintenance strategies. Managers can dynamically adjust maintenance cycles based on the health index, proactively identify hidden dangers in low-index equipment, and prevent failures from escalating into downtime accidents, significantly improving equipment availability and reducing operation and maintenance costs.

[0051] In step S4, a matching model between the transport vehicle attributes and the transport task requirements is established, and the matching index of the transport vehicle to the target task is calculated, including:

[0052] Each transport vehicle is analyzed and its attribute parameters, including load capacity L and maximum range R, are extracted. The required parameters for each task are then analyzed: cargo weight G, transport distance J, and required range Q. The matching index S for the vehicle to the task is then calculated: S = α1*G / L + α2*J / R + α3*Q / R. This matching model construction scheme achieves precise alignment between transportation resources and task requirements by quantitatively linking equipment attributes with task requirements. The model focuses on two core equipment attributes: load capacity and range. Combining the task's cargo weight, transport distance, and range requirements, it constructs a multi-factor weighted matching mechanism, creating a straightforward quantitative mapping between vehicle performance parameters and task requirements. This data-driven matching approach transcends the limitations of traditional scheduling, which relies on manual judgment and experience. It accurately identifies whether a vehicle has the basic capabilities to complete a task, thereby avoiding the risk of mission failure due to insufficient load capacity or range, and preventing the waste of resources caused by over-matching high-quality equipment to simple tasks. The weighted calculation mechanism flexibly adjusts weights based on the priorities of different tasks in mine transportation scenarios (e.g., prioritizing heavy loads or long-distance endurance), significantly improving the model's adaptability to complex task demands. By incorporating the matching index into the subsequent priority scoring system, the model forms a multi-dimensional evaluation loop with equipment health assessments and task completion, driving scheduling decisions.

[0053] In step S5, the health index, task completion and matching degree are integrated to build a priority scoring model to generate the priority of the transport vehicle, including:

[0054] The health index H, task completion index C, and matching index S are combined to construct a priority scoring model: S = β1*H+β2*C+β3*S, where S is the vehicle's priority score for the task, β1 is the weight of the health index on the priority score, β2 is the weight of the task completion index on the priority score, and β3 is the weight of the matching index on the priority score. β1, β2, and β3 are system settings. The health index, task completion index, and matching index are then input to output a vehicle's priority score for the task. By organically integrating multi-dimensional indicators, a three-dimensional evaluation system is constructed that covers equipment status, task capabilities, and demand matching. The model integrates three core elements, equipment health index, task completion, and task matching, into a unified evaluation framework, breaking the limitation of traditional scheduling that relies on a single metric. Vehicle priority determination comprehensively reflects the equipment's overall performance and task suitability. The system can flexibly adjust the weights of each dimension based on the actual needs of mine transportation. For example, the health index may be weighted more heavily for tasks requiring high reliability, while task completion may be emphasized for time-sensitive tasks. This significantly enhances the model's adaptability to complex scenarios. The priority score generated through quantitative calculation provides an intuitive and clear sorting basis for scheduling decisions, enabling the management system to quickly screen out vehicles with good health, outstanding task execution capabilities and a high degree of match with demand to undertake tasks. This not only avoids the problem of inefficient and high-configuration equipment, but also improves the efficiency of task allocation through scientific sorting, forming a virtuous mechanism in which vehicles with excellent health, strong execution capabilities and high demand matching are given priority to undertake tasks, thus optimizing the overall allocation of mine transportation resources and providing core technical support for intelligent and refined scheduling management.

[0055] In step S6, any task is analyzed and the priority scores of the vehicles for the tasks are sorted in descending order to generate a priority score set {S1, S2, ..., S n ,…,S N}, where N represents a total of N transport vehicles, S n Indicates the priority score of the nth transport vehicle for the task, calculates the distance the transport vehicle needs to reach the task starting point, and estimates the time it will take for the transport vehicle to arrive at the task starting point based on the average speed of the vehicles. If the estimated time to arrive at the task starting point meets the task time window, the vehicle information is added to the task's candidate vehicle set, and then the transport vehicle with the highest priority score is selected from the candidate vehicle set to match the task. If there are vehicles with the same priority score, the vehicle with the highest task completion rate is selected to match the task.

[0056] Real-time adjustments to abnormal tasks during the transportation process include: when a recommended transport vehicle is unable to perform a task due to a sudden failure, steps S2-S6 are re-executed, and based on the real-time data of the remaining available transport vehicles, the health index, task completion, matching score and priority score are recalculated to generate a new recommendation result; a transportation task allocation system that is both efficient and reliable is constructed. During the task matching stage, the system accurately selects vehicles that have both high comprehensive performance and meet the task timeliness requirements based on descending priority score sorting and time window constraints, avoiding matching deviations or time delays caused by relying solely on a single indicator. The establishment of a set of alternative vehicles and the decision-making logic guided by priority scores ensure that the equipment with the best overall performance is prioritized within the compliance time range, significantly improving the accuracy and execution efficiency of task allocation. In response to sudden failures during transportation, the real-time adjustment function uses a full-process dynamic recalculation mechanism to quickly generate new recommendations based on the latest status data of the remaining vehicles, completely changing the shortcomings of slow manual intervention and delayed data updates in traditional scheduling. This automated emergency response capability enables re-matching of tasks and equipment in record time, effectively mitigating the risk of transport chain disruptions caused by vehicle failures and ensuring the stable operation of mining production processes. This entire mechanism combines static priority assessment with dynamic, real-time adjustments, enabling efficient allocation of routine tasks while empowering the system with robustness to respond to emergencies. This provides end-to-end intelligent assurance for reliable transportation in complex mining environments.

[0057] The LoRaWAN-based intelligent management system for mining equipment includes: transport vehicle data acquisition module, transport vehicle data processing module, health index and task completion analysis module, matching analysis module, priority analysis module, and transport vehicle task management module;

[0058] The transport vehicle data collection module is used to collect the transport vehicle's operating data, health data, and mission history data;

[0059] The transport vehicle data processing module is used to pre-process and extract features from the data to generate standardized feature data;

[0060] The health index and task completion analysis modules are used to calculate the health index and task completion of the transport vehicle based on standardized feature data through the health assessment model and task completion model respectively;

[0061] The matching analysis module is used to establish a matching model between the transport vehicle attributes and the transport task requirements, and calculate the matching degree of the transport vehicle to the target task;

[0062] The priority analysis module is used to integrate the health index, task completion and matching scores to build a priority scoring model and analyze the priority of transport vehicles;

[0063] The transport vehicle task management module is used to recommend the highest priority transport vehicle for the target transport task based on priority, and to make real-time adjustments to abnormal tasks during the transport process.

[0064] The transport vehicle data acquisition module, transport vehicle data processing module, health index and task completion analysis module, matching analysis module, priority analysis module and transport vehicle task management module are connected to the core processor through LoRaWAN. After a task is assigned, the real-time updated data is backed up to the core processor.

[0065] Example 1: First, multi-dimensional data collection is performed. Real-time vehicle operating status information, including driving speed, fuel consumption, real-time location, and cargo loading status, is acquired through onboard sensors. Equipment health data, including engine speed, tire pressure, and remaining battery charge, is collected through the vehicle diagnostic interface. Historical task execution data, including the number of tasks received, the number of tasks completed on time, and the number of tasks actually completed, is extracted from the task management database to provide a data foundation for subsequent analysis.

[0066] Next, feature extraction and normalization are performed. For operational efficiency, the average driving speed is calculated and combined with the proportional relationship between fuel consumption and distance traveled to form an efficiency feature. Health status assessment compares the engine's real-time operating status with its rated state, while also generating health features based on the difference between tire pressure and the standard value. Task execution is reflected by the ratio of on-time completed tasks to completed tasks, as well as the ratio of completed tasks to received tasks. These three features are then integrated and processed using a unified linear normalization method to make data from different dimensions comparable.

[0067] Then, a core evaluation model was constructed. The health assessment phase uses a support vector machine regression model, taking normalized health feature data as input and outputting a health index within a reasonable range that intuitively reflects the vehicle's current technical status. The mission completion assessment then uses a weighted summation of normalized mission execution features, with weights determined through historical data training, to generate a mission completion index that measures the vehicle's past mission performance.

[0068] During the task matching stage, attribute parameters such as load capacity and maximum cruising range are extracted for each transport vehicle. At the same time, the required parameters such as cargo weight, transportation distance and required cruising range of the target task are analyzed. By comprehensively calculating the degree of matching between vehicle attributes and task requirements, a quantitative matching index is formed to determine the basic adaptability of the vehicle to perform the task.

[0069] Finally, a priority scoring model is established. The vehicle health index, task completion index, and task matching index are integrated into a unified evaluation system and linearly combined according to the system's preset weights to generate a priority score for each vehicle for a specific task. This score comprehensively reflects the vehicle's technical status, historical performance, and task adaptability, providing the core basis for task allocation. Through this comprehensive data-driven intelligent management mechanism, the system can dynamically optimize transport vehicle scheduling strategies, ensuring the healthy operation of equipment while improving the overall efficiency and reliability of mine transportation tasks.

[0070] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. The intelligent management method of mining equipment based on LoRaWAN is characterized by: The method comprises the following steps: S1. Collect the operation data, health data and mission history data of the transport vehicle; S2, preprocessing and feature extraction of data to generate standardized feature data; S3. Based on the standardized feature data, the health index and task completion degree of the transport vehicle are calculated using the health assessment model and the task completion degree model respectively; S4. Establish a matching model between the transport vehicle attributes and the transport task requirements to analyze the matching degree of the transport vehicle to the target task; S5. Based on the health index, task completion and matching degree, a priority scoring model is constructed to generate the priority of the transport vehicle; S6. Based on the priority score, recommend the highest priority transport vehicle for the target transport task, and make real-time adjustments to abnormal tasks during the transport process.

2. The LoRaWAN-based intelligent management method for mining equipment according to claim 1, characterized in that: In step S1, the operating data is collected in real time by on-board sensors, including driving speed v, fuel consumption f, location information p, and cargo status s, to form an operating data set {v, f, p, s}; The health data is obtained based on the vehicle diagnostic interface, including the real-time engine speed e, tire pressure t and battery power b, to form a health data set {e, t, b}; The task history data is extracted from the task management database, including the number r of received tasks, the number m of tasks completed on time, and the number a of completed tasks, forming a task history data set {r, m, a}.

3. The LoRaWAN-based intelligent management method for mining equipment according to claim 2, characterized in that: In step S2, an operation efficiency feature set {V, F} is obtained, where V is the average value of the driving speed v, and F is the ratio of the fuel consumption f to the driving distance; a health status feature set {E, T} is obtained, where E = (2e0-|e-e0|) / 2e0, e0 represents the rated speed of the engine, and T is the warning parameter obtained by comparing the tire pressure t with the standard pressure value t0, T = (1-|t-t0|) / t0; a task execution feature set {M, A} is obtained, where M represents the task on-time completion rate, which represents the ratio of the number of tasks completed on time to the number of completed tasks, and A represents the task completion rate, which represents the ratio of the number of completed tasks to the number of received tasks; the operation efficiency feature set, the health status feature set, and the task execution feature set are unified into a freight feature set {x1, x2,…, x i ,…,x I }, where I represents the number of freight features, x i Denotes the i-th freight feature, and generates the freight feature set {X1, X2,…, X i ,…,X I }.

4. The LoRaWAN-based intelligent management method for mining equipment according to claim 3, characterized in that: In step S3, a health assessment model is constructed: the normalized health status feature set is input into a regression model based on a support vector machine, and a health index H is output, where 0≤H≤1; Construct a task completion model: The task completion is obtained by weighting and summing the normalized task execution features. The weights are obtained through historical data training and the sum of the weights is 1. The normalized task execution features are input and the task completion index C is output, 0≤C≤1.

5. The LoRaWAN-based intelligent management method for mining equipment according to claim 4, characterized in that: In step S4, the matching model between the transport vehicle attributes and the transport task requirements is established, and the matching index of the transport vehicle to the target task is calculated, including: Analyze any transport vehicle and extract its attribute parameters, which are load capacity L and maximum cruising range R. Analyze any task requirement parameters: cargo weight G, transport distance J, and required cruising range Q. Then calculate the matching index S of the transport vehicle for the task, S = α1*G / L+α2*J / R+α3*Q / R.

6. The LoRaWAN-based intelligent management method for mining equipment according to claim 5, characterized in that: In step S5, the health index, task completion and matching degree are integrated to construct a priority scoring model to generate the priority of the transport vehicle, including: The health index H, task completion index C and matching index S are combined to construct a priority scoring model: S = β1*H+β2*C+β3*S, where S is the vehicle's priority score for the task, β1 is the influence weight of the health index on the priority score, β2 is the influence weight of the task completion index on the priority score, and β3 is the influence weight of the matching index on the priority score. β1, β2 and β3 are system settings, and the health index, task completion index and matching index are input to output the vehicle's priority score for the task.

7. The LoRaWAN-based intelligent management method for mining equipment according to claim 6, characterized in that: In step S6, any task is analyzed and the priority scores of the vehicles for the tasks are sorted in descending order to generate a priority score set {S1, S2, ..., S n ,…,S N }, where N represents a total of N transport vehicles, S n It represents the priority score of the nth transport vehicle for the task, calculates the distance the transport vehicle needs to reach the task starting point, and estimates the time it will take for the transport vehicle to arrive at the task starting point based on the average speed of the vehicle. If the estimated time of arrival at the task starting point meets the task time window, the vehicle information is placed in the set of alternative vehicles for the task, and then the transport vehicle with the highest priority score is selected from the set of alternative vehicles to match the task. If there are vehicles with the same priority score, the vehicle with the highest task completion rate is selected to match the task.

8. The LoRaWAN-based intelligent management method for mining equipment according to claim 6, characterized in that: The real-time adjustment of abnormal tasks during the transportation process includes: when the recommended transport vehicle is unable to perform the task due to a sudden failure, re-execute steps S2-S6, and recalculate the health index, task completion score, matching score and priority score based on the real-time data of the remaining available transport vehicles to generate a new recommendation result.

9. A LoRaWAN-based intelligent management system for mining equipment, wherein the system is applied to the LoRaWAN-based intelligent management method for mining equipment according to any one of claims 1 to 8, characterized in that: The system includes: a transport vehicle data acquisition module, a transport vehicle data processing module, a health index and task completion analysis module, a matching analysis module, a priority analysis module and a transport vehicle task management module; The transport vehicle data acquisition module is used to collect the transport vehicle's operating data, health data and mission history data; The transport vehicle data processing module is used to pre-process and extract features from the data to generate standardized feature data; The health index and task completion analysis module is used to calculate the health index and task completion of the transport vehicle respectively based on the standardized feature data through the health assessment model and the task completion model; The matching analysis module is used to establish a matching model between the transport vehicle attributes and the transport task requirements, and calculate the matching degree of the transport vehicle to the target task; The priority analysis module is used to comprehensively consider the health index, task completion and matching scores, construct a priority scoring model, and analyze the priority of the transport vehicle; The transport vehicle task management module is used to recommend the transport vehicle with the highest priority for the target transport task according to the priority, and to make real-time adjustments to abnormal tasks during the transport process.

10. The LoRaWAN-based intelligent management system for mining equipment according to claim 9, characterized in that: The transport vehicle data acquisition module, transport vehicle data processing module, health index and task completion analysis module, matching analysis module, priority analysis module and transport vehicle task management module are connected to the core processor via Lo RaWAN. After a task is assigned, the real-time updated data is backed up to the core processor.

Images