A battery management system for driverless vehicles underground in coal mines

Abstract

The present invention discloses a battery management system for driverless vehicles in coal mines, which relates to the technical field of vehicle data analysis. It includes determining a transportation path matching the transportation task information on the coal mine underground map, screening the transportation path according to the vehicle power situation, road conditions and battery conditions, and selecting a path with the highest vehicle-road adaptability, providing a reliable basis for the prediction of the vehicle battery discharge parameter curve and the comparison of battery discharge parameters in the follow-up. A standard curve of the vehicle battery discharge related parameters during the transportation of the driverless vehicle in the coal mine is set, and the difference between the standard curve and the actual curve is compared to evaluate the vehicle battery health. The vehicle battery health change situation is evaluated in units of single tasks, improving the reliability and adaptability of the battery management of the driverless vehicle, optimizing the maintenance and management of the battery, and thus prolonging the usability and safety of the vehicle battery.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle data analysis, and particularly to a battery management system for driverless vehicles in coal mines. Background Art

[0002] The background art of the battery management solution for driverless vehicles in coal mines is mainly based on the current development trends of mine intelligence and automation, as well as the continuous progress of battery technology. With the accelerating application of new-generation information technologies such as artificial intelligence and 5G, the driverless technology in mining areas has reached a quite high level of automation, and L4-level driverless has become possible in mining areas. The environment in coal mines is complex, posing higher requirements for the performance and safety of vehicle batteries. Therefore, the battery management solution needs to comprehensively consider various factors such as the health status, charge and discharge efficiency, safety, and service life of the battery. By real-time monitoring of key parameters of the battery, such as voltage, current, temperature, etc., combined with the degree of battery health change, dynamically adjust the charge and discharge strategy to optimize the battery performance, extend the battery life, and ensure the safe and stable operation of the vehicle. In addition, with the continuous development of battery technology, the research and development of high-capacity, high-power, and long-life power batteries have become the key, providing more possibilities for the battery management of driverless vehicles in coal mines.

[0003] In the prior art, the monitoring of the vehicle battery health is to check the vehicle battery at fixed intervals. However, each vehicle transportation task is different, and the regular battery monitoring cannot meet the requirements of complex battery management, resulting in poor reliability and adaptability of the battery management of driverless vehicles and being unfavorable for the maintenance of vehicle batteries.

[0004] Therefore, how to improve the reliability and adaptability of the battery management of driverless vehicles is a technical problem to be solved at present. Summary of the Invention

[0005] The purpose of the present invention is to solve the problem of poor reliability and adaptability of the battery management of driverless vehicles due to the inspection of the vehicle battery at fixed intervals in the prior art, and to propose a battery management system for driverless vehicles in coal mines, which includes

[0006] A determination module, configured to obtain the basic information, transportation task information, and coal mine underground map of the driverless vehicle in the coal mine, and determine a transportation path matching the transportation task information on the coal mine underground map;

[0007] A prediction module, configured to set a standard curve of the relevant parameters of the vehicle battery discharge during the transportation of the driverless vehicle in the coal mine according to the basic information, transportation task information, and transportation path of the driverless vehicle in the coal mine;

[0008] An analysis module is used to collect the actual curve of the vehicle battery discharge - related parameters during the transportation of the driverless vehicle underground in the coal mine, and evaluate the vehicle battery health by comparing the differences between the standard curve and the actual curve, so as to obtain the battery health change degree.

[0009] An optimization module is used to set the next vehicle battery charging and discharging strategy based on the battery health change degree, so as to optimize the battery management of the driverless vehicle underground in the coal mine.

[0010] In some embodiments of the present application, the determination module is specifically used for

[0011] The transportation task information includes the starting point, the ending point and the weight of the transported goods. The starting point and the ending point are marked on the underground coal - mine map, and multiple optional paths are determined by performing path search based on the starting point and the ending point through a path - planning algorithm. The road features on each optional path are extracted and divided into vehicle road features and non - vehicle road features.

[0012] The basic information of the driverless vehicle underground in the coal mine includes vehicle power information and vehicle battery information. The extreme values, average values and vehicle power consumption of the vehicle power characteristics of the driverless vehicle on the optional paths are predicted according to the vehicle power information and the weight of the transported goods. The road adaptability of each optional path is calculated based on the extreme values, average values of the vehicle power characteristics, vehicle power consumption, vehicle road features and non - vehicle road features. The types of vehicle power characteristics correspond to the types of vehicle road features.

[0013] ;

[0014] Among them, is the road adaptability of the th optional path, , are the numbers of types of vehicle power characteristics and non - vehicle road features respectively, , are the combined weights of the extreme value and average value of the rd vehicle power characteristic respectively, , are the extreme value and average value of the th vehicle power characteristic of the th optional path respectively, is the size of the th vehicle road feature, is the combined weight of the th non - vehicle road feature, is the th optional path's th non - vehicle road feature size, is the The power consumption of the vehicle for the optional path is the constant corresponding to the th optional path;

[0015] Find the optimal optional path from multiple optional paths through the road adaptability, and use the optimal optional path as the transportation path matching the transportation task information.

[0016] In some embodiments of the present application, the prediction module is specifically used for

[0017] Extract features according to the basic information of the driverless vehicle underground in the coal mine, the transportation task information, and the transportation path of the underground map of the coal mine, and construct a prediction model for the vehicle battery discharge parameters;

[0018] The prediction model of the vehicle battery discharge parameters outputs the change curve of the vehicle battery discharge-related parameters during the transportation of the driverless vehicle underground in the coal mine. The abscissa of the change curve is the distance of the transportation path, and the ordinate is the vehicle battery discharge-related parameters;

[0019] Collect the planning information of all driverless vehicles involved in the transportation path, and adjust the change curve of the vehicle battery discharge-related parameters according to the planning information to generate a standard curve of the vehicle battery discharge-related parameters.

[0020] In some embodiments of the present application, it further includes a traffic congestion module. The traffic congestion module is used to adjust the change curve of the vehicle battery discharge-related parameters according to the planning information. Specifically,

[0021] Mark all driverless vehicles on the underground map of the coal mine, and perform vehicle driving simulation on the underground map of the coal mine according to the planning information on the time scale;

[0022] Denote the driverless vehicle to be analyzed as the target vehicle, and denote other driverless vehicles as the remaining vehicles;

[0023] Split the transportation path of the target vehicle into multiple sections. During the vehicle driving simulation on the underground map of the coal mine, calculate the vehicle density around the target vehicle, and count the driving speeds of the target vehicle and the remaining vehicles within the preset range of the vehicle density to determine the average driving speed. Determine the vehicle intersection number of each section according to the transportation path of the target vehicle and the transportation path of the remaining vehicles;

[0024] Based on the vehicle intersection number, average driving speed, and vehicle density around the target vehicle of the section, determine the potential congestion sections and section positions in multiple sections, and capture the congestion information on the potential congestion sections;

[0025] Mark the potentially congested sections at the corresponding positions on the change curve of the vehicle battery discharge-related parameters, and adjust the change curve of the vehicle battery discharge-related parameters according to the congestion information.

[0026] In some embodiments of the present application, the analysis module includes an acquisition management unit and a difference calculation unit.

[0027] In some embodiments of the present application, the acquisition management unit is used to

[0028] Collect the actual values of the vehicle battery discharge-related parameters during the transportation of the underground coal mine driverless vehicle through the BMS system on the driverless vehicle, and monitor the vehicle positioning situation during the transportation of the driverless vehicle, so as to establish the actual curve of the vehicle battery discharge-related parameters during the transportation of the driverless vehicle.

[0029] In some embodiments of the present application, the difference calculation unit is used to

[0030] Obtain the actual driving conditions of the underground coal mine driverless vehicle, cooperate to count the actual driving conditions of all underground coal mine driverless vehicles, determine the congested sections, and mark the congested sections on the actual curve;

[0031] When comparing the differences between the standard curve and the actual curve, both the standard curve and the actual curve are divided into a congested part and a non-congested part;

[0032] Extract the curve characteristics of the congested part and the non-congested part of the standard curve and the actual curve respectively, compare the curve characteristics of the congested part and the non-congested part of the standard curve and the actual curve respectively, and comprehensively determine the degree of change in the vehicle battery health after the completion of this task.

[0033] In some embodiments of the present application, the optimization module is specifically used to

[0034] Analyze the degree of change in the vehicle battery health to set the next vehicle battery charge and discharge strategy, and help formulate the vehicle battery maintenance plan and safety management.

[0035] Compared with the prior art, the beneficial effects of the present invention are:

[0036] 1. Determine the transportation path that matches the transportation task information on the underground coal mine map, screen the transportation path according to the vehicle power situation, road conditions and battery conditions, and select a path with the highest vehicle and road adaptability to ensure the rationality of the path of the driverless vehicle, and provide a reliable basis for the prediction of the vehicle battery discharge parameter curve and the comparison of the battery discharge parameters in the future.

[0037] 2. Set the standard curve of the relevant parameters of the vehicle battery discharge during the transportation of the driverless vehicle underground in the coal mine. Compare the differences between the standard curve and the actual curve to evaluate the health of the vehicle battery, and obtain the change in the battery health caused by this task. Evaluate the change in the battery health of the vehicle on a single-task basis, which improves the reliability and adaptability of the battery management of the driverless vehicle, assists in the subsequent charge and discharge strategies, optimizes the maintenance and management of the battery, thereby extending the availability and safety of the vehicle battery, and ensuring the normal transportation of the driverless vehicle underground in the coal mine. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 FIG. is a schematic structural diagram of a battery management system for a driverless vehicle underground in a coal mine proposed by the present invention;

[0039] Figure 2 FIG. is a schematic structural diagram of an analysis module in a battery management system for a driverless vehicle underground in a coal mine proposed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments.

[0041] Refer to Figure 1 , a battery management system for a driverless vehicle underground in a coal mine, including the following modules and units,

[0042] A determination module is used to obtain the basic information, transportation task information, and underground coal mine map of the driverless vehicle underground in the coal mine, and determine the transportation path matching the transportation task information on the underground coal mine map.

[0043] In this embodiment, the basic information of the driverless vehicle includes the vehicle model, battery capacity, maximum cruising range, battery health status, etc. This information can be obtained through the vehicle management system or on-vehicle sensors. The transportation task information includes the starting point, ending point, cargo weight, transportation time, etc. of the transportation. This information is usually provided by the dispatching system of the mine. The underground coal mine map includes information such as the layout of the roadway, slope, bend, obstacles, etc. This information can be obtained through a three-dimensional geographic information system (3DGIS) or lidar scanning. After obtaining these data, preprocessing is required to ensure the accuracy and consistency of the data. For example, cleaning and calibration of the map data, and formatting and standardization of the vehicle and transportation task information.

[0044] In this embodiment, the path planning algorithm: Based on the underground coal mine map and transportation task information, the path planning algorithm (such as A* algorithm, Dijkstra algorithm, etc.) is used to calculate the optional transportation paths from the starting point to the ending point. Path feasibility check: Conduct a feasibility check on the planned paths to ensure that the paths meet the driving requirements of the vehicle (such as maximum gradient, minimum turning radius, etc.), and define the road suitability of the vehicle for each optional path, which describes the suitability between the vehicle and the road.

[0045] In some embodiments of the present application, the determining module is specifically configured to,

[0046] The transportation task information includes the starting point, the ending point, and the weight of the transported goods. The starting point and the ending point are marked on the underground coal mine map, and multiple optional paths are determined by searching for paths based on the starting point and the ending point through the path planning algorithm. The road features on each optional path are extracted, and the road features are divided into vehicle road features and non-vehicle road features;

[0047] The basic information of the driverless vehicle in the underground coal mine includes vehicle power information and vehicle battery information. According to the vehicle power information and the weight of the transported goods, the extreme values, average values, and vehicle power consumption of the vehicle power characteristics of the driverless vehicle on the optional paths are predicted. Based on the extreme values, average values of the vehicle power characteristics, vehicle power consumption, vehicle road features, and non-vehicle road features, the road suitability of each optional path is calculated. The types of vehicle power characteristics correspond to the types of vehicle road features;

[0048] The optimal optional path is found from multiple optional paths through the road suitability, and the optimal optional path is used as the transportation path that matches the transportation task information.

[0049] In this embodiment, the road suitability. Map modeling: Convert the map information of the underground coal mine into a graph structure in graph theory, where nodes represent key positions (such as intersections, loading and unloading points, etc.), and edges represent road sections and their attributes (such as length, gradient, turning radius, etc.). Using the selected path planning algorithm (such as A algorithm), search for all optional paths from the starting point to the ending point in the graph structure. The A algorithm evaluates the pros and cons of each node by combining the actual cost (the length of the path from the starting point to the current node) and the estimated cost (the estimated value from the current node to the target node), so as to guide the search to expand towards the target node. After obtaining all optional paths, it is necessary to comprehensively consider influencing factors such as road section conditions, vehicle battery conditions, and cargo load conditions to screen out the most reliable optional path.

[0050] In this embodiment, the vehicle road characteristics are homogeneous road characteristics such as slope, turning radius, and section speed limit that can be compared with the vehicle power, and the non-vehicle road characteristics are road characteristics such as road flatness and road congestion that cannot be compared with the vehicle power. A vehicle dynamics model is established, which is the basis for predicting vehicle power characteristics and power consumption. This model needs to comprehensively consider factors such as the mass, speed, acceleration of the vehicle, and the friction between the tires and the ground. For driverless vehicles, the influence of the control strategy of the autonomous driving system on the vehicle power characteristics also needs to be considered. The weight of the transported goods will directly affect the vehicle's power characteristics and power consumption. A heavier transported goods will increase the vehicle's load, resulting in the vehicle needing more power to overcome the friction, thereby increasing the power consumption. Therefore, during the prediction process, the weight of the transported goods needs to be used as an input parameter and its influence on the vehicle power characteristics needs to be considered. For each optional path, using the vehicle dynamics model and the information of the transported goods weight, predict the vehicle's power characteristics on this path. This includes the extreme values (maximum or minimum values) and average values of parameters such as the vehicle's speed, traction force, and turning radius. Based on the vehicle power characteristics and the weight of the transported goods, the vehicle's power consumption on this path can be further predicted. This usually involves converting the vehicle's power demand into electrical energy consumption and considering factors such as the charge and discharge efficiency of the battery.

[0051] In this embodiment, the vehicle power characteristics correspond to the types of vehicle road characteristics (the types are the same), and the ratio between the two illustrates the compatibility degree of the vehicle power and the road conditions. The compatibility degrees of the extreme values and the average values illustrate different stability conditions of the vehicle. For example, the ratio of the maximum climbing slope of the vehicle to the section slope, and the ratio of the maximum traction force of the vehicle to the traction force required by the road. It represents the correction of the vehicle power consumption to the sum of the compatibility degrees of the vehicle road characteristics and the non-vehicle road characteristics. It is to balance the magnitude of the correction function.

[0052] A prediction module is used to set a standard curve of the vehicle battery discharge-related parameters during the transportation of the underground coal mine driverless vehicle according to the basic information, transportation task information, and transportation path of the underground coal mine driverless vehicle.

[0053] In this embodiment, according to the basic information, transportation task information, and transportation path of the driverless vehicle, a standard change curve of the vehicle battery discharge parameters is set. This includes the change relationships of parameters such as the voltage, current, and capacity of the battery over time.

[0054] In some embodiments of the present application, the prediction module is specifically used for

[0055] extracting features according to the basic information, transportation task information, and transportation path of the underground coal mine driverless vehicle on the underground coal mine map, and constructing a vehicle battery discharge parameter prediction model;

[0056] The vehicle battery discharge parameter prediction model outputs the change curve of the vehicle battery discharge related parameters during the transportation of the underground driverless vehicle in the coal mine. The abscissa of the change curve is the distance of the transportation path, and the ordinate is the vehicle battery discharge related parameters;

[0057] Collect the planning information of all driverless vehicles involved in the transportation path, and adjust the change curve of the vehicle battery discharge related parameters according to the planning information to generate the standard curve of the vehicle battery discharge related parameters.

[0058] In this embodiment, the vehicle battery discharge parameter prediction model uses statistical methods to analyze historical data, identify key factors related to battery discharge parameters (such as voltage, current, capacity, etc.), and conduct correlation analysis on (load, power condition, road condition) to determine which factors have a significant impact on battery discharge parameters. Use visualization tools (such as charts, scatter plots, etc.) to display the relationship between data to help understand data characteristics and trends. According to the data analysis results, select the appropriate model type. This can be a simple empirical formula to describe the linear or nonlinear relationship between battery discharge parameters and key influencing factors.

[0059] Model establishment process:

[0060] Data preprocessing: Clean, denoise, normalize, etc. the collected data to ensure data quality.

[0061] Feature selection: According to the data analysis results, select the features that have a significant impact on battery discharge parameters as the model input.

[0062] Model training: Use the processed data to train the model and adjust the model parameters to optimize the prediction performance.

[0063] Model verification: Use an independent data set to verify the model performance to ensure that the model can accurately predict battery discharge parameters.

[0064] The model generates the standard change curve of battery discharge parameters according to the input data.

[0065] This curve takes the path length as the abscissa and the change of battery related discharge parameters (such as voltage, current, capacity, etc.) as the ordinate.

[0066] The curve can show the change trend of battery discharge parameters with the path length, helping to understand the discharge behavior of the battery under different transportation conditions.

[0067] It should be noted that the change curve of battery discharge parameters predicted by this model does not include the state of the vehicle during congestion. Therefore, it is necessary to consider the impact of congestion on the curve and adjust the curve. The frequent start and stop of the vehicle under congestion will have an impact on the discharge parameters and battery performance.

[0068] In some embodiments of the present application, a traffic congestion module is further included. The traffic congestion module is used to adjust the change curve of the vehicle battery discharge related parameters according to the planning information. Specifically,

[0069] All driverless vehicles are marked on the underground coal mine map, and vehicle driving simulation is carried out on the underground coal mine map according to the planning information on the time scale;

[0070] The driverless vehicle to be analyzed is denoted as the target vehicle, and other driverless vehicles are denoted as the remaining vehicles;

[0071] The transportation path of the target vehicle is split into multiple sections. During the vehicle driving simulation on the underground coal mine map, the vehicle density around the target vehicle is calculated, and the driving speeds of the target vehicle and the remaining vehicles within a preset range of the vehicle density are counted to determine the average driving speed. The vehicle intersection number of each section is determined according to the transportation path of the target vehicle and the transportation path of the remaining vehicles;

[0072] Based on the vehicle intersection number of the section, the average driving speed, and the vehicle density around the target vehicle, potential congestion sections and section positions in the multiple sections are determined, and congestion information on the potential congestion sections is captured;

[0073] The potential congestion sections are marked at the corresponding positions of the change curve of the vehicle battery discharge related parameters, and the change curve of the vehicle battery discharge related parameters is adjusted according to the congestion information.

[0074] In this embodiment, the vehicle density refers to the number of vehicles driving simultaneously on the road near the target vehicle, and the driving speed refers to the average speed of the vehicle driving on the road. The vehicle intersection number refers to the intersection points between different vehicle driving paths. The potential congestion sections are determined comprehensively based on the vehicle intersection number of the section, the average driving speed, and the vehicle density around the target vehicle. The congestion information on the potential congestion sections and the congestion sections are input into the vehicle battery discharge parameter prediction model to adjust the change curve of the vehicle battery discharge related parameters.

[0075] It can be understood that the standard curve of the discharge parameter is predicted according to the current state of the vehicle battery and the section conditions.

[0076] An analysis module is used to collect the actual curve of the vehicle battery discharge related parameters during the transportation of the driverless vehicle underground in the coal mine, compare the difference between the standard curve and the actual curve to evaluate the vehicle battery health, and obtain the battery health change degree.

[0077] In some embodiments of the present application, as Figure 2 shown, the analysis module includes a collection management unit and a difference calculation unit.

[0078] In some embodiments of the present application, the acquisition management unit is configured to

[0079] Collect the actual values of the vehicle battery discharge-related parameters of the driverless vehicle in the coal mine during transportation through the BMS system on the driverless vehicle, and monitor the vehicle positioning situation of the driverless vehicle during transportation, so as to establish the actual curve of the vehicle battery discharge-related parameters of the driverless vehicle during transportation.

[0080] In this embodiment, the battery management system (BMS) is the core component that controls the battery discharge strategy of the driverless vehicle. It is responsible for monitoring the state of the battery, including key parameters such as voltage, current, and temperature, and adjusting the battery discharge strategy according to these parameters. The main functions of the BMS include: State monitoring: Real-time monitoring of battery parameters such as voltage, current, and temperature through sensors to ensure that the battery operates within a safe range. Balancing control: Since the performance of each individual battery in the battery pack may vary, the BMS needs to implement balancing control of the battery pack to ensure that each individual battery can be fully discharged and avoid overcharging or over-discharging. Protection mechanism: When abnormal situations such as overvoltage, undervoltage, overcurrent, and overheating occur in the battery, the BMS needs to quickly activate the protection mechanism to cut off the charging and discharging circuit of the battery to prevent battery damage or safety accidents.

[0081] In some embodiments of the present application, the difference calculation unit is configured to

[0082] Obtain the actual driving conditions of the driverless vehicle in the coal mine, cooperate to count the actual driving conditions of all driverless vehicles in the coal mine, determine the congested sections, and mark the congested sections on the actual curve;

[0083] When comparing the differences between the standard curve and the actual curve, both the standard curve and the actual curve are divided into congested parts and non-congested parts;

[0084] Extract the curve characteristics of the congested parts and non-congested parts of the standard curve and the actual curve respectively, compare the curve characteristics of the congested parts and non-congested parts of the standard curve and the actual curve respectively, and comprehensively determine the degree of change in the vehicle battery health after the end of this task.

[0085] In this embodiment, the difference between the standard curve and the actual curve describes the degree of change in battery health after the execution of this task (this degree of change will be set very small to capture the battery health change after a single task). For example, if the voltage drop rate of the actual curve is significantly faster than the standard curve, it may indicate serious battery capacity attenuation; if the current fluctuation amplitude of the actual curve is large, it may indicate internal battery faults or aging phenomena.

[0086] In this embodiment, the two curves are divided into a congested part and a non-congested part, and the same part is compared. The curve features include slope features, fluctuation amplitude features, etc. For example, the slope difference may indicate that the discharge rate of the battery is different at different path distances. For example, a steeper actual curve slope may mean that the battery discharges faster on this section of the path, which may be caused by reasons such as battery capacity attenuation, internal resistance increase, or load change.

[0087] In this embodiment, the curve features of the congested part and the non-congested part of the standard curve and the actual curve are respectively compared, and the differences in each type of curve feature of each type of discharge parameter in the two parts of the congested part and the non-congested part are compared. Since there are frequent starts and stops when comparing the congested part and the non-congested part, the slope of the curve may be steeper, etc., and the thresholds of the two parts are different. After synthesis, the overall change degree of each discharge parameter in the two parts is determined, and the health change degree of the vehicle battery after this task is determined.

[0088] ;

[0089] Among them, is the health change degree of the vehicle battery after this task, 、 are the conversion coefficients of the congested part and the non-congested part respectively, 、 are the numbers of the discharge parameters of the congested part and the non-congested part respectively, 、 are the influence weights of the th discharge parameter and the th discharge parameter respectively, 、 are the overall change degrees of the th discharge parameter and the th discharge parameter respectively, represents the sum of the respective maximum values in, is a constant determined by the battery health degree before the task, in order to balance the magnitude of the correction function, represents the correction of the sum of the respective maximum values in to the sum of the congested part and the non-congested part.

[0090] The optimization module is used to set the charging and discharging strategy of the vehicle battery next time through the battery health change degree, so as to optimize the battery management of the driverless vehicle underground in the coal mine.

[0091] Referring to Figure 2 , in some embodiments of the present application, the optimization module is specifically used for,

[0092] Analyze the degree of change in the health of the vehicle battery to set the next charging and discharging strategy for the vehicle battery, and help formulate a vehicle battery maintenance plan and safety management.

[0093] In this embodiment, the degree of change in battery health, that is, the change in the State of Health (SOH) of the battery, is an important indicator for measuring the remaining battery life and performance. As the number of battery charge-discharge cycles increases, and affected by factors such as temperature and charge-discharge rate, physical and chemical changes will occur inside the battery, resulting in a gradual decrease in the SOH value and a reduction in the available battery capacity. This change not only affects the battery's driving range but also directly relates to the battery's charge-discharge efficiency and safety.

[0094] Charging strategy:

[0095] When the degree of change in battery health indicates a decline in battery performance, the charging strategy can be appropriately adjusted, such as reducing the charging rate and extending the charging time, to reduce damage to the battery and extend its life.

[0096] For batteries with a lower health level, a more gentle charging method, such as slow charging, can be adopted to avoid overheating and damage inside the battery caused by too fast a charging rate.

[0097] Discharging strategy:

[0098] According to the degree of change in battery health, the driving strategy of the driverless vehicle can be optimized, such as reasonably planning the route and avoiding unnecessary sudden accelerations and sudden brakes, to reduce energy loss during the battery discharge process.

[0099] In the case of a lower battery health level, the vehicle's power output can be adjusted to reduce the load requirement on the battery, thereby extending the battery's usage time.

[0100] In addition to helping adjust the charging and discharging strategy, the degree of change in battery health can also provide strong support for vehicle battery management in the following aspects:

[0101] Battery maintenance plan:

[0102] According to the degree of change in battery health, a more scientific battery maintenance plan can be formulated, including regular inspections, performance tests, and replacement plans. This helps to promptly detect and handle potential battery problems and extend the battery's service life.

[0103] Battery performance evaluation:

[0104] By monitoring the degree of change in battery health, the performance status of the battery can be evaluated in real time, providing an important reference for vehicle scheduling and operation. For example, in the case of a lower battery health level, vehicles can be preferentially arranged for charging or battery replacement to ensure the normal operation of the vehicles.

[0105] Safety Management:

[0106] The degree of battery health change can also help identify potential safety hazards of the battery. When the battery health drops to a certain level, it may mean that the battery has risks such as overheating and short - circuit. At this time, measures can be taken in a timely manner, such as reducing the vehicle running speed, restricting the depth of battery discharge, etc., to ensure the safety of the vehicle and personnel.

[0107] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0108] 1. Determine the transportation path matching the transportation task information on the underground coal mine map, screen the transportation path according to the vehicle power condition, road condition and battery condition, and select a path with the highest vehicle - road adaptability to ensure the rationality of the path of the driverless vehicle, providing a reliable basis for the subsequent prediction of the vehicle battery discharge parameter curve and the comparison of battery discharge parameters.

[0109] 2. Set the standard curve of the vehicle battery discharge - related parameters during the transportation of the underground coal mine driverless vehicle, compare the difference between the standard curve and the actual curve to evaluate the vehicle battery health, obtain the change of the battery health degree caused by this task, evaluate the change of the vehicle battery health with a single task as a unit, improve the reliability and adaptability of the battery management of the driverless vehicle, assist in the subsequent charge - discharge strategy, optimize the battery maintenance and management situation, thereby extending the availability and safety of the vehicle battery and ensuring the normal transportation of the underground coal mine driverless vehicle.

[0110] Through the description of the above - mentioned implementation manners, those skilled in the art can clearly understand that the present invention can be implemented by hardware or by means of software plus a necessary general - purpose hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non - volatile storage medium (which can be a CD - ROM, USB flash drive, mobile hard disk, etc.), including several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in various implementation scenarios of the present invention.

[0111] Those skilled in the art can understand that the drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the drawings are not necessarily essential for implementing the present invention.

[0112] Those skilled in the art can understand that the modules in the system in the implementation scenario can be distributed in the system of the implementation scenario according to the description of the implementation scenario, or can be correspondingly changed and located in one or more systems different from the present implementation scenario. The modules in the above - mentioned implementation scenario can be combined into one module, or can be further split into multiple sub - modules.

[0113] As described above, it is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention should cover within the protection scope of the present invention by making equivalent replacements or changes according to the technical solution of the present invention and its inventive concept.

Claims

1. A battery management system for a driverless vehicle underground in a coal mine, characterized in that, Including, A determination module, configured to obtain the basic information, transportation task information, and underground coal mine map of the driverless vehicle in the coal mine, and determine a transportation path matching the transportation task information on the underground coal mine map; A prediction module, configured to set a standard curve of parameters related to the discharge of the vehicle battery during the transportation of the driverless vehicle in the coal mine according to the basic information, transportation task information, and transportation path of the driverless vehicle in the coal mine; An analysis module, configured to collect the actual curve of parameters related to the discharge of the vehicle battery during the transportation of the driverless vehicle in the coal mine, and evaluate the health of the vehicle battery by comparing the differences between the standard curve and the actual curve, so as to obtain the degree of change in battery health; An optimization module, configured to set the next charge and discharge strategy of the vehicle battery according to the degree of change in battery health, so as to optimize the battery management of the driverless vehicle in the coal mine; Wherein, The determination module is specifically configured to, The transportation task information includes the starting point, the ending point, and the weight of the transported material, mark the starting point and the ending point on the underground coal mine map, perform path search based on the starting point and the ending point through a path planning algorithm to determine multiple optional paths, extract the road features on each optional path, and classify the road features into vehicle road features and non-vehicle road features; The basic information of the driverless vehicle in the coal mine includes vehicle power information and vehicle battery information. According to the vehicle power information and the weight of the transported material, predict the extreme value, average value, and vehicle power consumption of the vehicle power characteristics of the driverless vehicle on the optional path. Calculate the road suitability of each optional path based on the extreme value, average value, vehicle power consumption, vehicle road features, and non-vehicle road features of the vehicle power characteristics. The types of vehicle power characteristics correspond to the types of vehicle road features; ； Among them, is the road adaptability of the th optional path, and are respectively the number of types of vehicle power characteristics and non-vehicle road characteristics, and are respectively the combined weights of the extreme value and the average value of the th vehicle power characteristic, and are respectively the extreme value and the average value of the th vehicle power characteristic of the th optional path, is the magnitude of the th vehicle road characteristic, is the combined weight of the th non-vehicle road characteristic, is the magnitude of the th non-vehicle road characteristic of the th optional path, is the vehicle power consumption of the th optional path, is the constant corresponding to the th optional path; Find the optimal optional path among the multiple optional paths through the road suitability, and use the optimal optional path as the transportation path matching the transportation task information.

2. The battery management system of the driverless vehicle underground in a coal mine according to claim 1, wherein The prediction module is specifically configured to, Extract features according to the basic information, transportation task information, and transportation path of the underground coal mine map of the driverless vehicle in the coal mine, and construct a prediction model for vehicle battery discharge parameters; The prediction model for vehicle battery discharge parameters outputs a change curve of parameters related to the discharge of the vehicle battery during the transportation of the driverless vehicle in the coal mine. The abscissa of the change curve is the distance of the transportation path, and the ordinate is the parameters related to the discharge of the vehicle battery; Collect the planning information of all driverless vehicles involved in the transportation path, and adjust the change curve of the parameters related to the discharge of the vehicle battery according to the planning information to generate a standard curve of the parameters related to the discharge of the vehicle battery.

3. The battery management system of the driverless vehicle underground in a coal mine according to claim 2, characterized in that, It further includes a traffic congestion module, and the traffic congestion module is configured to adjust the change curve of the parameters related to the discharge of the vehicle battery according to the planning information. Specifically, Mark all driverless vehicles on the underground coal mine map, and perform vehicle driving simulation on the underground coal mine map according to the planning information on the time scale; Denote the driverless vehicle to be analyzed as the target vehicle, and denote other driverless vehicles as the remaining vehicles; The transportation path of the target vehicle is split into multiple sections. During the process of simulating vehicle driving on the underground coal mine map, the vehicle density around the target vehicle is calculated, and the driving speeds of the target vehicle and other vehicles with vehicle density within a preset range are statistically analyzed to determine the average driving speed. The number of vehicle intersections in each section is determined based on the transportation paths of the target vehicle and other vehicles. Based on the number of vehicle intersections in the section, the average driving speed, and the vehicle density around the target vehicle, potential congestion sections and their locations in the multiple sections are determined, and congestion information on the potential congestion sections is captured. The potential congestion sections are marked at the corresponding positions of the change curve of the parameters related to vehicle battery discharge, and the change curve of the parameters related to vehicle battery discharge is adjusted according to the congestion information.

4. The battery management system of the driverless vehicle in the coal mine according to claim 1, characterized in that, The analysis module includes a collection management unit and a difference calculation unit.

5. The battery management system of the driverless vehicle underground in a coal mine according to claim 4, wherein, The collection management unit is used for collecting the actual values of the parameters related to vehicle battery discharge during the transportation of the underground coal mine driverless vehicle through the BMS system on the driverless vehicle, and monitoring the vehicle positioning situation during the transportation of the driverless vehicle, so as to establish the actual curve of the parameters related to vehicle battery discharge during the transportation of the driverless vehicle.

6. The battery management system of the driverless vehicle in the coal mine according to claim 4, characterized in that, The difference calculation unit is used for obtaining the actual driving situation of the underground coal mine driverless vehicle, collaboratively statistically analyzing the actual driving situations of all underground coal mine driverless vehicles, determining the congestion sections, and marking the congestion sections on the actual curve; When comparing the differences between the standard curve and the actual curve, both the standard curve and the actual curve are divided into a congestion part and a non-congestion part; The curve features of the congestion part and the non-congestion part of the standard curve and the actual curve are extracted respectively, the curve features of the congestion part and the non-congestion part of the standard curve and the actual curve are compared respectively, and the degree of change in vehicle battery health after the completion of this task is determined comprehensively.

7. The battery management system of the driverless vehicle underground in a coal mine according to claim 1, characterized in that The optimization module is specifically used for analyzing the degree of change in vehicle battery health to set the next vehicle battery charge and discharge strategy, and helping to formulate the vehicle battery maintenance plan and safety management.

Images