Charging scheduling method and device, charging station, electronic equipment and chip

Abstract

The embodiment of the invention provides a charging scheduling method and device, a charging station, electronic equipment and a chip, and the method comprises the steps: obtaining the operation state parameters of a working vehicle; determining time sequence data corresponding to the operation state parameters; determining a discharge time prediction model according to the time sequence data; determining the residual discharge time of the working vehicle according to the discharge time prediction model; determining the time length required by the transportation task of the working vehicle; determining a predefined dynamic scheduling rule; determining a first vehicle according to a predefined dynamic scheduling rule; determining a scheduling path of the first vehicle from the current position to the target charging station; and under the condition that the scheduling path is from the heavy load path to the no-load path, the load state of the first vehicle is controlled to be switched from the first load state to the second load state, so that the first vehicle is charged in the second load state. Through the scheme of the invention, the charging resource distribution is optimized, and the mine transportation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of charging scheduling, and in particular to a charging scheduling method, device, charging station, electronic equipment and chip. Background Art

[0002] As the global mining industry accelerates its transition toward a green and low-carbon economy, the electrification of transport equipment in open-pit mines has become a key industry trend. Electric mining trucks, with their zero emissions, low noise, and low operating costs, are gradually replacing traditional diesel vehicles. However, the widespread adoption of electric mining trucks has also exposed a significant lag in charging scheduling management. Static route planning and scheduled charging methods are unable to respond to dynamic mine road conditions and dynamically adjust charging schedules based on charging station load conditions. This leads to irrational allocation of charging resources and compromises mine transportation efficiency. Summary of the Invention

[0003] The purpose of the embodiments of the present invention is to provide a charging scheduling method, device, charging station, electronic device and chip, which can solve the problem that static path planning and timed charging methods cannot respond to the dynamic road conditions of mines, so as to dynamically adjust the charging scheduling according to the load status of the charging station, resulting in unreasonable allocation of charging resources and affected mine transportation efficiency.

[0004] In view of this, an embodiment of a first aspect of the present invention provides a charging scheduling method.

[0005] An embodiment of the second aspect of the present invention provides a charging scheduling device.

[0006] An embodiment of a third aspect of the present invention provides a charging station.

[0007] An embodiment of a fourth aspect of the present invention provides an electronic device.

[0008] An embodiment of the fifth aspect of the present invention provides a chip.

[0009] In order to achieve the above-mentioned purpose, an embodiment of the first aspect of the present invention provides a charging scheduling method for a charging station, which is set on an empty path of a working section of a mine, and the working section includes an empty path and a heavy-load path. The charging scheduling method includes: obtaining operating status parameters of a working vehicle, the operating status parameters include the remaining battery power, the battery health status, the load status, the driving speed, the slope factor and the environmental parameters, the load status includes a first load status and a second load status, the first load status corresponds to the heavy-load path, and the second load status corresponds to the empty path; determining the timing data corresponding to the operating status parameters; determining the discharge time prediction according to the timing data a prediction model; determining the remaining discharge time of the working vehicle according to the discharge time prediction model; determining the duration required for the transportation task of the working vehicle; in response to the condition that the remaining discharge time is less than the duration required for the transportation task, determining a predefined dynamic scheduling rule; determining a first vehicle according to the predefined dynamic scheduling rule; determining a scheduling path for the first vehicle from the current position to the target charging station; in the case where the scheduling path is a heavy-load path to an empty-load path, controlling the load state of the first vehicle to switch from the first load state to the second load state, so that the first vehicle is charged in the second load state, and returning to the first load state after charging is completed, so as to complete the charging scheduling of the first vehicle.

[0010] The charging scheduling method proposed in this invention is applied to charging stations located on the unloaded paths within a mine's working section. It intelligently schedules charging for working vehicles operating in the mine environment. By constructing a charging prediction model, it predicts the shortest path and power consumption of vehicles reaching the charging station. Furthermore, by setting dynamic modulation rules comprising multiple variables, the method automatically determines in real time whether a working vehicle should initiate a charging task based on parameters such as the vehicle's load, remaining range, remaining power, and the charging station's load status, in conjunction with a discharge time prediction model. If the rule conditions are met, the first vehicle is identified as the one to be assigned a charging task, and the first vehicle is directed to reach the charging station on the unloaded path within the working section for charging.

[0011] Understandably, the discharge time prediction model analyzes multiple operating status parameters of working vehicles to predict the remaining discharge time of the vehicles under real-time operating conditions. This model then uses predefined dynamic scheduling rules to schedule charging for multiple working vehicles in need of charging. Charging stations are assigned to working vehicles based on charging priority, ensuring that working vehicles with the highest charging priority are assigned to charging stations with the lowest charging loads. This ensures normal mine transportation operations while maximizing the utilization efficiency of charging piles in charging stations, optimizing the allocation of charging resources, and improving mine transportation efficiency.

[0012] In some technical solutions, optionally, a discharge time prediction model is determined based on time series data, including: determining the data sampling frequency of the operating status parameters; determining the time series data corresponding to the operating status parameters based on the data sampling frequency; determining the input layer based on the time series data; constructing a neural network architecture based on a long short-term memory network; performing a time series prediction operation based on the neural network architecture to determine the output layer, the output layer including the remaining discharge time; and determining the discharge time prediction model based on the input layer and the output layer.

[0013] In this solution, a discharge time prediction model is constructed using time series data corresponding to multiple operating state parameters to predict the vehicle's remaining discharge time (RDT). The discharge time prediction model is a long short-term memory (LSTM) machine learning model. The discharge time prediction model includes an input layer, a hidden layer, and an output layer. The output layer includes time series data within a preset time period in the past, such as the remaining charge (SOC) of the working vehicle, the state of health (SOH) of the working vehicle's battery, the vehicle's current load status, the vehicle's driving speed, the equivalent slope factor, and the ambient temperature, namely, time series data. The time series data is continuously collected at a preset data sampling frequency, and the continuous parameters are converted into a time series matrix according to the sampling frequency to provide a structured data set for the LSTM input layer. After the input layer receives the time series data matrix, it is output through the hidden layer to generate the vehicle's RDT value.

[0014] In some technical solutions, optionally, determining a scheduling path for a first vehicle from a current position to a target charging station includes: generating priority scores for a plurality of working vehicles based on variables in a predefined dynamic scheduling rule; determining a first vehicle according to the priority scores, the first vehicle having the highest priority score; obtaining a real-time load status of the charging station; determining a target charging station according to the real-time load status of the charging station; and determining the shortest path from the current position of the first vehicle to the target charging station as the scheduling path.

[0015] In this solution, for the working vehicles creating a charging schedule, at least one working vehicle is ranked for charging using a predefined dynamic scheduling rule comprised of multiple preset rules. This determines the charging priority of the working vehicles, with the vehicle with the highest charging priority being the first vehicle. The shortest path from the first vehicle's current location to the target charging station is determined as the scheduling path. By combining the predefined dynamic scheduling rule with the real-time load status of the charging stations, the charging schedule for the working vehicles ensures that the working vehicle with the highest charging priority is assigned to the charging station with the lowest charging load.

[0016] In some technical solutions, optionally, after completing the charging scheduling of the first vehicle, it also includes: obtaining a new transport task request; determining at least one second vehicle corresponding to the new transport task request; determining the priority score of the second vehicle; updating the charging station load status; determining an updated charging instruction based on the priority score and the updated charging station load status; and sending the updated charging instruction to the second vehicle.

[0017] This solution dynamically adjusts the queue during the charging process. Based on the principle of dispatching the highest-priority vehicle to the lowest-loaded charging station, the charging station queue is adjusted in real time. After completing the charging schedule for the first vehicle, a response is made to new transport task requests, prioritizing the charging schedule for newly added heavy-loaded vehicles. In this case, the new transport task request is a sudden, high-priority task. The priority score of the second vehicle is compared with that of the multiple scheduled vehicles to exclude low-priority vehicles currently charging, freeing up charging resources for the second vehicle with the new transport task.

[0018] In some technical solutions, optionally, predefined dynamic scheduling rules are determined, including: determining multiple variables, the variables including the urgency weight of the transport task, the quantitative value of the vehicle health status and the global balance index, the urgency weight of the transport task and the numerical value corresponding to the load status are positively correlated, and the global balance index is used to determine the threshold value of the number of working vehicles at the charging station; the predefined dynamic scheduling rules are determined through multiple variables.

[0019] In this solution, multiple variables in the predefined dynamic scheduling rules are determined. The variables include: the urgency weight of the transportation task, the quantitative value of the vehicle health status and the global balance index. The charging priority scores of multiple working vehicles that receive charging scheduling instructions are determined through the predefined dynamic scheduling rules.

[0020] An embodiment of a second aspect of the present invention provides a charging scheduling device, comprising: a data acquisition module for acquiring operating status parameters of a working vehicle, the operating status parameters including a remaining battery charge, a battery health status, a load status, a driving speed, a slope factor, and environmental parameters, the load status including a first load status and a second load status, the first load status corresponding to a heavily loaded path and the second load status corresponding to an unloaded path; a data processing module for determining time series data corresponding to the operating status parameters; determining a discharge time prediction model based on the time series data; and determining a remaining discharge time of the working vehicle based on the discharge time prediction model; a vehicle determination module for determining a required transport task duration for the working vehicle; determining a predefined dynamic scheduling rule in response to a condition that the remaining discharge time is less than the required transport task duration; and determining a first vehicle based on the predefined dynamic scheduling rule; and a scheduling decision module for determining a scheduling path for the first vehicle from a current location to a target charging station; and, if the scheduling path is a heavily loaded path to an unloaded path, controlling the load status of the first vehicle to switch from the first load status to the second load status, causing the first vehicle to charge in the second load status and then returning to the first load status after charging is complete, thereby completing charging scheduling for the first vehicle.

[0021] The data acquisition module acquires operating status parameters such as vehicle location, remaining power, load status and ambient temperature in real time; the data processing module builds a machine learning model to predict the shortest path and power consumption of the vehicle to the charging station; the scheduling decision module generates charging instructions based on the dynamic priority algorithm, sets dynamic scheduling rules, and calculates and automatically determines whether the truck should create a charging task based on the truck load, remaining mileage, remaining power and charging pile saturation status, combined with the discharge time prediction model, in real time. It also allocates charging pile resources, so that the vehicle with the highest charging priority is assigned to the charging station with the lowest load, thereby improving the utilization efficiency of charging resources and the efficiency of mine transportation.

[0022] In some technical solutions, optionally, the scheduling decision module is also used to: obtain a new transport task request; determine at least one second vehicle corresponding to the new transport task request; determine the priority score of the second vehicle; update the charging station load status; determine the updated charging instruction based on the priority score and the updated charging station load status; and send the updated charging instruction to the second vehicle.

[0023] An embodiment of the third aspect of the present application provides a charging station, which is arranged on an empty path of a working section of a mine, and the working section includes an empty path and a loaded path; the charging station includes a charging scheduling device as mentioned in the second aspect.

[0024] An embodiment of the fourth aspect of the present application provides an electronic device, including a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of the charging scheduling method in the first aspect are implemented.

[0025] An embodiment of the fifth aspect of the present application provides a chip, which includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the steps of the charging scheduling method in the first aspect.

[0026] Additional aspects and advantages of the technical solutions of the present invention will become apparent in the following description or will be understood through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A schematic diagram of a charging scheduling method according to an embodiment of the present application is shown;

[0028] Figure 2 A partial flow chart of a charging scheduling method according to an embodiment of the present application is shown;

[0029] Figure 3 A partial flow chart of a charging scheduling method according to an embodiment of the present application is shown;

[0030] Figure 4 A partial flow chart of a charging scheduling method according to an embodiment of the present application is shown;

[0031] Figure 5 A partial flow chart of a charging scheduling method according to an embodiment of the present application is shown;

[0032] Figure 6 A schematic diagram of a charging scheduling method according to an embodiment of the present application is shown;

[0033] Figure 7 A schematic structural block diagram of a charging scheduling device according to an embodiment of the present application is shown;

[0034] Figure 8 A schematic structural block diagram of an electronic device according to an embodiment of the present application is shown.

[0035] in, Figure 7 and Figure 8 The corresponding relationship between the reference numerals and component names is as follows:

[0036] 900: Charging scheduling device; 902: Data acquisition module; 904: Data processing module; 906: Vehicle determination module; 908: Scheduling decision module; 1000: Electronic device; 1109: Memory; 1110: Processor. DETAILED DESCRIPTION

[0037] In order to more clearly understand the above-mentioned purposes, features and advantages of the embodiments of the present invention, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should be noted that the embodiments of the present application and the features therein can be combined with each other in the absence of conflict.

[0038] In the following description, many specific details are set forth to facilitate a full understanding of the present application. However, the embodiments of the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present application is not limited to the specific embodiments disclosed below.

[0039] The following is combined with Figures 1 to 8 , the charging scheduling method, device, charging station, electronic device and chip provided in the embodiments of the present application are described in detail through specific embodiments and their application scenarios.

[0040] This embodiment provides a charging scheduling method for a charging station, which is set on an empty path of a working section of a mine. The working section includes an empty path and a loaded path, such as Figure 1 As shown, the charging scheduling method includes:

[0041] Step S100: Acquiring operating status parameters of the working vehicle, the operating status parameters including the remaining battery power, battery health status, load status, driving speed, slope factor, and environmental parameters. The load status includes a first load status and a second load status, where the first load status corresponds to a loaded path and the second load status corresponds to an unloaded path.

[0042] Step S102: determining the time series data corresponding to the operating status parameters;

[0043] Step S104: determining a discharge time prediction model based on the time series data;

[0044] Step S106: determining the remaining discharge time of the working vehicle according to the discharge time prediction model;

[0045] Step S108: Determine the time required for the transport task of the working vehicle;

[0046] Step S110: In response to the condition that the remaining discharge time is less than the required time of the transportation task, determining a predefined dynamic scheduling rule;

[0047] Step S112: determining a first vehicle according to a predefined dynamic dispatch rule;

[0048] Step S114: determining a dispatch path for the first vehicle from the current location to the target charging station;

[0049] Step S116: When the scheduling path is from a heavy-loaded path to an empty-loaded path, control the load state of the first vehicle to switch from the first load state to the second load state, so that the first vehicle is charged in the second load state, and returns to the first load state after charging is completed, so as to complete the charging scheduling of the first vehicle.

[0050] The charging scheduling method proposed in this invention is applied to charging stations located on the unloaded paths within a mine's working section. It intelligently schedules charging for working vehicles operating in the mine environment. By constructing a charging prediction model, it predicts the shortest path and power consumption of vehicles reaching the charging station. Furthermore, by setting dynamic modulation rules comprising multiple variables, the method automatically determines in real time whether a working vehicle should initiate a charging task based on parameters such as the vehicle's load, remaining range, remaining power, and the charging station's load status, in conjunction with a discharge time prediction model. If the rule conditions are met, the first vehicle is identified as the one to be assigned a charging task, and the first vehicle is directed to reach the charging station on the unloaded path within the working section for charging.

[0051] Specifically, dynamic data of the working vehicle is collected in real time through sensors or system modules as operating status parameters of the working vehicle. The dynamic data includes the vehicle's current location, battery remaining charge (SOC), current load status, vehicle speed, and ambient temperature. An equivalent slope factor is determined based on analysis of the vehicle's current location and speed to determine the current slope position of the working vehicle. Historical battery charge and discharge data is obtained, and the vehicle's battery health status is determined based on the battery remaining charge and battery charge and discharge history data. Environmental parameters are determined based on ambient temperature data to provide scenario data for a discharge time prediction model to subsequently predict the vehicle's remaining discharge time. The collected continuous operating status parameters are stored as a time series to determine time series data. This time series data is then used as the input for a machine learning model, such as a long short-term memory (LSTM) model, to determine a discharge time prediction model used to predict the working vehicle's remaining discharge time (RDT), i.e., the expected duration of the working vehicle's battery under current operating conditions. The time required for the vehicle to complete its current mission, i.e., the duration of the transport mission, is determined using data on the working section length, vehicle speed, and vehicle mission type. If the RDT predicted by the discharge time prediction model is less than the duration of the transport mission, the charging station triggers charging scheduling for the vehicle to prevent the vehicle from running out of power mid-mission. If at least one vehicle requires charging scheduling, the charging priority of the at least one vehicle is determined using a predefined dynamic scheduling rule comprising multiple preset rules, with the vehicle with the highest charging priority being the first vehicle. The shortest path from the current location of the first vehicle, determined according to the predefined dynamic scheduling rule, to the target charging station is planned as the dispatch path. If the first vehicle needs to switch from a heavily loaded route to a charging station, the vehicle is controlled to unload before entering the charging station, switch from a heavily loaded state to an unloaded state, then enter the charging station for charging. After charging is complete, the vehicle returns to a heavily loaded state to continue transporting. Specifically, the first vehicle's load state is controlled to switch from a first loaded state to a second loaded state, allowing the first vehicle to charge in the second loaded state and then return to the first loaded state after charging is complete, completing the charging scheduling for the first vehicle.

[0052] Furthermore, predefined dynamic scheduling rules are used as preset conditions. These rules include: task urgency assessment, charging station load rate assessment, battery health assessment, and global balance indicators. These four predefined factors determine the charging priority of the working vehicles receiving the charging schedule, assigning the highest priority working vehicles to the charging stations with the lowest charging loads. The system dynamically allocates charging vehicles based on the queue lengths at the charging stations, distributing global load across multiple charging stations within the mining environment, reducing the idle rate of charging piles within the stations, and ensuring the continuous transportation of working vehicles.

[0053] Understandably, the discharge time prediction model analyzes multiple operating status parameters of working vehicles to predict the remaining discharge time of the vehicles under real-time operating conditions. This model then uses predefined dynamic scheduling rules to schedule charging for multiple working vehicles in need of charging. Charging stations are assigned to working vehicles based on charging priority, ensuring that working vehicles with the highest charging priority are assigned to charging stations with the lowest charging loads. This ensures normal mine transportation operations while maximizing the utilization efficiency of charging piles in charging stations, optimizing the allocation of charging resources, and improving mine transportation efficiency.

[0054] In addition, by controlling the load state switching of the working vehicle and switching from the first load state to the second load state before charging, the vehicle is forced to charge in an unloaded state, reducing the equipment or battery loss caused by the deadweight pressure when heavily loaded during the charging process, and improving the charging efficiency of the working vehicle.

[0055] Exemplarily, the work vehicle is a mining truck.

[0056] For example, the first load state is a loaded driving state of a mining truck driving from a mining area in a working section to a ore unloading point after being fully loaded, corresponding to the maximum load value of the working vehicle, and the vehicle motor reaches the output peak power.

[0057] For example, the second load state is the empty state of a mining truck driving from the unloading point in the working section to the mining area, corresponding to the working vehicle having no load in the cargo box or the vehicle load being less than the minimum load threshold. At this time, the working vehicle only carries its own load, and the vehicle motor only maintains basic power. Charging the working vehicle in the second load state can improve the charging efficiency.

[0058] Optionally, when the power station uses photovoltaic power generation, a photovoltaic power generation peak period is determined, and during the photovoltaic power generation peak period, the first vehicle in an unloaded state is preferentially scheduled for charging.

[0059] Optionally, an environmental parameter threshold can be set. When the collected ambient temperature exceeds the threshold, a compensation coefficient is added to the RDT prediction value to trigger vehicle charging scheduling instructions in advance. For example, when the collected ambient temperature is greater than 40°C, a compensation coefficient of 0.7 is added to trigger charging instructions for the current working vehicle in advance. This adapts to different operating environments and provides compensation for extreme working conditions.

[0060] In some embodiments, optionally, as Figure 2 As shown, step S104: determining a discharge time prediction model based on time series data, including:

[0061] Step S1040: determining the data sampling frequency of the operating status parameters;

[0062] Step S1042: determining time series data corresponding to the operating status parameters according to the data sampling frequency;

[0063] Step S1044: Determine the input layer according to the time series data;

[0064] Step S1046: constructing a neural network architecture based on a long short-term memory network;

[0065] Step S1048: performing a time series prediction operation according to the neural network architecture to determine an output layer, the output layer including the remaining discharge time;

[0066] Step S1050: Determine a discharge time prediction model based on the input layer and the output layer.

[0067] In this embodiment, a discharge time prediction model is constructed using time series data corresponding to multiple operating state parameters to predict the vehicle RDT. The discharge time prediction model is an LSTM machine learning model. The discharge time prediction model includes an input layer, a hidden layer, and an output layer. The output layer includes time series data within a preset time period in the past, such as the working vehicle SOC, working vehicle SOH, the vehicle's current load status, vehicle speed, equivalent slope factor, and ambient temperature, i.e., time series data. The time series data is continuously obtained at a preset data sampling frequency, and the continuous parameters are converted into a time series matrix according to the sampling frequency to provide a structured data set for the LSTM input layer. After the input layer receives the time series data matrix, it is output through the hidden layer to generate the vehicle's RDT value.

[0068] As can be understood, the LSTM machine learning model learns the nonlinear time-series relationships between multiple operating state parameters and uses these parameters to predict the RDT of the operating vehicle. High-frequency sampling captures instantaneous battery voltage fluctuations, improving the accuracy of the remaining discharge time prediction for the operating vehicle. Using the SOH parameter as a time-series input, the LSTM automatically learns the nonlinear characteristics of the discharge curve of an aging battery, further improving the model's prediction accuracy and providing a theoretical basis for subsequent vehicle selection for charging scheduling. For example, when a vehicle climbs a slope under the first load state, the parameters corresponding to the vehicle's current load state, vehicle speed, and equivalent gradient factor change. The LSTM automatically associates the SOC decay rate with the vehicle's predicted RDT value and updates it. Alternatively, in low-temperature environments, the internal resistance of the battery increases, resulting in a decrease in battery discharge efficiency. The LSTM predicts this effect using historical temperature series and combines it with other operating state parameters in the input layer to update the predicted RDT value.

[0069] Furthermore, the hidden layer of LSTM includes two layers of LSTM networks, with 128 neurons in each layer, and overfitting is prevented by setting the hidden ratio Dropout = 0.2.

[0070] Optionally, after the discharge time prediction model is deployed, working data in the mine working area is automatically collected, and the model weight is automatically updated through historical working data.

[0071] In some embodiments, optionally, as Figure 3 As shown, step S114: determining a scheduling path for the first vehicle from the current position to the target charging station, including:

[0072] Step S1140: generating priority scores for a plurality of working vehicles based on variables in a predefined dynamic scheduling rule;

[0073] Step S1142: Determine the first vehicle according to the priority score, where the first vehicle has the highest priority score;

[0074] Step S1144: Obtain the real-time load status of the charging station;

[0075] Step S1146: Determine the target charging station according to the real-time load status of the charging station;

[0076] Step S1148: Determine the shortest path from the current position of the first vehicle to the target charging station as the scheduling path.

[0077] In this embodiment, for the working vehicles for which a charging schedule is created, at least one working vehicle is sorted for charging according to a predefined dynamic scheduling rule comprising multiple preset rules to determine the charging priority of the working vehicles, with the vehicle with the highest charging priority being the first vehicle. Multiple paths from the current location of the first vehicle to the target charging station are determined through system analysis, and the path with the shortest distance is determined to be the shortest path. That is, the shortest path from the current location of the first vehicle to the target charging station, as determined by the predefined dynamic scheduling rule, is determined as the scheduling path. By combining the predefined dynamic scheduling rule with the real-time load status of the charging station, the charging schedule of the working vehicles satisfies the requirement that the working vehicle with the highest charging priority be assigned to the charging station with the lowest charging load.

[0078] Furthermore, the load status of at least one charging station within the mine's working area is collected. This includes the usage and scheduling status of multiple charging piles within the charging station. Scheduling status includes situations where a charging pile has received a charging scheduling instruction but a working vehicle has not yet arrived for charging. The load status of the charging station is determined based on the usage rate of the charging piles. The charging station with the lowest real-time load status value is selected as the target charging station.

[0079] Specifically, a charging priority score is determined for at least one working vehicle subject to charging scheduling. The priority score is determined by multiple variables in a predefined dynamic scheduling rule: a task urgency weight determined by the urgency of the transport task corresponding to the working vehicle, a vehicle health status quantification value determined by the battery health coefficient corresponding to the working vehicle, and a global balance index. The global balance index aims to reduce charging congestion at charging stations by setting a penalty factor to prevent multiple working vehicles to be charged from being dispatched to the same charging station at the same time. Combined with the charging station load rate, the first vehicle with the highest priority is dispatched to the charging station with the lowest charging load for charging, maximizing the charging efficiency of the working vehicles and reducing the idle rate of charging piles at the charging station during non-concentrated periods.

[0080] Optionally, based on a map of the mine working environment and real-time road conditions, a path with the lowest energy consumption from the current position of the first vehicle to the target charging station is calculated, and the path is determined as the shortest path, that is, the scheduling path from the first vehicle to the target charging station.

[0081] Understandably, by pre-defining dynamic scheduling rules to determine the first vehicle, the vehicle with the highest charging priority is dispatched to the charging station with the lowest charging load for charging, thus avoiding the congestion of multiple vehicles. By setting a global balance indicator and a penalty factor during the vehicle determination process, the priority of multiple vehicles can be lowered when they are dispatched to the same charging station at the same time, thus reducing the average charging waiting time of working vehicles and improving the utilization of charging resources in the mining environment.

[0082] Optionally, charging scheduling instructions for working vehicles are triggered by calculating charging costs and delay costs. The charging cost is the real-time charging cost of the working vehicle, calculated using the real-time electricity price and the estimated charge amount of the working vehicle: real-time charging cost = electricity price × estimated charge amount. The delay cost is the penalty for overtime on the working vehicle's current transport mission. The total cost of the working vehicle is determined by combining the charging and delay costs, which is the sum of the charging and delay costs. This cost calculation method can adapt to different electricity prices and reduce electricity consumption costs in the mining environment.

[0083] In some embodiments, optionally, as Figure 4 As shown, after step S116: completing the charging schedule of the first vehicle, the following steps are further included:

[0084] In step S1160: obtaining a new transport task request;

[0085] Step S1162: determining at least one second vehicle corresponding to the newly added transport task request;

[0086] In step S1164: determining the priority score of the second vehicle;

[0087] In step S1166: updating the charging station load status;

[0088] In step S1168: determining an updated charging instruction based on the priority score and the updated charging station load status;

[0089] In step S1170: the updated charging instruction is sent to the second vehicle.

[0090] In this embodiment, the queue is dynamically adjusted during the charging process. Based on the principle of dispatching the vehicle with the highest charging priority to the charging station with the lowest load, the charging station charging queue is adjusted in real time. After completing the charging scheduling of the first vehicle, a response is made to the newly added transport task request, so that the newly added heavy-loaded vehicle receives priority charging scheduling. In this case, the newly added transport task request is a sudden high-priority task. The priority score of the second vehicle is compared with the priority score of multiple working vehicles subject to charging scheduling to exclude the low-priority working vehicle currently charging, freeing up charging resources for the second vehicle with the newly added transport task.

[0091] Furthermore, after completing the charging scheduling for the first vehicle, the load status of multiple charging stations within the mine operation area is updated to determine the number of idle charging piles, the number of faulty charging piles, and reserved charging piles. A reserved charging pile is a charging pile that has been scheduled for charging but for which the working vehicle has not yet arrived. If the working vehicle corresponding to the reserved charging pile has a lower priority score than the first vehicle, the reserved charging pile is preferentially scheduled for charging by the second vehicle. After the second vehicle completes charging, the priority of the working vehicle is reconfirmed, the first and second vehicles are screened, and charging scheduling is performed for the updated first and second vehicles. Charging scheduling follows the principle of assigning the working vehicle with the highest charging priority to the charging station with the lowest load.

[0092] It can be understood that by dynamically adjusting the charging queue during the charging process, new tasks in the mining operation process can be responded to, so that the second vehicle corresponding to the new task can be promptly dispatched for charging, further reducing the idle rate of the charging station and improving the efficiency of charging resource utilization.

[0093] Optionally, the queue is dynamically adjusted based on the vehicle fault type and charging pile fault data at the charging station. When a working vehicle or charging pile fails, the charging schedule is updated. For example, if a second vehicle breaks down, the second vehicle's scheduling process and transportation task are interrupted, and the charging queue associated with that vehicle is updated, with a third vehicle taking over the second vehicle's charging schedule. The charging station corresponding to the second vehicle is then updated to the third vehicle. The third vehicle's charging priority score is lower than the second vehicle's, and the third vehicle's charging priority is higher than that of other working vehicles in the charging queue.

[0094] In some embodiments, optionally, as Figure 5 As shown, step S110: in response to the condition that the remaining discharge time is less than the required time of the transportation task, determining a predefined dynamic scheduling rule includes:

[0095] Step S1102: Determine multiple variables, including the urgency weight of the transport task, the quantified value of the vehicle health status, and a global balance index. The urgency weight of the transport task and the value corresponding to the load status are positively correlated. The global balance index is used to determine the threshold number of working vehicles at the charging station.

[0096] Step S1104: determining a predefined dynamic scheduling rule through multiple variables.

[0097] In this embodiment, multiple variables in the predefined dynamic scheduling rules are determined, and the variables include: the urgency weight of the transportation task, the quantitative value of the vehicle health status and the global balance index. The charging priority scores of multiple working vehicles that receive charging scheduling instructions are determined through the predefined dynamic scheduling rules.

[0098] Furthermore, the urgency weight of the transport task is positively correlated with the value corresponding to the load status. That is, the higher the load value collected by the working vehicle, the greater the urgency weight of the transport task for that working vehicle. The vehicle health status quantification value is a function mapping of the battery health. The lower the function mapping of the SOH, the greater the value of the vehicle health status quantification value. The higher the vehicle health status quantification value, the higher the charging priority of the working vehicle. The global balance indicator prevents multiple working vehicles waiting to be charged from being dispatched to the same charging station at the same time by setting a penalty factor. That is, the enterprise operator sets the charging quantity threshold for the charging station. When the number of working vehicles in the charging dispatch queue exceeds the charging quantity threshold, the charging priority score of the working vehicle is penalized. The vehicle's charging priority score is obtained by multiplying the urgency weight of the transport task, the vehicle health status quantification value, and the global balance indicator.

[0099] As can be understood, by setting urgency weights and quantified vehicle health values, predefined dynamic scheduling rules are established to give priority to heavy-load vehicles, ensuring the continuous operation of ore transportation. Furthermore, charging stations and liquid-cooled fast-charging stations are prioritized for working vehicles with high battery health values, improving the efficiency of charging resource utilization.

[0100] Furthermore, dual control is carried out through global balance indicators to limit the service upper limit of a single charging station, reduce the risk of charging piles being overloaded and burned, and reduce the occurrence of short-term congestion on the road sections near charging stations.

[0101] Optionally, the predefined dynamic scheduling rules include: the urgency weight of the transportation task, the quantitative value of the vehicle health status, the real-time load status of the charging station and the global balance index.

[0102] In one specific embodiment, the charging scheduling method optionally operates on a charging scheduling system comprising a data acquisition module, a data processing module, and a scheduling decision module. A charging prediction model is constructed to predict the shortest path and power consumption required for a vehicle to reach a charging station. Dynamic adjustment rules are then set to automatically determine in real time whether a truck should initiate a charging task based on the truck's load, remaining range, remaining power, and the saturation status of the charging pile and / or charging station, in conjunction with a discharge time prediction model.

[0103] Among them, the data acquisition module is used to obtain vehicle location, remaining power, task type, load status, ambient temperature, etc. in real time; the data processing module predicts the remaining discharge time of the vehicle through models, such as the LSTM machine learning model; the scheduling decision module generates charging instructions based on a dynamic priority algorithm and allocates charging station resources.

[0104] Furthermore, the discharge time prediction uses an LSTM machine learning model to predict the remaining discharge time (RDT). The LSTM machine learning model includes: an input layer that uses the past 10 minutes of time series data, including state of charge (SOC), state of hydration (SOH), load, speed, equivalent slope factor, and ambient temperature; a hidden layer that uses two LSTM layers, each with 128 neurons and a hidden layer ratio of 0.2; and an output layer that outputs the truck's remaining discharge time.

[0105] The charging scheduling method calculates and automatically determines whether the vehicle should create a charging task in real time based on the remaining mileage to the target point and the set power warning value, combined with the discharge time prediction model.

[0106] Furthermore, the charging scheduling method includes:

[0107] Step 1: Real-time monitoring of vehicle status, including parameters such as SOC, SOH, load, speed, equivalent slope factor, and ambient temperature, with a data sampling frequency of 1 second / time;

[0108] Step 2: Calculate the remaining discharge time and the shortest path for the vehicle to reach each charging station in real time based on the vehicle status;

[0109] Step 3: When the RDT is lower than the time to complete the task, a dispatch instruction is automatically generated, including recommended charging stations, route navigation, and charging mode.

[0110] Step 4: Dynamic priority assessment: task urgency (heavy-loaded vehicles take precedence over unloaded vehicles); charging station load rate (low-loaded charging stations are prioritized); battery health status (vehicles with low SOH are prioritized for fast charging); global balance indicators (to avoid multiple vehicles from concentrating on the same charging station);

[0111] Step 5: Dynamically adjust the queue during the charging process to respond to new tasks or sudden failures, following the principle of allocating the vehicle with the highest charging priority to the charging station with the lowest load.

[0112] The charging scheduling method provided by the present invention integrates dynamic scheduling rules and charging prediction models to ensure normal transportation operations while maximizing the utilization rate of charging piles.

[0113] The charging scheduling method is applicable to both unmanned and manned driving scenarios.

[0114] Alternatively, as Figure 6 As shown, the charging scheduling method includes:

[0115] Step S210: The intelligent dispatching system sends the target point to the GIS to obtain feedback on whether charging is required;

[0116] Step S212: After the GIS obtains the target point, it performs path planning and passes other relevant parameters to the training results to obtain the prediction results of charging and discharging;

[0117] Step S220: Obtaining the mine car charging and discharging records;

[0118] Step S222: collecting charge and discharge history data for one stage;

[0119] Step S224: Perform model training based on the input charge and discharge history data and output a charge and discharge model;

[0120] Step S230: Obtaining the charge and discharge training results.

[0121] By acquiring the charging and discharging records generated by the mining vehicles, the historical charging and discharging data during the collection phase constitutes big data. The big data is input into the Python algorithm in the programming language for model training, and the charging and discharging model is output. The charging and discharging training results of the output charging and discharging model are determined. The target point is sent to the Geographic Information System (GIS) through the intelligent scheduling system to obtain feedback on whether charging is required. After receiving feedback that the working vehicle needs to be charged, the GIS service is obtained. After the GIS obtains the target point, path planning is performed and other relevant parameters are passed to the training results to obtain the prediction results of multiple working vehicles. Based on the prediction results, the charging and discharging training results of the trucks in the mining operation environment are determined.

[0122] like Figure 7As shown, the embodiment of the present application further provides a charging scheduling device 900, including: a data acquisition module 902, used to obtain operating status parameters of a working vehicle, the operating status parameters including the remaining battery power, battery health status, load status, driving speed, slope factor and environmental parameters, the load status including a first load status and a second load status, the first load status corresponding to a heavy-loaded path, and the second load status corresponding to an unloaded path; a data processing module 904, used to determine time series data corresponding to the operating status parameters; determine a discharge time prediction model based on the time series data; and determine the remaining discharge time of the working vehicle based on the discharge time prediction model; The vehicle determination module 906 is used to determine the duration required for the transport task of the working vehicle; in response to the condition that the remaining discharge time is less than the duration required for the transport task, determine the predefined dynamic scheduling rules; determine the first vehicle according to the predefined dynamic scheduling rules; the scheduling decision module 908 is used to determine the scheduling path of the first vehicle from the current position to the target charging station; in the case where the scheduling path is a heavy-loaded path to an empty-loaded path, control the load state of the first vehicle to switch from the first load state to the second load state, so that the first vehicle is charged in the second load state, and returns to the first load state after charging is completed, so as to complete the charging scheduling of the first vehicle.

[0123] The data acquisition module acquires operating status parameters such as vehicle location, remaining power, load status and ambient temperature in real time; the data processing module builds a machine learning model to predict the shortest path and power consumption of the vehicle to the charging station; the scheduling decision module generates charging instructions based on the dynamic priority algorithm, sets dynamic scheduling rules, and calculates and automatically determines whether the truck should create a charging task based on the truck load, remaining mileage, remaining power and charging pile saturation status, combined with the discharge time prediction model, in real time. It also allocates charging pile resources, so that the vehicle with the highest charging priority is assigned to the charging station with the lowest load, thereby improving the utilization efficiency of charging resources and the efficiency of mine transportation.

[0124] In some embodiments, optionally, the scheduling decision module 908 is also used to: obtain a new transport task request; determine at least one second vehicle corresponding to the new transport task request; determine the priority score of the second vehicle; update the charging station load status; determine the updated charging instruction based on the priority score and the updated charging station load status; and send the updated charging instruction to the second vehicle.

[0125] like Figure 8 As shown, an embodiment of the present application further provides an electronic device 1000, including a processor 1110, a memory 1109, and a program or instruction stored in the memory 1109 and executable on the processor 1110. When the program or instruction is executed by the processor 1110, the various processes of the embodiment of the above-mentioned charging scheduling method are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0126] Optionally, the processor 1110 is configured to obtain operating status parameters of the working vehicle, the operating status parameters including remaining battery power, battery health status, load status, driving speed, slope factor, and environmental parameters, the load status including a first load status and a second load status, the first load status corresponding to a loaded path, and the second load status corresponding to an unloaded path;

[0127] Optionally, the processor 1110 is further configured to determine time series data corresponding to the operating state parameter; determine a discharge time prediction model based on the time series data; and determine a remaining discharge time of the working vehicle based on the discharge time prediction model.

[0128] Optionally, the processor 1110 is further configured to determine a required time for a transport task of the working vehicle; in response to a condition that the remaining discharge time is less than the required time for the transport task, determine a predefined dynamic scheduling rule; and determine the first vehicle according to the predefined dynamic scheduling rule;

[0129] Optionally, the processor 1110 is further configured to determine a dispatch path for the first vehicle from the current location to the target charging station; if the dispatch path is a heavily loaded path to an unloaded path, control the load state of the first vehicle to switch from the first loaded state to the second loaded state, so that the first vehicle is charged in the second loaded state, and return to the first loaded state after charging is completed, thereby completing the charging dispatch of the first vehicle;

[0130] Optionally, processor 1110 is further used to obtain a new transport task request; determine at least one second vehicle corresponding to the new transport task request; determine a priority score for the second vehicle; update the load status of the charging station; determine an updated charging instruction based on the priority score and the updated load status of the charging station; and send the updated charging instruction to the second vehicle.

[0131] The memory 1109 can be used to store software programs and various data. The memory 1109 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, applications or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 1109 may include a volatile memory or a non-volatile memory, or the memory 1109 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM). The memory 1109 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0132] The present application also provides a chip comprising a processor and a communication interface coupled to the processor. The processor is configured to execute programs or instructions to implement the various processes of the aforementioned charging scheduling method embodiment, achieving the same technical effects. To avoid repetition, these are not described here. Furthermore, the chip improves the data processing speed corresponding to the method of the present application.

[0133] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0134] In the present invention, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. The term "plurality" refers to two or more, unless expressly limited otherwise. Terms such as "installed," "connected," "connected," and "fixed" should be interpreted broadly. For example, "connected" can mean a fixed connection, a detachable connection, or an integral connection; "connected" can mean a direct connection or an indirect connection through an intermediary. Those skilled in the art will understand the specific meanings of these terms in the present invention based on specific circumstances.

[0135] In the description of the present invention, it should be understood that the directions or positional relationships indicated by terms such as "up", "down", "left", "right", "front" and "back" are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or unit referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they should not be understood as limiting the present invention.

[0136] Throughout this specification, terms such as "one embodiment," "some embodiments," and "specific embodiments" mean that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0137] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A charging scheduling method, characterized in that: For a charging station, the charging station is set on an empty path of a working section of a mine, the working section including the empty path and the loaded path, and the charging scheduling method includes: Obtaining operating status parameters of the working vehicle, the operating status parameters including remaining battery power, battery health status, load status, driving speed, slope factor, and environmental parameters, the load status including a first load status and a second load status, the first load status corresponding to a loaded path, and the second load status corresponding to the unloaded path; Determining the time series data corresponding to the operating status parameter; Determining a discharge time prediction model based on the time series data; determining a remaining discharge time of the working vehicle according to the discharge time prediction model; Determining the duration of the transport task of the working vehicle; In response to a condition that the remaining discharge time is less than a required time of the transportation task, determining a predefined dynamic scheduling rule; determining a first vehicle according to the predefined dynamic dispatch rule; determining a dispatch path for the first vehicle from a current location to a target charging station; When the scheduling path is from the heavy-load path to the empty-load path, the load state of the first vehicle is controlled to switch from the first load state to the second load state, so that the first vehicle is charged in the second load state, and restored to the first load state after charging is completed, so as to complete the charging scheduling of the first vehicle.

2. The charging scheduling method according to claim 1, characterized in that: Determining a discharge time prediction model according to the time series data includes: Determining a data sampling frequency of the operating status parameter; Determining time series data corresponding to the operating state parameter according to the data sampling frequency; Determine an input layer according to the time series data; Build a neural network architecture based on long short-term memory networks; performing a time series prediction operation according to the neural network architecture to determine an output layer, the output layer including a remaining discharge time; A discharge time prediction model is determined according to the input layer and the output layer.

3. The charging scheduling method according to claim 2, characterized in that: The determining of a dispatch path for the first vehicle from a current position to a target charging station includes: generating priority scores for the plurality of working vehicles based on variables in the predefined dynamic dispatch rule; determining a first vehicle according to the priority scores, the first vehicle having the highest priority score; Get the real-time load status of the charging station; Determining a target charging station according to the real-time load status of the charging station; The shortest path from the current position of the first vehicle to the target charging station is determined as a scheduling path.

4. The charging scheduling method according to claim 3, characterized in that: After completing the charging schedule for the first vehicle, the method further includes: Get new transport task request; Determining at least one second vehicle corresponding to the newly added transport task request; determining a priority score for the second vehicle; Update charging station load status; determining an updated charging instruction based on the priority score and the updated load status of the charging station; The updated charging instruction is sent to the second vehicle.

5. The charging scheduling method according to any one of claims 1 to 4, characterized in that: The determining of the predefined dynamic scheduling rule includes: Determining multiple variables, the variables including an urgency weight of the transport task, a quantified value of the vehicle health status, and a global balance index, wherein the urgency weight of the transport task and the numerical value corresponding to the load status are positively correlated, and the global balance index is used to determine a threshold value for the number of working vehicles at the charging station; A predefined dynamic scheduling rule is determined by using a plurality of the variables.

6. A charging scheduling device, characterized in that: include: a data acquisition module, configured to obtain operating status parameters of the working vehicle, the operating status parameters including remaining battery power, battery health status, load status, driving speed, slope factor, and environmental parameters, the load status including a first load status and a second load status, the first load status corresponding to a loaded path, and the second load status corresponding to an unloaded path; A data processing module, configured to determine time series data corresponding to the operating state parameter; determine a discharge time prediction model based on the time series data; and determine a remaining discharge time of the working vehicle based on the discharge time prediction model; a vehicle determination module, configured to determine a required duration for the transport task of the working vehicle; determine a predefined dynamic scheduling rule in response to a condition that the remaining discharge time is less than the required duration for the transport task; and determine a first vehicle according to the predefined dynamic scheduling rule; a scheduling decision module, configured to determine a scheduling path for the first vehicle from a current location to a target charging station; When the scheduling path is from the heavy-load path to the empty-load path, the load state of the first vehicle is controlled to switch from the first load state to the second load state, so that the first vehicle is charged in the second load state, and restored to the first load state after charging is completed, so as to complete the charging scheduling of the first vehicle.

7. The charging scheduling device according to claim 6, characterized in that: The scheduling decision module is also used to: Get new transport task request; Determining at least one second vehicle corresponding to the newly added transport task request; determining a priority score for the second vehicle; Update charging station load status; determining an updated charging instruction based on the priority score and the updated load status of the charging station; The updated charging instruction is sent to the second vehicle.

8. A charging station, characterized in that: The charging station is arranged on an empty path of a working section of the mine, wherein the working section includes the empty path and the loaded path; The charging station includes the charging scheduling device according to claim 6 or claim 7.

9. An electronic device, characterized in that: The method comprises a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the charging scheduling method according to any one of claims 1 to 5.

10. A chip, characterized in that: The chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the steps of the charging scheduling method according to any one of claims 1 to 5.

Images