A stable parking control method for electric mining vehicles

Abstract

The present application relates to the technical field of parking control, and provides a method for controlling the smooth parking of electric mining vehicles. The method comprises: when receiving a stop command, obtaining vehicle and road status data, the vehicle data including load, speed and acceleration, and the road data including slope and flatness. When the speed is greater than or equal to the braking threshold, a combined braking scheme is generated based on the load, speed, acceleration, slope and flatness. When the speed is less than the braking threshold, a motor braking scheme is generated. The scheme is predicted for stability, and if the probability of smooth parking is greater than or equal to the threshold, braking is performed, otherwise the scheme is updated. The present application solves the technical problem that it is difficult for electric mining vehicles to achieve smooth parking under different road surfaces and load conditions, and realizes the combined or separate control strategy of hydraulic braking and motor braking dynamically adjusted through intelligent analysis of the vehicle's operating status and road surface status, so as to improve the parking stability and ensure the safe and stable parking effect of electric mining vehicles.

Description

Technical Field

[0001] The present application relates to the technical field of parking control, and in particular to a method for controlling the smooth parking of an electric mining vehicle. Background Art

[0002] With the continuous development and technological progress of the mining industry, mining electric vehicles are key equipment for mine transportation. Their operating efficiency, safety and stability are crucial to ensuring the efficient operation of mine production operations. Mining electric vehicles usually need to operate in complex and changeable terrain, heavy loads and long-distance operating environments. These special conditions place extremely high demands on the vehicle control system. When facing complex and changeable mining environments, traditional parking control methods often rely on fixed braking parameters and lack the ability to accurately and real-timely perceive the vehicle's operating status and road conditions, resulting in insufficient parking control accuracy when the vehicle load changes or the road conditions are poor. Secondly, since mining roads often have large slopes and uneven roads, traditional methods are difficult to respond quickly to these dynamic changes when parking, resulting in delays or excessive braking during braking, which not only affects the smooth parking of the vehicle, but may also lead to dangerous accidents. In addition, the stability of traditional control methods is poor, especially when the vehicle is traveling at high speed or with a large load, it is easy to have problems such as insufficient braking force or braking failure, which seriously threatens the safety of mining operations. Summary of the invention

[0003] The present application provides a smooth parking control method for an electric mining vehicle, aiming to solve the technical problem that it is difficult for an electric mining vehicle to achieve smooth parking under different road surfaces and load conditions.

[0004] In view of the above problems, the present application provides a method for controlling the smooth parking of an electric mining vehicle.

[0005] The present application provides a method for controlling a smooth parking of an electric mining vehicle, the method comprising: when receiving a stop command of the electric mining vehicle, obtaining the operating status data of the electric mining vehicle and the road surface status monitoring data, wherein the operating status data of the electric mining vehicle includes the vehicle load, the vehicle moving speed and the vehicle moving acceleration, and the road surface status monitoring data includes the road surface slope and the road surface flatness; when the vehicle moving speed is greater than or equal to the hydraulic braking speed threshold, based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness, a random configuration of the combined control of hydraulic braking and motor braking is performed to generate a combined braking control scheme; when the vehicle moving speed is greater than or equal to the hydraulic braking speed threshold, the hydraulic braking and motor braking are combined and randomly configured to generate a combined braking control scheme; The vehicle moving speed is less than the hydraulic braking speed threshold, and the motor braking control is randomly configured based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road slope and the road flatness to generate a motor braking control scheme; a stability prediction is performed on the combined braking control scheme or the motor braking control scheme to obtain a smooth parking probability; when the smooth parking probability is greater than or equal to the smooth parking probability threshold, the electric vehicle braking control is performed according to the combined braking control scheme or the motor braking control scheme; when the smooth parking probability is less than the smooth parking probability threshold, the combined braking control scheme or the motor braking control scheme is updated.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The above-mentioned method for controlling the smooth parking of an electric mining vehicle first receives a stop command of the electric mining vehicle, and collects the real-time operating status data (such as load, moving speed and acceleration) and road surface status monitoring data (such as slope and flatness) of the vehicle according to the stop command. Subsequently, the braking method is selected according to the current moving speed of the vehicle. If the vehicle moves at a fast speed and reaches or exceeds the preset hydraulic braking speed threshold, the combined control scheme of hydraulic braking and motor braking will be randomly configured by comprehensively considering the vehicle load, speed, acceleration and road surface conditions. This combined braking can more effectively reduce the vehicle speed while maintaining the stability of the vehicle. On the contrary, if the vehicle moves at a slow speed and is lower than the hydraulic braking speed threshold, only motor braking will be selected, and the motor braking control scheme will be randomly configured based on the load, speed, acceleration, road surface slope and flatness. After the braking control scheme is determined, a stability prediction is performed to evaluate whether the scheme can achieve a smooth parking. This step is completed by calculating the probability of a smooth parking, which is related to a variety of factors, including the vehicle state, road surface conditions and the braking strategy itself. If the predicted smooth stop probability meets or exceeds the preset threshold, it means that the current control scheme is feasible and the braking control will be performed directly according to the scheme. If the smooth stop probability is lower than the threshold, it indicates that the braking strategy needs to be further optimized and the current combined braking or motor braking control scheme needs to be updated to increase the probability of smooth stopping until the requirements are met. This process is a dynamic, real-time data-based braking control optimization process designed to ensure that mining electric vehicles can stop smoothly and safely after receiving a stop command.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A schematic diagram of a flow chart of a method for controlling a stable parking of a mining electric vehicle in an embodiment;

[0011] Figure 2 The present invention is a flow chart of updating the vehicle moving speed of a method for controlling a smooth parking of an electric mining vehicle in one embodiment. DETAILED DESCRIPTION

[0012] The embodiment of the present application provides a method for controlling the smooth parking of an electric mining vehicle, thereby solving the technical problem that the electric mining vehicle is difficult to achieve smooth parking under different road surfaces and load conditions.

[0013] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0014] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0015] Examples, such as Figure 1 As shown, the present application provides a method for controlling a smooth parking of a mining electric vehicle, the method comprising:

[0016] When a stop command of the mining electric vehicle is received, the operating status data of the mining electric vehicle and the road surface status monitoring data are obtained, wherein the operating status data of the mining electric vehicle includes the vehicle load, vehicle moving speed and vehicle moving acceleration, and the road surface status monitoring data includes the road surface slope and road surface flatness.

[0017] In the embodiment of the present application, when the system terminal receives the stop command of the mining electric vehicle, the built-in sensor of the mining electric vehicle will be activated to collect the operation status data and road surface status monitoring data of the mining electric vehicle. The operation status data includes vehicle load, vehicle moving speed and vehicle moving acceleration, and the road surface status monitoring data includes road surface slope and road surface flatness. Among them, the vehicle load refers to the total weight currently carried by the mining electric vehicle, and heavier vehicles require greater braking force to stop. The vehicle moving speed refers to the instantaneous speed of the mining electric vehicle during driving, and the speed determines how much time and distance the vehicle needs to slow down to stop. The vehicle moving acceleration is the speed of the vehicle speed change. During the braking process, the magnitude of the acceleration reflects the strength of the braking force and the speed of the braking effect. The road surface slope refers to the ratio of the road height difference to the horizontal distance. The road surface flatness is the flatness of the road surface, which affects the friction between the tire and the ground, and then affects the braking effect. These data are crucial for formulating a suitable braking strategy, because they can help the system terminal understand the real-time status of the vehicle and the environment, so as to select the most appropriate braking method to ensure that the vehicle can stop smoothly and safely.

[0018] When the vehicle moving speed is greater than or equal to the hydraulic braking speed threshold, hydraulic braking and electric motor braking combined control are randomly configured based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness to generate a combined braking control scheme.

[0019] In one embodiment, when the driving speed of the mining electric vehicle reaches or exceeds the preset hydraulic braking speed threshold, the system terminal will formulate a braking strategy by comprehensively considering multiple factors. These factors include the vehicle's load capacity, current moving speed, speed change speed, and road conditions. Based on this information, the system terminal performs a joint control random configuration, that is, the hydraulic braking control scheme is configured through the hydraulic braking force rated interval and the hydraulic braking torque rated interval, and the motor braking control scheme is configured through the motor braking force rated interval and the motor braking torque rated interval, and then the two schemes are sequentially added to obtain a joint braking control scheme. Among them, hydraulic braking can usually provide stronger braking force, which is suitable for use in high-speed driving or when rapid deceleration is required. Motor braking has the advantages of fast response and precise control, and can play a role in low speed or when fine-tuning power is required. By combining these two braking methods, it is possible to more flexibly respond to braking needs at higher speeds and ensure that the vehicle can stop smoothly and quickly.

[0020] Further, if Figure 2 As shown, the present application provides a method for performing a random configuration of hydraulic braking and motor braking combined control when the vehicle moving speed is greater than or equal to the hydraulic braking speed threshold, and generating a combined braking control scheme, which also includes:

[0021] Obtain a mining electric vehicle parking space number; collect a set of historical braking command response durations in a preset time zone of the mining electric vehicle parking space number; perform a central trend analysis on the set of historical braking command response durations to obtain a braking command response characteristic duration; perform a speed prediction based on the braking command response characteristic duration according to the vehicle moving speed and the vehicle moving acceleration to obtain a predicted speed at the response moment; and update the vehicle moving speed according to the predicted speed at the response moment.

[0022] Preferably, in order to optimize the operating efficiency and safety of the mining electric vehicle, the system terminal first determines the bit number of the mining electric vehicle, which is the unique identifier of the mining electric vehicle. Subsequently, the bit number is used to collect the historical braking command response time data of the mining electric vehicle in the preset time zone, and a historical braking command response time set is constructed. These data reflect the length of time required for the mining electric vehicle to actually start braking from receiving the braking command. After that, the data in the historical braking command response time set are subjected to a central trend analysis, that is, appropriate statistics such as the mean value, median, etc. are selected to measure this central trend, and the braking command response characteristic time is obtained. This characteristic time represents the response speed of the mining electric vehicle to the braking command in most cases. Among them, the selection of the mean value, median, and mode is selected according to the data characteristics. If the data distribution is close to the normal distribution and there are no extreme values, the mean value is selected; if the data is skewed or there are outliers, the median is selected. After obtaining the braking command response characteristic time, the system terminal uses the speed formula to predict the speed according to the current moving speed and acceleration, combined with this characteristic time, and calculates the predicted speed at the response time. Then, the calculated response time predicted speed is used to update the vehicle's current moving speed. Because the updated speed takes into account the response delay of the braking command, it can make the braking control of the mining electric vehicle more accurate and timely, thereby improving the safety of operation.

[0023] Furthermore, the present application provides a method for generating a combined braking control scheme by performing a random configuration of hydraulic braking and motor braking combined control based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness when the vehicle moving speed is greater than or equal to the hydraulic braking speed threshold, including:

[0024] The hydraulic braking force rated range, the hydraulic braking torque rated range, the electric machine force rated range, and the electric machine torque rated range are obtained; based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness, a first-stage braking configuration is performed through the hydraulic braking force rated range and the hydraulic braking torque rated range to obtain a first-stage hydraulic braking control scheme; based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness, a second-stage braking configuration is performed through the electric machine force rated range and the electric machine torque rated range to obtain a second-stage motor braking control scheme; the first-stage hydraulic braking control scheme and the second-stage motor braking control scheme are added to the combined braking control scheme.

[0025] Optionally, the system terminal first obtains the rated intervals of hydraulic braking and motor braking, including the rated intervals of hydraulic braking force and hydraulic braking torque, the rated intervals of electric machine force and electric machine torque. These rated intervals of braking force and braking torque are the basis for the subsequent formulation of braking strategies to ensure that sufficient braking force can be provided under different working conditions. For hydraulic braking, the system terminal randomly configures the selected value of hydraulic braking force and the selected value of hydraulic braking torque according to the rated intervals of hydraulic braking force and hydraulic braking torque, and performs a first-stage braking configuration in combination with the load, moving speed, acceleration, and real-time information such as the slope and flatness of the mining electric vehicle. During the configuration process, the system terminal obtains a first-stage hydraulic braking control scheme that meets the current working conditions by repeatedly comparing with the hydraulic braking speed threshold. This stage mainly uses the powerful braking force and rapid response capability of hydraulic braking to cope with situations that require large braking force, such as braking at high speeds or when driving downhill with heavy loads. For motor braking, according to the same vehicle and road conditions, the rated range of motor braking is used for braking configuration to obtain the selected value of motor braking force and motor braking torque that can reduce the vehicle speed to 0 within the set time, so as to obtain a two-stage motor braking control scheme. Motor braking usually has the advantages of energy recovery, low noise, and precise control. It is suitable for use in situations where the vehicle speed is low or fine control of braking force is required. Through motor braking, the vehicle speed can be further reduced and energy recycling can be achieved at the same time. After obtaining the first-stage hydraulic braking control scheme and the second-stage motor braking control scheme, the system terminal combines the first-stage hydraulic braking control scheme and the second-stage motor braking control scheme and adds them to the combined braking control scheme. Through this combined braking method, the respective advantages of hydraulic braking and motor braking can be fully utilized to ensure that mining electric vehicles can achieve stable, safe and efficient braking under high-speed conditions.

[0026] Further, the present application provides a one-stage hydraulic braking control scheme obtained by performing a one-stage braking configuration based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness through the hydraulic braking force rated interval and the hydraulic braking torque rated interval, including:

[0027] By randomly configuring the hydraulic braking force rated interval and the hydraulic braking torque rated interval, a selected hydraulic braking force value and a selected hydraulic braking torque value are obtained; a first target braking duration is obtained; based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness, the vehicle speed at the first end moment of the first target braking duration is predicted; when the vehicle speed at the first end moment is less than or equal to the hydraulic braking speed threshold, the selected hydraulic braking force value and the selected hydraulic braking torque value are set as the first-stage hydraulic braking control scheme.

[0028] Optionally, in vehicle braking control, the system terminal determines the selected value of the hydraulic braking force and the selected value of the hydraulic braking torque by randomly configuring the rated interval of the hydraulic braking force and the rated interval of the hydraulic braking torque. The selection of these values ​​is random, but they are all within the corresponding rated intervals. Subsequently, the first target braking time preset by the user is obtained, that is, the time required for the user to start braking and reach the hydraulic braking speed threshold. Using these selected hydraulic braking force values, hydraulic braking torque values, and parameters such as the vehicle's current load, moving speed, moving acceleration, road surface slope and road surface flatness, combined with the pre-constructed hydraulic braking end-time vehicle speed prediction macro model, the vehicle speed at the end of the first target braking time is predicted. This prediction process takes into account a variety of factors that affect the vehicle's braking performance. Afterwards, the system terminal determines whether the predicted vehicle speed at the first end time is less than or equal to the preset hydraulic braking speed threshold. If this condition is met, it means that the current selected values ​​of hydraulic braking force and hydraulic braking torque can effectively decelerate the vehicle to below the desired speed within the braking time preset by the user, so the system terminal sets the current selected values ​​of hydraulic braking force and hydraulic braking torque as the hydraulic braking control scheme for the first stage. Otherwise, the system terminal reconfigures the selected values ​​of hydraulic braking force and hydraulic braking torque, and repeats the above process until the requirements of the hydraulic braking speed threshold are met. Among them, the reconfigured selected values ​​of hydraulic braking force and hydraulic braking torque are greater than the previous selected values ​​of hydraulic braking force and hydraulic braking torque. In summary, this process is to randomly select hydraulic braking force and torque, and predict the braking effect according to the braking time preset by the user and the vehicle and road conditions, and finally determine a suitable hydraulic braking control scheme to ensure that the vehicle can safely decelerate within the time expected by the user.

[0029] Further, the present application provides a method for predicting the vehicle speed at the first end point of the target braking duration according to the selected value of the hydraulic braking force and the selected value of the hydraulic braking torque, based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness, including:

[0030] The hydraulic braking force record data set, the hydraulic braking torque record data set, the first vehicle load record data set, the first moving speed record data set, the first moving acceleration record data set, the first road slope record data set, the first road flatness record data set, the first braking time record data set, the first terminal moment vehicle speed record data set and the first terminal moment vehicle acceleration record data set of the same model of mining electric vehicles are collected; N initial model architectures with different network topologies are constructed; 8 input nodes and 2 output nodes are configured for each of the N initial model architectures; and a first fully connected layer is constructed to fit the output mode values ​​of N similar output nodes.

[0031] Optionally, in order to optimize the braking performance of mining electric vehicles, the system terminal first performs comprehensive data collection, including collecting data in multiple dimensions such as hydraulic braking force, hydraulic braking torque, vehicle load, moving speed, moving acceleration, road slope, road flatness, braking time, vehicle speed at the end of braking, and vehicle acceleration of the same model of mining electric vehicles, and obtains a hydraulic braking force record data set, a hydraulic braking torque record data set, a first vehicle load record data set, a first moving speed record data set, a first moving acceleration record data set, a first road slope record data set, a first road flatness record data set, a first braking time record data set, a first terminal moment vehicle speed record data set, and a first terminal moment vehicle acceleration record data set. These data sets provide a solid foundation for subsequent model construction. Subsequently, in order to mine useful information from these complex data, N initial model architectures with different network topologies are constructed, such as recurrent neural network RNN, deep neural network DNN, long short-term memory network LSTM, etc. The diversity of these model architectures helps to explore the complex relationship between different data features, so as to find the optimal braking prediction results. In order to ensure that these models can effectively receive input data and output prediction results, each initial model architecture is configured with 8 input nodes, corresponding to the above 8 data sets (hydraulic braking force, hydraulic braking torque, etc.), and 2 output nodes for outputting the predicted vehicle speed and acceleration at the end of braking. In addition, a first fully connected layer is constructed, which is used to fuse the outputs of N similar output nodes, and obtain a more stable and reliable prediction result by calculating the mode value of these outputs. This fully connected layer plays a key role in the model. It can integrate the prediction results of multiple models to improve the accuracy and robustness of the overall prediction.

[0032] The hydraulic braking force record data set, the hydraulic braking torque record data set, the first vehicle load record data set, the first moving speed record data set, the first moving acceleration record data set, the first road surface gradient record data set, the first road surface flatness record data set, the first braking duration record data set, the first terminal moment vehicle speed record data set, and the first terminal moment vehicle acceleration record data set are divided into N training data sets, and the N initial model architectures are trained respectively to generate N hydraulic braking terminal moment vehicle speed prediction base models; according to the first fully connected layer, the N hydraulic braking terminal moment vehicle speed prediction base models are fused to generate a hydraulic braking terminal moment vehicle speed prediction macro model; through the hydraulic braking terminal moment vehicle speed prediction macro model, according to the hydraulic braking force selected value, the hydraulic braking torque selected value, based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface gradient and the road surface flatness, the first terminal moment vehicle speed and the first terminal moment vehicle acceleration of the target braking duration are predicted.

[0033] Optionally, in order to extract valuable information about the hydraulic braking performance of mining electric vehicles from multi-source data, the system terminal divides the collected hydraulic braking force record data set, hydraulic braking torque record data set, first vehicle load record data set, first moving speed record data set, first moving acceleration record data set, first road slope record data set, first road flatness record data set, first braking time record data set, first terminal moment vehicle speed record data set and first terminal moment vehicle acceleration record data set into N independent training data sets, verification data sets and test data sets. The purpose of this is to ensure that each model can access different parts of the data during training, thereby improving the generalization ability of the model. Subsequently, the constructed N initial model architectures with different network topologies are trained separately using N training data sets, verification data sets and test data sets. Each model will learn how to predict the vehicle speed at the hydraulic braking terminal moment from the input data features based on a training data set, and will be verified and tested respectively through the verification data set and the test data set, thereby generating N hydraulic braking terminal moment vehicle speed prediction base models. Specifically, for any initial model architecture, the system terminal uses random numbers to initialize the initial model architecture, sets the network weights and biases, and then uses a random training data set for training. The training process includes multiple iterations (epochs). In each epoch, the system terminal inputs the training data into the initial model architecture, calculates through each layer of the network until the predicted vehicle speed and predicted vehicle acceleration of the output layer are obtained, and uses the mean square error MSE to calculate the loss value between these two predicted values ​​and the corresponding first terminal moment vehicle speed record data and first terminal moment vehicle acceleration record data. Subsequently, the gradient is calculated based on the loss value, that is, the derivative of the loss value with respect to each parameter, and the weights and biases of the model are updated according to the gradient and learning rate using the optimizer to reduce the loss. At the end of each epoch, the performance of the model is evaluated using the corresponding validation data set to determine whether the loss on the validation data set for multiple epochs has not decreased. If not, the training stops and the current model is saved as the base model for predicting the vehicle speed at the hydraulic braking terminal moment. This helps prevent the model from overfitting on the training data set and performing poorly on unseen data. If early stopping is not triggered, when the maximum number of training times is reached, the training is stopped, and the performance of the current model is evaluated using the test data set to calculate indicators such as prediction accuracy and recall rate. If the expected expectations are met, the current model is saved as the base model for predicting the vehicle speed at the end of hydraulic braking. Otherwise, the complexity of the model and the learning rate are adjusted to improve the performance of the initial model architecture until the expected expectations are met. After all initial model architectures are trained and N base models for predicting the vehicle speed at the end of hydraulic braking are obtained, the system terminal uses the first fully connected layer to fuse their prediction results.The fully connected layer will comprehensively consider the output of all base models, and generate a more stable and accurate macro model for predicting the vehicle speed at the end of hydraulic braking by calculating the mode value. This macro model can make full use of the advantages of each base model to improve the accuracy of the overall prediction. When the system terminal inputs the selected value of hydraulic braking force, the selected value of hydraulic braking torque, the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road slope and the road flatness into the macro model for predicting the vehicle speed at the end of hydraulic braking, the macro model for predicting the vehicle speed at the end of hydraulic braking will quickly calculate the predicted vehicle speed and acceleration according to the input data characteristics, and use the predicted results as the vehicle speed at the first end and the vehicle acceleration at the first end, providing important reference information for the system terminal. By comparing the vehicle speed at the first end with the hydraulic braking speed threshold, the selected value of hydraulic braking force and the selected value of hydraulic braking torque that can meet the requirements of the hydraulic braking speed threshold under the first target braking time are obtained, ensuring that the mining electric vehicle can achieve stable, safe and efficient braking under high speed conditions.

[0034] Furthermore, the present application provides a two-stage motor braking control scheme based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness, through the motor force rated interval and the motor torque rated interval to perform a two-stage braking configuration, including:

[0035] By randomly configuring the motor mechanism force rated interval and the motor mechanism torque rated interval, a motor mechanism force selected value and a motor mechanism torque selected value are obtained; a second target braking duration is obtained; based on the motor mechanism force selected value and the motor mechanism torque selected value, the vehicle speed at the second end moment of the second target braking duration is predicted based on the vehicle load, the vehicle speed at the first end moment and the vehicle acceleration at the first end moment, the road surface slope and the road surface flatness; when the vehicle speed at the second end moment is equal to zero, the motor mechanism force selected value and the motor mechanism torque selected value are set as the two-stage motor braking control scheme.

[0036] Optionally, the system terminal randomly configures the selected value of the motor force and the selected value of the motor torque according to the rated interval of the motor force and the rated interval of the motor torque, and then obtains the second target braking time set by the user, which indicates the time required for the expected mining electric vehicle to decelerate from the current state to a complete stop. After that, the selected value of the motor force, the selected value of the motor torque, the vehicle load, the vehicle speed at the first end moment and the vehicle acceleration at the first end moment, the road slope and the road flatness are input into the pre-built motor braking end moment vehicle speed prediction macro model to predict the vehicle speed at the second end moment of the mining electric vehicle at the end of the second target braking time. If the vehicle speed at the second end moment is predicted to be zero, the current selected value of the motor force and the selected value of the motor torque are determined as the second stage motor braking control scheme. The whole process is similar to setting the first stage hydraulic braking control scheme, but the specific parameters and control methods vary due to different braking methods, but they are all for the purpose of achieving stable, safe and efficient braking of mining electric vehicles.

[0037] Further, the present application provides a method for predicting the vehicle speed at the second end time of the second target braking time according to the selected value of the motor force and the selected value of the motor torque, based on the vehicle load, the vehicle speed at the first end time and the vehicle acceleration at the first end time, the road slope and the road flatness, including:

[0038] Collect the motor force record data set, motor braking torque record data set, second vehicle load record data set, second moving speed record data set, second moving acceleration record data set, second road surface slope record data set, second road surface flatness record data set, second braking time record data set and second terminal time vehicle speed record data set of the same model of mining electric vehicles; construct M initial model architectures with different network topologies; configure 8 input nodes and 1 output node for each of the M initial model architectures; construct a second fully connected layer for fitting the output mode values ​​of the M output nodes; and integrate the motor force record data set, the motor braking torque record data set, the second vehicle load record data set, the second moving speed record data set, the second moving acceleration record data set, the second road surface slope The record data set, the second road surface flatness record data set, the second braking duration record data set and the second terminal moment vehicle speed record data set are divided into M training data sets, the M initial model architectures are trained respectively to generate M motor braking terminal moment vehicle speed prediction base models; according to the second fully connected layer, the M motor braking terminal moment vehicle speed prediction base models are fused to generate a motor braking terminal moment vehicle speed prediction macro model; according to the motor braking terminal moment vehicle speed prediction macro model, according to the motor braking terminal moment vehicle speed prediction macro model, according to the motor mechanism force selected value, the motor mechanism torque selected value, based on the vehicle load, the first terminal moment vehicle speed and the first terminal moment vehicle acceleration, the road surface slope and the road surface flatness, predict the second terminal moment vehicle speed of the second target braking time.

[0039] Optionally, similar to the aforementioned construction of a vehicle speed prediction macro model at the end of hydraulic braking, the system terminal will also construct M initial model architectures with different network topologies. Each model is designed to have 8 input nodes (corresponding to the above 8 data sets) and 1 output node (for predicting the vehicle speed at the end of braking). The collected motor force record data set, motor torque record data set, second vehicle load record data set, second moving speed record data set, second moving acceleration record data set, second road surface slope record data set, second road surface flatness record data set, second braking duration record data set and second end time vehicle speed record data set of the same model of mining electric vehicles are divided into M training data sets, verification data sets, and test data sets, and then the same training method as above is used to train M motor braking end time vehicle speed prediction base models. Subsequently, the second fully connected layer constructed by the same method as the first fully connected layer is used to perform mode fusion on the M motor braking end time vehicle speed prediction base models to obtain a motor braking end time vehicle speed prediction macro model. Afterwards, the selected value of the motor force, the selected value of the motor braking torque, the vehicle load, the vehicle speed at the first end moment and the vehicle acceleration at the first end moment, the road slope and the road flatness are input into the vehicle speed prediction macro model at the motor braking end moment, and the vehicle speed at the second end moment when the second target braking time ends is predicted to ensure that the mining electric vehicle can achieve stable, safe and efficient braking under low speed conditions.

[0040] When the vehicle moving speed is less than the hydraulic braking speed threshold, the motor braking control is randomly configured based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness to generate a motor braking control scheme.

[0041] In one embodiment, when the moving speed of the electric mining vehicle is less than a preset hydraulic braking speed threshold, the system terminal will directly perform random configuration of the motor braking control based on the vehicle load, vehicle moving speed and vehicle moving acceleration, road slope and road flatness, combined with the motor force selected value and the motor torque selected value randomly configured by the motor force rated interval and the motor torque rated interval, through the constructed macro model of vehicle speed prediction at the motor braking end moment, and generate a motor braking control scheme suitable for the current driving conditions to ensure that the electric mining vehicle can brake safely and smoothly.

[0042] A stability prediction is performed on the combined braking control scheme or the motor braking control scheme to obtain a stable parking probability.

[0043] In one embodiment, after obtaining the combined braking control scheme or the motor braking control scheme, the system terminal matches the combined braking control scheme or the motor braking control scheme with samples of the same model, obtains a data set of overturning amplitude records, and performs cluster analysis on the overturning amplitude record data set. Subsequently, data processing is performed on the clustering results, abnormal clusters are deleted, and data with the largest overturning amplitude is extracted from the remaining clusters. Threshold analysis is then performed on this data to quantify the probability of a smooth stop of the combined braking control scheme or the motor braking control scheme. This probability value reflects the effectiveness and reliability of the scheme, and provides an important decision-making basis for the system terminal.

[0044] Furthermore, the present application provides a method for predicting the stability of the combined braking control scheme or the motor braking control scheme to obtain a stable parking probability, including:

[0045] Based on the suspension stiffness characteristic value, combined with the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness, the combined braking control scheme or the motor braking control scheme is matched with samples of the same model to obtain an overturning amplitude record data set; based on the overturning amplitude deviation threshold, the overturning amplitude record data set is clustered and analyzed to obtain an overturning amplitude clustering result; the classes whose in-class clustering number of the overturning amplitude clustering result is less than or equal to the in-class number threshold are deleted to obtain high-frequency overturning amplitude record data; when the maximum value of the high-frequency overturning amplitude record data is greater than or equal to the overturning amplitude threshold, the smooth parking probability is set to 0; when the maximum value of the high-frequency overturning amplitude record data is less than the overturning amplitude threshold, the smooth parking probability is set to 1.

[0046] Preferably, the system terminal searches for samples of the same type of braking control scheme under the same or similar conditions in the database according to the suspension stiffness characteristic value, load, moving speed, acceleration, road slope and flatness of the mining electric vehicle, as well as the combined braking control scheme or the motor braking control scheme, and obtains the subversion amplitude record data set of these samples. Subsequently, the number of clusters K to be formed is determined according to the actual problem and the characteristics of the data, and the K value can also be assisted by the elbow method (Elbow Method), the silhouette coefficient (Silhouette Score) and other methods. Then, K data points are randomly selected from the subversion amplitude record data set as the initial cluster center. For each data point in the subversion amplitude record data set, the Euclidean distance is used to calculate its distance from each cluster center, and the data point is assigned to the cluster where the cluster center closest to it is located. For each cluster, the mean of all points in the cluster is recalculated as the new cluster center. Repeat the process of assigning data points to clusters and updating cluster centers until the preset number of iterations is reached, indicating that the clustering result has converged. At this time, the system terminal obtains the subversion amplitude clustering result. After clustering is completed, the system terminal deletes the clusters whose number of clusters in the overturning amplitude clustering node is less than or equal to the threshold of the number of clusters in the class. This is because these classes represent extreme situations or noise data that rarely occur, and they are not representative for evaluating the stability of the braking control scheme. The high-frequency overturning amplitude recording data obtained after screening can better reflect the common overturning amplitude conditions during braking. After that, the system terminal determines the probability of smooth parking based on the maximum value of the high-frequency overturning amplitude recording data. If this maximum value exceeds the preset overturning amplitude threshold, it means that under similar braking conditions, the mining electric vehicle is likely to have a large overturn or shake, so the probability of smooth parking is set to 0. On the contrary, if the maximum value is less than the overturning amplitude threshold, it is considered that under this braking control scheme, the probability of smooth parking for the mining electric vehicle is high, so the probability of smooth parking is set to 1.

[0047] When the smooth parking probability is greater than or equal to the smooth parking probability threshold, the electric vehicle braking control is performed according to the combined braking control scheme or the motor braking control scheme; when the smooth parking probability is less than the smooth parking probability threshold, the combined braking control scheme or the motor braking control scheme is updated.

[0048] In one embodiment, after evaluating the probability of a smooth stop of an electric mining vehicle, the system terminal will take corresponding measures. If the calculated probability of a smooth stop is greater than or equal to the preset smooth stop probability threshold, this means that under the current conditions, when braking according to the current combined braking control scheme or motor braking control scheme, the electric mining vehicle can have a higher probability of achieving a smooth stop. Therefore, the system terminal will directly adopt this control scheme to perform braking control on the electric vehicle. However, if the probability of a smooth stop is less than the threshold of the probability of a smooth stop, the system terminal will determine that the current braking control scheme may not be able to ensure a smooth stop of the electric mining vehicle under similar conditions. In order to improve the stability of the braking process, the system terminal will update the current combined braking control scheme or motor braking control scheme, that is, re-perform the aforementioned hydraulic braking and motor braking combined control random configuration or motor braking control random configuration, in the hope that under the new control scheme, the electric mining vehicle can achieve a higher probability of a smooth stop.

[0049] In summary, the embodiments of the present application have at least the following technical effects:

[0050] The embodiment of the present application first obtains the running state data and road monitoring data of the vehicle, wherein the running state data includes the vehicle's load, moving speed and acceleration, and the road monitoring data includes the slope and flatness. When the vehicle moving speed is greater than or equal to the hydraulic braking speed threshold, the hydraulic braking and motor braking are jointly controlled based on these data to generate a combined braking control scheme; and when the speed is less than the threshold, a corresponding control scheme is generated based on motor braking. Subsequently, the generated braking control scheme is predicted for stability to obtain the probability of stable parking. If the probability is greater than or equal to the preset threshold, the corresponding braking control is performed; otherwise, the braking control scheme is updated. When the vehicle speed is greater than or equal to the hydraulic braking threshold, based on the vehicle's load, moving speed, acceleration, and road conditions, the rated intervals of hydraulic braking force and motor braking force are used to perform two-stage braking configurations and generate corresponding control schemes. In this process, by analyzing historical data, a centralized trend analysis of the braking command response time is performed to optimize the prediction model of the vehicle speed, thereby improving the accuracy of the braking control. Through the training and integration of multiple models, more accurate braking speed prediction and parking control are achieved, ensuring that electric mining vehicles can achieve smooth parking in complex mining environments. These technical effects jointly solve the technical problem that electric mining vehicles are difficult to achieve smooth parking under different road and load conditions, and realize the intelligent analysis of vehicle operation status and road conditions, and dynamically adjust the joint or separate control strategy of hydraulic braking and motor braking to improve parking stability and ensure the safe and stable parking of electric mining vehicles.

[0051] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0052] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0053] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A stable parking control method for a mining electric vehicle, characterized in that: include: When a stop command of the mining electric vehicle is received, the running status data of the mining electric vehicle and the road surface status monitoring data are obtained, wherein the running status data of the mining electric vehicle includes the vehicle load, the vehicle moving speed and the vehicle moving acceleration, and the road surface status monitoring data includes the road surface slope and the road surface flatness; When the vehicle moving speed is greater than or equal to the hydraulic braking speed threshold, based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness, a combined braking control scheme is generated by performing a random configuration of hydraulic braking and electric motor braking combined control; When the vehicle moving speed is less than the hydraulic brake speed threshold, a motor brake control random configuration is performed based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness to generate a motor brake control scheme; Performing a stability prediction on the combined braking control scheme or the motor braking control scheme to obtain a stable parking probability; When the smooth parking probability is greater than or equal to the smooth parking probability threshold, performing electric vehicle braking control according to the combined braking control scheme or the motor braking control scheme; When the smooth parking probability is less than the smooth parking probability threshold, the combined braking control scheme or the motor braking control scheme is updated.

2. The method according to claim 1, characterized in that When the vehicle moving speed is greater than or equal to the hydraulic braking speed threshold, the hydraulic braking and motor braking combined control are randomly configured to generate a combined braking control scheme, which also includes: Obtain the mine electric parking space number; Collecting a set of historical braking command response durations in a preset time zone of the mining electric vehicle position number; Performing a central trend analysis on the historical braking command response time set to obtain a braking command response characteristic time; According to the vehicle moving speed and the vehicle moving acceleration, a speed prediction is performed based on the characteristic duration of the braking command response to obtain a predicted speed at the response time; The vehicle moving speed is updated according to the predicted speed at the response time.

3. The method according to claim 1, characterized in that When the vehicle moving speed is greater than or equal to the hydraulic braking speed threshold, the hydraulic braking and motor braking combined control are randomly configured based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness, and a combined braking control scheme is generated, including: Obtaining the hydraulic braking force rated range, the hydraulic braking torque rated range, the electric machine force rated range, and the electric machine torque rated range; Based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness, a first-stage braking configuration is performed through the hydraulic braking force rated interval and the hydraulic braking torque rated interval to obtain a first-stage hydraulic braking control scheme; Based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness, a two-stage braking configuration is performed through the motor force rated interval and the motor torque rated interval to obtain a two-stage motor braking control scheme; The one-stage hydraulic braking control scheme and the two-stage motor braking control scheme are added into the combined braking control scheme.

4. The method according to claim 3, characterized in that Based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness, a first-stage braking configuration is performed through the hydraulic braking force rated interval and the hydraulic braking torque rated interval to obtain a first-stage hydraulic braking control scheme, including: Obtaining a selected hydraulic braking force value and a selected hydraulic braking torque value by randomly configuring the hydraulic braking force rated interval and the hydraulic braking torque rated interval; Obtaining a first target braking duration; Predicting the vehicle speed at the first end point of the first target braking duration according to the selected value of the hydraulic braking force and the selected value of the hydraulic braking torque, based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface gradient and the road surface flatness; When the vehicle speed at the first end point is less than or equal to the hydraulic braking speed threshold, the selected value of the hydraulic braking force and the selected value of the hydraulic braking torque are set as the one-stage hydraulic braking control scheme.

5. The method according to claim 4, characterized in that Predicting the vehicle speed at the first end point of the target braking duration according to the selected value of the hydraulic braking force and the selected value of the hydraulic braking torque, based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface gradient and the road surface flatness, includes: Collect the hydraulic braking force record data set, hydraulic braking torque record data set, first vehicle load record data set, first moving speed record data set, first moving acceleration record data set, first road surface slope record data set, first road surface flatness record data set, first braking time record data set, first endpoint vehicle speed record data set and first endpoint vehicle acceleration record data set of the same model of mining electric vehicles; Construct N initial model architectures with different network topologies; Configuring 8 input nodes and 2 output nodes for each of the N initial model architectures; Construct the first fully connected layer to fit the output mode values ​​of N similar output nodes; Divide the hydraulic braking force record data set, the hydraulic braking torque record data set, the first vehicle load record data set, the first moving speed record data set, the first moving acceleration record data set, the first road slope record data set, the first road flatness record data set, the first braking duration record data set, the first endpoint vehicle speed record data set, and the first endpoint vehicle acceleration record data set into N training data sets, train the N initial model architectures respectively, and generate N hydraulic braking endpoint vehicle speed prediction base models; According to the first fully connected layer, the N basic models for predicting vehicle speed at the end point of hydraulic braking are integrated to generate a macro model for predicting vehicle speed at the end point of hydraulic braking; Through the macro model for predicting the vehicle speed at the end point of hydraulic braking, according to the selected value of the hydraulic braking force and the selected value of the hydraulic braking torque, based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness, the vehicle speed at the first end point of the target braking duration and the vehicle acceleration at the first end point are predicted.

6. The method according to claim 4, characterized in that Based on the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness, a two-stage braking configuration is performed through the motor force rated interval and the motor torque rated interval to obtain a two-stage motor braking control scheme, including: By randomly configuring the motor force rated interval and the motor torque rated interval, a motor force selected value and a motor torque selected value are obtained; Obtaining a second target braking duration; Predicting the vehicle speed at the second end point of the second target braking duration according to the selected value of the motor force and the selected value of the motor braking torque, based on the vehicle load, the vehicle speed at the first end point, the vehicle acceleration at the first end point, the road slope, and the road flatness; When the vehicle speed is equal to zero at the second end point, the selected value of the motor force and the selected value of the motor torque are set as the two-stage motor braking control scheme.

7. The method according to claim 6, characterized in that Predicting the vehicle speed at the second end point of the second target braking time according to the selected value of the motor force and the selected value of the motor braking torque, based on the vehicle load, the vehicle speed at the first end point, the vehicle acceleration at the first end point, the road slope, and the road flatness, includes: Collect the motor force record data set, motor braking torque record data set, second vehicle load record data set, second moving speed record data set, second moving acceleration record data set, second road surface slope record data set, second road surface flatness record data set, second braking duration record data set and second end point vehicle speed record data set of the same model of mining electric vehicles; Construct M initial model architectures with different network topologies; Configuring 8 input nodes and 1 output node for each of the M initial model architectures; Construct a second fully connected layer to fit the output mode values ​​of M output nodes; The motor force record data set, the motor torque record data set, the second vehicle load record data set, the second moving speed record data set, the second moving acceleration record data set, the second road surface gradient record data set, the second road surface flatness record data set, the second braking duration record data set and the second terminal moment vehicle speed record data set are divided into M training data sets, and the M initial model architectures are trained respectively to generate M motor braking terminal moment vehicle speed prediction base models; According to the second fully connected layer, the M vehicle speed prediction base models at the motor braking endpoint are integrated to generate a vehicle speed prediction macro model at the motor braking endpoint; According to the vehicle speed prediction macro model at the end moment of motor braking, according to the selected value of the motor force and the selected value of the motor torque, based on the vehicle load, the vehicle speed at the first end moment and the vehicle acceleration at the first end moment, the road surface slope and the road surface flatness, the vehicle speed at the second end moment of the second target braking duration is predicted.

8. The method according to claim 1, characterized in that Performing a stability prediction on the combined braking control scheme or the motor braking control scheme to obtain a stable parking probability includes: Based on the suspension stiffness characteristic value, combined with the vehicle load, the vehicle moving speed and the vehicle moving acceleration, the road surface slope and the road surface flatness, the combined braking control scheme or the motor braking control scheme is matched with the same model sample to obtain a rollover amplitude record data set; Based on the subversion amplitude deviation threshold, cluster analysis is performed on the subversion amplitude record data set to obtain a subversion amplitude clustering result; Deleting the classes whose in-class clustering number of the subversion amplitude clustering result is less than or equal to the in-class number threshold, and obtaining high-frequency subversion amplitude record data; When the maximum value of the high-frequency overturning amplitude recorded data is greater than or equal to the overturning amplitude threshold, the smooth parking probability is set to 0; When the maximum value of the high-frequency overturning amplitude recorded data is less than the overturning amplitude threshold, the smooth parking probability is set to 1.

Images