Control method and device of well mining vehicle, electronic equipment and storage medium

Abstract

The invention discloses a control method and device of a well industrial and mining vehicle, electronic equipment and a storage medium, and the control method of the well industrial and mining vehicle comprises the steps that the initial state information of a target well industrial and mining vehicle is acquired, and the initial state information comprises obstacle information and road information; target state information of the target well industrial and mining vehicle is determined according to the initial state information, and the target state information comprises vehicle state information and vehicle environment information; determining a target driving strategy of the target well industrial and mining vehicle according to the target state information; and controlling the running of the target well industrial and mining vehicle according to the target running strategy. The technical problem that in the prior art, due to the fact that the control precision of the well industrial and mining vehicle is low, the risk is high when the well industrial and mining vehicle is operated is solved.

Description

Technical Field

[0001] The present invention relates to the field of automation technology, and in particular to a control method, device, electronic equipment and storage medium for an underground mining vehicle. Background Art

[0002] Underground mining is a method of extracting mineral resources deep underground, which has unique challenges and risks. In this environment, transport vehicles are the key link between the surface and the depths of the mine, and their safe and efficient operation is essential to the entire mining operation. Underground mines usually have narrow and winding passages, coupled with changing terrain, which places high demands on vehicle control.

[0003] Although existing underground mining vehicle control systems have achieved a certain degree of automation, their adaptive capabilities are still limited. They often have difficulty effectively responding to the rapidly changing geological and topographical conditions in underground environments, such as sudden slope changes or unstable road surfaces. In emergency situations, such as sudden underground obstacles or safety threats, the reaction time of existing systems may not be sufficient to effectively avoid danger. This delay may cause safety risks, especially when running at high speeds or carrying heavy loads. In addition, existing systems are capable of basic path control and speed management, but they are still insufficient in accurately controlling the stability and operating accuracy of underground mining vehicles, especially in complex underground environments.

[0004] In the existing technology, autonomous flight of indoor drones usually relies on the fusion of lidar and visible light data. In order to improve the positioning and navigation accuracy of drones, it is usually necessary to add markers to them during flight, which increases the workload of construction and maintenance.

[0005] These limitations indicate that although existing technologies have made certain achievements in improving the automation and safety of underground mining vehicles, further technological innovation and improvement are still needed in terms of adaptive capabilities, real-time response, precise control, environmental perception, reliability, and energy efficiency. Summary of the invention

[0006] The embodiments of the present invention provide a control method, device, electronic device and storage medium for an underground mining car, so as to at least solve the technical problem in the prior art that the control accuracy of the underground mining car is low, thereby causing high risks when operating the underground mining car.

[0007] According to one embodiment of the present invention, a control method for an underground mining vehicle is provided, comprising: obtaining initial state information of a target underground mining vehicle, wherein the initial state information includes obstacle information and road information; determining target state information of the target underground mining vehicle based on the initial state information, wherein the target state information includes vehicle state information and vehicle environment information; determining a target driving strategy of the target underground mining vehicle based on the target state information; and controlling the driving of the target underground mining vehicle based on the target driving strategy.

[0008] Optionally, the control method of the underground mining vehicle also includes: obtaining preprocessing state information of the target underground mining vehicle; performing data processing operations on the preprocessing state information to obtain initial state information, wherein the data processing operations include denoising operations, standardization operations and data fusion operations.

[0009] Optionally, the control method of the underground mining car also includes: obtaining target training data of the target underground mining car; using the target training data to train the initial neural network model to generate a target neural network model, wherein the target neural network model is used to determine target state information; inputting the initial state information into the target neural network model to obtain the target state information.

[0010] Optionally, the control method of the underground mining vehicle also includes: training the initial neural network model using target training data to determine the target loss; updating the model parameters of the initial neural network model based on the target loss to obtain the target neural network model.

[0011] Optionally, the control method of the underground mining car also includes: obtaining vehicle motion state information of the target underground mining car, wherein the vehicle motion state information is obtained by monitoring the driving process of the target underground mining car controlled according to the target driving strategy; determining the target state of the target underground mining car according to the vehicle motion state information; in response to the target state being a dangerous state, controlling the target underground mining car to perform an emergency braking operation.

[0012] Optionally, the control method of the underground mining vehicle also includes: determining energy management information of the target underground mining vehicle according to the target driving strategy and vehicle motion state information; and determining an energy consumption strategy of the target underground mining vehicle according to the energy management information.

[0013] Optionally, the control method of the underground mining vehicle also includes: obtaining initial mining area environment information of the target underground mining vehicle; performing a cleaning operation on the initial mining area environment information to obtain target mining area environment information; performing a splicing operation on the target mining area environment information based on a splicing algorithm to obtain a mining area environment point cloud model; generating a target mining area map of the target underground mining vehicle based on the mining area environment point cloud model; and controlling the target mining area map to be displayed on the target display screen.

[0014] According to one embodiment of the present invention, a control device for an underground mining vehicle is also provided, including: a first acquisition module, used to acquire initial state information of a target underground mining vehicle, wherein the initial state information includes obstacle information and road information; a first determination module, used to determine target state information of the target underground mining vehicle based on the initial state information, wherein the target state information includes vehicle state information and vehicle environment information; a second determination module, used to determine a target driving strategy of the target underground mining vehicle based on the target state information; and a first control module, used to control the driving of the target underground mining vehicle based on the target driving strategy.

[0015] Optionally, the first acquisition module includes: a first acquisition unit, used to acquire preprocessing state information of the target underground mining vehicle; a first execution unit, used to perform data processing operations on the preprocessing state information to obtain initial state information, wherein the data processing operations include denoising operations, standardization operations and data fusion operations.

[0016] Optionally, the first determination module includes: a second acquisition unit, used to acquire target training data of a target underground mining vehicle; a training unit, used to train an initial neural network model using the target training data to generate a target neural network model, wherein the target neural network model is used to determine target state information; and an input unit, used to input the initial state information into the target neural network model to obtain target state information.

[0017] Optionally, the training unit includes: a training subunit, used to train the initial neural network model using target training data to determine a target loss; and an updating subunit, used to update model parameters of the initial neural network model based on the target loss to obtain a target neural network model.

[0018] Optionally, the control device of the underground mining car also includes: a second acquisition module, used to acquire vehicle motion state information of the target underground mining car, wherein the vehicle motion state information is obtained by monitoring the driving process of the target underground mining car controlled according to the target driving strategy; a third determination module, used to determine the target state of the target underground mining car based on the vehicle motion state information; and a second control module, used to control the target underground mining car to perform an emergency braking operation in response to the target state being a dangerous state.

[0019] Optionally, the control device of the underground mining vehicle also includes: a fourth determination module, used to determine the energy management information of the target underground mining vehicle based on the target driving strategy and vehicle motion state information; and a fifth determination module, used to determine the energy consumption strategy of the target underground mining vehicle based on the energy management information.

[0020] Optionally, the control device of the underground mining vehicle also includes: a third acquisition module, used to acquire initial mining area environment information of the target underground mining vehicle; a first execution module, used to perform a cleaning operation on the initial mining area environment information to obtain target mining area environment information; a second execution module, used to perform a splicing operation on the target mining area environment information based on a splicing algorithm to obtain a mining area environment point cloud model; a generation module, used to generate a target mining area map of the target underground mining vehicle based on the mining area environment point cloud model; and a third control module, used to control the display of the target mining area map on the target display screen.

[0021] According to one embodiment of the present invention, there is also provided an electronic device, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute any of the above-mentioned methods for controlling an underground mining vehicle.

[0022] According to one embodiment of the present invention, there is further provided a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute any of the above-mentioned methods for controlling an underground mining vehicle when run.

[0023] In an embodiment of the present invention, the initial state information of the target underground mining vehicle is obtained, wherein the initial state information includes obstacle information and road information, and the target state information of the target underground mining vehicle is determined based on the initial state information, wherein the target state information includes vehicle state information and vehicle environment information. This achieves the purpose of determining the target driving strategy of the target underground mining vehicle based on the target state information, and achieves the technical effect of controlling the driving of the target underground mining vehicle based on the target driving strategy, thereby solving the technical problem of low control accuracy of underground mining vehicles in the prior art, which leads to high risks when operating underground mining vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0025] Figure 1 is a flow chart of a control method for an underground mining vehicle according to one embodiment of the present invention;

[0026] Figure 2 This is a structural block diagram of a control system for an underground mining vehicle according to one embodiment of the present invention;

[0027] Figure 3 It is a structural block diagram of a control device for an underground mining vehicle according to one embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] According to an embodiment of the present invention, an embodiment of a control method for an underground mining vehicle is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system containing at least one set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] The method embodiment may also be performed in an electronic device, a similar control device or an electronic device including a memory and a processor. Taking an electronic device as an example, the electronic device may include one or more processors and a memory for storing data. Optionally, the electronic device may also include a communication device and a display device for communication functions. It will be understood by those skilled in the art that the above structural description is only illustrative and does not limit the structure of the above electronic device. For example, the electronic device may also include more or fewer components than the above structural description, or have a configuration different from the above structural description.

[0032] The processor may include one or more processing units. For example, the processor may include a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP) chip, a microcontroller unit (MCU), a field-programmable gate array (FPGA), a neural-network processing unit (NPU), a tensor processing unit (TPU), an artificial intelligence (AI) type processor, and other processing devices. Among them, different processing units may be independent components or integrated into one or more processors. In some instances, the electronic device may also include one or more processors.

[0033] The memory can be used to store computer programs, such as storing a computer program corresponding to the control method of the underground mining car in the embodiment of the present invention, and the processor implements the control method of the underground mining car by running the computer program stored in the memory. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the electronic device via a grid. Examples of the above-mentioned grid include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0034] The communication device is used to receive or send data via a grid. The specific examples of the above-mentioned grid may include a wireless grid provided by a communication provider of the mobile terminal. In one example, the communication device includes a grid adapter (network interface controller, NIC), which can be connected to other grid devices through a base station so as to communicate with the Internet. In one example, the communication device can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly. In some embodiments of the present solution, the communication device is used to connect to mobile devices such as mobile phones and tablets, and instructions can be sent to the vehicle-mounted terminal through the mobile device.

[0035] The display device may be a touch screen type liquid crystal display (LCD) and a touch display (also referred to as a "touch screen" or "touch display screen"). The liquid crystal display may enable a user to interact with a user interface of the vehicle-mounted terminal. In some embodiments, the vehicle-mounted terminal has a graphical user interface (GUI), and a user may interact with the GUI by finger contact and / or gestures on a touch-sensitive surface. The human-computer interaction function here may include a vehicle gear shifting function, and executable instructions for executing the human-computer interaction function are configured / stored in a computer program product or a readable storage medium executable by one or more processors.

[0036] Figure 1 FIG. 1 is a flow chart of a control method for an underground mining vehicle according to one embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0037] Step S102, obtaining initial state information of the target underground mining vehicle, wherein the initial state information includes obstacle information and road information.

[0038] Optionally, the execution subject of this embodiment is a mine vehicle control system. It should be noted that other electronic devices and processors can also serve as execution subjects, and no further limitations are given here.

[0039] Specifically, Figure 2 As shown in the figure, the underground mining vehicle control system includes the following modules:

[0040] 1) A deep learning-driven environmental perception module that uses a variety of sensors (such as lidar, infrared cameras, ultrasonic sensors, etc.) to collect downhole environmental data and processes this data in real time through deep learning algorithms to accurately identify environmental changes and potential obstacles.

[0041] 2) Augmented reality assisted driving module, which uses augmented reality technology to project key information (such as road conditions, obstacles, vehicle status, etc.) into the driver's field of view in real time, improving the driver's environmental perception and reaction speed.

[0042] 3) Adaptive control module, which dynamically adjusts the vehicle's speed, direction and anti-shake strategy based on the vehicle's real-time status and external environment to adapt to different underground conditions.

[0043] 4) Energy management module, which optimizes energy consumption through intelligent algorithms, improves the vehicle's energy efficiency, and reduces environmental impact.

[0044] 5) Wireless communication and data synchronization module, to achieve efficient and reliable data communication between the vehicle and the control center, and to support remote monitoring and command issuance.

[0045] In the technical solution provided in the above step S102 of the present invention, the underground mining vehicle control system uses a variety of sensors such as laser radar, infrared camera, ultrasonic sensor, etc. to collect environmental data around the vehicle in real time.

[0046] Specifically, the above-mentioned sensors can capture the position, size, shape and movement state of objects around the mine car (obstacle information), as well as information such as the slope and slippery conditions of the road surface (road information).

[0047] Step S104, determining target state information of the target underground mining vehicle according to the initial state information, wherein the target state information includes vehicle state information and vehicle environment information.

[0048] In the technical solution provided in the above step S104 of the present invention, the deep learning-driven environmental perception module of the underground mining vehicle control system can analyze the above obstacle information and road information in real time according to the neural network model, and classify and interpret them to identify key elements (vehicle environmental information) in the current environment, such as passable areas, obstacles, slope changes, etc.

[0049] Specifically, the adaptive control module of the underground mining vehicle control system fuses the above initial state information and target state information, performs real-time analysis on the fused data, and determines the vehicle's current state information (such as speed, acceleration, direction) and environmental information (such as obstacle distance, road type).

[0050] Optionally, the adaptive control module of the underground mining car control system receives the initial state information sent by the above-mentioned multiple sensors and the target state information output by the neural network model, and performs data fusion on the above-mentioned initial state information and target state information to construct a comprehensive vehicle state model and environmental model of the underground mining car for subsequent real-time analysis of the mine car data.

[0051] Step S106, determining a target driving strategy of the target underground mining vehicle according to the target state information.

[0052] In the technical solution provided in the above step S106 of the present invention, the adaptive control module of the underground mining vehicle control system can evaluate whether the current underground mining vehicle driving strategy is suitable for the existing environment and vehicle status based on the above data analysis results.

[0053] Optionally, if the existing driving strategy is not suitable for the current vehicle's environmental loading and vehicle status, the adaptive control module can formulate a new driving strategy according to predetermined rules.

[0054] Specifically, the new driving strategy may include adjusting the speed of the underground mining vehicle, changing the driving path of the underground mining vehicle, or taking certain safety measures.

[0055] Specifically, the adaptive control module generates specific control instructions, such as acceleration, deceleration, steering or application of brakes, based on the above decision results, and coordinates with the wireless communication and data synchronization module to send them to the execution system. The control system sends these control instructions to the corresponding execution components such as the power system, braking system and steering system of the underground mining vehicle.

[0056] Step S108, controlling the driving of the target underground mining vehicle according to the target driving strategy.

[0057] In the technical solution provided in the above step S108 of the present invention, the underground mining vehicle control system controls the target underground mining vehicle to travel according to the target driving strategy of the underground mining vehicle formulated by the adaptive control module.

[0058] From the above steps S102 to S108, it can be learned that in the present invention, the initial state information of the target underground mining vehicle is obtained, wherein the initial state information includes obstacle information and road information, and the target state information of the target underground mining vehicle is determined according to the initial state information, wherein the target state information includes vehicle state information and vehicle environment information, thereby achieving the purpose of determining the target driving strategy of the target underground mining vehicle according to the target state information, and achieving the technical effect of controlling the driving of the target underground mining vehicle according to the target driving strategy, thereby solving the technical problem of low control accuracy of underground mining vehicles in the prior art, thereby causing high risks when operating underground mining vehicles.

[0059] The purpose of the present invention is to provide an intelligent control system for underground mining vehicles. Through an environmental perception module driven by deep learning, the vehicle can more accurately identify and adapt to complex underground mine environments. This includes being able to cope with sudden changes in terrain, unstable road conditions, and the appearance of obstacles, thereby improving the safety and reliability of the vehicle in extreme or uncertain environments. Using augmented reality technology, key environmental and vehicle status information is displayed to the driver in real time, which not only improves the driver's perception of the surrounding environment, but also enables the driver to respond and make decisions faster. At the same time, the adaptive control unit can dynamically adjust the vehicle's driving strategy according to the real-time environment and vehicle status, such as speed, direction, and suspension system settings, to adapt to current road conditions in the best way. Therefore, this technical solution significantly improves the safety, efficiency, and environmental adaptability of underground mining vehicles.

[0060] The above method of this embodiment is further described in detail below.

[0061] As an optional implementation, obtaining the initial state information of the target underground mining vehicle includes: obtaining preprocessing state information of the target underground mining vehicle, performing data processing operations on the preprocessing state information, and obtaining initial state information, wherein the data processing operations include denoising operations, standardization operations, and data fusion operations.

[0062] In this embodiment, the underground mining vehicle control system receives vehicle data from multiple sensors of the underground mining vehicle (such as speed sensors, accelerometers, lidars, infrared cameras, etc.). Furthermore, the raw data collected by the control system must first be preprocessed. The above preprocessing operations include denoising operations, standardization operations, and data fusion operations.

[0063] Specifically, data fusion is the process of combining data collected by different sensors to form a unified and comprehensive environmental perception image.

[0064] Optionally, the preprocessed data is used to remove environmental noise and correct for bias between sensors to improve the accuracy and reliability of the data.

[0065] As an optional implementation, determining the target state information of the target underground mining vehicle based on the initial state information includes: obtaining target training data of the target underground mining vehicle, training an initial neural network model using the target training data, and generating a target neural network model, wherein the target neural network model is used to determine the target state information, and inputting the initial state information into the target neural network model to obtain the target state information.

[0066] In this embodiment, the underground mining car control system determines the target state information of the target underground mining car based on the acquired initial state information, including the following steps: the deep learning-driven environmental perception module of the control system obtains the target training data (labeled training data) of the target underground mining car, and uses the target training data to train the initially established neural network model to obtain the target neural network model, wherein the target neural network model is used to determine the target state information, and the control system then inputs the initial state information of the underground mining car into the target neural network model for training, thereby obtaining the trained target state information, that is, the environmental data of the underground mining car, such as traversable areas, obstacles, slope changes, etc.

[0067] Specifically, the neural network learns through training the ability to identify important features from environmental data, such as obstacle recognition, road condition assessment, and potential danger prediction. The specific steps include:

[0068] 1) Prepare training data and use labeled image data (e.g., images labeled with obstacles, road boundaries, etc.) to train the model.

[0069] 2) Forward propagation: The input image passes through the neural network model, and each layer gradually extracts and transforms features.

[0070] 3) Loss function: Use an appropriate loss function (such as cross entropy loss) to measure the gap between the model output and the actual label.

[0071] 4) Back-propagation and optimization: The gradient of the loss function with respect to the network parameters is calculated through the back-propagation algorithm, and the weights of the network are updated using an optimization algorithm (such as stochastic gradient descent).

[0072] In addition, the performance of the model can be tested based on data that has not participated in training, its performance in the actual downhole environment can be evaluated, and the network parameters (such as learning rate, number of layers, convolution kernel size, etc.) can be adjusted according to the test results to improve the accuracy and robustness of the neural network model.

[0073] Specifically, the algorithms in the deep learning-driven environmental perception module can analyze, classify and interpret environmental data in real time to identify key elements in the current environment, such as traversable areas, obstacles, slope changes, etc.

[0074] Optionally, the deep learning module can also continuously learn and optimize through historical data and real-time feedback to improve its accuracy and adaptability.

[0075] As an optional implementation, the target training data is used to train the initial neural network model, and generating the target neural network model includes: training the initial neural network model with the target training data, determining the target loss, and updating the model parameters of the initial neural network model based on the target loss to obtain the target neural network model.

[0076] In this embodiment, the target training data is used to train the initial neural network model, and generating the target neural network model includes the following steps: the underground mining car control system uses the target training data of the underground mining car to train the initial neural network model, further determines the target loss of the initial neural network model, and based on the above target loss, updates the model parameters of the initial neural network model multiple times until the initial neural network model training is completed to obtain the target neural network model.

[0077] Specifically, the deep learning module can use the above pre-processed target state data as input. The deep learning module usually contains multiple neural network layers and can recognize complex patterns and associations.

[0078] 1) Select layer type: Design the CNN architecture and choose the appropriate number of layers and the type of each layer.

[0079] 2) Convolutional layer: used to extract features from the image. Each convolutional layer contains multiple convolution kernels that slide over the image to capture local features.

[0080] 3) Activation function: such as ReLU (Rectified Linear Unit), which is used to introduce nonlinearity and help the network learn complex patterns.

[0081] 4) Pooling layer: used to reduce the spatial size of the feature map (e.g., max pooling), which helps reduce the amount of computation and prevent overfitting.

[0082] 5) Fully connected layer: Usually located at the end of the network, used to map the learned features to the final output (e.g., classification or regression).

[0083] As an optional implementation, the method also includes: obtaining vehicle motion state information of the target underground mining vehicle, wherein the vehicle motion state information is obtained by monitoring the driving process of the target underground mining vehicle controlled according to the target driving strategy, determining the target state of the target underground mining vehicle based on the vehicle motion state information, and in response to the target state being a dangerous state, controlling the target underground mining vehicle to perform an emergency braking operation.

[0084] In this embodiment, the control method of the underground mining car also includes the following steps: the underground mining car control system continuously monitors the driving process of the target underground mining car according to the target driving strategy, obtains the vehicle motion state information of the target underground mining car, and further determines the current vehicle state of the target underground mining car based on the acquired vehicle motion state information; if there are dangerous factors in the current vehicle state of the target underground mining car, the control system can control the target underground mining car to perform emergency braking.

[0085] Specifically, the control system continuously monitors the safety of underground mining vehicles, that is, it detects in real time any factors that may affect the safety of the mining vehicles, such as system anomalies, environmental changes, etc. When there are factors around the mining vehicles that affect its safety, emergency response is carried out, and when potential safety risks are detected, countermeasures are quickly taken, such as emergency braking or obstacle avoidance.

[0086] As an optional implementation, the method further includes: determining energy management information of the target underground mining vehicle according to the target driving strategy and vehicle motion state information, and determining an energy consumption strategy of the target underground mining vehicle according to the energy management information.

[0087] In this embodiment, the control method of the underground mining car also includes the following steps: the energy management module within the control system can determine the energy usage of the target underground mining car based on the target driving strategy of the mining car and the vehicle motion state information, and formulate a suitable energy consumption strategy for the target underground mining car based on the received energy usage.

[0088] Specifically, the energy management module is mainly used to optimize the use, monitoring and adjustment of energy to improve energy efficiency and reduce environmental impact. The energy management module has the following functions:

[0089] 1. Energy status monitoring

[0090] Energy storage monitoring: Real-time monitoring of the energy storage status of mining trucks, such as battery power or remaining fuel.

[0091] Energy consumption monitoring: Track the energy consumption patterns of mining trucks, including energy efficiency during driving, energy consumption at idle speed, etc.

[0092] 2. Data Collection and Analysis

[0093] Collect operating data: Collect operating data of mining trucks, including speed, acceleration, driving route, load weight, etc., which will affect energy consumption.

[0094] Environmental considerations: Consider environmental factors that affect energy efficiency, such as temperature, road conditions, slope, etc.

[0095] 3. Energy efficiency optimization

[0096] Energy consumption model establishment: Based on the collected data, an energy consumption model is established to predict energy demand under different conditions.

[0097] Driving strategy optimization: Optimize driving strategy based on energy consumption model, such as adjusting driving speed and planning more efficient driving routes.

[0098] 4. Demand response and adjustment

[0099] Demand forecasting: predicting upcoming energy needs, such as the additional energy required when driving uphill or with a load.

[0100] Dynamic Adjustment: Dynamically adjust energy distribution based on predicted demand to ensure efficient use of energy among various parts of the vehicle.

[0101] The energy management module ensures that the vehicle's energy is used most efficiently while ensuring performance, while also reducing operating costs and environmental impact. In underground mining vehicles, which have high energy requirements and complex working environments, an efficient energy management system is essential to ensure sustainable operation of the vehicle.

[0102] Specifically, the mine vehicle control system also includes wireless communication and data synchronization modules, which are mainly responsible for realizing information exchange between the vehicle and external systems (such as the control center, other vehicles, infrastructure, etc.) in the mine vehicle intelligent control system. Vehicle status reporting: Transmitting the vehicle's real-time data (such as location, speed, energy usage, etc.) to the control center for monitoring and analysis. Environmental information sharing: Transmitting environmental information perceived by the vehicle, such as obstacle location, road conditions, etc., to assist in decision-making.

[0103] Optional, wireless communication and data synchronization module ensures that mining trucks can smoothly receive and send key information in complex underground mining environments by providing a stable and efficient communication link, ensuring the safety and efficiency of operation.

[0104] As an optional implementation, the method also includes: obtaining initial mining area environment information of the target underground mining vehicle, performing a cleaning operation on the initial mining area environment information to obtain target mining area environment information, performing a splicing operation on the target mining area environment information based on a splicing algorithm to obtain a mining area environment point cloud model, generating a target mining area map of the target underground mining vehicle based on the mining area environment point cloud model, and controlling the target mining area map to be displayed on the target display screen.

[0105] In this embodiment, the control of the underground mining car also includes the following steps: the control system obtains the initial mining area environment information of the target underground mining car, performs a cleaning operation on the initial mining area environment information data, obtains the target mining area environment information, and splices the target mining area environment information based on the splicing algorithm, so as to obtain a complete mining area environment point cloud model, and fuses the matching image information and the mining area environment point cloud model to establish a high-precision mining area map. Furthermore, the target mining area map can also be controlled to be displayed on the display screen of the mine car driver.

[0106] It is worth noting that in the present invention, the driver is not on the mine car, but in a separately built driving cabin. The driving cabin is equipped with an augmented reality assisted driving module and a remote vehicle remote controller. The augmented reality assisted driving module includes a naked eye 3D real-time interactive large screen and a high-precision mining area map module.

[0107] Specifically, the control system first collects a large amount of mining area environmental data (image information and point cloud data of mining area roads, roadsides, etc.) by using various sensors such as lidar, cameras, and ultrasonic sensors. Secondly, the mining area environmental data is cleaned through a deep learning cleaning algorithm; specifically, the large amount of data is denoised, invalid data and interference data are identified, and removed from the core data, while ensuring the authenticity and integrity of the core data.

[0108] Furthermore, the cleaned point cloud data are spliced ​​using a splicing algorithm to form a complete point cloud model of the mining environment.

[0109] 1) Rough stitching: unify the point cloud data in different coordinate systems into the same coordinate system so that their graphics roughly overlap, provide a good initial value for precise stitching, set a lower threshold to improve accuracy, and prevent it from falling into local extreme values.

[0110] 2) Accurate stitching requires that all point cloud data be stitched together tightly to eliminate the deviation in rough stitching and form a complete 3D model.

[0111] According to the characteristics of point cloud data, and taking into account that the effect of using data with a larger amount of data as source data to stitch data with a smaller amount of data is far inferior to the effect of using data with a smaller amount of data as source data to stitch data with a larger amount of data, a bidirectional stitching method can be used, for example.

[0112] Specifically, the bidirectional stitching algorithm mainly consists of two loops. The program first reads the point cloud data and stores it in an array in chronological order, and then enters the first loop for forward stitching. Only when the current point cloud data contains fewer points than the previous one, the current point cloud data will be stitched to the previous point cloud data, otherwise no operation will be performed.

[0113] After each stitching, the obtained transformation matrix will be applied to all unprocessed matrices to ensure that the relative positions between the unprocessed matrices remain unchanged, and to prevent the distance between adjacent point cloud data from gradually becoming farther due to stitching, affecting the stitching effect. After the forward stitching is completed, the second loop is entered. The second loop is reverse stitching from back to front. Only when the current point cloud data contains fewer points than the previous one, the current point cloud data is stitched to the previous point cloud data, otherwise no operation is performed.

[0114] After each stitching, the transformation matrix is ​​applied to all the unprocessed matrices, so that the point cloud data that has been stitched in the first cycle will move along with the movement of the point cloud data in the second stitching and be stitched to the correct position. After two cycles, the stitching results of all point cloud data and their transformation matrices can be obtained, and the program ends after saving them.

[0115] It is worth mentioning that the algorithm makes reasonable use of the continuity of the input point cloud data. Each stitching is only performed between two adjacent point cloud data, avoiding the situation where the stitching effect is reduced due to insufficient overlap between the interval point cloud data. At the same time, it ensures that the relative positions of the unprocessed point cloud data remain unchanged after each stitching, preventing the change of the algorithm initial value caused by the order of stitching from affecting the stitching result.

[0116] During the stitching process in each direction, only the situation where the number of points contained in the current point cloud data is less than that in the previous one is processed. On the one hand, each stitching is to stitch small point cloud data into large point cloud data, which improves the accuracy. On the other hand, it avoids increasing the number of extra stitching times, which leads to a decrease in program running efficiency.

[0117] Specifically, the matching image information and the mining area environment point cloud model are data-fused to create a high-precision mining area map, which can be directly displayed on the naked-eye 3D large screen for the driver to watch. At the same time, the mine car will send positioning information and current location mining area environment data in real time during the driving process in the underground mine. The local map image displayed on the naked-eye 3D large screen is updated with the positioning information. The mining area environment data can be further detected and identified. When the changed mining area environment information is confirmed, it will be updated to the mining area map.

[0118] Furthermore, when the changing mining environment information affects the automatic driving (for example, sudden obstacles), the driver can promptly remotely control the mine car through the remote vehicle remote control.

[0119] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a grid device, etc.) to execute the methods of various embodiments of the present invention.

[0120] In this embodiment, a control device for an underground mining vehicle is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0121] Figure 3 is a structural block diagram of a control device 300 for an underground mining vehicle according to one embodiment of the present invention. Figure 3 As shown, the device includes: a first acquisition module 301 , a first determination module 302 , a second determination module 303 and a first control module 304 .

[0122] The first acquisition module 301 is used to acquire the initial state information of the target underground mining vehicle, wherein the initial state information includes obstacle information and road information;

[0123] A first determination module 302 is used to determine target state information of a target underground mining vehicle according to the initial state information, wherein the target state information includes vehicle state information and vehicle environment information;

[0124] The second determination module 303 is used to determine the target driving strategy of the target underground mining vehicle according to the target state information;

[0125] The first control module 304 is used to control the driving of the target underground mining vehicle according to the target driving strategy.

[0126] Optionally, the first acquisition module 301 includes: a first acquisition unit, used to acquire preprocessing state information of the target underground mining vehicle; a first execution unit, used to perform data processing operations on the preprocessing state information to obtain initial state information, wherein the data processing operations include denoising operations, standardization operations and data fusion operations.

[0127] Optionally, the first determination module 302 includes: a second acquisition unit, used to acquire target training data of the target underground mining vehicle; a training unit, used to train the initial neural network model using the target training data to generate a target neural network model, wherein the target neural network model is used to determine target state information; an input unit, used to input the initial state information into the target neural network model to obtain the target state information.

[0128] Optionally, the training unit includes: a training subunit, used to train the initial neural network model using target training data to determine a target loss; and an updating subunit, used to update model parameters of the initial neural network model based on the target loss to obtain a target neural network model.

[0129] Optionally, the control device 300 of the underground mining car also includes: a second acquisition module, used to acquire vehicle motion state information of the target underground mining car, wherein the vehicle motion state information is obtained by monitoring the driving process of the target underground mining car controlled according to the target driving strategy; a third determination module, used to determine the target state of the target underground mining car based on the vehicle motion state information; and a second control module, used to control the target underground mining car to perform an emergency braking operation in response to the target state being a dangerous state.

[0130] Optionally, the control device 300 of the underground mining vehicle also includes: a fourth determination module, used to determine the energy management information of the target underground mining vehicle based on the target driving strategy and vehicle motion state information; and a fifth determination module, used to determine the energy consumption strategy of the target underground mining vehicle based on the energy management information.

[0131] Optionally, the control device 300 of the underground mining vehicle also includes: a third acquisition module, used to acquire the initial mining area environment information of the target underground mining vehicle; a first execution module, used to perform a cleaning operation on the initial mining area environment information to obtain the target mining area environment information; a second execution module, used to perform a splicing operation on the target mining area environment information based on a splicing algorithm to obtain a mining area environment point cloud model; a generation module, used to generate a target mining area map of the target underground mining vehicle based on the mining area environment point cloud model; and a third control module, used to control the display of the target mining area map on the target display screen.

[0132] An embodiment of the present invention further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the above-mentioned control method for an underground mining vehicle.

[0133] Optionally, in this embodiment, the electronic device may be configured to store a computer program for performing the following steps:

[0134] Step S102, obtaining initial state information of the target underground mining vehicle, wherein the initial state information includes obstacle information and road information;

[0135] Step S104, determining target state information of the target underground mining vehicle according to the initial state information, wherein the target state information includes vehicle state information and vehicle environment information;

[0136] Step S106, determining a target driving strategy of a target underground mining vehicle according to the target state information;

[0137] Step S108, controlling the driving of the target underground mining vehicle according to the target driving strategy.

[0138] Optionally, when the processor executes the program, the following steps are also implemented: obtaining preprocessing state information of the target underground mining vehicle; performing data processing operations on the preprocessing state information to obtain initial state information, wherein the data processing operations include denoising operations, standardization operations and data fusion operations.

[0139] Optionally, when the processor executes the program, the following steps are also implemented: obtaining target training data of the target underground mining vehicle; using the target training data to train the initial neural network model to generate a target neural network model, wherein the target neural network model is used to determine target state information; inputting the initial state information into the target neural network model to obtain the target state information.

[0140] Optionally, when the processor executes the program, the following steps are also implemented: using target training data to train the initial neural network model to determine the target loss; based on the target loss, updating the model parameters of the initial neural network model to obtain the target neural network model.

[0141] Optionally, when the processor executes the program, the following steps are also implemented: obtaining vehicle motion state information of the target underground mining vehicle, wherein the vehicle motion state information is obtained by monitoring the driving process of the target underground mining vehicle controlled according to the target driving strategy; determining the target state of the target underground mining vehicle based on the vehicle motion state information; and in response to the target state being a dangerous state, controlling the target underground mining vehicle to perform an emergency braking operation.

[0142] Optionally, when executing the program, the processor further implements the following steps: determining energy management information of the target underground mining vehicle according to the target driving strategy and vehicle motion state information; and determining an energy consumption strategy of the target underground mining vehicle according to the energy management information.

[0143] Optionally, when the processor executes the program, the following steps are also implemented: obtaining initial mining area environment information of the target underground mining vehicle; performing a cleaning operation on the initial mining area environment information to obtain target mining area environment information; performing a splicing operation on the target mining area environment information based on a splicing algorithm to obtain a mining area environment point cloud model; generating a target mining area map of the target underground mining vehicle based on the mining area environment point cloud model; and controlling the target mining area map to be displayed on the target display screen.

[0144] An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned substation environment analysis method when running on a computer or a processor.

[0145] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0146] Step S102, obtaining initial state information of the target underground mining vehicle, wherein the initial state information includes obstacle information and road information;

[0147] Step S104, determining target state information of the target underground mining vehicle according to the initial state information, wherein the target state information includes vehicle state information and vehicle environment information;

[0148] Step S106, determining a target driving strategy of a target underground mining vehicle according to the target state information;

[0149] Step S108, controlling the driving of the target underground mining vehicle according to the target driving strategy.

[0150] Optionally, the storage medium is configured to store program code for executing the following steps: obtaining preprocessing state information of the target underground mining vehicle; performing data processing operations on the preprocessing state information to obtain initial state information, wherein the data processing operations include denoising operations, standardization operations, and data fusion operations.

[0151] Optionally, the storage medium is configured to store program code for executing the following steps: obtaining target training data of a target underground mining vehicle; training an initial neural network model using the target training data to generate a target neural network model, wherein the target neural network model is used to determine target state information; and inputting the initial state information into the target neural network model to obtain target state information.

[0152] Optionally, the storage medium is configured to store program code for executing the following steps: training the initial neural network model using target training data to determine a target loss; and updating model parameters of the initial neural network model based on the target loss to obtain a target neural network model.

[0153] Optionally, the storage medium is configured to store program code for executing the following steps: obtaining vehicle motion state information of a target underground mining vehicle, wherein the vehicle motion state information is obtained by monitoring a driving process of the target underground mining vehicle controlled according to a target driving strategy; determining a target state of the target underground mining vehicle based on the vehicle motion state information; and in response to the target state being a dangerous state, controlling the target underground mining vehicle to perform an emergency braking operation.

[0154] Optionally, the storage medium is configured to store program codes for executing the following steps: determining energy management information of a target underground mining vehicle based on a target driving strategy and vehicle motion state information; and determining an energy consumption strategy of the target underground mining vehicle based on the energy management information.

[0155] Optionally, the storage medium is configured to store program codes for executing the following steps: obtaining initial mining area environment information of a target underground mining vehicle; performing a cleaning operation on the initial mining area environment information to obtain target mining area environment information; performing a splicing operation on the target mining area environment information based on a splicing algorithm to obtain a mining area environment point cloud model; generating a target mining area map of the target underground mining vehicle based on the mining area environment point cloud model; and controlling the display of the target mining area map on a target display screen.

[0156] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0157] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0158] In some embodiments provided in the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0159] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0160] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0161] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a grid device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc., which can store program codes.

[0162] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A control method for an underground mining vehicle, characterized in that: include: Acquire initial state information of the target underground mining vehicle, wherein the initial state information includes obstacle information and road information; Determining target state information of the target underground mining vehicle according to the initial state information, wherein the target state information includes vehicle state information and vehicle environment information; Determining a target driving strategy for the target underground mining vehicle according to the target state information; The driving of the target underground mining vehicle is controlled according to the target driving strategy.

2. The control method of an underground mining vehicle according to claim 1, characterized in that: Acquiring the initial state information of the target underground mining vehicle includes: Obtaining preprocessing status information of the target underground mining vehicle; Performing a data processing operation on the preprocessing state information to obtain the initial state information, wherein the data processing operation includes a denoising operation, a standardization operation, and a data fusion operation.

3. The control method of an underground mining vehicle according to claim 1, characterized in that: Determining the target state information of the target underground mining vehicle according to the initial state information includes: Acquire target training data of the target underground mining vehicle; Using the target training data to train an initial neural network model to generate a target neural network model, wherein the target neural network model is used to determine the target state information; The initial state information is input into the target neural network model to obtain the target state information.

4. The control method of an underground mining vehicle according to claim 3, characterized in that: Using the target training data to train the initial neural network model to generate the target neural network model includes: Using the target training data to train the initial neural network model and determine the target loss; The model parameters of the initial neural network model are updated based on the target loss to obtain the target neural network model.

5. The control method of an underground mining vehicle according to claim 1, characterized in that: The method further comprises: Acquiring vehicle motion state information of the target underground mining vehicle, wherein the vehicle motion state information is obtained by monitoring a driving process of the target underground mining vehicle controlled according to the target driving strategy; Determining a target state of the target underground mining vehicle according to the vehicle motion state information; In response to the target state being a dangerous state, the target underground mining vehicle is controlled to perform an emergency braking operation.

6. The control method of an underground mining vehicle according to claim 5, characterized in that: The method further comprises: Determining energy management information of the target underground mining vehicle according to the target driving strategy and the vehicle motion state information; An energy consumption strategy of the target underground mining vehicle is determined according to the energy management information.

7. The control method of an underground mining vehicle according to claim 1, characterized in that: The method further comprises: Obtaining initial mining area environment information of the target underground mining vehicle; Performing a cleaning operation on the initial mining area environmental information to obtain target mining area environmental information; Performing a splicing operation on the target mining area environment information based on a splicing algorithm to obtain a mining area environment point cloud model; Generate a target mining area map of the target underground mining vehicle according to the mining area environment point cloud model; Control the target mining area map to be displayed on a target display screen.

8. A control device for an underground mining vehicle, characterized in that: include: A first acquisition module is used to acquire initial state information of a target underground mining vehicle, wherein the initial state information includes obstacle information and road information; A first determination module is used to determine the target state information of the target underground mining vehicle according to the initial state information, wherein the target state information includes vehicle state information and vehicle environment information; A second determination module is used to determine a target driving strategy of the target underground mining vehicle according to the target state information; The first control module is used to control the driving of the target underground mining vehicle according to the target driving strategy.

9. An electronic device, comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the control method for an underground mining vehicle as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the control method of the underground mining vehicle described in any one of claims 1 to 7 when running on a computer or a processor.

Images