A method and system for remotely controlling mining vehicles based on 5G network

Abstract

The present invention discloses a method and system for remotely controlling mining vehicles based on a 5G network, and relates to the technical field of remotely controlled vehicles. The method for remotely controlling mining vehicles based on a 5G network acquires and preprocesses the real-time vehicle condition data and real-time traveling environment image data of each mining vehicle to be controlled in real time; and performs data analysis on the preprocessed real-time vehicle condition data of each mining vehicle to be controlled. The present invention utilizes the high speed and low latency characteristics of the 5G network, and the method can acquire and process the vehicle status and environmental data in real time, significantly improving the real-time and accuracy of remote control. Through real-time analysis of vehicle condition and environmental image data, the method can generate safety indicators and environmental indicators in a timely manner, and provide accurate data for the evaluation of control complexity, which ensures that even in a complex mining environment, the accuracy and reliability of remote operation are guaranteed, greatly reducing the risk of control errors.

Description

Technical Field

[0001] The present invention relates to the field of remote control vehicle technology, and specifically to a method and system for remotely controlling mining vehicles based on a 5G network. Background Art

[0002] With the rapid development of industrial automation and information technology, especially the widespread application of 5G communication technology, remote control systems have become one of the key technologies to improve the efficiency and safety of mining operations. In the field of mining vehicle operation, traditional manual operation methods face several limitations and challenges, especially in harsh environmental conditions and high-risk operation scenarios.

[0003] The operating environment in mining areas is complex and changeable, with a variety of potential risks, such as complex terrain, low visibility, and extreme climatic conditions, which seriously challenge the safety and efficiency of traditional operating methods.

[0004] Manual operation of mining vehicles is not only labor-intensive, but also poses safety risks in certain environments. In addition, the efficiency and accuracy of manual operation are also limited by the operator's skills and physical strength, making it difficult to adapt to the long-term and high-intensity mining operations.

[0005] Before the 5G network, traditional wireless communication technologies (such as 3G and 4G) could not meet the high requirements of remote control systems for real-time data transmission in terms of bandwidth, latency and connection stability. These technical limitations affected the response speed and reliability of the remote control system.

[0006] The introduction of 5G technology provides new possibilities for solving the above problems. 5G networks have the characteristics of high bandwidth, low latency and high reliability, and can support more complex and efficient remote control applications.

[0007] Based on the above solution, it is found that the limitations of the existing technology include at least the following problems. First, in the traditional mining vehicle control system, data transmission often relies on a slower network connection or periodic data update, which limits the real-time and accuracy of the operation. In addition, the traditional method is often difficult to dynamically adapt to the complex and changeable mining environment during design and implementation, such as changes in road conditions and sudden obstacles, thereby reducing the flexibility of control and the safety of the vehicle. Secondly, the traditional method usually causes control command delays or failures due to network instability during vehicle remote control operation, thereby increasing the possibility of accident risks. Summary of the invention

[0008] In view of the shortcomings of the prior art, the present invention provides a method and system for remotely controlling mining vehicles based on a 5G network, which solves the problem that in traditional mining vehicle control systems, data transmission often relies on slower network connections or periodic data updates, thereby limiting the real-time and accuracy of operations. In addition, traditional methods are often difficult to dynamically adapt to complex and changeable mining environments, such as changes in road conditions and sudden obstacles, during design and implementation, thereby reducing the flexibility of control and the safety of the vehicle. Secondly, traditional methods usually cause control command delays or failures due to network instability during vehicle remote control operations, thereby increasing the possibility of accident risks.

[0009] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for remotely controlling mining vehicles based on 5G network, comprising the following steps: real-time acquisition and preprocessing of real-time vehicle condition data and real-time traveling environment image data of each mining vehicle to be controlled; performing data analysis on the preprocessed real-time vehicle condition data of each mining vehicle to be controlled, and obtaining the real-time vehicle condition safety index of each mining vehicle to be controlled; performing regional extraction on the preprocessed real-time traveling environment image data of each mining vehicle to be controlled, and obtaining the real-time road area data and real-time obstacle area data of each mining vehicle to be controlled; The real-time road area data and real-time obstacle area data are comprehensively analyzed to obtain the real-time driving environment index of each mining area vehicle to be controlled; the real-time vehicle condition safety index and real-time driving environment index of each mining area vehicle to be controlled are comprehensively analyzed to obtain the control complexity evaluation value of each mining area vehicle to be controlled; the control complexity evaluation value of each mining area vehicle to be controlled is compared and analyzed with the preset evaluation threshold, and corresponding remote control measures are taken based on the analysis results; when the mining area vehicle to be controlled is remotely controlled, the real-time 5G network transmission data is obtained in real time, and monitoring and analysis are carried out, and corresponding network emergency measures are taken based on the monitoring and analysis results.

[0010] Furthermore, the real-time vehicle condition data specifically includes the current speed value, the current cargo capacity, the current engine power, and the current pressure value of each tire, and the real-time traveling environment image data specifically includes the pixel value of each pixel point in the real-time traveling environment image.

[0011] Furthermore, the specific formula for calculating the control complexity evaluation value of each mining vehicle to be controlled is as follows:

[0012] ;

[0013] in, is the control complexity evaluation value of the i-th mining vehicle to be controlled, is the real-time vehicle safety index of the i-th mining vehicle to be controlled, is the vehicle condition safety factor of the i-th mining vehicle to be controlled stored in the database, is the real-time driving environment index of the i-th mining vehicle to be controlled, is the driving environment coefficient of the i-th mining vehicle to be controlled stored in the database, , is a natural constant, , The number of vehicles in the mining area to be controlled.

[0014] Furthermore, the specific steps for obtaining the real-time road area data and real-time obstacle area data of each mining vehicle to be controlled are as follows: based on the edge detection algorithm, the pixel value of each pixel point in the real-time traveling environment image of each mining vehicle to be controlled after preprocessing is subjected to edge recognition, and a number of road edge pixel points in the road area of ​​each mining vehicle to be controlled and a number of obstacle edge pixel points in each obstacle area are obtained; for each mining vehicle to be controlled, a number of road edge pixel points in the road area are respectively subjected to road contour connection processing, and a number of road pixel points and a number of road edge pixel points in the road contour after the road contour connection processing are marked as real-time road area data; for each mining vehicle to be controlled, a number of obstacle edge pixel points in each obstacle area are respectively subjected to obstacle contour connection processing, and a number of obstacle pixel points and a number of obstacle edge pixel points in each obstacle contour after the obstacle contour connection processing are marked as real-time obstacle area data.

[0015] Furthermore, the specific steps for obtaining the real-time driving environment index of each mining area vehicle to be controlled are as follows: the pixel values ​​of several road pixel points and several road edge pixel points within the road contour of each mining area vehicle to be controlled are comprehensively analyzed to obtain the real-time vehicle driving road smoothness index of each mining area vehicle to be controlled; the number of obstacle pixel points within each obstacle contour of each mining area vehicle to be controlled and the number of obstacle edge pixel points are summed and analyzed to obtain the total obstacle area value of each mining area vehicle to be controlled; the real-time vehicle driving road smoothness index and the total obstacle area value of each mining area vehicle to be controlled are standardized respectively; the real-time vehicle driving road smoothness index and the total obstacle area value of each mining area vehicle to be controlled after the standardized processing are comprehensively analyzed to obtain the real-time driving environment index of each mining area vehicle to be controlled.

[0016] Furthermore, the specific formula for calculating the real-time vehicle road smoothness index and the real-time driving environment index of each mining area vehicle to be controlled is as follows:

[0017] ;

[0018] in, is the real-time vehicle road smoothness index of the i-th mining area vehicle to be controlled, is the first vehicle in the road contour to be controlled in the mining area The pixel value of each road pixel, is the first vehicle in the road contour to be controlled in the mining area The pixel value of the road edge pixel, is the real-time driving environment index of the i-th mining vehicle to be controlled, is the real-time vehicle road roughness index of the i-th mining vehicle to be controlled after normalization, is the road coefficient of the i-th mining vehicle to be controlled stored in the database, is the total obstacle area of ​​the i-th mining vehicle to be controlled after standardized processing, is the obstacle coefficient of the i-th mining vehicle to be controlled stored in the database, , , is the number of vehicles in the mining area to be controlled, , is the number of road pixels within the road outline, , It is the number of road edge pixels within the road outline.

[0019] Furthermore, the specific steps for obtaining the real-time vehicle condition safety index of each mining area vehicle to be controlled are as follows: obtain the maximum safe speed value, the maximum safe cargo capacity, the maximum safe engine power, and the maximum safe pressure value of each tire of each mining area vehicle to be controlled; analyze the current speed value, the current cargo capacity, the current engine power, and the current pressure value of each tire of each mining area vehicle to be controlled with the maximum safe speed value, the maximum safe cargo capacity, the maximum safe engine power, and each maximum tire pressure, respectively, to obtain the current speed deviation value, the current cargo capacity deviation value, the current engine power deviation value, and the current tire deviation value of each mining area vehicle to be controlled; comprehensively analyze the current speed deviation value, the current cargo capacity deviation value, the current engine power deviation value, and the current tire deviation value of each mining area vehicle to be controlled to obtain the real-time vehicle condition safety index of each mining area vehicle to be controlled; wherein, the specific formula for calculating the current speed deviation value, the current tire deviation value, and the real-time vehicle condition safety index of each mining area vehicle to be controlled is as follows:

[0020] ;

[0021] in, is the current speed deviation value of the i-th mining vehicle to be controlled, is the current speed value of the i-th mining vehicle to be controlled, is the maximum safe speed value of the i-th mining vehicle to be controlled, is the current tire deviation value of the i-th mining vehicle to be controlled, is the current pressure of the jth tire of the i-th mining vehicle to be controlled, is the maximum safe pressure value of the jth tire of the iith mining vehicle to be controlled, is the real-time vehicle safety index of the i-th mining vehicle to be controlled, is the speed deviation coefficient of the i-th mining vehicle to be controlled stored in the database, is the current cargo capacity deviation value of the i-th mining vehicle to be controlled, is the cargo capacity deviation coefficient of the i-th mining vehicle to be controlled stored in the database, is the current engine power deviation value of the i-th mining vehicle to be controlled, is the cargo capacity deviation coefficient of the i-th mining vehicle to be controlled stored in the database, is the cargo capacity deviation coefficient of the i-th mining vehicle to be controlled stored in the database, , , is the number of vehicles in the mining area to be controlled, , is the number of tires.

[0022] Furthermore, the control complexity evaluation value of each mine vehicle to be controlled is compared and analyzed with the preset evaluation threshold value, and the specific steps of taking corresponding remote control measures based on the analysis results are as follows: the control complexity evaluation value of each mine vehicle to be controlled is compared and analyzed with the first evaluation threshold value and the second evaluation threshold value; if there is a mine vehicle to be controlled whose control complexity evaluation value is less than or equal to the first evaluation threshold value, the first remote operation mode is activated for the mine vehicle to be controlled, and the mine vehicle to be controlled is remotely controlled based on the set first driving state; if there is a mine vehicle to be controlled whose control complexity evaluation value is higher than the first evaluation threshold value and less than or equal to the second evaluation threshold value, the second remote operation mode is activated for the mine vehicle to be controlled, and the mine vehicle to be controlled is remotely controlled based on the set second driving state; if there is a mine vehicle to be controlled whose control complexity evaluation value is higher than the second evaluation threshold value, the third remote operation mode is activated for the mine vehicle to be controlled, and the mine vehicle to be controlled is remotely controlled based on the set third driving state.

[0023] Furthermore, when the mining vehicle to be controlled is remotely controlled, the real-time 5G network transmission data is obtained in real time, and monitoring and analysis are carried out. The specific steps for taking corresponding network emergency measures based on the monitoring and analysis results are as follows: obtain the maximum allowable delay jitter value, maximum allowable packet loss rate, minimum bandwidth value, and minimum signal strength value of 5G network transmission; when the mining vehicle to be controlled is remotely controlled, the real-time 5G network transmission data of each mining vehicle to be controlled is obtained in real time, and the real-time 5G network transmission data specifically includes the current delay jitter value, current packet loss rate, current bandwidth value, and current signal strength value; the current delay jitter value, current packet loss rate, maximum allowable delay jitter, and minimum signal strength value of each mining vehicle to be controlled are obtained. The dynamic value and the maximum allowed packet loss rate are analyzed respectively to obtain the current transmission efficiency index of each mining area vehicle to be controlled; when the mining area vehicle to be controlled is remotely controlled, the current bandwidth value, current signal strength value, minimum bandwidth value, and minimum signal strength value of each mining area vehicle to be controlled are analyzed in real time to obtain the current transmission quality index of each mining area vehicle to be controlled; the current transmission efficiency index and the current transmission quality index of each mining area vehicle to be controlled are comprehensively analyzed to obtain the real-time network stability index of each mining area vehicle to be controlled; among them, the specific formulas for calculating the current transmission efficiency index, the current transmission quality index, and the real-time network stability index of each mining area vehicle to be controlled are as follows:

[0024] ;

[0025] in, is the current transmission efficiency index of the i-th mining vehicle to be controlled, is the current delay jitter value of the i-th mining vehicle to be controlled, is the maximum allowable delay jitter value for 5G network transmission. is the current packet loss rate of the i-th mining vehicle to be controlled, is the maximum allowed packet loss rate for 5G network transmission, is the current transmission quality index of the i-th mining vehicle to be controlled, is the current bandwidth value of the i-th mining vehicle to be controlled, The minimum bandwidth value for 5G network transmission. is the current signal strength value of the i-th mining vehicle to be controlled, is the minimum signal strength value for 5G network transmission. is the real-time network stability index of the i-th mining vehicle to be controlled, is a natural constant, is the transmission efficiency coefficient stored in the database, is the transmission quality coefficient stored in the database, , , The number of vehicles in the mining area to be controlled.

[0026] A system for remotely controlling mining area vehicles based on a 5G network, comprising: a vehicle condition data acquisition module, a camera module, a vehicle condition analysis module, an environmental analysis module, a comprehensive analysis module, a remote control module, and a monitoring module; the vehicle condition data acquisition module is used to acquire and preprocess the real-time vehicle condition data of each mining area vehicle to be controlled in real time; the camera module is used to acquire and preprocess the real-time traveling environment image data of each mining area vehicle to be controlled in real time; the vehicle condition analysis module is used to perform data analysis on the real-time vehicle condition data of each mining area vehicle to be controlled after preprocessing, and obtain the real-time vehicle condition safety index of each mining area vehicle to be controlled; the environmental analysis module is used to perform regional extraction on the real-time traveling environment image data of each mining area vehicle to be controlled after preprocessing, and obtain the real-time road area of ​​each mining area vehicle to be controlled The system collects real-time 5G network data and real-time obstacle area data of each mining vehicle to be controlled, and comprehensively analyzes the real-time road area data and real-time obstacle area data of each mining vehicle to be controlled to obtain the real-time driving environment index of each mining vehicle to be controlled; the comprehensive analysis module is used to comprehensively analyze the real-time vehicle safety index and real-time driving environment index of each mining vehicle to be controlled to obtain the control complexity evaluation value of each mining vehicle to be controlled; the remote control module is used to compare and analyze the control complexity evaluation value of each mining vehicle to be controlled with the preset evaluation threshold value, and take corresponding remote control measures based on the analysis results; the monitoring module is used to obtain real-time 5G network transmission data in real time when remotely controlling the mining vehicle to be controlled, and perform monitoring and analysis, and take corresponding network emergency measures based on the monitoring and analysis results.

[0027] The present invention has the following beneficial effects:

[0028] (1) This method of remotely controlling mining vehicles based on a 5G network can obtain and process vehicle status and environmental data in real time by utilizing the high speed and low latency characteristics of the 5G network, significantly improving the real-time and accuracy of remote control. Through real-time analysis of vehicle condition and environmental image data, it can generate safety indicators and environmental indicators in a timely manner, providing accurate data for the evaluation of control complexity. This ensures that the accuracy and reliability of remote operation are guaranteed even in a complex mining environment, greatly reducing the risk of control errors.

[0029] (2) This method of remotely controlling mining vehicles based on 5G networks can identify and analyze road and obstacle conditions by analyzing real-time driving environment image data, and adjust the control strategy in real time to adapt to environmental changes. This dynamic adaptation function enables each vehicle to be optimally controlled according to the current driving environment and vehicle conditions, thereby improving the flexibility and efficiency of mining vehicle operations and ensuring the safe driving of vehicles in a changing environment.

[0030] (3) This method of remotely controlling mining vehicles based on 5G networks ensures the continuity and stability of remote control instructions by continuously monitoring real-time 5G network transmission data and adjusting network emergency measures according to the current network status. When faced with network fluctuations or instability, timely response measures can be taken, such as adjusting the data transmission frequency or changing the control strategy, thereby ensuring the efficiency and safety of remote control of mining vehicles and reducing the risk of accidents caused by network problems.

[0031] (4) The system for remotely controlling mining vehicles based on the 5G network enhances its modularity and scalability by decomposing the functions of remotely controlling mining vehicles based on the 5G network into a vehicle condition data acquisition module, a camera module, a vehicle condition analysis module, an environmental analysis module, a comprehensive analysis module, a remote control module, and a monitoring module. This modular design not only enables each part to work and be optimized independently, but also facilitates future upgrades and maintenance. For example, if it is necessary to introduce more advanced data analysis technology or replace more efficient camera equipment, the corresponding modules can be upgraded separately without redesigning the entire system. Such a design architecture also facilitates the integration of new functions or interfaces with other systems in the future, thereby enhancing the flexibility of the overall system and its future application potential.

[0032] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a flow chart of a method for remotely controlling mining vehicles based on a 5G network in the present invention.

[0034] Figure 2 This is a system block diagram of the present invention for remotely controlling mining vehicles based on a 5G network. DETAILED DESCRIPTION

[0035] The embodiments of the present application provide a method and system for remotely controlling mining vehicles based on a 5G network, thereby solving the problem that in traditional mining vehicle control systems, data transmission often relies on slower network connections or periodic data updates, thereby limiting the real-time and accuracy of operations. In addition, traditional methods are often difficult to dynamically adapt to complex and changeable mining environments, such as changes in road conditions and sudden obstacles, during design and implementation, thereby reducing the flexibility of control and the safety of the vehicle. Secondly, traditional methods usually cause control command delays or failures due to network instability during vehicle remote control operations, thereby increasing the possibility of accident risks.

[0036] The overall idea of ​​the problem in the embodiment of this application is as follows:

[0037] First, the vehicle condition data and driving environment image data of each vehicle to be controlled in the mining area are collected in real time through the 5G network. These data include the vehicle speed, cargo capacity, engine power, tire pressure, and surrounding road and obstacle images. Secondly, the pre-processed data is analyzed in detail, and safety indicators and environmental indicators are extracted from the vehicle condition data and environmental image data respectively, including the identification and analysis of roads and obstacles, so as to evaluate the control complexity of each vehicle. Finally, the evaluation value of the control complexity is compared with the preset evaluation threshold to determine the appropriate remote control mode and implement corresponding control measures. At the same time, the status of the 5G network is continuously monitored to ensure the communication quality, so as to adjust the network emergency measures in time to ensure the stability and safety of remote control.

[0038] See also Figure 1 , an embodiment of the present invention provides a technical solution: a method for remotely controlling mining area vehicles based on a 5G network, comprising the following steps: real-time acquisition and preprocessing of real-time vehicle condition data and real-time traveling environment image data of each mining area vehicle to be controlled; performing data analysis on the preprocessed real-time vehicle condition data of each mining area vehicle to be controlled to obtain the real-time vehicle condition safety index of each mining area vehicle to be controlled; performing regional extraction on the preprocessed real-time traveling environment image data of each mining area vehicle to be controlled to obtain the real-time vehicle front road area data and real-time obstacle area data ... vehicle front road area data and real-time obstacle area data of each mining area vehicle to be controlled. Comprehensively analyze the real-time road area data and real-time obstacle area data to obtain the real-time driving environment index of each mining area vehicle to be controlled; comprehensively analyze the real-time vehicle safety index and real-time driving environment index of each mining area vehicle to be controlled to obtain the control complexity evaluation value of each mining area vehicle to be controlled; compare and analyze the control complexity evaluation value of each mining area vehicle to be controlled with the preset evaluation threshold, and take corresponding remote control measures based on the analysis results; when remotely controlling the mining area vehicle to be controlled, obtain real-time 5G network transmission data in real time, monitor and analyze it, and take corresponding network emergency measures based on the monitoring and analysis results.

[0039] The real-time vehicle condition data specifically includes the current speed value, the current cargo load, the current engine power, and the current pressure value of each tire. The real-time traveling environment image data specifically includes the pixel value of each pixel point in the real-time traveling environment image.

[0040] The current cargo load is the actual weight of the cargo carried on the vehicle, and the current cargo load data is obtained through the on-board computer or the dispatching system.

[0041] Specifically, the specific formula for calculating the control complexity evaluation value of each mining vehicle to be controlled is as follows:

[0042] ;

[0043] in, is the control complexity evaluation value of the i-th mining vehicle to be controlled, is the real-time vehicle safety index of the i-th mining vehicle to be controlled, is the vehicle condition safety factor of the i-th mining vehicle to be controlled stored in the database, is the real-time driving environment index of the i-th mining vehicle to be controlled, is the driving environment coefficient of the i-th mining vehicle to be controlled stored in the database, , is a natural constant, , is the number of vehicles in the mining area to be controlled, and the above values ​​are normalized before calculation and analysis, so they can be directly added together.

[0044] It needs to be explained that , The specific calculation process is as follows: obtain the vehicle condition safety reference index and driving environment reference index of each vehicle to be controlled in the mining area and perform sum analysis to obtain the control complexity reference and value of each vehicle to be controlled in the mining area, and perform proportion analysis on each vehicle condition safety reference index and driving environment reference index respectively with the control complexity evaluation and value, and the proportion analysis result is the corresponding coefficient.

[0045] Among them, the method of obtaining the vehicle condition safety reference index is to obtain the reference speed value, reference cargo capacity, reference engine power, and reference pressure value of each tire of each mining vehicle to be controlled under the vehicle condition safety standard state, and conduct a comprehensive analysis of the vehicle condition safety reference index. The calculation logic used in the comprehensive analysis is consistent with the calculation logic for calculating the real-time vehicle condition safety index.

[0046] The method for obtaining the driving environment reference index is to obtain the reference pixel values ​​of several road reference pixels and several road edge reference pixels within the road contour when the road surface is flat (because its environmental reference index is the reference index when the road surface is flat and there are no obstacles, so the obstacle area is 0, that is, the impact of obstacles is not considered), and perform comprehensive analysis to obtain the reference index of the flatness of the road ahead of the vehicle. The calculation logic used in the comprehensive analysis is consistent with the calculation logic of calculating the real-time flatness index of the road ahead of the vehicle.

[0047] In this embodiment, by using reference indicators (based on the vehicle condition in standard state and the most ideal driving environment), the method can more accurately evaluate the control complexity of each vehicle in the current state. This comparative analysis helps the operator understand the degree of deviation of the vehicle control requirements at any given time point, thereby providing more accurate data support for making operational decisions, especially in emergency or unconventional operation scenarios. Using this method, the evaluation of all vehicles is based on unified standards and calculation logic, which ensures the consistency and repeatability of operations. The standardized process ensures the comparability of data from different vehicles and different operating conditions, so that the remote control method maintains consistent operating standards in the entire mining vehicle group, reducing the risk of errors caused by the remote control method. Operation errors caused by differences in human judgment. By comparing real-time data with reference indicators, this method can identify vehicles that require special attention or may require emergency intervention, thereby optimizing the allocation of resources. For example, if the real-time environmental indicators of a vehicle differ greatly from the reference indicators, this method may prioritize allocating more monitoring resources or adjusting its operation strategy to ensure vehicle safety and operational efficiency. By using automated data analysis and comprehensive evaluation modules, this method can make data-driven decisions quickly without human intervention, which not only improves operational efficiency but also reduces the possibility of human error. Especially in complex or dangerous mining environments, automated and intelligent decision-making is particularly important.

[0048] Specifically, the specific steps for obtaining the real-time vehicle front road area data and real-time obstacle area data of each mining vehicle to be controlled are as follows: based on the edge detection algorithm, the pixel value of each pixel point in the real-time moving environment image of each mining vehicle to be controlled after preprocessing is subjected to edge recognition, and a number of road edge pixel points in the road area of ​​each mining vehicle to be controlled and a number of obstacle edge pixel points in each obstacle area are obtained; for each mining vehicle to be controlled, a number of road edge pixel points in the road area are respectively subjected to road contour connection processing, and a number of road pixel points and a number of road edge pixel points in the road contour after the road contour connection processing are marked as real-time vehicle front road area data; for each mining vehicle to be controlled, a number of obstacle edge pixel points in each obstacle area are respectively subjected to obstacle contour connection processing, and a number of obstacle pixel points and a number of obstacle edge pixel points in each obstacle contour after the obstacle contour connection processing are marked as real-time obstacle area data.

[0049] Among them, common edge detection algorithms include:

[0050] Sobel algorithm: Determines the edge by calculating the approximation of the first-order derivative of the image grayscale. It is particularly suitable for rough edge detection.

[0051] Canny edge detection: It is a widely used edge detection algorithm, which is widely adopted due to its advantages of low error rate, high accuracy of edge point positioning and single response edge.

[0052] The specific steps of edge detection are as follows:

[0053] Apply the selected edge detection algorithm to the preprocessed grayscale image. For example, if using the Canny algorithm, set the low and high thresholds. These two thresholds help determine when to start and end edge tracing.

[0054] The edge detection algorithm outputs a binary image where edge pixels are white (or 1) and non-edge pixels are black (or 0).

[0055] From the edge detection results, edge pixels forming the road contour are identified and extracted.

[0056] Similarly, edge pixels that identify the obstacle outline are extracted from the results.

[0057] Use contour tracking algorithms (such as chain code tracking) to connect road edge pixels to form a complete road contour.

[0058] The contour tracking method is also used to connect the pixel points on the edge of the obstacle to form the obstacle contour.

[0059] After the road contour connection is completed, the pixel points within the road contour and the pixel points of the contour itself are marked as real-time road area data in front of the vehicle.

[0060] Similarly, the pixels within the obstacle outline and the pixels at the edge of the outline are marked as real-time obstacle area data.

[0061] In this embodiment, by accurately identifying the road edge and the obstacle edge, the method can provide accurate road profile and obstacle location information for remote control, which is crucial for the safe driving of mining vehicles in complex or changeable terrain. This detailed environmental perception capability can help remote operators make more accurate driving decisions and avoid potential collisions or accidents, thereby greatly enhancing driving safety. With the real-time update and analysis of road and obstacle information, the method can instantly adjust the driving strategy to adapt to environmental changes, such as automatically bypassing obstacles or adjusting the driving route, thereby improving the operating efficiency and responsiveness of the vehicle in the mining area. By using advanced edge detection technology such as Canny or Sobel algorithm, the method can not only accurately identify key features in the environment, but also output edge detection results with high resolution. This high-quality image analysis result directly improves the accuracy of remote control, allowing the operator to more finely control each movement of the vehicle to ensure the accuracy and reliability of the operation. The method reduces the reliance on manual intervention through automated image analysis and processing, so that resources can be more effectively allocated to other key operating tasks. In addition, the efficient operation of the method also means that the cost and time loss caused by misjudgment or delayed response can be reduced.

[0062] Specifically, the specific steps for obtaining the real-time driving environment index of each mining area vehicle to be controlled are as follows: the pixel values ​​of several road pixel points and several road edge pixel points within the road contour of each mining area vehicle to be controlled are comprehensively analyzed to obtain the real-time vehicle front road smoothness index of each mining area vehicle to be controlled; the number of obstacle pixel points within each obstacle contour of each mining area vehicle to be controlled and the number of obstacle edge pixel points are summed and analyzed to obtain the total obstacle area of ​​each mining area vehicle to be controlled; the real-time vehicle front road smoothness index and the total obstacle area of ​​each mining area vehicle to be controlled are standardized; the real-time vehicle front road smoothness index and the total obstacle area of ​​each mining area vehicle to be controlled after the standardized processing are comprehensively analyzed to obtain the real-time driving environment index of each mining area vehicle to be controlled.

[0063] The specific formula for calculating the real-time vehicle front road smoothness index and real-time driving environment index of each mining area vehicle to be controlled is as follows:

[0064] ;

[0065] in, is the real-time vehicle road smoothness index of the i-th mining vehicle to be controlled, is the first vehicle in the road contour to be controlled in the mining area The pixel value of each road pixel, is the first vehicle in the road contour to be controlled in the mining area The pixel value of the road edge pixel, is the real-time driving environment index of the i-th mining vehicle to be controlled, is the real-time vehicle road roughness index of the i-th mining vehicle to be controlled after normalization, is the road coefficient of the i-th mining vehicle to be controlled stored in the database, is the total obstacle area of ​​the i-th mining vehicle to be controlled after standardized processing, is the obstacle coefficient of the i-th mining vehicle to be controlled stored in the database, , , is the number of vehicles in the mining area to be controlled, , is the number of road pixels within the road outline, , It is the number of road edge pixels within the road outline.

[0066] It should be explained that in this embodiment , The specific values ​​are 0.6 and 0.4 respectively (obtained through regression analysis of the total obstacle area in historical data and the proportion of the roughness index of the road ahead of the vehicle. Past data and experience can predict and simulate vehicle performance under different driving conditions).

[0067] In this embodiment, the method calculates the road roughness index by comprehensively analyzing the pixel points within the road contour and the pixel points at the edge of the road, which can provide the operator with accurate road condition information. Through this sophisticated analysis, the unevenness of the road surface, potholes or other potential driving obstacles can be identified, thereby helping the remote operator make better driving decisions and ensure safe and efficient driving of the vehicle. By analyzing the number of pixels within the obstacle contour, the method can calculate the total area of ​​the obstacle, which provides key obstacle information for remote control. Knowing the specific size and location of the obstacle can help the operator evaluate the possible impact of the obstacle, optimize the obstacle avoidance strategy, and reduce collisions and accidents. The method can dynamically adjust the vehicle's driving strategy according to the actual situation. For example, when the driving environment indicators show a large obstacle or an extremely uneven road surface, the method can instantly adjust the vehicle speed or route, and even initiate emergency measures when necessary to cope with complex or dangerous driving conditions. By using the coefficients stored in the database (such as the road coefficient and the obstacle coefficient), the method can optimize the current control strategy based on past data and experience. This analysis based on historical data can help predict and simulate vehicle performance under different driving conditions, provide data support for remote control, and improve the accuracy and efficiency of control.

[0068] Specifically, the specific steps for obtaining the real-time vehicle condition safety index of each mining area vehicle to be controlled are as follows: obtain the maximum safe speed value, the maximum safe cargo capacity, the maximum safe engine power, and the maximum safe pressure value of each tire of each mining area vehicle to be controlled; analyze the current speed value, the current cargo capacity, the current engine power, and the current pressure value of each tire of each mining area vehicle to be controlled with the maximum safe speed value, the maximum safe cargo capacity, the maximum safe engine power, and each maximum tire pressure, respectively, to obtain the current speed deviation value (i.e., the difference between the current speed and the maximum safe speed value), the current cargo capacity deviation value (i.e., the difference between the current cargo capacity and the maximum safe cargo capacity), the current engine power deviation value (i.e., the difference between the current engine power and the maximum safe engine power), and the current tire deviation value (i.e., the difference between the current tire pressure value and the maximum safe pressure value) of each mining area vehicle to be controlled; comprehensively analyze the current speed deviation value, the current cargo capacity deviation value, the current engine power deviation value, and the current tire deviation value of each mining area vehicle to be controlled to obtain the real-time vehicle condition safety index of each mining area vehicle to be controlled.

[0069] The specific formula for calculating the current speed deviation value, current tire deviation value, and real-time vehicle safety index of each mining vehicle to be controlled is as follows:

[0070] ;

[0071] in, is the current speed deviation value of the i-th mining vehicle to be controlled, is the current speed value of the i-th mining vehicle to be controlled, is the maximum safe speed value of the i-th mining vehicle to be controlled, is the current tire deviation value of the i-th mining vehicle to be controlled, is the current pressure of the jth tire of the i-th mining vehicle to be controlled, is the maximum safe pressure value of the jth tire of the i-th mining vehicle to be controlled, is the real-time vehicle safety index of the i-th mining vehicle to be controlled, is the speed deviation coefficient of the i-th mining vehicle to be controlled stored in the database, is the current cargo capacity deviation value of the i-th mining vehicle to be controlled, is the cargo capacity deviation coefficient of the i-th mining vehicle to be controlled stored in the database, is the current engine power deviation value of the i-th mining vehicle to be controlled, is the cargo capacity deviation coefficient of the i-th mining vehicle to be controlled stored in the database, is the cargo capacity deviation coefficient of the i-th mining vehicle to be controlled stored in the database, , , is the number of tires, and all parameters used in calculating the real-time vehicle safety index are unit-less values, so they can be calculated directly.

[0072] Among them, the maximum safe speed value is provided by the vehicle manufacturer in the user manual or technical specifications, the maximum safe cargo capacity is provided by the manufacturer in the technical specifications, the maximum safe engine power is provided by the manufacturer in the technical specifications, and the maximum safe pressure value of each tire is provided by the tire manufacturer and marked on the sidewall of the tire.

[0073] The calculation logic of the current cargo load deviation value, the current engine power deviation value and the current speed deviation value of each mining vehicle to be controlled is consistent, and the calculation formula used is also consistent.

[0074] It needs to be explained that , , , The specific acquisition process is as follows: perform mean analysis on the maximum safety pressure value of each tire of each mining area vehicle to be controlled to obtain the mean value of the maximum safety pressure of the tire of each mining area vehicle to be controlled, and then standardize the maximum safety speed value, maximum safety cargo capacity, maximum safety engine power, and mean value of the maximum safety pressure of each mining area vehicle to be controlled, and perform sum analysis after standardization to obtain the safety sum value of each mining area vehicle to be controlled, and perform proportion analysis on the maximum safety speed value, maximum safety cargo capacity, maximum safety engine power, and mean value of the maximum safety pressure of each mining area vehicle to be controlled after standardization, respectively, and the proportion analysis result is the corresponding coefficient.

[0075] In this embodiment, the method provides a real-time safety assessment by monitoring and comparing the difference between the vehicle's current operating status and the maximum safety standards (such as speed, cargo capacity, engine power and tire pressure) in real time. This continuous assessment ensures that the vehicle does not exceed its safe operating parameters at any given moment, greatly reducing the risk of accidents caused by overloading, speeding or equipment overloading. By calculating deviation values ​​and performing comprehensive analysis, the method can accurately identify any conditions that may endanger vehicle safety. For example, if a vehicle's current speed or tire pressure exceeds the safety threshold, the method can immediately notify the operator or automatically adjust the vehicle settings to restore it to a safe state. This real-time The feedback mechanism increases the speed and effectiveness of response to emergencies. Through real-time analysis and tracking of vehicle condition data, the method can effectively predict potential maintenance needs and fault warnings. For example, frequent engine power deviations may indicate reduced engine efficiency or possible future failures. In this way, maintenance can be more proactive and preventive rather than merely reactive, thereby reducing downtime and repair costs. Standardizing the safety parameters of all vehicles and comparing them with global safety and values ​​can achieve global risk management and control. This standardized approach not only ensures the operational safety of all vehicles, but also simplifies safety monitoring and management across vehicles and equipment.

[0076] Specifically, the control complexity evaluation value of each mine vehicle to be controlled is compared and analyzed with the preset evaluation threshold value, and the specific steps of taking corresponding remote control measures based on the analysis results are as follows: the control complexity evaluation value of each mine vehicle to be controlled is compared and analyzed with the first evaluation threshold value (the vehicle is in good running condition, the driving environment conditions are simple, and it can be driven safely) and the second evaluation threshold value (the vehicle is in poor running condition, the driving environment conditions are complex, and it cannot be driven safely); if there is a mine vehicle to be controlled whose control complexity evaluation value is less than or equal to the first evaluation threshold value, the first remote operation mode is turned on for the mine vehicle to be controlled (the vehicle itself is in good condition, there are a small number of tiny obstacles on the road and the road condition is good, there are no potholes, gravel or irregular terrain, and the vehicle is driving in a straight line), and the mine vehicle to be controlled is remotely controlled based on the set first driving state, that is, the steering wheel rotation angle is set to between ±1° and ±5°, and the vehicle driving speed is 5-15km / h to ensure straight line adjustment.

[0077] If there is a mining vehicle to be controlled whose control complexity assessment value is higher than the first assessment threshold and less than or equal to the second assessment threshold, the second remote operation mode will be turned on the mining vehicle to be controlled (the vehicle itself has a fault or there are obvious potholes, cracks or unevenness on the road, and there are obstacles on the road that do not hinder the safe driving of the vehicle), and the mining vehicle to be controlled will be remotely controlled based on the set second driving state, that is, the steering wheel turning angle is set between ±1° and ±5°, and the vehicle speed is set to the minimum driving speed. At the same time, the relevant remote operation staff will be notified to send an assistance alarm, that is, the subsequent road sections will be assisted by the remote operation staff.

[0078] If there is a mining vehicle to be controlled whose control complexity assessment value is higher than the second assessment threshold, the third remote operation mode will be turned on the mining vehicle to be controlled (the vehicle itself has a fault, and there are large deep pits or large depressions on the road, there are large cracks or serious damage on the surface, and there are large obstacles on the road, such as machinery and equipment, construction materials or other large objects, and the vehicle cannot drive safely), and the mining vehicle to be controlled will be remotely controlled based on the set third driving state, that is, the mining vehicle to be controlled will be stopped immediately, and the relevant mining staff will be notified to send a vehicle abnormality alarm. When the relevant mining staff solves the vehicle's own fault, the relevant remote operation staff will be notified to send an assistance alarm, that is, the subsequent sections will be driven with the assistance of the remote operation staff.

[0079] In this embodiment, by setting different operation modes corresponding to different vehicle conditions and environmental conditions, the method can respond to various scenarios in a personalized manner. This strategy ensures that each vehicle is operated in its most suitable state, from simple straight-line driving to precise control in complex environments, thereby improving the accuracy of control and the efficiency of vehicle use. The method can timely adjust the operation mode to adapt to current driving needs by evaluating the vehicle's operating status and environmental conditions in real time. For example, when the vehicle encounters a complex road surface or mechanical failure, the method will automatically reduce the driving speed or stop and wait for manual intervention, which greatly reduces the possibility of accidents and enhances the safety of operation. When the vehicle operation complexity is low, the method can automatically adopt a simpler operation strategy, thereby saving manpower and attention resources and allocating them to vehicles that require more complex operation or emergency handling. This dynamic resource allocation improves overall operational efficiency while ensuring high responsiveness in critical situations. For vehicles with high operation complexity, the method can quickly take emergency measures such as stopping and notify relevant staff. This rapid emergency response mechanism ensures that problems can be effectively handled even under extreme conditions to protect the safety of the vehicle and the driving environment.

[0080] Specifically, when remotely controlling the mining area vehicle to be controlled, real-time 5G network transmission data is obtained in real time, and monitoring and analysis are carried out. The specific steps for taking corresponding network emergency measures based on the monitoring and analysis results are as follows: obtain the maximum allowable delay jitter value, maximum allowable packet loss rate, minimum bandwidth value, and minimum signal strength value of 5G network transmission; when remotely controlling the mining area vehicle to be controlled, real-time 5G network transmission data of each mining area vehicle to be controlled is obtained in real time. The real-time 5G network transmission data specifically includes the current delay jitter value, current packet loss rate, current bandwidth value, and current signal strength value; The current delay jitter value, current packet loss rate, maximum allowable delay jitter value, and maximum allowable packet loss rate of the vehicle are analyzed respectively to obtain the current transmission efficiency index of each mining area vehicle to be controlled; when the mining area vehicle to be controlled is remotely controlled, the current bandwidth value, current signal strength value, minimum bandwidth value, and minimum signal strength value of each mining area vehicle to be controlled are analyzed in real time to obtain the current transmission quality index of each mining area vehicle to be controlled; the current transmission efficiency index and current transmission quality index of each mining area vehicle to be controlled are comprehensively analyzed to obtain the real-time network stability index of each mining area vehicle to be controlled.

[0081] The specific formula for calculating the current transmission efficiency index, current transmission quality index, and real-time network stability index of each mining vehicle to be controlled is as follows:

[0082] ;

[0083] in, is the current transmission efficiency index of the i-th mining vehicle to be controlled, is the current delay jitter value of the i-th mining vehicle to be controlled, is the maximum allowable delay jitter value for 5G network transmission. is the current packet loss rate of the i-th mining vehicle to be controlled, is the maximum allowed packet loss rate for 5G network transmission, is the current transmission quality index of the i-th mining vehicle to be controlled, is the current bandwidth value of the i-th mining vehicle to be controlled, The minimum bandwidth value for 5G network transmission. is the current signal strength value of the i-th mining vehicle to be controlled, The minimum signal strength value for 5G network transmission. is the real-time network stability index of the i-th mining vehicle to be controlled, is a natural constant, is the transmission efficiency coefficient stored in the database, is the transmission quality coefficient stored in the database, , , The number of vehicles in the mining area to be controlled.

[0084] Among them, the maximum allowable delay jitter value of 5G network transmission is obtained according to the maximum allowable delay jitter value of the International Telecommunication Union, and is 20ms in this embodiment.

[0085] The maximum allowable packet loss rate of 5G network transmission is obtained according to the protocol used for video streaming transmission (such as HLS, DASH, RTMP, RTSP), where the protocol stipulates that the tolerance range of packet loss rate is 0.1%-3%, and 3% is taken in this embodiment.

[0086] The minimum bandwidth value of 5G network transmission is obtained according to the current mainstream frequency band range of 5G network. The current mainstream frequency band range of 5G network is 100Mbps-1Gbps, and 100Mbps is taken in this embodiment.

[0087] The minimum signal strength value of 5G network transmission is obtained based on reference industry standards and documents (such as ITU, 3GPP, etc.), and is 20dB in this embodiment.

[0088] The current packet loss rate is the ratio of lost data packets to the total data packets sent at the current time point, which can be directly obtained through network monitoring tools (such as PRTG Network Monitor, Nagios, Zabbix, etc.).

[0089] The current delay jitter value is the change in the network delay at the current time point compared to the previous time point, and is directly obtained through the built-in delay jitter value monitoring function of the network quality monitoring platform (such as PRTG Network Monitor or Zabbix).

[0090] It needs to be explained that , The specific acquisition process is as follows: perform weighted analysis on the maximum allowable delay jitter value and maximum allowable packet loss rate, minimum bandwidth value and minimum signal strength value of 5G network transmission (all performed after standardization) to obtain the transmission efficiency reference index and transmission quality reference index of 5G network transmission respectively; perform sum analysis on the transmission efficiency reference index and transmission quality reference index of 5G network transmission (performed after standardization) to obtain the network stability and value; perform proportion analysis on the transmission efficiency reference index and transmission quality reference index of 5G network transmission and the network stability and value respectively, and the proportion analysis result is the corresponding coefficient.

[0091] In this implementation scheme, the method ensures the efficiency and stability of data transmission by real-time monitoring of key performance indicators of the 5G network (such as delay jitter, packet loss rate, bandwidth and signal strength). This monitoring can promptly detect any adverse changes in the network status and respond quickly, thereby ensuring the real-time and reliability of remote operation and ensuring that vehicle control instructions are transmitted in a timely and accurate manner. Through comprehensive analysis of network transmission data, the method can adjust the data transmission requirements and strategies according to the current network conditions. For example, if it is detected that the bandwidth is lower than the minimum standard, the method can automatically reduce the data transmission rate or optimize the quality of the transmitted data, thereby more effectively utilizing available network resources and avoiding operation delays or instruction losses caused by network congestion. The method can not only monitor the current network status, but also adjust the presets based on historical data and performance indicators. The network emergency measures enhance the adaptability of the method to different network environments. This adaptive mechanism enables the remote control method to maintain efficient operation under various network conditions and reduce operational interruptions caused by network problems. Through real-time monitoring and emergency measures, the method can prevent or minimize the remote control risks caused by network problems. For example, when the network quality is not sufficient to support safe operation, the method can automatically adjust the vehicle to a safe state, such as slowing down or parking, to prevent accidents caused by delays or command loss. Comprehensive analysis of network stability indicators provides valuable data support to help decision makers evaluate the potential impact of the network environment on remote operations and support more scientific risk management and decision making. These data can be used to optimize network infrastructure, improve network emergency measures, or develop more effective operating protocols and strategies.

[0092] See also Figure 2, an embodiment of the present invention provides a technical solution: a system for remotely controlling mining area vehicles based on 5G network, comprising a vehicle condition data acquisition module, a camera module, a vehicle condition analysis module, an environmental analysis module, a comprehensive analysis module, a remote control module, and a monitoring module; the vehicle condition data acquisition module is used to acquire and preprocess the real-time vehicle condition data of each mining area vehicle to be controlled in real time; the camera module is used to acquire and preprocess the real-time traveling environment image data of each mining area vehicle to be controlled in real time; the vehicle condition analysis module is used to perform data analysis on the real-time vehicle condition data of each mining area vehicle to be controlled after preprocessing, and obtain the real-time vehicle condition safety index of each mining area vehicle to be controlled; the environmental analysis module is used to perform regional extraction on the real-time traveling environment image data of each mining area vehicle to be controlled after preprocessing, and obtain the real-time vehicle front image of each mining area vehicle to be controlled The system collects the real-time road area data and the real-time obstacle area data of each mining vehicle to be controlled, and comprehensively analyzes the real-time vehicle front road area data and the real-time obstacle area data of each mining vehicle to be controlled, so as to obtain the real-time driving environment index of each mining vehicle to be controlled; the comprehensive analysis module is used to comprehensively analyze the real-time vehicle safety index and the real-time driving environment index of each mining vehicle to be controlled, so as to obtain the control complexity evaluation value of each mining vehicle to be controlled; the remote control module is used to compare and analyze the control complexity evaluation value of each mining vehicle to be controlled with the preset evaluation threshold value, and take corresponding remote control measures based on the analysis results; the monitoring module is used to obtain the real-time 5G network transmission data in real time when the mining vehicle to be controlled is remotely controlled, and to monitor and analyze it, and take corresponding network emergency measures based on the monitoring and analysis results.

[0093] In summary, this application has at least the following effects:

[0094] By utilizing the high speed and low latency characteristics of the 5G network, the vehicle status and environmental data can be acquired and processed in real time, significantly improving the real-time and accuracy of remote control. Through real-time analysis of vehicle conditions and environmental image data, safety indicators and environmental indicators can be generated in a timely manner, providing accurate data for the assessment of control complexity. This ensures that even in complex mining environments, the accuracy and reliability of remote operations are guaranteed, greatly reducing the risk of control errors.

[0095] By analyzing real-time driving environment image data, it can identify and analyze road and obstacle conditions, and adjust control strategies in real time to adapt to environmental changes. This dynamic adaptation function enables each vehicle to perform optimal control based on the current driving environment and vehicle conditions, improving the flexibility and efficiency of vehicle operations in mining areas and ensuring the safe driving of vehicles in changing environments.

[0096] By continuously monitoring real-time 5G network transmission data and adjusting network emergency measures according to the current network status, the continuity and stability of remote control instructions are ensured. When faced with network fluctuations or instability, timely response measures can be taken, such as adjusting data transmission frequency or changing control strategies, thereby ensuring the efficiency and safety of remote control of mining vehicles and reducing the risk of accidents caused by network problems.

[0097] By decomposing the functions of 5G network remote control of mining vehicles into vehicle condition data acquisition module, camera module, vehicle condition analysis module, environmental analysis module, comprehensive analysis module, remote control module, and monitoring module, the system enhances its modularity and scalability. This modular design not only enables each part to work and optimize independently, but also facilitates future upgrades and maintenance. For example, if it is necessary to introduce more advanced data analysis technology or replace more efficient camera equipment, the corresponding modules can be upgraded individually without redesigning the entire system. Such a design architecture also facilitates the integration of new functions or interfaces with other systems in the future, thereby enhancing the flexibility of the overall system and its future application potential.

[0098] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0099] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for remotely controlling mining vehicles based on a 5G network, characterized in that: The following steps are involved: Real-time acquisition and preprocessing of the real-time vehicle condition data and real-time traveling environment image data of each vehicle to be controlled in the mining area, and comprehensive analysis is performed to obtain the real-time vehicle condition safety index and real-time traveling environment index of each vehicle to be controlled in the mining area. The real-time vehicle condition data specifically includes the current speed value, the current cargo load, the current engine power, and the current pressure value of each tire. The real-time traveling environment image data specifically includes the pixel value of each pixel point in the real-time traveling environment image. Comprehensively analyze the real-time vehicle safety index and real-time driving environment index of each mine vehicle to be controlled, obtain the control complexity evaluation value of each mine vehicle to be controlled, and compare and analyze them with the preset evaluation threshold respectively, and take corresponding remote control measures based on the analysis results, and at the same time, take real-time network monitoring when remotely controlling the mine vehicle to be controlled; The specific formula for calculating the control complexity evaluation value of each mining vehicle to be controlled is as follows: ； in, is the control complexity evaluation value of the i-th mining vehicle to be controlled, is the real-time vehicle safety index of the i-th mining vehicle to be controlled, is the vehicle condition safety factor of the i-th mining vehicle to be controlled stored in the database, is the real-time driving environment index of the i-th mining vehicle to be controlled, is the driving environment coefficient of the i-th mining vehicle to be controlled stored in the database, , e is a natural constant, , The number of vehicles in the mining area to be controlled; The specific steps to obtain the real-time vehicle safety index of each mining vehicle to be controlled are as follows: Obtain the maximum safe speed value, maximum safe cargo capacity, maximum safe engine power, and maximum safe pressure value of each tire of each mining vehicle to be operated; Analyze the current speed value, current cargo load, current engine power, and current tire pressure of each mining area vehicle to be controlled with the maximum safe speed value, maximum safe cargo load, maximum safe engine power, and each maximum tire pressure, respectively, to obtain the current speed deviation value, current cargo load deviation value, current engine power deviation value, and current tire deviation value of each mining area vehicle to be controlled; Comprehensively analyze the current speed deviation value, current cargo load deviation value, current engine power deviation value, and current tire deviation value of each mining area vehicle to be controlled to obtain the real-time vehicle safety index of each mining area vehicle to be controlled; The specific formula for calculating the current speed deviation value, current tire deviation value, and real-time vehicle safety index of each mining vehicle to be controlled is as follows: ； in, is the current speed deviation value of the i-th mining vehicle to be controlled, is the current speed value of the i-th mining vehicle to be controlled, is the maximum safe speed value of the i-th mining vehicle to be controlled, is the current tire deviation value of the i-th mining vehicle to be controlled, is the current pressure of the jth tire of the i-th mining vehicle to be controlled, is the maximum safe pressure value of the jth tire of the i-th mining vehicle to be controlled, is the real-time vehicle safety index of the i-th mining vehicle to be controlled, is the speed deviation coefficient of the i-th mining vehicle to be controlled stored in the database, is the current cargo capacity deviation value of the i-th mining vehicle to be controlled, is the cargo capacity deviation coefficient of the i-th mining vehicle to be controlled stored in the database, is the current engine power deviation value of the i-th mining vehicle to be controlled, is the cargo capacity deviation coefficient of the i-th mining vehicle to be controlled stored in the database, is the cargo capacity deviation coefficient of the i-th mining vehicle to be controlled stored in the database, , is the number of vehicles in the mining area to be controlled, , is the number of tires.

2. The method for remotely controlling mining vehicles based on a 5G network according to claim 1 is characterized in that: The specific steps for obtaining the real-time driving environment index of each mining vehicle to be controlled are as follows: Performing area extraction on the real-time traveling environment image data of each mining area vehicle to be controlled after preprocessing, and obtaining the real-time road area data and real-time obstacle area data of each mining area vehicle to be controlled; The real-time road area data and real-time obstacle area data of each mining area vehicle to be controlled are comprehensively analyzed to obtain the real-time driving environment index of each mining area vehicle to be controlled.

3. The method for remotely controlling mining vehicles based on 5G network according to claim 2 is characterized in that: The specific steps for obtaining the real-time road area data and real-time obstacle area data of each mining vehicle to be controlled are as follows: Based on the edge detection algorithm, the pixel value of each pixel point in the real-time traveling environment image of each mining area vehicle to be controlled after preprocessing is detected to perform edge recognition, and a number of road edge pixel points of the road area of ​​each mining area vehicle to be controlled and a number of obstacle edge pixel points of each obstacle area are obtained; For each mining vehicle to be controlled, a plurality of road edge pixel points in the road area are respectively processed by road contour connection, and a plurality of road pixel points in the road contour after the road contour connection processing and a plurality of road edge pixel points are marked as real-time road area data; For each mining vehicle to be controlled, several obstacle edge pixel points in each obstacle area are respectively processed by obstacle contour connection, and several obstacle pixel points in each obstacle contour after the obstacle contour connection processing and several obstacle edge pixel points are marked as real-time obstacle area data.

4. The method for remotely controlling mining vehicles based on a 5G network according to claim 3 is characterized in that: The specific steps for obtaining the real-time driving environment index of each mining vehicle to be controlled are as follows: The pixel values ​​of several road pixel points and several road edge pixel points within the road contour of each mining area vehicle to be controlled are respectively comprehensively analyzed to obtain the real-time vehicle road smoothness index of each mining area vehicle to be controlled; The number of obstacle pixels within each obstacle outline of each mining vehicle to be controlled and the number of obstacle edge pixels are summed up and analyzed respectively to obtain the total value of the obstacle area of ​​each mining vehicle to be controlled; Standardize the real-time vehicle road roughness index and total obstacle area value of each mining area vehicle to be controlled; The real-time vehicle road smoothness index and the total obstacle area of ​​each vehicle to be controlled in the mining area after standardization are comprehensively analyzed to obtain the real-time driving environment index of each vehicle to be controlled in the mining area.

5. The method for remotely controlling mining vehicles based on a 5G network according to claim 4 is characterized in that: The specific formula for calculating the real-time vehicle road smoothness index and real-time driving environment index of each mining area vehicle to be controlled is as follows: ； in, is the real-time vehicle road smoothness index of the i-th mining vehicle to be controlled, is the pixel value of the dth road pixel point within the road contour of the i-th mining vehicle to be controlled, is the pixel value of the g-th road edge pixel point within the road contour of the i-th mining vehicle to be controlled, is the real-time driving environment index of the i-th mining vehicle to be controlled, is the real-time vehicle road roughness index of the i-th mining vehicle to be controlled after normalization, is the road coefficient of the i-th mining vehicle to be controlled stored in the database, is the total obstacle area of ​​the i-th mining vehicle to be controlled after standardized processing, is the obstacle coefficient of the i-th mining vehicle to be controlled stored in the database, , , is the number of vehicles in the mining area to be controlled, , is the number of road pixels within the road outline, , It is the number of road edge pixels within the road outline.

6. The method for remotely controlling mining vehicles based on 5G network according to claim 1 is characterized in that: The control complexity evaluation value of each mining vehicle to be controlled is compared and analyzed with the preset evaluation threshold, and the specific steps of taking corresponding remote control measures based on the analysis results are as follows: Compare and analyze the control complexity evaluation value of each mining vehicle to be controlled with the first evaluation threshold and the second evaluation threshold respectively; If there is a mining vehicle to be controlled whose control complexity evaluation value is less than or equal to the first evaluation threshold, the first remote operation mode is activated for the mining vehicle to be controlled, and the mining vehicle to be controlled is remotely controlled based on the set first driving state; If there is a mine vehicle to be controlled whose control complexity evaluation value is higher than the first evaluation threshold and less than or equal to the second evaluation threshold, the second remote operation mode is activated for the mine vehicle to be controlled, and the mine vehicle to be controlled is remotely controlled based on the set second driving state; If there is a mining vehicle to be controlled whose control complexity evaluation value is higher than the second evaluation threshold, the third remote operation mode is activated for the mining vehicle to be controlled, and the mining vehicle to be controlled is remotely controlled based on the set third driving state.

7. The method for remotely controlling mining vehicles based on 5G network according to claim 1 is characterized in that: The specific steps for taking real-time network monitoring when remotely controlling mining vehicles are as follows: Obtain the maximum allowable delay jitter value, maximum allowable packet loss rate, minimum bandwidth value, and minimum signal strength value for 5G network transmission; When remotely controlling the mining vehicle to be controlled, real-time 5G network transmission data of each mining vehicle to be controlled is obtained in real time, and the real-time 5G network transmission data specifically includes current delay jitter value, current packet loss rate, current bandwidth value, and current signal strength value; The current delay jitter value, current packet loss rate, maximum allowable delay jitter value, and maximum allowable packet loss rate of each mining area vehicle to be controlled are analyzed respectively to obtain the current transmission efficiency index of each mining area vehicle to be controlled; When remotely controlling the mining area vehicle to be controlled, the current bandwidth value, current signal strength value, minimum bandwidth value, and minimum signal strength value of each mining area vehicle to be controlled are analyzed in real time to obtain the current transmission quality index of each mining area vehicle to be controlled; Comprehensively analyze the current transmission efficiency index and current transmission quality index of each mining area vehicle to be controlled to obtain the real-time network stability index of each mining area vehicle to be controlled; The specific formula for calculating the current transmission efficiency index, current transmission quality index, and real-time network stability index of each mining vehicle to be controlled is as follows: ； in, is the current transmission efficiency index of the i-th mining vehicle to be controlled, is the current delay jitter value of the i-th mining vehicle to be controlled, is the maximum allowable delay jitter value for 5G network transmission. is the current packet loss rate of the i-th mining vehicle to be controlled, is the maximum allowed packet loss rate for 5G network transmission, is the current transmission quality index of the i-th mining vehicle to be controlled, is the current bandwidth value of the i-th mining vehicle to be controlled, The minimum bandwidth value for 5G network transmission. is the current signal strength value of the i-th mining vehicle to be controlled, is the minimum signal strength value for 5G network transmission. is the real-time network stability index of the i-th mining vehicle to be controlled, e is a natural constant, is the transmission efficiency coefficient stored in the database, is the transmission quality coefficient stored in the database, , , The number of vehicles in the mining area to be controlled.

8. A system for remotely controlling mining vehicles based on a 5G network, applying the method for remotely controlling mining vehicles based on a 5G network as described in any one of claims 1 to 7, characterized in that: include: Vehicle condition data acquisition module, camera module, vehicle condition analysis module, environmental analysis module, comprehensive analysis module, remote control module, monitoring module; The vehicle condition data acquisition module is used to acquire and pre-process the real-time vehicle condition data of each mining vehicle to be controlled in real time; The camera module is used to acquire and pre-process the real-time traveling environment image data of each mining vehicle to be controlled in real time; The vehicle condition analysis module is used to analyze the pre-processed real-time vehicle condition data of each mining area vehicle to be controlled, and obtain the real-time vehicle condition safety index of each mining area vehicle to be controlled; The environmental analysis module is used to perform regional extraction on the real-time traveling environment image data of each mining area vehicle to be controlled after preprocessing, obtain the real-time road area data and real-time obstacle area data of each mining area vehicle to be controlled, and perform comprehensive analysis on the real-time road area data and real-time obstacle area data of each mining area vehicle to be controlled, to obtain the real-time traveling environment index of each mining area vehicle to be controlled; The comprehensive analysis module is used to comprehensively analyze the real-time vehicle safety index and the real-time driving environment index of each mining vehicle to be controlled, and obtain the control complexity evaluation value of each mining vehicle to be controlled; The remote control module is used to compare and analyze the control complexity evaluation value of each mining vehicle to be controlled with a preset evaluation threshold, and take corresponding remote control measures based on the analysis results; The monitoring module is used to obtain real-time 5G network transmission data and perform monitoring and analysis when remotely controlling the mining vehicle to be controlled, and take corresponding network emergency measures based on the monitoring and analysis results.

Images