Method and system for controlling transportation device in coal mine area

Abstract

The invention relates to the technical field of industrial automation and intelligent control. The invention provides a coal mine area transportation device control method and system, and the method comprises the steps: obtaining historical operation state data and position data of a transportation device, and historical geographic information data; constructing a state analysis initial model, and training the state analysis initial model to obtain a state analysis model; the operation state data and the corresponding position data of the transportation device and the real-time geographic information data are collected in real time, and a multi-source real-time data set is obtained; inputting the multi-source real-time data set into the state analysis model to obtain a state analysis result; based on a state analysis result, planning an optimal transportation path for the transportation device through a path planning algorithm; according to the state analysis result and the optimal transportation path, a scheduling decision is made, the scheduling decision is issued to the transportation device to be executed, and the transportation process is monitored in real time. The problem that the optimal transportation efficiency and safety are difficult to achieve through a traditional method is solved.

Description

Technical Field

[0001] The present invention relates to the field of industrial automation and intelligent control technology, and in particular to a method and system for controlling a coal mine transportation device. Background Art

[0002] In coal mining operations, transport devices play a vital role in efficiently transporting coal from the mining face to the processing or storage area. With the continuous expansion of coal mining scale and the increase in mining depth, the transportation tasks within the coal mining area have become more and more complicated, which has put forward higher requirements for the control and management of transport devices.

[0003] Traditional coal mine transportation device control methods mostly rely on manual experience and fixed rules. This method is often difficult to achieve optimal transportation efficiency and safety when facing complex and changing coal mine environments and transportation needs. For example, manual scheduling may not be able to accurately grasp the operating status and location information of each transportation device in real time, resulting in inflexible and inefficient scheduling decisions; at the same time, fixed transportation routes may no longer be applicable due to geological changes, equipment failures and other factors, increasing uncertainty and risk in the transportation process. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for controlling coal mine transportation equipment, aiming to solve the problem that traditional coal mine transportation equipment control methods are unable to accurately grasp the operating status and location information of each transportation equipment in real time, resulting in inflexible scheduling decisions and difficulty in achieving optimal transportation efficiency and safety.

[0005] The present invention is achieved through the following technical solutions:

[0006] A method for controlling a coal mine transport device comprises the following steps:

[0007] Obtain the historical operation status data of each transportation device in the coal mining area and the location data of the corresponding time point, as well as the historical geographic information data of the coal mining area, to obtain a multi-source historical data set;

[0008] Based on the machine learning algorithm, an initial state analysis model is constructed, and the initial state analysis model is trained through multi-source historical data sets to obtain a state analysis model;

[0009] Collect the operation status data and corresponding location data of each transportation device in the coal mining area in real time, as well as the real-time geographic information data of the coal mining area, to obtain a multi-source real-time data set;

[0010] Input multi-source real-time data sets into the state analysis model to obtain the state analysis results of each transportation device;

[0011] Based on the status analysis results of each transport device, the optimal transport path is planned for each transport device through the path planning algorithm;

[0012] According to the status analysis results of each transportation device and the corresponding optimal transportation path, the scheduling decision of each transportation device is made, the scheduling decision is issued to each transportation device for execution, and the transportation process is monitored in real time.

[0013] Optionally, the specific process of obtaining the historical operation status data of each transportation device in the coal mining area and the location data of the corresponding time point, as well as the historical geographic information data of the coal mining area, and obtaining the multi-source historical data set is as follows:

[0014] Through the sensor network and positioning system in the coal mine area, the historical operation status data of each transport device during operation is continuously collected, and the historical position data of each transport device at the corresponding time point is synchronously recorded;

[0015] Obtain historical geographic information data from the geographic information system of the coal mining area to reflect the natural environment and infrastructure conditions of the coal mining area;

[0016] Preprocess the collected historical operation status data, historical location data at corresponding time points, and historical geographic information data;

[0017] The preprocessed historical status data, historical location data at corresponding time points, and historical geographic information data are integrated to form a multi-source historical data set containing multiple types of data.

[0018] Optionally, the specific process of constructing the initial state analysis model based on the machine learning algorithm and training the initial state analysis model through multi-source historical data sets to obtain the state analysis model is as follows:

[0019] According to the operation characteristics and demand analysis of each transportation device in the coal mining area, an initial state analysis model is constructed based on neural network;

[0020] The multi-source historical data set is divided into a training set and a validation set. The historical operation status data, historical location data at the corresponding time point, and historical geographic information data in the training set are used as input features, and the corresponding transportation device status is used as the output label. The initial model is analyzed by iterative training status.

[0021] After training is completed, the state analysis model is obtained, and the performance of the state analysis model is evaluated using the validation set. The state analysis model is adjusted and optimized according to the performance evaluation results until the model performance meets the requirements.

[0022] Optionally, the status analysis results of each transportation device include current operating status evaluation of each transportation device, estimated remaining working time, energy efficiency, current load status, location accuracy, and path feasibility evaluation based on real-time geographic information data.

[0023] Optionally, the specific process of planning the optimal transportation path for each transportation device through a path planning algorithm based on the status analysis results of each transportation device is:

[0024] Collect the state analysis results of each transport device and integrate them into a state evaluation vector as the input of the A* algorithm;

[0025] Set the map size of the coal mining area, the starting and ending positions of each transport device, and the obstacle set;

[0026] Create an open list and a closed list; the open list is used to store the nodes to be searched, and initially contains only the starting point node; the closed list is used to store the searched nodes, and initially is empty; in the node structure of the A* algorithm, add corresponding fields to store the status information of the transport device;

[0027] During the search process, the evaluation function f(n) of each node n is calculated. The evaluation function f(n) is shown in the following formula (1):

[0028] f(n)=g(n)+h(n)(1)

[0029] Among them, g(n) represents the actual cost function, and h(n) represents the heuristic estimated cost function;

[0030] Traverse and search the nodes in the open list, take the node with the smallest valuation function value from the open list as the current node, and check whether it is the terminal node. If the current node is not the terminal node, generate the predicted child node according to the state evaluation vector corresponding to the current node and the state information of the adjacent nodes, and calculate the actual cost value, heuristic estimated cost value and valuation function value of the child node; add the predicted child node to the open list and update the corresponding parent node information; find the terminal node through traversal search, and backtrack according to the corresponding parent node information to obtain the optimal transportation path.

[0031] Optionally, according to the state analysis results of each transport device, the heuristic estimation cost function is adjusted to reflect the path selection preferences of different transport devices in different states. The adjusted heuristic estimation cost function h ′ (n) is expressed as follows:

[0032] h ′ (n) = h(n)*w(s) (2)

[0033] Among them, h(n) represents the original heuristic estimation cost function, and w(s) represents the weight factor calculated according to the state evaluation vector.

[0034] Optionally, the actual cost function g(n) is expressed as shown in the following formula (3):

[0035] g(n)=d(n)*c(s) (3)

[0036] Where d(n) represents the distance or time from the starting point to node n, and c(s) represents the cost per unit distance or per unit time calculated according to the state evaluation vector.

[0037] Optionally, the specific process of formulating a scheduling decision for each transport device according to the status analysis results of each transport device and the corresponding optimal transport path, issuing the scheduling decision to each transport device for execution, and monitoring the transport process in real time is as follows:

[0038] Based on the status analysis results of each transport device and the corresponding optimal transport path, the scheduling decision of each transport device is made by comprehensively considering the requirements of the transport task;

[0039] The formulated dispatching decision is sent to each transport device through the communication network of the coal mine area;

[0040] During the transportation process, the sensor network and positioning system in the coal mine area monitor the operating status, location information and changes in the surrounding environment of each transportation device in real time. At the same time, the scheduling decision is dynamically adjusted based on the real-time monitoring data;

[0041] All relevant data in the transportation process are recorded and stored for optimizing status analysis models and scheduling strategies.

[0042] Optionally, it also includes a fault warning and emergency handling mechanism, the specific process is as follows:

[0043] While collecting the operating status data and corresponding location data of each transportation device in the coal mine area in real time, the abnormal data is monitored and analyzed in real time;

[0044] When the operating status data or location data of the transport device is detected to be abnormal, a fault warning is immediately triggered and a fault analysis report is generated;

[0045] Based on the fault analysis report, the cause, impact scope and severity of the fault are evaluated in combination with the state analysis model, and an emergency response plan is formulated based on the evaluation results;

[0046] The fault warning information, fault analysis report, assessment results and emergency treatment plan are promptly notified to relevant personnel through the communication network in the coal mine area to handle the fault;

[0047] After the fault is handled, the fault handling process is recorded and summarized for subsequent optimization of the fault warning and emergency handling mechanism.

[0048] The present invention also provides a coal mine area transportation device control system, which is used to implement the coal mine area transportation device control method, comprising:

[0049] The data collection module is used to obtain the historical operation status data and the location data of the corresponding time points of each transportation device in the coal mining area, as well as the historical geographic information data of the coal mining area, and to collect the operation status data and the corresponding location data of each transportation device in the coal mining area in real time, as well as the real-time geographic information data of the coal mining area, to form a multi-source historical data set and a multi-source real-time data set;

[0050] A model building module is used to build an initial state analysis model based on a machine learning algorithm and train the initial state analysis model using a multi-source historical data set to obtain a state analysis model;

[0051] A state analysis module, which is used to input multi-source real-time data sets into the state analysis model to obtain the state analysis results of each transportation device;

[0052] A path planning module is used to plan the optimal transportation path for each transportation device through a path planning algorithm based on the status analysis results of each transportation device;

[0053] The scheduling decision module is used to make scheduling decisions for each transport device based on the status analysis results of each transport device and the corresponding optimal transport path, and issue the scheduling decisions to each transport device for execution;

[0054] The monitoring and adjustment module is used to monitor the transportation process in real time, dynamically adjust the scheduling decision based on the real-time monitoring data, and record and store all relevant data in the transportation process;

[0055] The fault emergency warning module is used to monitor and analyze abnormal data in real time, trigger fault warnings, generate fault analysis reports, evaluate the cause, scope and severity of the fault, formulate emergency response plans, and notify relevant personnel to handle the fault, while recording and summarizing the fault handling process.

[0056] The technical solution of the present invention has at least the following advantages and beneficial effects:

[0057] Improve transportation efficiency and safety: By real-time collection and analysis of the operating status, location and geographic information data of the transportation equipment and the coal mining area, the overall situation of the transportation system can be dynamically grasped, so as to make more accurate and efficient scheduling decisions; the application of path planning algorithms enables the transportation route to be flexibly adjusted according to actual conditions, avoiding transportation interruptions or delays caused by geological changes, equipment failures and other factors, and further improving transportation efficiency; the real-time monitoring function can promptly detect and deal with potential safety hazards, effectively reducing the risks in the transportation process.

[0058] Enhance the flexibility and intelligence of scheduling decisions: The state analysis model built using machine learning algorithms can automatically learn and adapt to the transportation patterns and environmental changes within the coal mining area, thereby generating more intelligent and reasonable scheduling decisions. It breaks away from the traditional manual scheduling’s reliance on experience and fixed rules, making scheduling decisions more flexible and efficient, and able to cope with a variety of complex and changing transportation needs.

[0059] Optimize resource utilization and reduce costs: Through precise scheduling and route planning, the idle time and waiting time of transportation equipment can be minimized, and the utilization rate of equipment can be improved; the real-time monitoring function can also detect and handle equipment failures in a timely manner, reduce downtime and maintenance costs caused by equipment failures, and help optimize resource utilization in coal mining areas, reduce transportation costs, and improve economic benefits.

[0060] Improve management level and decision-making efficiency: The present invention enables managers in coal mining areas to understand the operating status of the transportation system more intuitively and comprehensively, which helps to improve the scientificity and accuracy of management decisions, allowing managers to respond more quickly to various emergencies; at the same time, the intelligent control method also reduces the workload of managers and improves work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 This is a flow chart of a method for controlling a coal mine area transportation device according to Embodiment 1 of the present invention;

[0062] Figure 2 This is a schematic diagram of the structure of a coal mine area transportation device control system according to Example 3 of the present invention. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions 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 part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0064] Example 1

[0065] Reference Figure 1 , a method for controlling a coal mine transport device, comprising the steps of:

[0066] Step 1: Obtain the historical operation status data of each transportation device in the coal mining area and the location data of the corresponding time point, as well as the historical geographic information data of the coal mining area, to obtain a multi-source historical data set.

[0067] In this embodiment, the specific process of obtaining the historical operation status data of each transportation device in the coal mining area and the location data of the corresponding time point, as well as the historical geographic information data of the coal mining area, and obtaining the multi-source historical data set is as follows:

[0068] Through the sensor network and positioning system in the coal mining area, the historical operation status data of each transportation device during operation is continuously collected, and the historical position data of each transportation device at the corresponding time point is synchronously recorded; the historical geographic information data is obtained from the geographic information system of the coal mining area to reflect the natural environment and infrastructure conditions of the coal mining area; the collected historical operation status data, historical position data at the corresponding time point and historical geographic information data are preprocessed; the preprocessed historical status data, historical position data at the corresponding time point and historical geographic information data are integrated to form a multi-source historical data set containing multiple types of data.

[0069] In this embodiment, the sensor network in the coal mining area is used to continuously monitor and record the operating status data of each transportation device (such as a mine car, a belt conveyor, etc.). These data include but are not limited to operating speed, energy consumption, load conditions, fault records, etc. Through the positioning system in the coal mining area (such as GPS, RFID, etc.), the location information of each transportation device at a specific time point is tracked and recorded in real time, which helps to understand the movement trajectory and residence time of the transportation device. Historical geographic information data is obtained from the geographic information system of the coal mining area. The historical geographic information data covers the topography, road network, building distribution, underground tunnel layout, etc. of the coal mining area to reflect the natural environment and infrastructure conditions of the coal mining area. The collected historical operating status data, location data and geographic information data are preprocessed, including data cleaning (removing erroneous or invalid data), data format conversion (ensuring data format consistency for subsequent processing) and data standardization (converting data into a unified dimension or range to improve data comparability). The preprocessed historical status data, location data and geographic information data are integrated to form a multi-source historical data set containing multiple types of data. The multi-source historical data set will be used as input for subsequent machine learning model training and state analysis. The integrated multi-source historical data set is stored in a suitable storage medium (such as a database, data warehouse, etc.) for subsequent analysis and use.

[0070] Step 2: Based on the machine learning algorithm, build an initial state analysis model, train the initial state analysis model through multi-source historical data sets, and obtain a state analysis model.

[0071] In this embodiment, based on the machine learning algorithm, the initial state analysis model is constructed, and the initial state analysis model is trained through multi-source historical data sets. The specific process of obtaining the state analysis model is as follows:

[0072] According to the operation characteristics and demand analysis of each transportation device in the coal mining area, including understanding the working principles, performance parameters, common failure modes and operating environment of different transportation devices. Since the state analysis of transportation devices involves multiple input features (such as historical operation status data, location data, geographic information data, etc.) and complex nonlinear relationships, neural networks are selected as machine learning algorithms, and the initial state analysis model is constructed based on neural networks; according to the task type and data characteristics, the appropriate neural network type is selected, such as feedforward neural networks, convolutional neural networks (CNN), recurrent neural networks (RNN), etc.

[0073] In summary, this embodiment builds an initial model for state analysis based on a convolutional neural network. Determine the specific tasks of state analysis, such as equipment fault detection, production process state classification, and biological health status assessment; clarify the type and format of input data, such as images, videos, one-dimensional signals, etc.; collect task-related data sets to ensure that the data is representative and contains various possible states; if the data is an image or video, ensure that they have consistent size and format; if the data is a one-dimensional signal, it may be necessary to convert it into a two-dimensional matrix form in order to apply convolution operations; clean the data to remove noise and outliers; perform data enhancement, such as rotation, flipping, scaling, etc., to increase the diversity of the data; normalize or standardize the data so that the values ​​of the input data are on the same scale. According to the type of input data and task requirements, select a suitable CNN infrastructure, such as LeNet, AlexNet, VGG, ResNet, etc.; for image data, a standard two-dimensional convolution layer can be used; for one-dimensional signals, a one-dimensional convolution layer can be used or it can be converted to a two-dimensional form before using a two-dimensional convolution layer. Determine the number of convolutional layers and the number, size, and step size of convolutional kernels in each layer; use appropriate activation functions (such as ReLU) to increase the nonlinearity of the network; after the convolutional layer, a pooling layer (such as max pooling) is usually used to reduce the dimension and computation of the data. After the convolutional and pooling layers, add a fully connected layer to extract high-level features and perform classification or regression; determine the number of neurons in the fully connected layer based on the number of output categories; after the fully connected layer, use an appropriate activation function (such as Softmax for classification tasks). Select an appropriate loss function based on the task type, such as cross entropy loss for classification tasks and mean square error for regression tasks; select an appropriate optimizer to update the weights of the network, such as Adam, SGD, etc.

[0074] The multi-source historical data set is divided into a training set and a validation set. The historical operating status data, historical location data at the corresponding time point and historical geographic information data in the training set are used as input features, and the corresponding transportation device status is used as the output label. The initial model is analyzed through iterative training status.

[0075] After the training is completed, the state analysis model is obtained. The performance of the state analysis model is evaluated using the validation set. The state analysis model is adjusted and optimized according to the performance evaluation results until the model performance meets the requirements. The model is trained using the training set data, and the weights of the network are updated through the back propagation algorithm. During the training process, the performance of the validation set is monitored to prevent overfitting. Hyperparameters such as the learning rate and regularization parameter are adjusted according to the performance of the validation set. After the training is completed, the trained model is saved for subsequent use. The performance of the model is evaluated using the test set data, and indicators such as accuracy, recall, and F1 score are calculated. The model's incorrect prediction cases are analyzed to find out the shortcomings of the model. The model's architecture, hyperparameters, etc. are adjusted according to the evaluation results to improve the model's performance. Different data enhancement methods, regularization techniques, etc. are tried to improve the model's generalization ability. The trained model is integrated into the state analysis system to realize real-time or offline state analysis functions. The system is tested in the actual environment to ensure that the model can run correctly and give accurate state analysis results. The performance of the model is continuously monitored in actual applications, and the model is updated and optimized according to actual needs and data changes.

[0076] Step 3: Collect the operation status data and corresponding location data of each transportation device in the coal mining area, as well as the real-time geographic information data of the coal mining area in real time to obtain a multi-source real-time data set.

[0077] In this embodiment, the status analysis results of each transportation device include the current operating status evaluation of each transportation device, the estimated remaining working time, energy efficiency, current load status, location accuracy, and path feasibility evaluation based on real-time geographic information data.

[0078] In this embodiment, the operating status data of each transport device, such as speed, acceleration, load condition, energy consumption, etc., are collected in real time through the sensor network in the coal mining area; the location data of each transport device at the corresponding time point, including longitude, latitude, altitude, etc., are recorded in real time through the synchronous positioning system. Geographic information data, such as topography, road conditions, obstacle locations, etc., are obtained in real time from the geographic information system of the coal mining area. These data are used to reflect the current natural environment and infrastructure conditions of the coal mining area. The collected real-time operating status data, location data and geographic information data are preprocessed, including data cleaning, denoising, format conversion, etc., to ensure the accuracy and consistency of the data. The preprocessed real-time status data, location data and geographic information data are integrated to form a multi-source real-time data set containing multiple types of data. This data set will be used for subsequent status analysis and path planning. The collected data is verified regularly to ensure the accuracy and reliability of the data; according to the actual situation, the multi-source real-time data set is updated in time to reflect the latest status of the coal mining area.

[0079] Step 4: Input the multi-source real-time data set into the state analysis model to obtain the state analysis results of each transportation device.

[0080] In this embodiment, the pre-processed real-time data is integrated into an input format acceptable to the model. This usually includes integrating the operating status data (such as speed, acceleration, load, etc.), location data (such as longitude, latitude, altitude, etc.) and geographic information data (such as terrain, obstacle location, etc.) into a multi-dimensional feature vector, ensuring that each feature vector contains enough information to reflect the current state and surrounding environment of the transportation device. The constructed feature vector is input into the trained state analysis model. The state analysis result of the transportation device is output according to the input feature vector. The state analysis result includes the current operating status evaluation of the transportation device (such as normal operation, fault warning, maintenance required, etc.), the estimated remaining working time, energy efficiency, current load status, location accuracy, and path feasibility evaluation based on real-time geographic information data. The output results of the state analysis model are parsed to obtain the specific state information of each transportation device, and the state information is stored in the database so that it can be easily accessed and used in subsequent operations such as path planning and scheduling decisions.

[0081] Step 5: Based on the status analysis results of each transport device, an optimal transport path is planned for each transport device through a path planning algorithm.

[0082] In this embodiment, based on the status analysis results of each transport device, the specific process of planning the optimal transport path for each transport device through the path planning algorithm is as follows:

[0083] The status analysis results of each transport device are collected and integrated into a status evaluation vector as the input of the A* algorithm. Each vector contains the key status information of the corresponding transport device. The status analysis results include but are not limited to the current operating status evaluation, estimated remaining working time, energy efficiency, current load status, location accuracy and path feasibility evaluation based on real-time geographic information data.

[0084] Set the map size of the coal mining area, the starting and ending positions of each transportation device, and the obstacle set; the map size of the coal mining area is determined according to the actual size and layout of the coal mining area; the starting and ending positions can be set according to the specific requirements of the transportation task; the obstacle set includes fixed obstacles (such as buildings, equipment) and dynamic obstacles (such as other transportation devices, personnel) within the coal mining area.

[0085] Create an open list and a closed list; the open list is used to store the nodes to be searched, and initially contains only the starting point node; the closed list is used to store the searched nodes, and initially is empty; in the node structure of the A* algorithm, add corresponding fields to store the status information of the transport device;

[0086] During the search process, the evaluation function f(n) of each node n is calculated. The evaluation function f(n) is shown in the following formula (1):

[0087] f(n)=g(n)+h(n)(1)

[0088] Among them, g(n) represents the actual cost function, which represents the actual cost from the starting point to node n, which can be calculated based on factors such as distance, time or energy consumption; h(n) represents the heuristic estimation cost function;

[0089] Traverse and search the nodes in the open list, take the node with the smallest valuation function value from the open list as the current node, and check whether it is the terminal node. If the current node is not the terminal node, generate the predicted child node according to the state evaluation vector corresponding to the current node and the state information of the adjacent nodes, and calculate the actual cost value, heuristic estimated cost value and valuation function value of the child node; add the predicted child node to the open list and update the corresponding parent node information; find the terminal node through traversal search, and backtrack according to the corresponding parent node information to obtain the optimal transportation path.

[0090] In this embodiment, the heuristic estimation cost function is adjusted according to the state analysis results of each transport device, with the goal of reflecting the path selection preferences of different transport devices in different states. The adjusted heuristic estimation cost function h ′ (n) is expressed as follows:

[0091] h ′ (n) = h(n)*w(s) (2)

[0092] Among them, h(n) represents the original heuristic estimation cost function, and w(s) represents the weight factor calculated according to the state evaluation vector.

[0093] In this embodiment, the actual cost function g(n) is expressed as follows:

[0094] g(n)=d(n)*c(s) (3)

[0095] Where d(n) represents the distance or time from the starting point to node n, and c(s) represents the cost per unit distance or per unit time calculated according to the state evaluation vector.

[0096] For example, assuming h(n) is the Manhattan distance, the expression of is as shown in equation (4):

[0097] h(n)=|x goal -x n |+|y hoal -yn | (4)

[0098] Among them, (x goal ,y goal ) represents the coordinates of the target node, (x n ,y n ) represents the coordinates of the current node n; the expression of w(s) is shown in the following formula (5):

[0099] w(s)=a*P1+b*P2+…+k*P n (5)

[0100] Among them, a, b, ..., k represent weight coefficients, P1, P2, ..., P n Represents the state assessment value; the state assessment value is different state assessment indicators obtained based on the state analysis model.

[0101] Step 6: According to the status analysis results of each transportation device and the corresponding optimal transportation path, make scheduling decisions for each transportation device, send the scheduling decisions to each transportation device for execution, and monitor the transportation process in real time.

[0102] In this embodiment, according to the status analysis results of each transport device and the corresponding optimal transport path, a scheduling decision for each transport device is made, the scheduling decision is issued to each transport device for execution, and the specific process of real-time monitoring of the transport process is as follows:

[0103] Based on the status analysis results of each transportation device and the corresponding optimal transportation path, the requirements of the transportation task are comprehensively considered to make scheduling decisions for each transportation device; the formulated scheduling decisions are sent to each transportation device through the communication network of the coal mining area; during the transportation process, the operating status, location information and surrounding environmental changes of each transportation device are monitored in real time through the sensor network and positioning system in the coal mining area, and at the same time, the scheduling decisions are dynamically adjusted according to the real-time monitoring data; all relevant data in the transportation process are recorded and stored for optimizing the status analysis model and scheduling strategy.

[0104] In this embodiment, based on the status analysis results of each transport device (including operation status evaluation, estimated remaining working time, energy efficiency, current load status, position accuracy and path feasibility evaluation) and the corresponding optimal transport path, the current transportation task requirements, such as coal demand, transportation time limit, priority, etc., are comprehensively considered. According to the comprehensive evaluation results, a specific scheduling decision is made for each transport device, including departure time, transportation speed, loading capacity, path selection, etc. The scheduling decision should ensure maximum transportation efficiency while ensuring safety and equipment reliability. When making scheduling decisions, some additional factors, such as weather changes, equipment maintenance plans, etc., can also be considered to further optimize the scheduling strategy. Through the communication network, the formulated scheduling decision is sent to each transport device in the form of a data packet. The data packet should contain detailed scheduling information, such as departure time, path coordinates, loading requirements, etc. After receiving the scheduling decision, each transport device should reply with a confirmation message to ensure that the scheduling decision is correctly received and understood. The sensor network and positioning system in the coal mining area are used to collect the operation status data (such as speed, load, energy consumption, etc.) and location information of each transport device in real time. The collected data is analyzed in real time to monitor whether the transportation process is carried out in accordance with the predetermined scheduling decision. At the same time, any possible abnormalities or deviations are detected. According to the real-time analysis results, if there is a deviation or abnormality between the transportation process and the predetermined scheduling decision, dynamic adjustments should be made immediately. For example, if a transportation device fails or is congested, its path can be replanned or the scheduling plan of other transportation devices can be adjusted. All data in the transportation process (including scheduling decisions, real-time status data, adjustment records, etc.) are recorded and stored. These data can be used for subsequent state analysis model optimization and scheduling strategy improvement.

[0105] Example 2

[0106] In this embodiment, a fault warning and emergency handling mechanism is also included, and the specific process is as follows:

[0107] While collecting the operating status data and corresponding location data of each transportation device in the coal mine area in real time, abnormal data is monitored and analyzed in real time. A sensor network and positioning system are deployed in the coal mine area to collect the operating status data and corresponding location data of each transportation device in real time; the collected data is pre-processed, including data cleaning and format conversion, to ensure the accuracy and availability of the data; abnormal values ​​in the data are monitored in real time, such as sudden changes in operating status data and abnormal offsets in location data, so as to detect potential faults in a timely manner.

[0108] When an abnormality is detected in the operating status data or location data of the transportation device, a fault warning is immediately triggered and a fault analysis report is generated; the fault analysis report should include the time and location of the fault, the transportation device involved, detailed information on the abnormal data, etc.

[0109] Based on the fault analysis report, combined with the state analysis model, the cause, scope of impact and severity of the fault are evaluated, and an emergency response plan is formulated based on the evaluation results; combined with historical data and experience knowledge, the possible causes of the fault are analyzed, such as equipment aging, improper operation, environmental factors, etc.; the impact of the fault on transportation operations is evaluated, including production interruption time, economic losses, safety risks, etc.

[0110] The fault warning information, fault analysis report, assessment results and emergency treatment plan shall be promptly notified to relevant personnel through the communication network of the coal mine area, and the fault shall be handled; during the handling process, communication with relevant personnel shall be maintained to ensure the accuracy and timeliness of the information;

[0111] After the fault is handled, the fault handling process is recorded and summarized, including the handling time, handling personnel, handling results, etc., for subsequent optimization of the fault warning and emergency handling mechanism. Regularly evaluate and improve the fault warning and emergency handling mechanism; collect and analyze feedback and data during the fault handling process to identify problems and deficiencies in the mechanism; optimize and improve the mechanism based on the evaluation results to improve the accuracy of fault warning and the efficiency of emergency handling.

[0112] Example 3

[0113] Based on Example 1 and Example 2, refer to Figure 2 In this embodiment, a coal mine area transportation device control system is provided, which is used to implement the coal mine area transportation device control method, including:

[0114] The data collection module 101 is used to obtain the historical operation status data and the location data of the corresponding time points of each transportation device in the coal mining area, as well as the historical geographic information data of the coal mining area, and to collect the operation status data and the corresponding location data of each transportation device in the coal mining area in real time, as well as the real-time geographic information data of the coal mining area, to form a multi-source historical data set and a multi-source real-time data set;

[0115] The model building module 102 is used to build an initial state analysis model based on a machine learning algorithm, and train the initial state analysis model using a multi-source historical data set to obtain a state analysis model;

[0116] The state analysis module 103 is used to input multi-source real-time data sets into the state analysis model to obtain the state analysis results of each transportation device;

[0117] A path planning module 104 is used to plan an optimal transportation path for each transportation device through a path planning algorithm based on the status analysis results of each transportation device;

[0118] The scheduling decision module 105 is used to formulate the scheduling decision of each transport device according to the status analysis result of each transport device and the corresponding optimal transport path, and issue the scheduling decision to each transport device for execution;

[0119] The monitoring and adjustment module 106 is used to monitor the transportation process in real time, dynamically adjust the scheduling decision according to the real-time monitoring data, and record and store all relevant data in the transportation process;

[0120] The fault emergency warning module 107 is used to monitor and analyze abnormal data in real time, trigger fault warnings, generate fault analysis reports, evaluate the cause, scope and severity of the fault, formulate emergency response plans, and notify relevant personnel to handle the fault, while recording and summarizing the fault handling process.

[0121] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for controlling a coal mine transport device, characterized in that: Includes steps: Obtain the historical operation status data of each transportation device in the coal mining area and the location data of the corresponding time point, as well as the historical geographic information data of the coal mining area, to obtain a multi-source historical data set; Based on the machine learning algorithm, an initial state analysis model is constructed, and the initial state analysis model is trained through multi-source historical data sets to obtain a state analysis model; Collect the operation status data and corresponding location data of each transportation device in the coal mining area in real time, as well as the real-time geographic information data of the coal mining area, to obtain a multi-source real-time data set; Input multi-source real-time data sets into the state analysis model to obtain the state analysis results of each transportation device; Based on the status analysis results of each transport device, the optimal transport path is planned for each transport device through the path planning algorithm; According to the status analysis results of each transportation device and the corresponding optimal transportation path, the scheduling decision of each transportation device is made, the scheduling decision is issued to each transportation device for execution, and the transportation process is monitored in real time.

2. The coal mine area transportation device control method according to claim 1, characterized in that: The specific process of obtaining the historical operation status data of each transportation device in the coal mining area and the location data of the corresponding time point, as well as the historical geographic information data of the coal mining area, and obtaining the multi-source historical data set is as follows: Through the sensor network and positioning system in the coal mine area, the historical operation status data of each transport device during operation is continuously collected, and the historical position data of each transport device at the corresponding time point is synchronously recorded; Obtain historical geographic information data from the geographic information system of the coal mining area to reflect the natural environment and infrastructure conditions of the coal mining area; Preprocess the collected historical operation status data, historical location data at corresponding time points, and historical geographic information data; The preprocessed historical status data, historical location data at corresponding time points, and historical geographic information data are integrated to form a multi-source historical data set containing multiple types of data.

3. The coal mine area transportation device control method according to claim 1, characterized in that: The specific process of constructing the initial state analysis model based on the machine learning algorithm and training the initial state analysis model through multi-source historical data sets to obtain the state analysis model is as follows: According to the operation characteristics and demand analysis of each transportation device in the coal mining area, an initial state analysis model is constructed based on neural network; The multi-source historical data set is divided into a training set and a validation set. The historical operation status data, historical location data at the corresponding time point, and historical geographic information data in the training set are used as input features, and the corresponding transportation device status is used as the output label. The initial model is analyzed by iterative training status. After training is completed, the state analysis model is obtained, and the performance of the state analysis model is evaluated using the validation set. The state analysis model is adjusted and optimized according to the performance evaluation results until the model performance meets the requirements.

4. The coal mine area transportation device control method according to claim 1, characterized in that: The status analysis results of each transportation device include the current operation status evaluation of each transportation device, the estimated remaining working time, energy efficiency, current load status, location accuracy, and path feasibility evaluation based on real-time geographic information data.

5. The coal mine area transportation device control method according to claim 1, characterized in that: The specific process of planning the optimal transportation path for each transportation device through the path planning algorithm based on the status analysis results of each transportation device is as follows: Collect the state analysis results of each transport device and integrate them into a state evaluation vector as the input of the A* algorithm; Set the map size of the coal mining area, the starting and ending positions of each transport device, and the obstacle set; Create an open list and a closed list; the open list is used to store the nodes to be searched, and initially contains only the starting point node; the closed list is used to store the searched nodes, and initially is empty; in the node structure of the A* algorithm, add corresponding fields to store the status information of the transport device; During the search process, the evaluation function f(n) of each node n is calculated. The evaluation function f(n) is shown in the following formula (1): f(n)=g(n)+h(n) (1) Among them, g(n) represents the actual cost function, and h(n) represents the heuristic estimated cost function; Traverse and search the nodes in the open list, take the node with the smallest valuation function value from the open list as the current node, and check whether it is the terminal node. If the current node is not the terminal node, generate the predicted child node according to the state evaluation vector corresponding to the current node and the state information of the adjacent nodes, and calculate the actual cost value, heuristic estimated cost value and valuation function value of the child node; add the predicted child node to the open list and update the corresponding parent node information; find the terminal node through traversal search, and backtrack according to the corresponding parent node information to obtain the optimal transportation path.

6. The coal mine area transportation device control method according to claim 5, characterized in that: According to the state analysis results of each transport device, the heuristic estimation cost function is adjusted to reflect the path selection preferences of different transport devices in different states. The expression of the adjusted heuristic estimation cost function h′(n) is shown in the following formula (2): h′(n)=h(n)*w(s) (2) Among them, h(n) represents the original heuristic estimation cost function, and w(s) represents the weight factor calculated according to the state evaluation vector.

7. The coal mine area transportation device control method according to claim 5, characterized in that: The actual cost function g(n) is expressed as follows: g(n)=d(n)*c(s) (3) Where d(n) represents the distance or time from the starting point to node n, and c(s) represents the cost per unit distance or per unit time calculated according to the state evaluation vector.

8. The coal mine area transportation device control method according to claim 1, characterized in that: The specific process of formulating the scheduling decision of each transportation device according to the status analysis results of each transportation device and the corresponding optimal transportation path, issuing the scheduling decision to each transportation device for execution, and monitoring the transportation process in real time is as follows: Based on the status analysis results of each transport device and the corresponding optimal transport path, the scheduling decision of each transport device is made by comprehensively considering the requirements of the transport task; The formulated dispatching decision is sent to each transport device through the communication network of the coal mine area; During the transportation process, the sensor network and positioning system in the coal mine area monitor the operating status, location information and changes in the surrounding environment of each transportation device in real time. At the same time, the scheduling decision is dynamically adjusted based on the real-time monitoring data; All relevant data in the transportation process are recorded and stored for optimizing status analysis models and scheduling strategies.

9. The coal mine area transportation device control method according to claim 1, characterized in that: It also includes fault warning and emergency handling mechanisms. The specific process is as follows: While collecting the operating status data and corresponding location data of each transportation device in the coal mine area in real time, the abnormal data is monitored and analyzed in real time; When the operating status data or location data of the transport device is detected to be abnormal, a fault warning is immediately triggered and a fault analysis report is generated; Based on the fault analysis report, the cause, impact scope and severity of the fault are evaluated in combination with the state analysis model, and an emergency response plan is formulated based on the evaluation results; The fault warning information, fault analysis report, assessment results and emergency treatment plan are promptly notified to relevant personnel through the communication network in the coal mine area to handle the fault; After the fault is handled, the fault handling process is recorded and summarized for subsequent optimization of the fault warning and emergency handling mechanism.

10. A coal mine area transportation device control system, used to implement the coal mine area transportation device control method according to any one of claims 1 to 9, characterized in that: include: The data collection module is used to obtain the historical operation status data and the location data of the corresponding time points of each transportation device in the coal mining area, as well as the historical geographic information data of the coal mining area, and to collect the operation status data and the corresponding location data of each transportation device in the coal mining area in real time, as well as the real-time geographic information data of the coal mining area, to form a multi-source historical data set and a multi-source real-time data set; A model building module is used to build an initial state analysis model based on a machine learning algorithm and train the initial state analysis model using a multi-source historical data set to obtain a state analysis model; A state analysis module, which is used to input multi-source real-time data sets into the state analysis model to obtain the state analysis results of each transportation device; A path planning module is used to plan the optimal transportation path for each transportation device through a path planning algorithm based on the status analysis results of each transportation device; The scheduling decision module is used to make scheduling decisions for each transport device based on the status analysis results of each transport device and the corresponding optimal transport path, and issue the scheduling decisions to each transport device for execution; The monitoring and adjustment module is used to monitor the transportation process in real time, dynamically adjust the scheduling decision based on the real-time monitoring data, and record and store all relevant data in the transportation process; The fault emergency warning module is used to monitor and analyze abnormal data in real time, trigger fault warnings, generate fault analysis reports, evaluate the cause, scope and severity of the fault, formulate emergency response plans, and notify relevant personnel to handle the fault, while recording and summarizing the fault handling process.

Images