Coal mine transportation chain intelligent scheduling system based on machine learning

Abstract

The invention relates to the field of industrial control, in particular to a coal mine transportation chain intelligent scheduling system based on machine learning. The system comprises a monitoring scheduling layer, a control layer and a data storage layer. The monitoring scheduling layer is used for acquiring coal mine transportation chain data and generating a predicted value corresponding to the coal mine transportation chain data according to the coal mine transportation chain data; and generating a corresponding scheduling instruction according to the predicted value, and sending the scheduling instruction to a control layer. And the control layer is used for completing real-time scheduling of the coal mine transportation chain according to the scheduling instruction. And the data storage layer is used for storing the coal mine transportation chain data and carrying out abnormal alarm by analyzing the coal mine transportation chain data. According to the method, accurate prediction of the coal mine transportation chain can be realized according to the coal mine transportation chain data. And the scheduling strategy is dynamically adjusted by using the prediction result, so that common errors and delay in manual scheduling are avoided, and the scheduling efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the field of industrial control, and in particular to an intelligent dispatching system for a coal mine transportation chain based on machine learning. Background Art

[0002] As an important part of the mining process, the coal mine transportation system is responsible for transporting the mined coal from the mine to the ground or processing plant. The efficiency of the transportation chain directly affects the overall efficiency and cost of coal mine production. The traditional coal mine transportation chain is usually composed of mine cars, transportation tracks, mechanical equipment, etc., and relies on manual scheduling and management. During the operation, problems such as uneven resource scheduling and transportation delays are inevitable. With the development of information technology and automation technology, the intelligence of coal mine transportation chains has gradually become a trend.

[0003] In recent years, the rapid development of machine learning and artificial intelligence technologies has provided new ideas for the optimization of coal mine transportation systems. Machine learning models can analyze a large amount of historical data, discover patterns and make predictions, thereby realizing intelligent optimization of mine car scheduling, transportation routes, etc. In addition, the Internet of Things (IoT) technology makes it easier to collect and monitor real-time data. Combined with cloud computing and big data analysis, it can process and predict the operating status of the coal mine transportation chain in real time, further improving transportation efficiency and safety.

[0004] In the traditional coal mine transportation system, transportation tasks and scheduling usually rely on manual management and experience judgment. Dispatchers manually allocate mine car resources based on the coal mine production plan, combined with factors such as the number of mine cars, transportation routes, and transportation time. However, this manual scheduling method has many shortcomings. First, manual scheduling is inefficient and easily affected by workload and human factors, resulting in untimely scheduling or uneven resource allocation, affecting transportation efficiency. Secondly, the manual scheduling method cannot respond to emergencies in system operation in real time, such as equipment failure, mine car overload, or weather changes, which can easily lead to transportation bottlenecks or delays. Finally, manual scheduling often relies on experience, is difficult to optimize based on historical data, and cannot effectively mine the potential laws in the data, resulting in inefficient resource utilization.

[0005] In addition to manual scheduling, some coal mines have also adopted simple automated scheduling systems, such as control systems based on preset rules. These systems usually rely on rule engines to schedule and assign tasks to mine cars according to set conditions. However, such systems have poor flexibility and cannot cope with complex and dynamically changing transportation environments. In addition, their scheduling optimization capabilities are limited, making it difficult to make accurate demand forecasts and resource allocation adjustments based on real-time or historical data. Summary of the invention

[0006] The purpose of the present invention is to provide a coal mine transportation chain monitoring and scheduling system to solve the problem that the prior art cannot accurately predict demand and adjust resource allocation due to the complex and dynamically changing coal mine transportation environment.

[0007] An embodiment of the present invention provides an intelligent scheduling system for a coal mine transportation chain based on machine learning, the system comprising: a monitoring and scheduling layer, a control layer and a data storage layer; the control layer and the data storage layer are both in communication connection with the monitoring and scheduling layer; the monitoring and scheduling layer is used to obtain coal mine transportation chain data, and generate a predicted value corresponding to the coal mine transportation chain data according to the coal mine transportation chain data; and generate a corresponding scheduling instruction according to the predicted value and send the scheduling instruction to the control layer; the control layer is used to complete the real-time scheduling of the coal mine transportation chain according to the scheduling instruction; the data storage layer is used to store the coal mine transportation chain data, and perform abnormal alarm by analyzing the coal mine transportation chain data; the coal mine transportation chain data comprises historical coal mine transportation chain data, a first real-time coal mine transportation chain data and a second real-time coal mine transportation chain data; wherein the second real-time coal mine transportation chain data is the coal mine transportation chain data corresponding to the next time series of the time series corresponding to the first real-time coal mine transportation chain data.

[0008] Optionally, the monitoring and scheduling layer includes: a real-time monitoring module, a machine learning model construction module and a scheduling module; the real-time monitoring module is used to obtain the historical coal mine transportation chain data and the first real-time coal mine transportation chain data; and, send the historical coal mine transportation chain data to the machine learning model construction module, and send the first real-time coal mine transportation chain data to the scheduling module; the machine learning model construction module is used to construct a scheduling model based on the historical coal mine transportation chain data; the scheduling model includes a prediction model and a machine learning classification model; the scheduling module is used to generate the scheduling instructions based on the first real-time coal mine transportation chain data and the scheduling model.

[0009] Optionally, the machine learning model construction module includes: a first data processing submodule, a prediction model construction submodule and a machine learning classification model construction submodule; the first data processing submodule is used to preprocess the historical coal mine transportation chain data to generate a historical sample data set, and the historical sample data set is data obtained by normalizing the historical coal mine transportation chain data; the prediction model construction submodule is used to construct the prediction model based on the historical sample data set and a first preset machine learning network architecture; the first preset machine learning network architecture is an ARMA model architecture or a BP neural network model architecture; the machine learning classification model construction submodule is used to construct the machine learning classification model based on the historical sample data set, the scheduling instructions corresponding to the historical sample data set and the second preset machine learning network architecture; the second preset machine learning network architecture is a machine learning classification model network architecture constructed based on the support vector machine algorithm.

[0010] Optionally, the historical coal mine transportation chain data includes basic data of the coal mine transportation chain and real-time data of the coal mine transportation chain; the prediction model construction submodule uses the basic data of the coal mine transportation chain as model boundary data; and uses the real-time data of the coal mine transportation chain as model training data; the basic data of the coal mine transportation chain is the total number of mine cars and the total number of transportation tracks, and the real-time data of the coal mine transportation chain is the number of mine cars and the number of transportation tracks in operation at historical moments.

[0011] Optionally, the scheduling module includes a second data processing submodule and a scheduling command generation submodule; the second data processing submodule is used to preprocess the real-time coal mine transportation chain data to generate a real-time sample data set, and the real-time sample data set is data obtained by normalizing the first real-time coal mine transportation chain data; the scheduling command generation submodule is used to generate a first real-time coal mine transportation chain data prediction value based on the real-time sample data set; and, based on the first real-time coal mine transportation chain data prediction value, generate the scheduling instruction and send the scheduling instruction to the control layer, the first real-time coal mine transportation chain data prediction value is the coal mine transportation chain data prediction value corresponding to the next time series of the time series corresponding to the first real-time coal mine transportation chain data.

[0012] Optionally, the data storage layer includes an abnormal alarm module; the abnormal alarm module is used to determine whether an abnormality occurs in the coal mine transportation chain according to the second real-time coal mine transportation chain data and the predicted value of the first real-time coal mine transportation chain data, and to issue an alarm.

[0013] Optionally, the abnormal alarm module includes a third data processing submodule, an alarm signal generating submodule and an alarm signal displaying submodule; the third data processing submodule is used to preprocess the first real-time coal mine transportation chain data prediction value to generate a second real-time coal mine transportation chain data prediction value, and the second real-time coal mine transportation chain data prediction value is the data obtained by denormalizing the first real-time coal mine transportation chain data prediction value; the alarm signal generating submodule is used to generate abnormal alarm information according to the second real-time coal mine transportation chain data, the second real-time coal mine transportation chain data prediction value and a preset threshold; the alarm signal displaying submodule is used to display and / or broadcast the abnormal alarm information.

[0014] Optionally, the data storage layer includes a data storage module; the data storage module is used to store the historical coal mine transportation chain data, the first real-time coal mine transportation chain data, the second real-time coal mine transportation chain data, the first real-time coal mine transportation chain data predicted value and the second real-time coal mine transportation chain data predicted value.

[0015] Optionally, the data storage module is also used to protect the data security of the historical coal mine transportation chain data, the first real-time coal mine transportation chain data, the second real-time coal mine transportation chain data, the first real-time coal mine transportation chain data predicted value and the second real-time coal mine transportation chain data predicted value; and to trace the data sources of the historical coal mine transportation chain data, the first real-time coal mine transportation chain data, the second real-time coal mine transportation chain data, the first real-time coal mine transportation chain data predicted value and the second real-time coal mine transportation chain data predicted value.

[0016] Optionally, the data storage module also includes a data security and trusted traceability submodule; the data security and trusted traceability submodule is used to construct a blockchain data storage architecture; and to generate a unique traceability code corresponding to the historical coal mine transportation chain data, the first real-time coal mine transportation chain data, the second real-time coal mine transportation chain data, the first real-time coal mine transportation chain data predicted value and the second real-time coal mine transportation chain data predicted value.

[0017] Compared with the prior art, the coal mine transportation chain intelligent scheduling system based on machine learning provided by the present invention has the following beneficial effects: A coal mine transport chain intelligent scheduling system based on machine learning, the system includes: a monitoring and scheduling layer, a control layer and a data storage layer, wherein the control layer and the data storage layer are both connected to the monitoring and scheduling layer in communication. The monitoring and scheduling layer is used to obtain coal mine transport chain data, and generate a prediction value corresponding to the coal mine transport chain data according to the coal mine transport chain data; and generate a corresponding scheduling instruction according to the prediction value and send the scheduling instruction to the control layer. The control layer is used to complete the real-time scheduling of the coal mine transport chain according to the scheduling instruction. The data storage layer is used to store the coal mine transport chain data and perform abnormal alarm by analyzing the coal mine transport chain data; the coal mine transport chain data includes historical coal mine transport chain data, first real-time coal mine transport chain data and second real-time coal mine transport chain data; wherein the second real-time coal mine transport chain data is the coal mine transport chain data corresponding to the next time series of the time series corresponding to the first real-time coal mine transport chain data. The present invention can effectively overcome some technical bottlenecks and management shortcomings in traditional coal mine transportation systems by introducing an intelligent monitoring and scheduling system for coal mine transportation chains; it can accurately predict coal mine transportation chains based on coal mine transportation chain data; and dynamically adjust scheduling strategies using prediction results, thereby avoiding common errors and delays in manual scheduling and improving scheduling efficiency and accuracy. In summary, by introducing an intelligent scheduling system for coal mine transportation chains based on machine learning, coal mine transportation chains can achieve more accurate and automated scheduling, reduce reliance on manual intervention, improve resource utilization efficiency, reduce human errors and operational risks, and promote the development of coal mine transportation management towards intelligence and refinement. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0019] Figure 1 A schematic diagram of the modular structure of a coal mine transportation chain intelligent scheduling system based on machine learning provided by an embodiment of the present invention; Figure 2 A schematic diagram of the modular structure of a machine learning model building module in an embodiment of the present invention; Figure 3 Schematic diagram of the modular structure of the scheduling module in an embodiment of the present invention; Figure 4 Schematic diagram of the modular structure of the abnormal alarm module in an embodiment of the present invention; Figure 5 A schematic diagram of a modular structure of a data storage module in an embodiment of the present invention; Figure 6 This is a schematic diagram of the modular structure of an intelligent monitoring and dispatching system for a coal mine transportation chain in an embodiment of the present invention; Figure 7 It is a schematic flow chart of the BP neural network model construction method in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0021] The embodiment of the present invention provides a coal mine transportation chain intelligent scheduling system based on machine learning, see Figure 1 A modular structure schematic diagram of a coal mine transportation chain intelligent scheduling system based on machine learning is shown, the system includes: a monitoring and scheduling layer, a control layer and a data storage layer; the control layer and the data storage layer are both communicated with the monitoring and scheduling layer.

[0022] The above-mentioned monitoring and scheduling layer is used to obtain the coal mine transportation chain data, generate the predicted value corresponding to the coal mine transportation chain data according to the coal mine transportation chain data; and generate the corresponding scheduling instructions according to the predicted value and send the scheduling instructions to the control layer. The above-mentioned control layer is used to complete the real-time scheduling of the coal mine transportation chain according to the scheduling instructions. The above-mentioned data storage layer is used to store the coal mine transportation chain data and to make abnormal alarms by analyzing the coal mine transportation chain data. The above-mentioned coal mine transportation chain data includes historical coal mine transportation chain data, first real-time coal mine transportation chain data and second real-time coal mine transportation chain data; wherein, the second real-time coal mine transportation chain data is the coal mine transportation chain data corresponding to the next time series of the time series corresponding to the first real-time coal mine transportation chain data.

[0023] It should be noted that when the monitoring and scheduling layer needs to obtain data information of the second real-time coal mine transportation chain data, the second real-time coal mine transportation chain data is converted into the first real-time coal mine transportation chain data.

[0024] Optionally, continue to see Figure 1 The above-mentioned monitoring and scheduling layer includes: real-time monitoring module, machine learning model building module and scheduling module.

[0025] The real-time monitoring module is used to obtain historical coal mine transportation chain data and first real-time coal mine transportation chain data; and send the historical coal mine transportation chain data to the machine learning model construction module, and send the first real-time coal mine transportation chain data to the scheduling module. The machine learning model construction module is used to build a scheduling model based on the historical coal mine transportation chain data; the scheduling model includes a prediction model and a machine learning classification model. The scheduling module is used to generate scheduling instructions based on the first real-time coal mine transportation chain data and the scheduling model.

[0026] Alternatively, see Figure 2 The modular structure diagram of the machine learning model construction module shown in the figure, the above-mentioned machine learning model construction module includes: a first data processing sub-module, a prediction model construction sub-module and a machine learning classification model construction sub-module.

[0027] The above-mentioned first data processing submodule is used to preprocess the historical coal mine transportation chain data to generate a historical sample data set, which is data obtained by normalizing the historical coal mine transportation chain data. The above-mentioned prediction model construction submodule is used to construct a prediction model based on the historical sample data set and the first preset machine learning network architecture; wherein the first preset machine learning network architecture is an ARMA model architecture or a BP neural network model architecture. The above-mentioned machine learning classification model construction submodule is used to construct a machine learning classification model based on the historical sample data set, the scheduling instructions corresponding to the historical sample data set and the second preset machine learning network architecture; wherein the second preset machine learning network architecture is a machine learning classification model network architecture constructed based on the support vector machine algorithm.

[0028] Optionally, the historical coal mine transportation chain data includes basic data of the coal mine transportation chain and real-time data of the coal mine transportation chain. The prediction model construction submodule uses the basic data of the coal mine transportation chain as model boundary data; and uses the real-time data of the coal mine transportation chain as model training data; the basic data of the coal mine transportation chain is the total number of mine cars and the total number of transportation tracks, and the real-time data of the coal mine transportation chain is the number of mine cars and the number of transportation tracks in operation at historical moments.

[0029] Alternatively, see Figure 3 The modular structure diagram of the scheduling module shown in the figure, the above-mentioned scheduling module includes a second data processing sub-module and a scheduling command generation sub-module.

[0030] The second data processing submodule is used to preprocess the first real-time coal mine transportation chain data to generate a real-time sample data set, which is data obtained by normalizing the first real-time coal mine transportation chain data. The scheduling command generation submodule is used to generate a first real-time coal mine transportation chain data prediction value based on the real-time sample data set; and, based on the first real-time coal mine transportation chain data prediction value, generate a scheduling instruction and send the scheduling instruction to the control layer; the first real-time coal mine transportation chain data prediction value is the coal mine transportation chain data prediction value corresponding to the next time series of the time series corresponding to the first real-time coal mine transportation chain data.

[0031] Optionally, continue to see Figure 1 , the above-mentioned data storage layer includes an abnormal alarm module.

[0032] The above-mentioned abnormal alarm module is used to determine whether an abnormality occurs in the coal mine transportation chain according to the second real-time coal mine transportation chain data and the predicted value of the first real-time coal mine transportation chain data, and to issue an alarm.

[0033] Alternatively, see Figure 4 The schematic diagram of the modular structure of the abnormal alarm module shown in the figure, the abnormal alarm module includes a third data processing submodule, an alarm signal generating submodule and an alarm signal displaying submodule.

[0034] The third data processing submodule is used to preprocess the first real-time coal mine transport chain data prediction value to generate the second real-time coal mine transport chain data prediction value, which is the data obtained by denormalizing the first real-time coal mine transport chain data prediction value. The alarm signal generation submodule is used to generate abnormal alarm information according to the second real-time coal mine transport chain data, the second real-time coal mine transport chain data prediction value and the preset threshold value; the alarm signal display submodule is used to display or broadcast the abnormal alarm information.

[0035] Optionally, continue to see Figure 1 The above-mentioned data storage layer includes a data storage module.

[0036] The data storage module is used to store historical coal mine transportation chain data, first real-time coal mine transportation chain data, second real-time coal mine transportation chain data, first real-time coal mine transportation chain data predicted value and second real-time coal mine transportation chain data predicted value.

[0037] It should be noted that historical sample data sets and real-time sample data sets can be stored according to actual needs.

[0038] Optionally, the above-mentioned data storage module is also used to protect the data security of historical coal mine transportation chain data, the first real-time coal mine transportation chain data, the second real-time coal mine transportation chain data, the first real-time coal mine transportation chain data predicted value and the second real-time coal mine transportation chain data predicted value; and to trace the data sources of historical coal mine transportation chain data, the first real-time coal mine transportation chain data, the second real-time coal mine transportation chain data, the first real-time coal mine transportation chain data predicted value and the second real-time coal mine transportation chain data predicted value.

[0039] Alternatively, see Figure 5 The modular structure diagram of the data storage module shown is that the data storage module also includes a data security and trusted tracing submodule.

[0040] The above-mentioned data security and trusted traceability sub-module is used to build a blockchain data storage architecture; and to generate unique traceability codes corresponding to historical coal mine transportation chain data, first real-time coal mine transportation chain data, second real-time coal mine transportation chain data, first real-time coal mine transportation chain data predicted values, and second real-time coal mine transportation chain data predicted values.

[0041] The embodiment of the present invention can effectively overcome some technical bottlenecks and management shortcomings in the traditional coal mine transportation system by introducing an intelligent monitoring and scheduling system for the coal mine transportation chain. First, the machine learning model can train the prediction model based on historical operation data, thereby realizing accurate prediction of the coal mine transportation chain. The real-time monitoring module in the system monitors the status of the coal mine transportation chain in real time. The machine learning module and scheduling module in the system can automatically analyze the status of the current transportation chain and dynamically adjust the scheduling strategy according to the prediction results, avoiding common errors and delays in manual scheduling and improving the efficiency and accuracy of scheduling.

[0042] Secondly, the introduction of advanced algorithms such as machine learning classification models, ARMA models and BP neural networks can optimize the transportation chain according to the complexity and variability of transportation tasks. These algorithms can automatically generate scheduling instructions based on different transportation needs and real-time conditions, and continuously optimize the prediction results through continuous learning and training, thereby improving the system's adaptability and flexibility.

[0043] Finally, through real-time data monitoring and big data analysis, the system can conduct comprehensive monitoring and fault warning of the coal mine transportation chain. Once the system detects an abnormal situation, such as a mine car running overtime or a transportation route congestion, the system can issue an alarm in time and automatically adjust the scheduling plan, reducing the time for manual intervention and emergency response, and improving the safety and stability of coal mine transportation.

[0044] In summary, the coal mine transportation chain intelligent monitoring and scheduling system provided by the embodiment of the present invention is based on machine learning, and through the organic combination of real-time monitoring, data processing, prediction model and automatic scheduling, the coal mine transportation efficiency and resource utilization rate are significantly improved. The system can collect various operating data of the coal mine transportation chain in real time, such as the number of mine cars, transportation time, mine car time consumption, etc., and analyze and predict historical data through machine learning models (including support vector machines, ARMA models and BP neural networks) to generate accurate scheduling instructions. Compared with traditional manual scheduling, the system has a high degree of automation, reduces human intervention and operational errors, and improves the accuracy and response speed of scheduling decisions. Through continuous deep learning and model optimization, the system can dynamically adjust the scheduling strategy according to changes in actual operations, optimize resource allocation, and avoid transportation bottlenecks and idle waste. Its fault warning mechanism can also issue an alarm in time when equipment abnormalities or transportation problems occur, and adjust the transportation tasks to ensure efficient, safe and stable operation of coal mine transportation. Overall, this solution has greatly improved the intelligence level of the coal mine transportation chain, which not only reduces operating costs, but also enhances the system's flexibility, adaptability and long-term self-optimization capabilities, providing strong technical support for the automation and refined management of coal mine transportation.

[0045] The embodiment of the present invention also provides a coal mine transport chain intelligent monitoring and dispatching system, see Figure 6 The modular structure diagram of a coal mine transportation chain intelligent monitoring and dispatching system is shown, and the system includes a monitoring and dispatching layer, a control layer, and a data storage layer. Among them, the monitoring and dispatching layer interacts with the control layer through the CANopen protocol, and the monitoring and dispatching layer interacts with the data storage layer through the database.

[0046] Specifically, the control layer includes a lower computer, and the monitoring and scheduling layer interacts with the lower computer through the CANopen protocol; the lower computer is the underlying hardware device or control system that directly controls the on-site equipment of the coal mine transportation chain to execute actions and collect operation data. The monitoring and scheduling layer includes a real-time monitoring module, a machine learning model building module, and a scheduling module. The machine learning model module includes a data processing module, a prediction model building module and a machine learning classification model module; the real-time monitoring module is used to obtain and monitor the real-time operation status data of the coal mine transportation chain, and transmit the real-time operation status data of the coal mine transportation chain to the machine learning model module connected thereto through the CANopen protocol; the data processing module performs data cleaning, feature preprocessing, data integration, data change detection and data dimension reduction on the real-time operation status data of the coal mine transportation chain transmitted by the real-time monitoring module to form a sample data set, and transmits the sample data set and data feature information to the prediction model building module and the machine learning classification model; the prediction model building module performs machine learning training according to the received sample data set to build a prediction model (for example: ARMA model or BP neural network model); the machine learning classification model performs machine learning training according to the received sample data set and the scheduling instruction label to build a machine learning classification model; the scheduling model is formed by the trained prediction model and the machine learning classification model; the scheduling model is transmitted to the scheduling module, and the scheduling module outputs the corresponding scheduling instruction by inputting the real-time coal mine transportation chain data to the scheduling model; the control layer completes the real-time scheduling of the coal mine transportation chain according to the scheduling instruction output by the scheduling module.

[0047] Exemplarily, the specific method of constructing the machine learning classification model is as follows: The machine learning classification model is trained through deep learning methods to match the coal mine transportation chain data with the dispatching instructions. First, the system collects the real-time operation status data of the coal mine transportation chain from the real-time monitoring module and preprocesses it. In the data processing module, the data is cleaned, feature preprocessed, integrated, detected for data changes, and dimensionally reduced to generate a sample data set. The processed sample data set is transmitted to the machine learning classification model.

[0048] The first step in the training process is normalization, which is to eliminate the scale differences of different features so that the feature values ​​are in a similar range and avoid some features having too much impact on the training process due to their large values. The normalized data will be used as input data for the machine learning classification model. The normalization method uses one of the two methods: min-max scaling or standardization (z-score).

[0049] The machine learning classification model is trained using the Support Vector Machine (SVM) algorithm. The SVM algorithm aims to achieve data classification by constructing a hyperplane to maximize the interval between different categories. Specifically, the SVM algorithm will find an optimal separation hyperplane based on the training sample set so that the sample data can be correctly classified, that is, different coal mine transportation chain data can be classified into corresponding scheduling instruction labels.

[0050] During the training process, the model will judge whether the classification model meets the expected conditions based on the set evaluation indicators such as accuracy and recall. If the performance of the model meets the requirements, the training process is completed and the model is used for actual scheduling tasks; if the conditions are not met, the model hyperparameters such as kernel function, C value, γ value, etc. are adjusted and iterative training is performed again to optimize the model performance. Through this process, the machine learning classification model is trained and used to generate scheduling instructions for the coal mine transportation chain.

[0051] The selection of the support vector machine (SVM) algorithm for the machine learning classification model fully considers the characteristics of the coal mine transportation chain data and the actual application needs. The data generated by the coal mine transportation chain has the characteristics of high dimensionality, nonlinearity, and complexity. When processing high-dimensional data, the SVM algorithm can map the nonlinear problem in the low-dimensional space to the high-dimensional space through the kernel function technique, thereby finding a linearly separable hyperplane in the high-dimensional space and effectively solving the data classification problem. Compared with some other classification models, the selection of the SVM algorithm for the machine learning classification model has the following advantages: its structural risk minimization principle enables the model to obtain good generalization ability when processing small sample data, and in the coal mine transportation scenario, due to the influence of factors such as equipment failure and weather changes, the data sample distribution may be uneven. This feature of the SVM algorithm can reduce the risk of overfitting. In addition, the SVM algorithm can flexibly adapt to different data distributions by adjusting the kernel function and its parameters, and has stronger adaptability to the complex and changeable data in the coal mine transportation chain. Therefore, choosing the SVM algorithm as the training algorithm for the machine learning classification model can better process the operation data of the coal mine transportation chain, generate accurate scheduling instructions, and improve the efficiency and safety of coal mine transportation.

[0052] For example, the ARMA model is constructed in the following way: The ARMA model (autoregressive moving average model) is used for modeling and forecasting of time series data. In the above system, the ARMA model is mainly used to predict the operating status of the coal mine transportation chain, especially key indicators such as transportation volume or equipment status changes in the future. Its construction process includes data normalization, smoothing decomposition, parameter calculation and error adjustment.

[0053] First, the data processing module will perform normalization based on the collected sample data set. This is to ensure that the data is in the same dimension so that the time series model can be established more accurately. The normalized data is decomposed through smoothing to obtain three parts: Deterministic data whose order does not change over time, white noise with unit root 1, The ARMA model attempts to decompose the time series into a trend component (deterministic data that does not change over time) and a random disturbance component (white noise).

[0054] The core formula of the ARMA model is: , in, represents the observed value at the current moment, is the autoregressive coefficient, yes white noise with a unit root of 1, is the moving average coefficient, yes The ARMA model describes how the observed value at each moment in the time series is determined by the past observed value (autoregressive part) and the past error term (moving average part).

[0055] During the construction process, it is first necessary to determine whether the predicted value of the ARMA model is consistent with the actual value. If the predicted result is in line with expectations, the model is built. If not, the system will calculate the error between the model predicted value and the actual value, and adjust the autoregressive coefficient and moving average coefficient in the ARMA model through iterative optimization, and use machine learning algorithms (such as particle swarm optimization or genetic algorithm) to optimize the model parameters to obtain the best prediction results.

[0056] Exemplarily, the combination of the machine learning classification model and the ARMA model is as follows: In the system's scheduling module, the ARMA model and the machine learning classification model jointly provide a basis for the scheduling instructions of the coal mine transportation chain. Specifically, the ARMA model is used to make time series predictions on the future operating status of the coal mine transportation chain, providing the necessary future data predictions for the scheduling module. The machine learning classification model adjusts the scheduling strategy in real time and generates scheduling instructions based on the real-time monitored operating data and the prediction results of the ARMA model. The combination of the two enables the scheduling system to have both the ability to predict the future and the ability to respond to changes in operating status in real time, thus achieving efficient intelligent scheduling.

[0057] Assume that during the operation of the coal mine transportation chain, it is monitored that the load of the transport vehicles (such as the amount of coal transported) fluctuates. After the real-time monitoring module obtains this data, it transmits it to the machine learning classification model. After data preprocessing and normalization, the support vector machine model is trained to eventually form a machine learning classification model, which can give real-time scheduling instructions based on the current state of the coal mine transportation chain (such as vehicle load, speed, etc.). At the same time, the ARMA model can predict the fluctuation of transportation volume in the future by analyzing historical load data, and provide the scheduling system with future load trend forecasts. Combining these two models, the scheduling module can accurately determine whether it is necessary to increase or decrease the number of transport vehicles, or adjust the transportation route, thereby achieving more efficient transportation scheduling.

[0058] Through such a combination, the operation of the coal mine transportation chain can be more intelligent and refined, reducing resource waste and improving operational efficiency.

[0059] The BP neural network model can also be used as a prediction model in the coal mine transportation chain intelligent monitoring and scheduling system provided by the embodiment of the present invention.

[0060] Exemplarily, the specific method of constructing the BP neural network model is as follows: As one of the prediction models, the BP neural network model is responsible for scheduling prediction based on the input of real-time monitoring data and historical data. Its construction process includes normalization, network training, error optimization and iterative adjustment. The core of the BP neural network model is to use a multi-layer perceptron to gradually calculate from the input layer to the hidden layer to the output layer, and optimize the parameters in order to accurately predict the operation status of the transportation chain and finally generate scheduling instructions. Figure 7 The schematic flow chart of the BP neural network model construction method shown in FIG. The detailed process of BP neural network model construction is as follows: Step S702: Data preprocessing and normalization Specifically, first, the data processing module processes the collected real-time operating status data of the coal mine transportation chain to obtain a preprocessed sample data set. In order to ensure the training effect of the neural network model, all input data needs to be normalized. The purpose of normalization is to compress the value range of different feature data to a unified range, usually between 0 and 1, so as to avoid the adverse effects of too large or too small values ​​of certain features on network training.

[0061] The normalized data set will be used as the input data set of the BP neural network, and the normalized data set contains various feature information used to train the model. It will be used as the parameters of the BP neural network model to help the network better establish the relationship between different feature data and prediction results.

[0062] Step S704: Construction and training of BP neural network model Specifically, the BP neural network consists of three layers: input layer, hidden layer and output layer. In the construction process, the structure of the neural network needs to be determined first, including the number of neurons, input and output dimensions.

[0063] Assuming that the input layer has m neurons and the output layer has n neurons, the input data set contains m feature values ​​and the output data set contains n predicted values. These input and output data will be calculated through weight parameters and activation functions to obtain the predicted output of the BP neural network.

[0064] The core formula of BP neural network is as follows: , in, is the output of the neural network, Yes Connection Input and the weights of the neurons, is the bias term. The learning goal of the BP neural network is to adjust the weight parameters through the back propagation algorithm to minimize the predicted value. The error between the actual value.

[0065] Step S706: Error calculation and optimization Specifically, during the network training process, the error between the predicted value and the actual value needs to be calculated, and the weight parameters of the neural network are adjusted through the back propagation algorithm. The key formula for error calculation is as follows: , in, is the total error, is the predicted value of the neural network, is the actual value. In order to minimize the error, the BP neural network gradually adjusts the weights and biases through the gradient descent method until the error drops to an acceptable range.

[0066] The role of the error function is to measure the gap between the predicted value and the actual value and guide the training process of the neural network. Specifically, the network will calculate the gradient based on the error back propagation and update the weights and biases of each layer through iterative optimization algorithms (such as gradient descent or Adam optimizer) to reduce the error.

[0067] Step S708: Network training and parameter update Specifically, the training of BP neural network is an iterative process. In each iteration, the network first calculates the error between the predicted value and the actual value, and adjusts the network parameters through error back propagation. If the error meets the preset accuracy requirements, the training process ends and the model is built. If the error is too large, the iteration continues, and the network performance is optimized by adjusting hyperparameters such as the number of neurons, learning rate, and activation function until the predetermined error range is reached.

[0068] Step S710: Application of BP neural network model Specifically, the trained BP neural network model will be used for real-time scheduling of the coal mine transportation chain. During the real-time scheduling process, the operating status data collected by the real-time monitoring module will be transmitted as input to the trained BP neural network model. The model calculates the prediction results based on the input data and generates scheduling instructions based on the prediction results. In this way, the BP neural network can flexibly respond to different operating status changes in the coal mine transportation chain, optimize the scheduling plan in a timely manner, and improve scheduling efficiency.

[0069] Assume that in the coal mine transportation chain, the load of the transport vehicle is a key indicator that needs to be predicted. The system first obtains the current load data of the vehicle through the real-time monitoring module, including information such as transportation volume, vehicle speed, and transportation route. The data processing module cleans and normalizes this data to obtain a sample data set.

[0070] These data will be passed as input to the BP neural network model for training. During the training process, the network continuously adjusts the weight parameters until the error between the output value (predicted load) and the actual load is minimized. Once the network training is completed, the model can be used to predict the load in the future and generate dispatch instructions based on the prediction results. For example, if the predicted load is too high, the dispatch system may instruct to increase the number of vehicles or adjust the transportation route; if the predicted load is too low, the system may reduce the number of vehicles or optimize the route.

[0071] In this way, the BP neural network can not only make accurate scheduling predictions based on real-time data, but also automatically adjust parameters as the data changes to cope with various changes that may occur in the transportation chain.

[0072] It should be noted that the embodiment of the present invention can use the ARMA model and the BP neural network for prediction at the same time. Specifically, in the actual coal mine transportation scenario, different specific scheduling methods are used for different transportation chain status data. For example, when it is monitored that the average running time of the mine car on a certain transportation line exceeds the preset threshold, and the transportation volume of the line continues to be high for a period of time, it indicates that the line may be congested. At this time, the scheduling system will adopt the following scheduling method: First, the ARMA model is used to predict the transportation volume of the line in the future. If the predicted transportation volume will remain at a high level, the scheduling module instructs the mine car to be deployed from other relatively idle lines to the congested line to increase the transportation capacity. At the same time, according to the analysis of the real-time operation data by the machine learning classification model, the departure time interval of the mine car on the line is adjusted, and the interval is appropriately shortened to improve the transportation efficiency. In addition, if the BP neural network model predicts that the coal production in a certain area will increase significantly in the next few hours, the dispatching system will plan the transportation route in advance based on the analysis of real-time operation data by the machine learning classification model, give priority to arranging mine cars to transport coal to the area, and reasonably allocate the number of mine cars based on the predicted production to ensure that the coal can be transported out of the mine in a timely and efficient manner.

[0073] In the coal mine transportation chain intelligent monitoring and scheduling system provided by the embodiment of the present invention, when the parameters of the machine learning classification model need to be updated, the scheduling module will iteratively train the model to optimize the scheduling results. The goal of each iteration is to adjust the parameters of the model so that the scheduling instructions are more accurate and can better adapt to the real-time changes of the coal mine transportation chain. The number of iterations is determined according to the update of the parameters in the scheduling model. Specifically, the number of iterations is The parameters are updated in two parts. and They represent the first and second update parameters of the scheduling model respectively. The formula is as follows: , in, is the total number of iterations, and Represents the number of iterations required to update the parameters of the prediction model and the machine learning classification model, respectively. Through this formula, the scheduling module can adjust the parameters during each training so that the model is optimized at multiple levels, thereby effectively improving the accuracy and adaptability of scheduling decisions.

[0074] In this system, the training step size (i.e., the adjustment amplitude in each iteration) is set to 60 times. This step size means that each model parameter update will be carried out for 60 steps, thereby adjusting the network parameters and gradually improving the prediction accuracy of the scheduling model.

[0075] The setting of 60 iterations or more is to ensure that the model is fully trained and avoid insufficient fitting of the data when the number of iterations is too small. After each iteration, the model will be tested on a new training set to check whether the error has been effectively reduced. If the error has not been significantly reduced, the scheduling module will continue to iterate until the training reaches the preset accuracy requirement.

[0076] Through multiple iterations of training, the scheduling model is gradually optimized and can more accurately predict the operating status of the coal mine transportation chain. Once the training is completed, the model can be used to generate scheduling instructions. For example, given the number of mine cars and the running time, the model can predict future transportation demand and generate scheduling instructions based on the prediction results. These instructions can guide the arrangement of mine cars in the coal mine transportation chain, the allocation of transportation tasks, etc.

[0077] The scheduling module also continuously updates the scheduling strategy based on real-time data and trained models to ensure the efficiency and safety of the coal mine transportation chain. For example, if the model predicts that the transportation volume in a certain area will increase, the scheduling system may instruct to increase the number of mine cars or adjust the transportation route to optimize resource utilization.

[0078] Assume that in a certain training, the number of mine cars, running time and mine car time recorded by the real-time monitoring module are input data, which are passed to the neural network model after normalization. During the training process, the BP neural network model continuously updates the weights through the gradient descent method and optimizes the network parameters in iteration. After these iterations, the model has been able to accurately predict the mine car load and transportation tasks in the future. Based on this prediction, the scheduling module will automatically adjust the number of mine cars and the allocation of transportation tasks according to the results of the model output, thereby improving the overall coal mine transportation efficiency.

[0079] In this way, the model can not only make predictions based on historical data, but also flexibly adjust when monitoring data changes in real time, ensuring that the scheduling system is highly adaptable and accurate.

[0080] In order to further improve the performance of the intelligent monitoring and dispatching system of the coal mine transportation chain, a data security and trusted traceability module combined with blockchain is constructed, which can effectively ensure data security, improve system transparency and optimize cross-system collaboration. The core goal of introducing blockchain technology is to build a decentralized data storage and management platform so that each data block in the system is tamper-proof and traceable. By designing the blockchain data storage architecture, key data in the coal mine transportation chain process, such as the number of mine cars, running time, mine car time and other raw data, as well as sample data, feature data, model parameters, etc. generated by machine learning models, can be encrypted and distributedly stored in blockchain nodes. Each data block contains information such as timestamp, data hash value, hash value of the previous data block, etc., to ensure the order and tamper-proofness of data during storage, and to standardize the data chain process through smart contracts. In order to achieve this goal, the creation and verification of data blocks not only rely on the consensus mechanism of blockchain nodes, but also combine the identification verification of monitoring equipment and data integrity verification to ensure that only verified data can be successfully written into the blockchain network.

[0081] To implement a trusted traceability mechanism, each data set is identified by generating a unique traceability code, which runs through the entire data life cycle, from collection, transmission, processing to model application. When it is necessary to trace the transportation chain data at a certain moment, the system can query the relevant data blocks and their chains on the blockchain according to the traceability code, and clearly display the data generation path, change records, and detailed information on processing operations. In this way, if an abnormality occurs, such as data fluctuations exceeding the set reasonable range, the system can automatically trigger the backtracking mechanism to quickly locate the source of the abnormality and determine whether it is a monitoring equipment failure, data transmission interference, or an abnormality in the model itself. In this process, blockchain technology helps to quickly find problems and repair them by providing a transparent and tamper-proof record, thereby ensuring the stable operation of the entire transportation chain.

[0082] The coordinated optimization of machine learning models and blockchain data storage systems can be enhanced through data quality feedback mechanisms. Trusted data stored in blockchain can be used as a "quality inspector" to feed back into the training phase of machine learning models. When it is found that the deviation between training data and historical high-quality data stored in the blockchain is too large, the system can suspend training and prompt the need to re-examine the data collection source or preprocessing process. This mechanism effectively avoids the impact of "dirty data" on model performance, ensures the quality of model training data, and thus improves the accuracy and reliability of predictions. In order to further optimize the model evolution process, when model parameters (such as hyperparameters of machine learning models or weights of neural networks) are updated, key indicators before and after the update (such as accuracy, recall, prediction error, etc.) and related data version information are recorded in the blockchain. This information provides a reliable basis for subsequent model updates, and combined with the consensus verification mechanism of the blockchain, it can ensure that each model update is verifiable and scientific.

[0083] In order to achieve cross-system data collaboration, the intelligent monitoring and dispatching system of the coal mine transportation chain can integrate the trusted data on the blockchain with the enterprise's operation management system by connecting with management systems such as the enterprise ERP and MES. Based on the trusted data shared by the blockchain, coal mining companies can more accurately predict transportation volume, optimize production plans, and carry out material procurement and production scheduling based on transportation efficiency, thereby improving the scientificity and accuracy of overall operational decisions. At the same time, by establishing an industry data sharing alliance with multiple coal mining companies and anonymizing and sharing common data through the blockchain network, it can promote the iteration and collaborative innovation of technology within the industry and accelerate the improvement of the intelligence level of the entire coal mining industry.

[0084] In the process of combining blockchain and machine learning, the algorithm design of data tracing and abnormal warning is particularly important. The following formula can be used to describe the implementation of the abnormal warning mechanism: , in, represents the outlier value at time t, is the data value at time t, It is a forecast value based on historical data. is the preset abnormal threshold. When the threshold is exceeded, the system triggers an abnormal warning and starts the traceability process.

[0085] The purpose of this formula is to determine whether the current data deviates from the normal range by comparing the predicted values ​​of real-time data with historical data. If the deviation is too large, it is judged as abnormal. Through this mechanism, the system can automatically identify and alarm, reduce the burden of manual monitoring, and improve overall operational efficiency. For example, if the change in the load of a mining car at a certain moment exceeds the historical prediction range, the system will query the generation process of the data through the blockchain, analyze whether the fluctuation is caused by equipment failure, data transmission error or model abnormality, and take targeted measures to repair it.

[0086] In short, the application of blockchain-based data security and trusted traceability modules in the intelligent monitoring and dispatching system of the coal mine transportation chain not only improves the security and transparency of the data, but also optimizes the data quality and model training process through combination with machine learning models, and realizes the collaborative innovation and upgrading of coal mine industry technology at multiple levels and dimensions.

[0087] The embodiment of the present invention provides a coal mine transportation chain intelligent scheduling system based on machine learning. The system is a coal mine transportation chain intelligent monitoring and scheduling system solution based on machine learning, which combines real-time monitoring, data processing and machine learning algorithms. Its beneficial effects are mainly reflected in the following aspects: Improving coal mine transportation efficiency The system provided by the embodiment of the present invention continuously collects the operation status data of the coal mine transportation chain (such as the number of mine cars, operation time, mine car time, etc.) through the real-time monitoring module, and uses machine learning to build a model for prediction and scheduling. The system can adjust the transportation tasks and resource allocation in real time. In particular, when the transportation demand suddenly increases or a failure occurs, the system can respond quickly and optimize the scheduling instructions, thereby avoiding resource waste and transportation bottlenecks, and improving the overall coal mine transportation efficiency.

[0088] Reduce human intervention and optimize scheduling decisions Traditional coal mine transportation scheduling usually relies on manual experience for adjustment. However, in complex environments, manual decisions are prone to errors and are difficult to cope with rapidly changing transportation needs. The system provided by the embodiment of the present invention introduces a machine learning classification model, and the system can make autonomous decisions based on real-time data, reduce the frequency of human intervention, automatically generate scheduling instructions, and make real-time adjustments based on the results predicted by the model. This automated scheduling capability not only improves the intelligence level of the system, but also ensures the accuracy and timeliness of scheduling decisions.

[0089] Enhance the system's adaptability and flexibility The machine learning model introduced by the system provided by the embodiment of the present invention can continuously adjust itself according to different time periods, transportation status and external environmental changes when using the gradient descent method for parameter optimization. This makes the system highly adaptive, and can respond quickly to complex and dynamic changes in the coal mine transportation chain, and adjust the prediction model and scheduling strategy according to the changes to ensure that the system can operate efficiently.

[0090] Improve prediction accuracy and reduce errors The system provided by the embodiment of the present invention uses advanced machine learning algorithms such as support vector machines, BP neural networks and ARMA models, so that the system can more accurately predict the operating status of the transportation chain. These predictions not only cover factors such as the number of mine cars, transportation time, and mine car time consumption, but also provide accurate basis for subsequent scheduling decisions. This high-precision prediction capability can effectively reduce the error of human estimation and avoid excessive or insufficient situations that may occur in scheduling.

[0091] Optimize resource allocation and cost control Since the system provided by the embodiment of the present invention introduces a machine learning model that can perform data processing, prediction and scheduling in real time, the system can configure transportation resources more reasonably. For example, based on the prediction model, the system can make timely adjustments when there are insufficient mine carts or mine carts are overloaded to avoid waste of resources or excessive loads during transportation. By dynamically adjusting the number of mine carts, transportation routes and transportation sequences, the system can maximize the utilization efficiency of transportation resources and achieve cost control.

[0092] Real-time monitoring and fault warning capabilities The system provided by the embodiment of the present invention can not only monitor the operating status of the coal mine transportation chain in real time, but also provide fault warnings for equipment status, transportation process, etc. based on real-time data. Once an abnormality is found (such as too long transportation time, abnormal operation status of the mine car, etc.), the system can immediately issue an alarm and propose an improved scheduling plan based on the machine learning model. This function significantly improves the safety and reliability of the system and avoids significant losses caused by equipment failure or transportation bottlenecks.

[0093] Gradual self-learning and model optimization The self-learning ability of the machine learning model introduced into the system provided by the embodiment of the present invention enables the system to continuously optimize its scheduling decisions based on historical data accumulation and feedback during long-term operation. Through continuous training of machine learning algorithms and iterative optimization of model parameters, the system can gradually improve its prediction ability and scheduling accuracy when facing more diverse operating scenarios. This learning mechanism makes the system more and more accurate, adaptable and efficient in continuous use.

[0094] Efficient data processing and decision support The data processing module in the system provided by the embodiment of the present invention performs preprocessing operations such as cleaning, feature selection and dimension reduction on the real-time monitoring data, which not only improves the quality of the data, but also improves the training speed and decision-making efficiency of the machine learning model. Through efficient data processing, the system can extract useful features from a large amount of real-time data, support the rapid generation of scheduling instructions, reduce decision-making delays, and enhance the real-time response capability of the system.

[0095] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the control device through a computer, and the program can be stored in a computer-readable storage medium. When the program is executed, it may include the processes of the above-mentioned method embodiments, wherein the storage medium may be a memory, a disk, an optical disk, etc.

[0096] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements. The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0097] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the scope defined by the claims.

Claims

1. A coal mine transportation chain intelligent scheduling system based on machine learning, characterized in that: The system comprises: a monitoring and scheduling layer, a control layer and a data storage layer; the control layer and the data storage layer are both in communication connection with the monitoring and scheduling layer; The monitoring and scheduling layer is used to obtain coal mine transportation chain data, generate prediction values ​​corresponding to the coal mine transportation chain data according to the coal mine transportation chain data; and generate corresponding scheduling instructions according to the prediction values ​​and send the scheduling instructions to the control layer; The control layer is used to complete the real-time scheduling of the coal mine transportation chain according to the scheduling instructions; The data storage layer is used to store the coal mine transportation chain data and to issue abnormal alarms by analyzing the coal mine transportation chain data; the coal mine transportation chain data includes historical coal mine transportation chain data, first real-time coal mine transportation chain data and second real-time coal mine transportation chain data; wherein the second real-time coal mine transportation chain data is the coal mine transportation chain data corresponding to the next time series of the time series corresponding to the first real-time coal mine transportation chain data.

2. The system according to claim 1, characterized in that The monitoring and scheduling layer includes: a real-time monitoring module, a machine learning model building module and a scheduling module; The real-time monitoring module is used to obtain the historical coal mine transportation chain data and the first real-time coal mine transportation chain data; and send the historical coal mine transportation chain data to the machine learning model building module, and send the first real-time coal mine transportation chain data to the scheduling module; The machine learning model building module is used to build a scheduling model based on the historical coal mine transportation chain data; the scheduling model includes a prediction model and a machine learning classification model; The scheduling module is used to generate the scheduling instruction according to the first real-time coal mine transportation chain data and the scheduling model.

3. The system according to claim 2, characterized in that The machine learning model construction module includes: a first data processing submodule, a prediction model construction submodule and a machine learning classification model construction submodule; The first data processing submodule is used to pre-process the historical coal mine transportation chain data to generate a historical sample data set, wherein the historical sample data set is data obtained by normalizing the historical coal mine transportation chain data; The prediction model construction submodule is used to construct the prediction model according to the historical sample data set and a first preset machine learning network architecture; the first preset machine learning network architecture is an ARMA model architecture or a BP neural network model architecture; The machine learning classification model construction submodule is used to construct the machine learning classification model according to the historical sample data set, the scheduling instructions corresponding to the historical sample data set and the second preset machine learning network architecture; the second preset machine learning network architecture is a machine learning classification model network architecture constructed based on the support vector machine algorithm.

4. The system according to claim 3, characterized in that The historical coal mine transportation chain data includes basic data of the coal mine transportation chain and real-time data of the coal mine transportation chain; The prediction model construction submodule uses the basic data of the coal mine transportation chain as the model boundary data; and uses the real-time data of the coal mine transportation chain as the model training data; the basic data of the coal mine transportation chain is the total number of mine cars and the total number of transportation tracks, and the real-time data of the coal mine transportation chain is the number of mine cars and the number of transportation tracks in operation at historical moments.

5. The system according to claim 3, characterized in that The scheduling module includes a second data processing submodule and a scheduling command generation submodule; The second data processing submodule is used to preprocess the first real-time coal mine transportation chain data to generate a real-time sample data set, wherein the real-time sample data set is data obtained by normalizing the first real-time coal mine transportation chain data; The scheduling command generation submodule is used to generate a first real-time coal mine transportation chain data prediction value based on the real-time sample data set; and, based on the first real-time coal mine transportation chain data prediction value, generate the scheduling instruction and send the scheduling instruction to the control layer, the first real-time coal mine transportation chain data prediction value is the coal mine transportation chain data prediction value corresponding to the next time series of the time series corresponding to the first real-time coal mine transportation chain data.

6. The system according to claim 5, characterized in that The data storage layer includes an abnormal alarm module; The abnormal alarm module is used to determine whether an abnormality occurs in the coal mine transportation chain according to the second real-time coal mine transportation chain data and the predicted value of the first real-time coal mine transportation chain data, and to issue an alarm.

7. The system according to claim 6, characterized in that The abnormal alarm module includes a third data processing submodule, an alarm signal generating submodule and an alarm signal displaying submodule; The third data processing submodule is used to pre-process the first real-time coal mine transportation chain data prediction value to generate a second real-time coal mine transportation chain data prediction value, wherein the second real-time coal mine transportation chain data prediction value is data obtained by denormalizing the first real-time coal mine transportation chain data prediction value; The alarm signal generation submodule is used to generate abnormal alarm information according to the second real-time coal mine transportation chain data, the second real-time coal mine transportation chain data prediction value and a preset threshold; The alarm signal display submodule is used to display and / or broadcast the abnormal alarm information.

8. The system according to claim 7, characterized in that The data storage layer includes a data storage module; The data storage module is used to store the historical coal mine transportation chain data, the first real-time coal mine transportation chain data, the second real-time coal mine transportation chain data, the first real-time coal mine transportation chain data predicted value and the second real-time coal mine transportation chain data predicted value.

9. The system according to claim 8, characterized in that The data storage module is also used to protect the data security of the historical coal mine transportation chain data, the first real-time coal mine transportation chain data, the second real-time coal mine transportation chain data, the first real-time coal mine transportation chain data predicted value and the second real-time coal mine transportation chain data predicted value; and to trace the data sources of the historical coal mine transportation chain data, the first real-time coal mine transportation chain data, the second real-time coal mine transportation chain data, the first real-time coal mine transportation chain data predicted value and the second real-time coal mine transportation chain data predicted value.

10. The system according to claim 9, characterized in that The data storage module also includes a data security and trusted tracing submodule; The data security and trusted traceability submodule is used to construct a blockchain data storage architecture; and to generate a unique traceability code corresponding to the historical coal mine transportation chain data, the first real-time coal mine transportation chain data, the second real-time coal mine transportation chain data, the first real-time coal mine transportation chain data predicted value and the second real-time coal mine transportation chain data predicted value.

Images