Open-pit mine production management and control optimization system based on full-life-cycle management concept

Abstract

The invention discloses a strip mine production management and control optimization system based on a full life cycle management idea, and belongs to the technical field of mine production management, and the system comprises the steps: collecting geological exploration data, production plan data and equipment state data, and carrying out the integration to generate production management and control data; the method comprises the following steps: preprocessing production management and control data to obtain production management and control processing data; a model is constructed by using big data analysis and a machine learning algorithm, and a scientific basis is provided for decision making; the ore grade prediction is obtained, the mining priority of each mining area is determined in combination with the market demands and mining costs of different ores, and the dynamic adjustment of the mine production plan is realized; the mining operation including the equipment state, the work progress and the safety condition is comprehensively monitored by adopting the Internet of Things technology, and an early warning prompt is sent out in time to respond to the abnormal condition; and performing environmental influence evaluation on each stage of the mine life cycle by calculating an environmental damage index, making and executing a reclamation plan, and promoting ecological restoration of the mining area.

Description

Technical Field

[0001] The present invention relates to the technical field of mine production management, and particularly to an open-pit mine production control and optimization system based on the concept of full life cycle management. Background Art

[0002] The production management of open-pit mines is a complex systematic project, involving multiple links such as geological exploration, production planning, equipment management, safety monitoring, environmental protection, and treatment and restoration. Traditional mine management systems are usually limited to the optimization of a single link and lack an overall grasp of the full life cycle, resulting in problems such as low resource utilization rate, many potential safety hazards, and great environmental impact.

[0003] In the prior art, there are still many deficiencies in the production management methods of open-pit mines, such as:

[0004] Insufficient data integration and analysis: Traditional mine management systems are not comprehensive enough in collecting and integrating geological exploration, production planning, and equipment status data, resulting in a lack of scientific basis for production control decisions;

[0005] Inaccurate prediction of ore grade: The accuracy of predicting ore grade in the prior art is not high, and it is impossible to reasonably determine the mining priorities of each mining area;

[0006] Lack of effective monitoring means: In mining operations, there is a lack of means to monitor the equipment status, work progress, and safety conditions in real time, making it difficult to detect and respond to abnormal situations in a timely manner;

[0007] Insufficient environmental impact assessment and ecological restoration: Insufficient attention is paid to the environmental impact assessment of each stage of the mine life cycle, which is not conducive to the ecological restoration of the mining area. Summary of the Invention

[0008] The purpose of the present invention is to overcome the deficiencies of the prior art and provide an open-pit mine production control and optimization system based on the concept of full life cycle management to solve the problems raised in the above background art.

[0009] The purpose of the present invention can be achieved through the following technical solutions: An open-pit mine production control and optimization system based on the concept of full life cycle management, including:

[0010] A data integration and analysis module, including a data collection unit, a data preprocessing unit, and a data analysis unit; respectively used for collecting geological exploration data, production planning data, and equipment status data, and integrating and generating production control data based on the full life cycle;

[0011] Performing preprocessing on the production control data to obtain production control processed data;

[0012] Establish a relationship prediction model between ore grade and geological factors using regression analysis; establish a fault prediction model using neural network for predicting the probability of equipment failure; based on the constructed relationship prediction model and fault prediction model, analyze the production control data of the open-pit mine to provide a scientific basis for decision-making;

[0013] Dynamic programming and optimization module, based on the relationship prediction model, uses actual geological exploration data to obtain ore grade prediction, combines the market demand for ores of different grades and the mining cost, determines the mining priority of each mining area, and realizes dynamic adjustment of the production plan of the open-pit mine;

[0014] Intelligent monitoring and management module, uses Internet of Things technology to achieve comprehensive monitoring of mining operations, including equipment status, work progress, and safety status, and issues early warning prompts in a timely manner to respond to abnormal situations;

[0015] Environmental protection and sustainable development module, obtains the entire life cycle of mine exploitation, conducts environmental impact assessment on each stage of the mine life cycle by calculating the environmental damage index, formulates and implements a reclamation plan to promote the ecological restoration of the mining area.

[0016] Preferably, the data collection unit includes:

[0017] Geological exploration data collection: Collect data on the geological structure and ore grade distribution of the mining area to provide basic geological information for mining planning;

[0018] Production plan data collection: Obtain annual, quarterly, and monthly production plan data;

[0019] Equipment status data collection: Real-time collect the operating parameters of mining equipment;

[0020] Based on the geological exploration data, production plan data, and equipment status data, integrate and generate production control data.

[0021] Preferably, the data preprocessing unit includes:

[0022] Check the quality of the collected data, identify and process missing values;

[0023] Remove duplicate data records to ensure data uniqueness;

[0024] Correct incorrect data through data verification rules, and standardize or normalize data from different sources and with different dimensions.

[0025] Preferably, the relationship prediction model specifically includes:

[0026] A relationship prediction model for predicting the relationship between ore grade and geological factors through multiple regression; among them, the expression of the relationship prediction model is:

[0027] PY = β0 + β1·YS1 + β2·YS2 +... + β n ·YS n ;

[0028] Wherein, PY is the predicted ore grade of the target ore body; YS1, YS2,..., YS n are geological factors, and n is the total number of geological factors; β0, β1, β2,..., β n are regression coefficients;

[0029] Using historical geological exploration data to train the relationship prediction model, and using the least squares method to solve the regression coefficients. The goal is to minimize the sum of squared errors. By taking the partial derivatives of the sum of squared errors with respect to β0, β1, β2,..., β n and setting them to 0, a system of equations is obtained, and the regression coefficients are obtained by solving the system of equations;

[0030] Obtain the actual geological exploration data of each mining area as the input of the relationship prediction model, obtain the predicted ore grade of each mining area, and formulate a mining plan for each mining area.

[0031] Preferably, the fault prediction model specifically includes:

[0032] Based on the equipment status data, a fault prediction model is constructed using a multi-layer perceptron. This model consists of an input layer, multiple hidden layers, and an output layer;

[0033] Among them, the number of nodes in the input layer is set to the dimension of the equipment status data. Different characteristics of the equipment status data correspond to different nodes in the input layer, and each node receives a corresponding equipment status data characteristic as input;

[0034] By setting multiple hidden layers to enhance the non-linear expression ability of the model, the number of nodes in each hidden layer needs to be determined according to experience or experiments;

[0035] The number of nodes in the output layer is the number of label types. The label types include equipment fault categories or normal operation labels, and each node corresponds to one label type;

[0036] Input the preprocessed equipment status data into the input layer of the model. At the same time, randomly initialize the weights and biases of the model; use forward propagation to calculate layer by layer, and calculate the output of each hidden layer in turn until the last hidden layer;

[0037] Through the output layer, calculate the output of the last hidden layer, the connection weights, and the biases to obtain the input of each node in the output layer, and then obtain the output of the output layer through the activation function; among them, the output of the output layer is the fault prediction probability of each label type;

[0038] Among the outputs of the output layer, select the label type with the highest fault prediction probability as the final model prediction result;

[0039] Compare the output of the model with the true labels, and use the loss function to measure the difference between the model prediction result and the actual situation; use backpropagation to update the weights and biases of the model according to the loss function;

[0040] Repeat the above processes of forward propagation, loss function calculation, and backpropagation, and train the model through multiple iterations until the performance of the model reaches the preset standard.

[0041] Preferably, determine the mining priorities of each mining area, and the specific steps are as follows:

[0042] Input the actual geological exploration data into the relationship prediction model to obtain the ore grade predictions of each mining area;

[0043] Collect the market demand for ores of different grades, classify the ores of different grades, and determine the influence weights of ores of each grade in the market;

[0044] Combine the ore grade predictions, the influence weights of ores of each grade in the market, and the mining costs to calculate the mining priority index of each mining area;

[0045] The calculation formula is as follows:

[0046]

[0047] In the formula, PI is the mining priority index; PY is the ore grade prediction of this mining area; JZ is the influence weight of ores of this grade in the market; CB is the mining cost of this mining area;

[0048] Obtain the mining priority index PI of each mining area through calculation, sort all mining areas, and determine the mining order and priority of each mining area, so as to realize the optimal allocation of resources.

[0049] Preferably, comprehensively monitor the equipment status of the mining operation, including:

[0050] Collect real-time equipment operation data through various sensors installed on the equipment, transmit the equipment operation data to the supervision center, and display the operation status of the equipment on the visualization interface, including the equipment name, number, current operation parameter values, and operation status icons; among them, when the equipment is operating normally, the operation status icon shows green; when the equipment is operating abnormally, the operation status icon shows red;

[0051] Based on the equipment failure prediction model, input the real-time equipment operation data into the equipment failure prediction model to obtain the model failure prediction result; if the model failure prediction result is a failure type label, it is determined that the equipment operation state is abnormal, the operation state icon is displayed in red and a failure warning is automatically issued; if the model failure prediction result is a normal operation label, it is determined that the equipment operation state is normal and the operation state icon is displayed in green.

[0052] Preferably, comprehensively monitor the work progress of the mining operation, including:

[0053] According to the overall goals and task requirements of the mining operation, formulate a work plan and a task allocation plan; decompose the work tasks into specific subtasks, and clarify the responsible person, start time, end time and expected results of each subtask;

[0054] Display the work plan and task allocation on the visualization interface in the form of a Gantt chart, which is convenient for managers to view and adjust at any time;

[0055] Through the position sensor and the production sensor, obtain the actual progress data of the mining operation in real time; compare and analyze the actual progress data with the planned progress, and calculate the progress deviation value; among them, the actual progress data is measured by the actual mining depth of the open-pit mine;

[0056] The calculation formula is as follows:

[0057] JP = SJ - HJ;

[0058] In the formula, JP is the progress deviation; SJ is the actual progress data; HJ is the planned progress;

[0059] If the progress deviation JP is positive, it means that the actual progress is faster than the planned progress; if the progress deviation JP is 0, it means that the actual progress is equal to the planned progress;

[0060] If the progress deviation JP is negative, it means that the actual progress is slower than the planned progress, and a warning prompt is issued in time and measures are taken to make adjustments.

[0061] Preferably, comprehensively monitor the safety status of the mining operation, including:

[0062] Based on the precise positioning system of UWB ultra-wideband technology, real-time locate the underground operation personnel in the open-pit mine, and display the position information of the operation personnel in real time on the visualization interface, and record the activity track of the operation personnel; when it is identified that the operation personnel enter the dangerous area, the system automatically issues a sound alarm for prompt.

[0063] Preferably, the method for calculating the environmental damage index is as follows:

[0064] Obtain the entire life cycle of mine exploitation, including exploration, planning, mining, closure and reclamation; conduct environmental impact assessments for each stage of the mine life cycle, collect ecological environment indicators for each stage, and calculate the environmental damage index; among them, the ecological environment indicators include but are not limited to vegetation coverage rate, air quality index, and water oxygen content index.

[0065] The calculation formula is:

[0066]

[0067] In the formula, EDI is the environmental damage index of this stage; I i represents the i-th ecological environment indicator, i = 1, 2,..., n, where n is the total number of ecological environment indicators; w i represents the weight coefficient corresponding to the i-th ecological environment indicator;

[0068] Set an environmental damage threshold, compare the environmental damage index obtained by calculation for each stage with the environmental damage threshold. If the environmental damage index of this stage ≥ the environmental damage threshold, it indicates that the environmental damage degree of this stage is serious and urgent and effective measures need to be taken to reduce environmental pressure and improve the ecological environment; otherwise, it indicates that the environmental damage degree of this stage is within the controllable range, but continuous attention and monitoring should still be carried out to ensure the stability and sustainable development of the ecological environment.

[0069] Compared with the existing solutions, the beneficial effects achieved by the present invention are:

[0070] By incorporating the exploration, planning, mining, closure and reclamation links of the open-pit mine into a unified management system, the present invention realizes the optimized management of the entire life cycle. Through data integration and intelligent analysis, it realizes the scientific and intelligent management of the mine and improves the management efficiency.

[0071] By obtaining the prediction of ore grade and combining with the market demand and mining cost of different ores, the present invention determines the mining priority of each mining area, can realize the optimized allocation of resources, and enterprises can improve the market competitiveness of products according to the market demand, which is beneficial to enhancing the enterprise's ability to cope with market risks.

[0072] Through the Internet of Things technology, the present invention realizes the real-time monitoring and rapid response to the equipment status and safety conditions, reduces the occurrence of safety accidents and enhances safety; by evaluating and controlling the environmental impact at each stage of the mine life cycle, formulating and implementing a reclamation plan, it promotes the ecological restoration of the mining area, realizes the coordinated development of mine development and the ecological environment, and reduces the environmental impact. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] The present invention will be further described below with reference to the accompanying drawings.

[0074] Figure 1This is the module structure diagram of the open-pit mine production control and optimization system proposed by the present invention based on the concept of full life cycle management. Detailed implementation manners

[0075] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments.

[0076] Please refer to Figure 1 , the present invention is an open-pit mine production control and optimization system based on the concept of full life cycle management, including:

[0077] A data integration and analysis module, including a data collection unit, a data preprocessing unit, and a data analysis unit;

[0078] The data collection unit is used to collect geological exploration data, production plan data, and equipment status data, and integrate and generate production control data based on the full life cycle;

[0079] In some preferred implementation manners, the data collection unit includes:

[0080] Geological exploration data collection: Collect data on the geological structure of the mining area and the distribution of ore grades to provide basic geological information for mining planning;

[0081] Production plan data collection: Obtain annual, quarterly, and monthly production plan data, including but not limited to production target and mining progress arrangement;

[0082] Equipment status data collection: Real-time collect the operating parameters of mining equipment, including but not limited to vibration, temperature, pressure, and working hours;

[0083] Based on the geological exploration data, production plan data, and equipment status data, integrate and generate production control data;

[0084] The data preprocessing unit is used to preprocess the production control data to obtain production control processed data;

[0085] In some preferred implementation manners, the data preprocessing unit includes:

[0086] Check the quality of the collected data, identify and process missing values; for example, for numerical data, the mean, median, or mode can be used for filling according to the data distribution; for categorical data, the category with the highest frequency can be used for filling;

[0087] Remove duplicate data records to ensure the uniqueness of the data; for example, if the same operating parameters of the same device at the same moment are recorded multiple times in the device monitoring data, only one record is retained;

[0088] Correct the incorrect data through data verification rules, and standardize or normalize the data from different sources and with different dimensions; for example, for geological exploration data that is clearly not in line with the actual situation, such as the grade being too high or too low beyond the reasonable range, it can be corrected by comparing with historical data.

[0089] A data analysis unit for using regression analysis to establish a relationship prediction model between ore grade and geological factors; using a neural network to establish a fault prediction model for predicting the probability of equipment failure; based on the established relationship prediction model and fault prediction model, analyzing the production control data of the open-pit mine to provide a scientific basis for decision-making.

[0090] In some preferred embodiments, the relationship prediction model specifically includes:

[0091] A relationship prediction model for predicting the relationship between ore grade and geological factors through multiple regression; where the geological factors include, but are not limited to, formation thickness, ore body dip angle.

[0092] Among them, the expression of the relationship prediction model is:

[0093] PY = β0 + β1·YS1 + β2·YS2 +... + β n ·YS n ;

[0094] In the formula, PY is the prediction of the ore grade of the target ore body; YS1, YS2,..., YS n are geological factors, and n is the total number of geological factors; β0, β1, β2,..., β n are regression coefficients;

[0095] It should be noted that the ore grade refers to the content of useful components in the ore, which is an important indicator for measuring the quality of the ore and is usually expressed as a mass percentage.

[0096] Use historical geological exploration data to train the relationship prediction model, use the least squares method to solve the regression coefficients, with the goal of minimizing the sum of squared errors. By taking the partial derivatives of the sum of squared errors with respect to β0, β1, β2,..., β n and setting them to 0, a system of equations is obtained, and solving the system of equations gives the regression coefficients.

[0097] Obtain the actual geological exploration data of each mining area as the input of the relationship prediction model, get the ore grade prediction of each mining area, and formulate a mining plan for each mining area.

[0098] In some preferred embodiments, the fault prediction model specifically includes:

[0099] Based on the device status data, a fault prediction model is constructed using a multi-layer perceptron, which consists of an input layer, multiple hidden layers, and an output layer;

[0100] Among them, the number of nodes in the input layer is set to the dimension of the device status data. Different features of the device status data correspond to different nodes in the input layer, and each node receives a corresponding device status data feature as input;

[0101] By setting multiple hidden layers to enhance the non-linear expression ability of the model, the number of nodes in each hidden layer needs to be determined according to experience or experiments;

[0102] The number of nodes in the output layer is the number of label types, and the label types include device fault categories or normal operation labels. Each node corresponds to one label type;

[0103] Input the preprocessed device status data into the input layer of the model. At the same time, randomly initialize the weights and biases of the model; use forward propagation for layer-by-layer calculation, and calculate the output of each hidden layer in turn until the last hidden layer;

[0104] Through the output layer, calculate the output of the last hidden layer, the connection weights, and biases to obtain the input of each node in the output layer, and then obtain the output of the output layer through the activation function; among them, the output of the output layer is the fault prediction probability of each label type;

[0105] Select the label type with the highest fault prediction probability in the output of the output layer as the final model prediction result;

[0106] Compare the output of the model with the true label, and use the loss function to measure the difference between the model prediction result and the actual situation; use backpropagation to update the weights and biases of the model according to the loss function; among them, the above technology is an existing technology, and the specific process and calculation formula will not be elaborated here;

[0107] Repeat the above process of forward propagation, loss function calculation, and backpropagation, and train the model through multiple iterations until the performance of the model reaches the preset standard; among them, the preset standard is set according to the actual requirements for model accuracy.

[0108] The dynamic programming and optimization module, based on the relationship prediction model, uses the actual geological exploration data to obtain the ore grade prediction, combines the market demand for ores with different grades and the mining costs, determines the mining priorities of each mining area, and realizes the dynamic adjustment of the production plan of the open-pit mine;

[0109] In some preferred embodiments, the steps to determine the mining priorities of each mining area are as follows:

[0110] Input the actual geological exploration data into the relationship prediction model to obtain the ore grade prediction for each mining area;

[0111] Collect the market demand for ores of different grades, classify the ores of different grades, and determine the influence weights of ores of each grade in the market;

[0112] Combine the ore grade prediction, the influence weights of ores of each grade in the market, and the mining cost to calculate the mining priority index for each mining area;

[0113] The calculation formula is as follows:

[0114]

[0115] In the formula, PI is the mining priority index; PY is the ore grade prediction for this mining area; JZ is the influence weight of ores of this grade in the market; CB is the mining cost of this mining area;

[0116] Obtain the mining priority index PI for each mining area through calculation, sort all mining areas, determine the mining order and priority of each mining area, so as to realize the optimal allocation of resources;

[0117] It should be noted that with the change of market demand and the progress of mining technology, the influence weights of ore grades and mining costs will change. Therefore, the mining priority index should be dynamically adjusted according to specific situations to ensure the rationality and effectiveness of mining strategies.

[0118] The intelligent monitoring and management module uses Internet of Things technology to achieve comprehensive monitoring of mining operations, including equipment status, work progress, and safety status, and issues early warning prompts in a timely manner to respond to abnormal situations;

[0119] In some preferred embodiments, comprehensive monitoring of the equipment status of mining operations includes:

[0120] Collect real-time equipment operation data through various sensors installed on the equipment, transmit the equipment operation data to the supervision center, and display the operation status of the equipment on the visualization interface, including equipment name, number, current operation parameter values, and operation status icons; among them, when the equipment is operating normally, the operation status icon shows green; when the equipment is operating abnormally, the operation status icon shows red;

[0121] Based on the equipment fault prediction model, input the real-time equipment operation data into the equipment fault prediction model to obtain the model fault prediction result; if the model fault prediction result is a fault type label, it is determined that the operation status of the equipment is abnormal, the operation status icon shows red and a fault early warning is automatically issued; if the model fault prediction result is a normal operation label, it is determined that the operation status of the equipment is normal, and the operation status icon shows green;

[0122] In some preferred embodiments, the work progress of the mining operation is comprehensively monitored, including:

[0123] According to the overall objectives and task requirements of the mining operation, formulate a work plan and a task assignment plan; decompose the work tasks into specific subtasks, and clarify the responsible person, start time, end time and expected results of each subtask;

[0124] Display the work plan and task assignment on the visualization interface in the form of a Gantt chart, which is convenient for managers to view and adjust at any time;

[0125] Through position sensors and production sensors, real-time obtain the actual progress data of the mining operation; compare and analyze the actual progress data with the planned progress, and calculate the progress deviation value; among them, the actual progress data is measured by the actual mining depth of the open-pit mine;

[0126] The calculation formula is as follows:

[0127] JP = SJ - HJ;

[0128] In the formula, JP is the progress deviation; SJ is the actual progress data; HJ is the planned progress;

[0129] If the progress deviation JP is positive, it means that the actual progress is faster than the planned progress; if the progress deviation JP is 0, it means that the actual progress is equal to the planned progress;

[0130] If the progress deviation JP is negative, it means that the actual progress is slower than the planned progress, and a warning prompt is sent in time and measures are taken for adjustment;

[0131] In some preferred embodiments, the safety status of the mining operation is comprehensively monitored, including:

[0132] Based on the precise positioning system of UWB ultra-wideband technology, the underground operation personnel in the open-pit mine are real-time positioned, and the position information of the operation personnel is real-time displayed on the visualization interface, and the activity track of the operation personnel is recorded; when it is identified that the operation personnel enter the dangerous area, the system automatically issues a sound alarm for prompt; among them, the dangerous area includes, but is not limited to, unbolted roadways and high gas accumulation areas;

[0133] It should be noted that the realization of the system identifying that the operation personnel enter the dangerous area based on the precise positioning of UWB ultra-wideband technology is the prior art and will not be elaborated here;

[0134] Environmental protection and sustainable development module, obtaining the entire life cycle of mine exploitation, evaluating the environmental impacts at each stage of the mine life cycle by calculating the environmental damage index, formulating and implementing a reclamation plan to promote the ecological restoration of the mining area; among them, the reclamation plan includes but is not limited to terrain reshaping, soil improvement, vegetation restoration, and water quality restoration.

[0135] In some preferred embodiments, the method for calculating the environmental damage index is as follows:

[0136] Obtain the entire life cycle of mine exploitation, including exploration, planning, mining, closure, and reclamation; evaluate the environmental impacts at each stage of the mine life cycle, collect the ecological environment indicators at each stage, and calculate the environmental damage index; among them, the ecological environment indicators include but are not limited to vegetation coverage rate, air quality index, and water oxygen content index.

[0137] The calculation formula is:

[0138]

[0139] In the formula, EDI is the environmental damage index of this stage; I i represents the i-th ecological environment indicator, i = 1, 2,..., n, and n is the total number of ecological environment indicators; w i represents the weight coefficient corresponding to the i-th ecological environment indicator.

[0140] Set an environmental damage threshold, compare the environmental damage index obtained by calculation at each stage with the environmental damage threshold. If the environmental damage index of this stage ≥ the environmental damage threshold, it means that the environmental damage degree of this stage is serious, and urgent and effective measures need to be taken to reduce the environmental pressure and improve the ecological environment.

[0141] On the contrary, it means that the environmental damage degree of this stage is within the controllable range, but continuous attention and monitoring should still be carried out to ensure the stability and sustainable development of the ecological environment.

[0142] Among them, the environmental damage threshold is set according to the actual regional ecological environment carrying capacity and environmental protection regulations.

[0143] In several embodiments provided by the present invention, it should be understood that the disclosed system can be implemented in other ways. For example, the above-described invention embodiments are merely illustrative. For example, the division of modules is only a logical function division, and there can be other division methods in actual implementation.

[0144] The modules described as separation fittings may or may not be physically separated. The fittings shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0145] In addition, in each embodiment of the present invention, the functional modules may be integrated in a processing unit, may exist separately as individual physical units, or two or more units may be integrated in one unit. The above integrated units may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0146] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms.

[0147] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An open-pit mine production control and optimization system based on the concept of full life cycle management, characterized in that, Including: A data integration and analysis module, including a data collection unit, a data preprocessing unit, and a data analysis unit; They are respectively used to collect geological exploration data, production plan data, and equipment status data, and integrate and generate production control data based on the entire life cycle; Perform preprocessing on the production control data to obtain production control processed data; Use regression analysis to establish a relationship prediction model between ore grade and geological factors; use neural network to establish a fault prediction model for predicting the probability of equipment failure; based on the constructed relationship prediction model and fault prediction model, analyze the production control data of the open-pit mine to provide a scientific basis for decision-making; A dynamic programming and optimization module, based on the relationship prediction model, uses actual geological exploration data to obtain ore grade prediction, combines the market demand for ores with different grades and the mining cost, determines the mining priority of each mining area, and realizes dynamic adjustment of the production plan of the open-pit mine; An intelligent monitoring and management module, which uses Internet of Things technology to achieve comprehensive monitoring of mining operations, including equipment status, work progress, and safety status, and issues early warning prompts in a timely manner to respond to abnormal situations; An environmental protection and sustainable development module, obtains the entire life cycle of mine exploitation, conducts environmental impact assessment on each stage of the mine life cycle by calculating the environmental damage index, formulates and implements a reclamation plan to promote the ecological restoration of the mining area.

2. The optimized open-pit mine production control and management system based on the concept of full life cycle management according to claim 1, characterized in that The data collection unit includes: Geological exploration data collection: Collect data on the geological structure of the mining area and the distribution of ore grades to provide basic geological information for mining planning; Production plan data collection: Obtain annual, quarterly, and monthly production plan data; Equipment status data collection: Real-time collect the operating parameters of mining equipment; Based on the geological exploration data, production plan data, and equipment status data, integrate and generate production control data.

3. The optimized open-pit mine production control system based on the concept of full life cycle management according to claim 2, characterized in that, The data preprocessing unit includes: Check the quality of the collected data, identify and process missing values; Remove duplicate data records to ensure data uniqueness; Correct incorrect data through data verification rules, and standardize or normalize data from different sources and with different dimensions.

4. The optimized open-pit mine production control system based on the concept of full life cycle management according to claim 3, characterized in that, The described relationship prediction model specifically includes: A relationship prediction model for predicting the relationship between ore grade and geological factors through multiple regression; among them, the expression of the relationship prediction model is: PY = β0 + β1·YS1 + β2·YS2 +... + β n ·YS n ; where PY is the prediction of the ore grade of the target ore body; YS1, YS2,..., YS n are geological factors, and n is the total number of geological factors; β0, β1, β2,..., β n are regression coefficients; Training the relationship prediction model using historical geological exploration data, solving the regression coefficients using the least squares method, with the goal of minimizing the sum of squared errors. By taking the partial derivatives of the sum of squared errors with respect to β0, β1, β2,..., β n taking the partial derivatives and setting them to 0 to obtain a system of equations, and solving the system of equations to obtain the regression coefficients; Obtain the actual geological exploration data of each mining area as the input of the relationship prediction model, obtain the ore grade prediction of each mining area, and formulate a mining plan for each mining area.

5. The open-pit mine production control and optimization system based on the concept of full life cycle management according to claim 4, characterized in that The described fault prediction model specifically includes: Based on the equipment status data, use a multi-layer perceptron to construct a fault prediction model, which consists of an input layer, multiple hidden layers, and an output layer; Among them, the number of nodes in the input layer is set to the dimension of the equipment status data. Different characteristics of the equipment status data correspond to different nodes in the input layer, and each node receives a corresponding equipment status data characteristic as input; Set multiple hidden layers to enhance the non-linear expression ability of the model. The number of nodes in each hidden layer needs to be determined according to experience or experiments; The number of nodes in the output layer is the number of label types, where the label types include equipment failure categories or normal operation labels, and each node corresponds to one label type; Input the preprocessed equipment status data into the input layer of the model. At the same time, randomly initialize the weights and biases of the model; use forward propagation to perform layer-by-layer calculations, and successively calculate the outputs of each hidden layer until the last hidden layer; Through the output layer, calculate the output of the last hidden layer, connection weights, and biases to obtain the input of each node in the output layer, and then obtain the output of the output layer through the activation function; among them, the output of the output layer is the failure prediction probability of each label type; Select the label type with the highest failure prediction probability in the output of the output layer as the final model prediction result; Compare the output of the model with the true label, and use the loss function to measure the difference between the model prediction result and the true situation; use backpropagation to update the weights and biases of the model according to the loss function; Repeat the above processes of forward propagation, loss function calculation, and backpropagation, and train the model iteratively multiple times until the performance of the model reaches the preset standard.

6. The open-pit mine production control and optimization system based on the concept of full life cycle management according to claim 5, characterized in that, Determine the mining priorities of each mining area, and the specific steps are as follows: Input the actual geological exploration data into the relationship prediction model to obtain the ore grade prediction of each mining area; Collect the market demand for ores of different grades, classify the ores of different grades, and determine the influence weights of ores of each grade in the market; Combine the ore grade prediction, the influence weights of ores of each grade in the market, and the mining cost to calculate the mining priority index of each mining area; The calculation formula is as follows: In the formula, PI is the mining priority index; PY is the ore grade prediction of this mining area; JZ is the influence weight of ores of this grade in the market; CB is the mining cost of this mining area; Obtain the mining priority index PI of each mining area through calculation, sort all mining areas, determine the mining order and priority of each mining area, so as to achieve the optimal allocation of resources.

7. The optimized open-pit mine production control system based on the concept of full life cycle management according to claim 6, characterized in that Comprehensively monitor the equipment status of mining operations, including: Collect real-time equipment operation data through various sensors installed on the equipment, transmit the equipment operation data to the supervision center, and display the operation status of the equipment on the visualization interface, including equipment name, number, current operation parameter values, and operation status icons; among them, when the equipment is operating normally, the operation status icon shows green; when the equipment is operating abnormally, the operation status icon shows red; Based on the equipment failure prediction model, input the real-time equipment operation data into the equipment failure prediction model to obtain the model failure prediction result; if the model failure prediction result is a failure type label, it is determined that the equipment is operating abnormally, the operation status icon shows red and a failure warning is automatically issued; if the model failure prediction result is a normal operation label, it is determined that the equipment is operating normally, and the operation status icon shows green.

8. The optimized open-pit mine production control system based on the concept of full life cycle management according to claim 7, characterized in that, Comprehensively monitor the work progress of mining operations, including: According to the overall objectives and task requirements of the mining operation, formulate a work plan and task allocation plan; decompose the work tasks into specific subtasks, and clarify the responsible person, start time, end time and expected results of each subtask; Display the work plan and task allocation on the visualization interface in the form of a Gantt chart, which is convenient for management personnel to view and adjust at any time; Through position sensors and production sensors, obtain the actual progress data of the mining operation in real time; compare and analyze the actual progress data with the planned progress, and calculate the progress deviation value; among them, the actual progress data is measured by the actual mining depth of the open-pit mine; The calculation formula is as follows: JP = SJ - HJ; In the formula, JP is the progress deviation; SJ is the actual progress data; HJ is the planned progress; If the progress deviation JP is positive, it means that the actual progress is faster than the planned progress; if the progress deviation JP is 0, it means that the actual progress is equal to the planned progress; If the progress deviation JP is negative, it means that the actual progress is slower than the planned progress, and an early warning prompt will be issued in time and measures will be taken to adjust.

9. The optimized open-pit mine production control system based on the concept of full life cycle management according to claim 8, characterized in that, Comprehensively monitor the safety status of the mining operation, including: Based on the precise positioning system of UWB ultra-wideband technology, real-time position the underground operation personnel in the open-pit mine, and display the position information of the operation personnel on the visualization interface in real time, and record the activity track of the operation personnel; when it is identified that the operation personnel enter the dangerous area, the system will automatically issue an audible alarm for prompt.

10. The optimized open-pit mine production control system based on the concept of full life cycle management according to claim 8, characterized in that, The method for calculating the environmental damage index is as follows: Obtain the entire life cycle of mine exploitation, including exploration, planning, exploitation, pit closure and reclamation; conduct environmental impact assessments on each stage of the mine life cycle, collect ecological environment indicators for each stage, and calculate the environmental damage index; among them, the ecological environment indicators include but are not limited to vegetation coverage rate, air quality index, and water oxygen content index; The calculation formula is: where EDI is the environmental damage index at this stage; I i represents the i-th ecological environment index, i = 1, 2,..., n, where n is the total number of ecological environment indexes; w i represents the weight coefficient corresponding to the i-th ecological environment index; Set an environmental damage threshold, compare the environmental damage index obtained by calculation for each stage with the environmental damage threshold. If the environmental damage index of this stage ≥ the environmental damage threshold, it means that the environmental damage degree of this stage is serious, and urgent and effective measures need to be taken to reduce the environmental pressure and improve the ecological environment; otherwise, it means that the environmental damage degree of this stage is within the controllable range, but continuous attention and monitoring should still be carried out to ensure the stability and sustainable development of the ecological environment.

Images