A method for cost statistics based on the balance of mine energy loss

Abstract

The present invention relates to the technical field of mine energy loss cost statistics, and in particular to a method for cost statistics based on mine energy loss balance. A variety of sensors are deployed in mine equipment and areas to collect data, which is processed through anomaly detection, interpolation supplementation, and classified storage; an energy consumption model is constructed by integrating equipment power, load, and environmental factors, and electricity, fuel, and total energy costs are calculated accordingly and the proportions are analyzed; genetic algorithms, particle swarm algorithms, and LSTM models are used to optimize equipment parameters and energy distribution paths respectively, and predict energy demand and costs; a visualization interface is developed to display energy consumption and cost data, and a decision-making report is generated and pushed to management personnel; the actual and predicted data are regularly compared, and equipment, process, and market information are collected to optimize the energy loss and cost accounting models and algorithms; this method realizes refined energy management, improves utilization efficiency, reduces costs, provides scientific decision-making support for mine energy management, and enhances the system's adaptability and sustainability.

Description

Technical Field

[0001] The present invention relates to the technical field of mine energy loss cost statistics, and specifically to a method for cost statistics based on mine energy loss balance. Background Art

[0002] Mine energy management plays a crucial role in mine production, which is directly related to the production efficiency, cost control and sustainable development of enterprises. With the continuous progress of industrialization, the demand for energy in mine enterprises shows an increasing trend, and the proportion of energy cost in the total mine cost is also increasing day by day. In this context, realizing refined energy management, improving energy utilization efficiency and reducing costs have become important issues that mine enterprises urgently need to solve.

[0003] In the process of mine production, there are many factors affecting energy consumption, among which the problems in aspects such as equipment operation status, production process and external environment are particularly prominent. Some mine equipment is severely aged, with low operation efficiency and high energy consumption, which undoubtedly increases the energy cost burden of enterprises. At the same time, the irrationality of the production process also leads to energy waste. For example, some process flow designs are not optimized enough, resulting in unscientific distribution and utilization of energy in each link. In addition, the mine production environment is complex and changeable, and environmental factors such as temperature, humidity and altitude have an unignorable impact on equipment energy consumption. For example, a high-temperature environment may make it difficult for equipment to dissipate heat, thus increasing energy consumption; in high-altitude areas, the air is thin, and the operation resistance of equipment increases, which also leads to an increase in energy consumption.

[0004] Traditional mine energy management models are often relatively extensive, and mainly have the following deficiencies: First, there is a lack of accurate monitoring and analysis means for energy consumption. Traditional methods can mostly only conduct simple total statistics on energy consumption, and cannot deeply analyze the specific energy consumption of each equipment, each process link and different energy types, making it difficult to accurately grasp the key nodes and main influencing factors of energy consumption, and thus unable to provide accurate data support for the formulation of energy-saving and consumption-reducing measures. Second, the energy management decision-making lacks scientificity and timeliness. Due to the lack of comprehensive and accurate data basis, managers often make decisions based on experience when formulating energy management decisions, making it difficult to achieve scientific decision-making. Moreover, the traditional model cannot timely reflect the real-time changes in energy consumption and cost, resulting in lagged decision-making and being unable to timely respond to sudden problems and market changes during the production process. Third, it is difficult to adapt to the dynamic changes of mine production. During the mine production process, situations such as equipment failures, process adjustments and market energy price fluctuations occur from time to time. The traditional energy management model lacks flexibility and adaptability, and cannot effectively respond and adjust to these changes in a timely manner, thus affecting the energy utilization efficiency and economic benefits of mine enterprises.

[0005] In view of the many drawbacks of the traditional mine energy management mode, there is an urgent need for a more scientific and efficient energy management method to achieve refined management of mine energy, optimize energy utilization, reduce costs, and enhance the scientific nature and timeliness of decision-making, thereby enhancing the competitiveness of mine enterprises in the market and promoting the sustainable development of the mine industry. Therefore, in response to the above problems, a cost statistics method based on mine energy loss balance is proposed. Summary of the Invention

[0006] The purpose of the present invention is to provide a cost statistics method based on mine energy loss balance to solve the problems raised in the above background technology.

[0007] To achieve the above purpose, the present invention provides the following technical solutions:

[0008] A cost statistics method based on mine energy loss balance includes the following steps:

[0009] Step S1, data collection and transmission: Install intelligent electricity meters as power monitors at the electrical equipment of the mine, set fuel flow meters on fuel consumption equipment and equip them with fuel level sensors, deploy temperature sensors, humidity sensors, pressure sensors in the mine area, and install operating state sensors on the equipment, and transmit the data collected by all sensors to the data processing center through wired and wireless networks;

[0010] Step S2: Data preprocessing and storage: In the data processing center, use anomaly detection methods to eliminate abnormal data points according to data statistical laws and equipment operation logics, use interpolation algorithms to supplement missing data, and classify and store data in a relational database and a distributed file system according to equipment type, production process links, energy type, and time dimension;

[0011] Step S3: Energy loss model construction: For each piece of equipment in the mine, construct an equipment energy consumption model by comprehensively considering the power characteristics of the equipment, load impact, and environmental factors; analyze the mine production process flow, and construct a process flow energy consumption model based on the accumulation of equipment energy consumption and auxiliary energy consumption in each link; obtain the energy loss cost by subtracting the effective output energy consumption from the total mine energy input, and establish an energy loss decomposition model according to equipment, process flow links, and energy types;

[0012] Step S4: Cost accounting: Calculate the electricity cost according to the electricity price calculation method of the power company and the data of the power monitor, calculate the fuel cost according to the fuel flow meter data and the fuel unit price, summarize the total mine energy cost and analyze the proportion of each energy cost;

[0013] Step S5: Optimization Analysis: Use the genetic algorithm to optimize the equipment operation parameters with the lowest energy consumption cost per unit product and the highest energy utilization efficiency as the optimization objectives; use the particle swarm optimization algorithm to optimize the energy distribution path with the minimum energy loss as the optimization objective; use the LSTM time series prediction model combined with production planning information to predict the energy demand and cost under different future production plans and market conditions.

[0014] Step S6: Visualization and Decision Support: Develop a visualization interface to display equipment energy consumption, process energy consumption, and energy cost data; automatically generate an energy management decision support report based on the cost accounting and optimization analysis results and push it to the mine management personnel.

[0015] Step S7: Feedback and Continuous Optimization: Regularly collect actual energy consumption, cost, and equipment operation data and compare them with the system prediction results, collect information on equipment failures, production process adjustments, and market energy price fluctuations, and optimize and adjust the energy loss model, cost accounting model, and optimization algorithm based on the comparison and collected information.

[0016] As a preferred solution, the anomaly detection method is an anomaly detection method based on principle, that is, for the data sequence , calculate its mean and standard deviation , if or , then it is determined as abnormal data and excluded; the interpolation algorithm is the cubic spline interpolation algorithm.

[0017] As a preferred solution, the construction method of the equipment energy consumption model is: Let the equipment power characteristic function be , the load influence function be , the environmental influence correction function be , then the equipment energy consumption model Among them, is the time variable, is the load variable, is the environmental variable vector, represents the energy consumption of the equipment under , and conditions, and the environmental variable vector includes temperature, humidity, pressure, and altitude; the construction method of the process energy consumption model is: Let the energy consumption of the th equipment in the process be , and the auxiliary energy consumption be , then the process energy consumption model , represents the total energy consumption of the process, represents the number of equipment in the process.

[0018] As a preferred solution, the calculation method of electricity cost is as follows: Let the unit price of electricity be , the total electricity consumption be , and the electricity cost be . When the electricity pricing method includes basic electricity charges , peak-valley electricity charges, and power factor adjustment electricity charges , among which, the peak-valley electricity charges include the unit price during the peak period, the electricity consumption during the peak period, the unit price during the valley period, the electricity consumption during the valley period, the unit price during the normal period, and the electricity consumption during the normal period. The electricity cost is . The calculation method of fuel cost is as follows: Let the unit price of fuel be , the total fuel consumption be , and the fuel cost be . The total energy cost is calculated as , where is the cost of other energy sources.

[0019] As a preferred solution, the application method of the genetic algorithm is as follows: The encoding of equipment operation parameters adopts binary encoding or real number encoding. A fitness function is constructed with the lowest energy consumption cost per unit product and the highest energy utilization efficiency as the optimization objectives , where and are weight coefficients, is the energy consumption cost per unit product, is the energy utilization efficiency. Through roulette wheel selection operation , single-point crossover operation or multi-point crossover operation, and basic bit mutation operation, the optimal combination of equipment operation parameters is iteratively searched according to a predetermined number of iterations. Among them, is the probability that the individual is selected, and is the population size.

[0020] As a preferred solution, the application method of the particle swarm optimization algorithm is as follows: The encoding of the energy distribution path is the particle position in the particle swarm optimization algorithm. With the minimum energy loss as the optimization objective, the particle velocity update formula is , and the particle position update formula is , where and are the velocities of the particle at the -th and -th iterations respectively, is the inertia weight, and are learning factors, and is a random number between is the individual optimal position of particle at the -th iteration, is the global optimal position of the swarm at the -th iteration, and are the positions of particle at the -th and -th iterations respectively. Initialize the positions and velocities of the particle swarm, and set the inertia weight , learning factors and .

[0021] As an optimal solution, the application method of the LSTM time series prediction model is as follows: Using historical energy cost data, production data, and influencing factor data as input variables. Before inputting into the model, production planning information including planned extraction volume planned ore dressing volume , planned equipment operation duration is normalized. Let the input gate of the LSTM cell at time be , where is the input gate weight matrix, is the output of the hidden layer at the previous time, is the input at the current time, is the input gate bias vector, is the sigmoid function, the forget gate , where is the forget gate weight matrix, is the forget gate bias vector, the output gate , where is the output gate weight matrix, is the output gate bias vector, the candidate memory cell , where is the candidate memory cell weight matrix, is the candidate memory cell bias vector, the memory cell , where represents element-wise multiplication, the output of the hidden layer . By learning and training the historical data, adjust the weights and biases of the LSTM cell, and combine the production planning information to predict the energy demand and cost under different future production plans and market conditions.

[0022] ​As a preferred solution, the visualization interface display forms include bar charts, line charts, and pie charts; the decision support report push methods include email, mobile phone text messages, or internal system message push.

[0023] As can be seen from the technical solution provided by the present invention above, a method for cost statistics based on mine energy loss balance provided by the present invention has the beneficial effects as follows:

[0024] 1. Achieve refined energy management:

[0025] Multi-type sensors comprehensively collect data, covering information such as power equipment, fuel consumption equipment, mine area environment, and equipment operation status, making mine energy management no longer extensive; whether it is the real-time monitoring of power consumption, the precise control of fuel use, or the consideration of the impact of environmental factors on equipment energy consumption, it provides an all-round perspective for mine energy management; this helps to accurately locate the key links and main factors of energy consumption, for example, determining which equipment is a major energy consumer and which process links have energy-saving potential, thus providing detailed data support for formulating targeted energy-saving measures;

[0026] Classify and store data and construct multiple energy models, including equipment energy consumption models, process energy consumption models, and energy loss decomposition models, to deeply analyze the details of energy consumption and loss in mine production; based on the cost accounting and analysis of these models, the proportion of each energy cost can be accurately obtained, enabling enterprises to clearly understand the contribution of different energies to the total cost, and then optimizing energy procurement and use strategies to achieve refined energy management from the whole to the part, from macro to micro, and effectively improve energy utilization efficiency;

[0027] 2. Optimize energy utilization and reduce costs:

[0028] The genetic algorithm optimizes the equipment operation parameters with the goal of the lowest energy consumption cost per unit product and the highest energy utilization efficiency, which can directly act on the equipment operation level; by adjusting key parameters such as the working frequency, power setting, and operation time of the equipment, the equipment operates in the best state, reducing unnecessary energy waste and lowering the energy consumption cost per unit product; for example, without affecting production efficiency, reasonably reducing the equipment power or optimizing the operation time can significantly reduce power consumption, thereby reducing energy costs;

[0029] The particle swarm optimization algorithm optimizes the energy distribution path, aiming to minimize energy loss; in the complex energy supply network of the mine, find the optimal energy distribution method to ensure the minimum loss of energy during transmission and distribution; this avoids energy waste caused by unreasonable energy distribution, improves energy transmission efficiency, and indirectly reduces energy costs;

[0030] The LSTM time series prediction model combines production planning information to provide enterprises with forecasts of energy demand and costs under different future production plans and market conditions. Based on this, enterprises can plan energy procurement and production arrangements in advance, avoid cost increases caused by insufficient or excessive energy supply, and make reasonable procurement decisions when energy market prices fluctuate, reducing procurement costs and achieving dynamic optimization of energy costs.

[0031] 3. Improve the scientificity and timeliness of decision-making:

[0032] The visualization interface presents complex data in an intuitive chart form, such as using bar charts to show equipment energy consumption comparisons, line charts to present energy consumption trends, and pie charts to analyze the energy cost structure, etc., enabling mine managers to quickly understand the energy consumption and cost situation and clearly see key information at a glance. This helps managers quickly detect abnormal situations, such as a sudden increase in the energy consumption of a certain device or an abnormal change in the proportion of a certain energy cost, and thus take timely measures.

[0033] The automatically generated energy management decision support report, based on comprehensive cost accounting and in-depth optimization analysis results, provides managers with systematic and detailed decision-making basis. The report not only includes a detailed analysis of the current energy management situation but also includes predictions of future trends and optimization suggestions, enabling managers to consider multiple factors when making decisions and avoid blind decisions. Timely pushing of the report ensures that managers can obtain the latest information in a timely manner and quickly make scientific and reasonable decisions, such as adjusting production plans, optimizing equipment maintenance strategies, and formulating energy procurement plans, effectively improving the overall operation and management efficiency of the mine.

[0034] 4. Enhance the adaptability and sustainability of the system:

[0035] Regularly collecting the comparison between actual data and system prediction results and gathering various relevant information can timely detect problems and deficiencies in the system. Whether it is abnormal energy consumption caused by equipment failures, changes in energy consumption due to production process adjustments, or the impact of market energy price fluctuations on costs, all can be timely captured by this feedback mechanism.

[0036] Optimizing and adjusting the energy loss model, cost accounting model, and optimization algorithm according to the feedback information enables the system to continuously adapt to various dynamic changes in the mine production process. This ensures that the system always maintains high accuracy and effectiveness and can continuously provide reliable support for mine energy management. With the development of mine production and the changes in the external environment, the system can continuously evolve, long-term helping mine enterprises achieve the goals of efficient energy utilization, effective cost control, and sustainable development, and maintaining an advantage in the long-term market competition. Description of the Drawings

[0037] Figure 1 Schematic diagram of the method flow for cost statistics based on the balance of mine energy loss in the present invention. Specific embodiments

[0038] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0039] In order to better understand the above technical solutions, the above technical solutions will be described in detail below in conjunction with the specification drawings and specific embodiments.

[0040] As Figure 1 shown, an embodiment of the present invention provides a method for cost statistics based on the balance of mine energy loss, including the following steps:

[0041] Step S1, data collection and transmission: Install intelligent electricity meters as power monitors at the power equipment in the mine, set up fuel flow meters on the fuel consumption equipment and equip them with fuel level sensors, deploy temperature sensors, humidity sensors, pressure sensors in the mine area, and install operating state sensors on the equipment, and transmit the data collected by all sensors to the data processing center through wired and wireless networks; specifically including the following steps:

[0042] Step S1-1: Operations related to data collection of power equipment and fuel consumption equipment:

[0043] Preparation for data collection of power equipment:

[0044] On various power equipment in the mine, select a suitable location to install intelligent electricity meters to ensure that they can accurately measure parameters such as voltage, current, and power of the power equipment; after installation, debug and calibrate the intelligent electricity meters to make them work properly and the measurement accuracy meets the requirements;

[0045] Install fuel flow meters on the fuel supply pipelines of fuel consumption equipment (such as transport vehicles, fuel boilers, etc.), and install fuel level sensors on the fuel storage containers (fuel tanks); after installation, also perform debugging and calibration to ensure that the sensors can accurately measure fuel flow and liquid level changes;

[0046] Equipment connection and data transmission settings:

[0047] Connect the intelligent electricity meters to the mine internal network through appropriate communication cables (such as Ethernet cables or specific industrial communication cables), configure their data transmission parameters, including transmission frequency (such as set to transmit data every 5 minutes) and data format (such as using the industrial standard Modbus format), to ensure that the power data can be accurately and timely transmitted to the data processing center;

[0048] Connect the fuel flowmeter and the liquid level sensor to the data acquisition module, and the data acquisition module converts the analog signals collected by the sensors into digital signals; then, according to the network environment of the mine, select an appropriate transmission method (such as the wired RS-485 bus or the wireless GPRS network) to transmit the data to the data processing center; at the same time, set corresponding receiving programs and storage paths in the data processing center to preliminarily process and store the received power and fuel data;

[0049] Step S1-2: Data acquisition and transmission operation of the mine area environment and equipment operating status:

[0050] Sensor deployment and installation:

[0051] In the mine area, according to the environmental monitoring requirements and regional characteristics, reasonably distribute environmental sensors such as temperature sensors, humidity sensors, and pressure sensors; for example, install them at key positions such as different working areas, ventilation outlets, and equipment machine rooms in the mining area to ensure that the overall environmental conditions of the mine can be accurately reflected; at the same time, install operating status sensors on various types of equipment in the mine, such as vibration sensors, rotational speed sensors, and digital input / output sensors, etc., to comprehensively monitor the operating status of the equipment. Ensure that the sensors are firmly installed and do not affect the normal operation of the equipment during installation;

[0052] Data transmission and processing preparation:

[0053] Connect the environmental sensors and the equipment operating status sensors to the data acquisition nodes. The data acquisition nodes can be distributed data collectors or microprocessors integrated inside the sensors; these nodes are responsible for collecting sensor data and transmitting the data to the data processing center through pre-set wired (such as laying communication cables) or wireless networks (such as Wi-Fi, ZigBee, etc., select an appropriate frequency band according to the actual situation and configure the communication protocol to avoid interference);

[0054] In the data processing center, establish a classification storage mechanism for environmental data and equipment operating status data. According to information such as sensor type, location, and collection time, accurately store the data into the corresponding database tables to provide a reliable data basis for subsequent in-depth analysis and decision-making; at the same time, set up data integrity and accuracy check programs to ensure that the received data is complete and error-free. If any abnormality is found, send an alarm to notify relevant personnel for handling;

[0055] Step S2: Data Preprocessing and Storage: At the data processing center, an anomaly detection method is used to eliminate abnormal data points based on data statistical laws and equipment operation logic. For missing data, an interpolation algorithm is used for supplementation. The data is classified and stored in a relational database and a distributed file system according to equipment type, production process link, energy type, and time dimension. The specific steps are as follows:

[0056] Step S2-1: Data Anomaly Detection and Processing:

[0057] Anomaly Detection Method Selection and Parameter Calculation:

[0058] Adopt an anomaly detection method based on principle; for each data sequence (such as the power data sequence of electrical equipment, fuel consumption data sequence, etc.), first calculate its mean value and standard deviation ; when calculating the mean value, add up all the data values in the data sequence and then divide by the number of data points; when calculating the standard deviation, according to the mathematical formula of the standard deviation, first calculate the square of the difference between each data point and the mean value, add up these squared differences and then divide by the number of data points minus 1, and then take the square root of the result;

[0059] Set the anomaly judgment threshold; according to principle, if the data point or , then determine that this data point is abnormal data; here, the mean value and standard deviation are calculated for the currently processed data sequence;

[0060] Elimination of Abnormal Data:

[0061] Traverse each data point in the data sequence and compare it with the calculated anomaly judgment threshold; if the data point meets the anomaly condition, that is, xi < μ - 3σ or xi > μ + 3σ, then eliminate this abnormal data point from the data sequence; when eliminating the abnormal data point, record the position of the abnormal data point (such as the timestamp or the serial number in the data sequence) and related information (such as the equipment type it belongs to, data type, etc.) for subsequent analysis of the anomaly cause;

[0062] Recording and Analysis of Abnormal Data (Optional):

[0063] Store the eliminated abnormal data points and their related information in a special abnormal data record table; conduct a preliminary analysis of the abnormal data to judge the possible causes of the anomaly, such as sensor failure, sudden abnormal operation of the equipment, external interference, etc.; if the number of abnormal data is large or the abnormal situation is relatively serious, it may be necessary to promptly notify the relevant maintenance personnel to check and repair the equipment or sensors to ensure the accuracy of subsequent data;

[0064] Step S2-2: Missing data processing:

[0065] Missing data identification:

[0066] In the data sequence, identify the positions with missing data by checking the continuity of the timestamps or serial numbers of the data points; for example, if the data sequence is arranged in chronological order and it is found that there are missing data points within a certain time period, it is determined that there are missing data within that time period; at the same time, record the range of the missing data (start time and end time or start serial number and end serial number) as well as the data type and device to which it belongs;

[0067] Interpolation algorithm selection and application:

[0068] Select the cubic spline interpolation algorithm to supplement the missing data; for the interval with missing data, calculate the estimated values of the missing data points according to the existing data points before and after the interval using the cubic spline interpolation formula; the cubic spline interpolation algorithm constructs a piecewise cubic polynomial function, making the function and its first and second derivatives continuous within each piecewise interval, so as to reasonably estimate the missing data while ensuring the smoothness of the data;

[0069] Fill the estimated values of the calculated missing data points into the corresponding missing positions in the original data sequence to obtain a complete data sequence; during the filling process, ensure that the time order or logical order of the data is correct and consistent with other relevant data;

[0070] Step S2-3: Data classification and storage:

[0071] Data classification rule formulation:

[0072] Formulate data classification rules according to equipment type, production process links, energy type, and time dimension; for example, equipment types can be divided into mining equipment, transportation equipment, ore dressing equipment, etc.; production process links can include mining, crushing, grinding, flotation, etc.; energy types can be divided into electricity, fuel, coal, etc.; the time dimension can be divided according to different time granularities such as day, week, month, year, etc.;

[0073] Relational database storage structure design:

[0074] Design the table structure of the relational database according to the data classification rules; create different tables to store different types of data. For example, create a device operation data table containing fields such as device ID (associated with device type), timestamp, operation parameters (such as power, rotation speed, etc.); create an energy consumption data table containing fields such as energy type, consumption time, consumption quantity, etc.; create a production process data table containing fields such as process step name, time period, relevant parameters (such as output, quality index, etc.). Ensure the relevance and integrity of the data by establishing appropriate primary key and foreign key relationships, facilitating data query and analysis;

[0075] Distributed file system storage configuration:

[0076] For some large-scale, unstructured or semi-structured data (such as backups of raw sensor acquisition data, detailed logs of device operation status, etc.), select a suitable distributed file system (such as Hadoop Distributed File System HDFS) for storage; in the distributed file system, create a corresponding folder structure to correspond to the data classification. For example, create different folders according to device type, and then create sub-folders according to the time dimension under each device type folder, and store the data files belonging to the device type and time range in the corresponding folders. At the same time, configure relevant parameters of the distributed file system, such as data block size, number of replicas, etc., to ensure the reliability and efficiency of data storage;

[0077] Data storage and index establishment:

[0078] Store the complete data after exception handling and missing data supplementation into the relational database and the distributed file system respectively according to the classification rules; in the relational database, use SQL statements or database management tools to insert the data into the corresponding tables; in the distributed file system, use file upload operations to store the data files in the specified location. At the same time, in order to improve data query efficiency, establish appropriate indexes for commonly used query fields (such as device ID, timestamp, etc.) in the relational database, so as to quickly locate and obtain the required data during subsequent data query and analysis;

[0079] Step S3: Energy loss model construction: For each device in the mine, construct a device energy consumption model by comprehensively considering the device power characteristics, load impact, and environmental factors; analyze the mine production process flow, and construct a process flow energy consumption model based on the accumulation of device energy consumption and auxiliary energy consumption in each link; obtain the energy loss cost by subtracting the effective output energy consumption from the total mine energy input, and establish an energy loss decomposition model according to the device, process flow link, and energy type. The specific operation steps are as follows:

[0080] Step S3-1: Device energy consumption model construction:

[0081] Determination of the device power characteristic function:

[0082] For each device in the mine, analyze its power characteristics; determine the device power characteristic function through the technical data provided by the device manufacturer, the monitoring and analysis of device test data or actual operation data (where, is the power of the device at time Power is used to represent the work done per unit time and reflects the rate at which the device consumes electrical energy or other energy and converts it into other forms of energy; is a time variable used to describe different moments during the operation of the device. It is a dimension of the change in the device operation state. By analyzing the power at different time points, the dynamic change of the device power during the entire operation cycle can be understood; is a function of time used to describe the change law of the device power with time. Different types of devices have different change laws of power with time, and the specific form may be a linear function, a polynomial function, an exponential function, etc., which need to be determined according to the actual characteristics of the device);

[0083] During the process of determining the power characteristic function, the influence of different working modes of the device (such as startup, normal operation, standby, etc.) on the power should be considered, and the power characteristic sub-functions in different working modes should be established separately or in the form of a piecewise function to accurately describe the change of the device power with time;

[0084] Analysis of the load influence function:

[0085] Study the influence of the device load on energy consumption and determine the load influence function (where, is the degree to which the device energy consumption is affected by the load, indicating the change ratio or multiple relationship of the device energy consumption relative to the reference state (such as no-load or rated load, etc.) under different load conditions; is the load variable, which can be the throughput of the device (such as ore throughput, transportation volume, etc.), the working intensity (such as the load rate of the motor), etc., parameters related to the load. The load variable directly affects the working load of the device, and thus affects the device energy consumption. The energy conversion efficiency and loss conditions inside the device are different under different load levels; is a function of the load variable used to describe the quantitative relationship between the load and the degree of energy consumption influence. For some devices, the energy consumption may have a simple linear relationship with the load, but for many actual devices, this relationship may be more complex, possibly a quadratic function relationship or other non-linear relationships, which depends on the physical characteristics and working principles of the device and needs to be determined through experimental tests and data analysis to determine the specific function form);

[0086] Derivation of the environmental impact correction function:

[0087] Considering the influence of environmental factors (such as temperature, humidity, pressure, altitude, etc.) on the energy consumption of equipment, an environmental impact correction function is established (wherein, is the correction coefficient of environmental factors on the energy consumption of equipment, which is used to adjust the energy consumption calculation of equipment under different environmental conditions to more accurately reflect the actual energy consumption situation; is the environmental variable vector, which includes environmental parameters such as temperature, humidity, pressure, altitude, etc. These environmental factors will affect the energy consumption of equipment through various ways such as affecting the heat dissipation performance of equipment, air density (which in turn affects the running resistance of equipment, etc.), and insulation performance of electrical equipment; is a function about the environmental variable vector used to describe the relationship between environmental factors and the energy consumption correction coefficient. Different environmental factors have different degrees and ways of influencing energy consumption. Therefore, the specific form of is relatively complex and may be a multivariate function of multiple environmental variables. Its function expression is determined through a large amount of experimental data and theoretical analysis);

[0088] Integration of the equipment energy consumption model:

[0089] Integrate the above-determined equipment power characteristic function, load influence function, and environmental impact correction function into the equipment energy consumption model , wherein, is the energy consumption of the equipment at time , with a load of and environmental conditions of . It represents the total energy consumed by the equipment under specific operating conditions and is a comprehensive measure of the energy consumption of the equipment over a period of time. Through integral calculation, it takes into account the influence of power variation over time as well as load and environmental factors;

[0090] Step S3-2: Construction of the energy consumption model for the technological process:

[0091] Analysis of the technological process and calculation of equipment energy consumption:

[0092] Analyze the production technological process of the mine in detail and divide it into multiple clear technological links (such as mining, transportation, crushing, grinding, flotation, dehydration, etc.); for each technological link, determine the list of equipment involved;

[0093] According to the established equipment energy consumption model, calculate the energy consumption of each equipment in the technological process; for each equipment, obtain relevant data such as the running time, load change situation, and environmental conditions during the technological process, and substitute them into the equipment energy consumption model to calculate the energy consumption of the equipment under specific technological links (wherein, is the energy consumption of the th device in the process flow, which reflects the energy consumed by the device to perform its specific tasks in the entire process flow and is an important indicator for evaluating the energy utilization efficiency and cost of each device in the process flow; represents the device serial number in the process flow, where, is the number of devices in the process flow. By traversing different device serial numbers, the energy consumption of all devices in the entire process flow can be calculated and summarized);

[0094] Auxiliary energy consumption determination:

[0095] Identify and calculate the auxiliary energy consumption in the process flow where, is the auxiliary energy consumption in the process flow, such as lighting electricity consumption, ventilation system energy consumption, equipment preheating energy consumption, etc. Although these auxiliary energy consumptions do not directly participate in the production process of the product, they are essential for maintaining the normal operation of the entire process flow and need to be considered when calculating the total energy consumption to comprehensively evaluate the energy consumption of the process flow);

[0096] Process flow energy consumption model establishment:

[0097] Accumulate the energy consumption of each device link and add the auxiliary energy consumption to construct a process flow energy consumption model where, is the total energy consumption of the entire process flow, which is the sum of all energy consumptions from raw material input to final product output in the entire process flow, including the energy consumption of each device and the energy consumption of the auxiliary system. It is a key parameter for measuring the energy utilization efficiency and cost of the process flow and provides a total energy consumption data basis for optimizing the process flow and reducing energy consumption, represents the number of devices in the process flow);

[0098] Step S3-3: Construction of energy loss decomposition model:

[0099] Obtaining energy input and effective output data:

[0100] Determine the total energy input sources of the mine (such as the total power supply, total fuel procurement, input quantities of other energies such as coal), and obtain accurate energy input data through corresponding monitoring devices (such as electricity meters, flow meters, etc.); at the same time, determine the form of effective output energy (such as the energy content of qualified ore products, electricity output to the outside) and its corresponding quantity or energy value during the mine production process;

[0101] Let the total power input be (where, $E_{total}$ is the total electrical energy obtained by the mine from the external power grid, which is monitored in real time and cumulatively measured by an electricity meter installed at the power access point, and is one of the basic data for calculating power costs and energy losses);

[0102] The total fuel input is (where, Measured by a flow meter installed at the fuel storage tank or refueling point, it reflects the total amount of fuel purchased and used by the mine within a certain period, and is used to calculate fuel costs and evaluate the contribution of fuel in energy consumption);

[0103] The input of other energy is (where, Used to comprehensively count the energy input of the mine, covering various energy forms used in the mine production process);

[0104] For the effective output energy, let the energy content of qualified mineral products be (where, Depending on the quality of the mineral products (such as ore grade) and production volume, it is calculated by analyzing the physical and chemical properties of the mineral products and production statistics, combined with the energy conversion formula, and represents the useful energy contained in the final products during the mine production process);

[0105] The externally output electricity is (where, If the mine has excess electricity to output externally (such as the electricity generated by power generation equipment and fed into the grid), the output electricity is measured by an electricity meter. This part of the output electricity can be regarded as an effective part of the mine's energy utilization and needs to be deducted from the total energy input when calculating energy losses);

[0106] Calculation of energy loss cost:

[0107] The energy loss cost is obtained by subtracting the effective output energy consumption from the total energy input of the mine; according to the market price of energy (such as electricity unit price, fuel unit price, etc.), the energy value of energy loss is converted into a cost value;

[0108] Let the electricity unit price be (where, Determined by the power supplier according to factors such as market supply and demand relationship and power generation cost, and is used to calculate the contribution of electricity in power costs and energy loss costs);

[0109] The fuel unit price is (where, Varies according to the fluctuations in the fuel market price, and is a key parameter for calculating fuel costs and evaluating fuel energy loss costs);

[0110] The unit price of other energy is (where, for calculating the cost of the corresponding energy and the loss cost);

[0111] The power loss amount is (where represents the net power loss amount during the production process of the mine, that is, the part of the input power that is not converted into effective output (such as product energy or exported power));

[0112] The power loss cost is (where is obtained by multiplying the unit price of electricity by the power loss amount, reflecting the economic cost caused by power loss);

[0113] The fuel loss amount is (where is the total fuel input minus the actually effectively utilized fuel amount during the production process, resulting in the fuel loss amount; is the effectively utilized fuel amount);

[0114] The fuel loss cost is (where the calculation method is similar to the power loss cost, used to measure the economic loss caused by fuel loss);

[0115] The loss cost of other energy (where the loss cost of each other energy is obtained by multiplying the unit price of the corresponding energy by the loss amount);

[0116] The total energy loss cost (where the loss costs of electricity, fuel, and other energy are added together to obtain the total energy loss cost of the mine, comprehensively reflecting the energy utilization efficiency and economic cost situation during the mine production process);

[0117] Establishment of the energy loss decomposition model:

[0118] Establish an energy loss decomposition model according to equipment, technological process links, and energy types; for the energy loss decomposition at the equipment level, calculate the proportion of each equipment in the energy loss based on the energy consumption model and actual operation data of each equipment; at the technological process link level, determine the energy loss contribution of each process link according to the technological process energy consumption model; for the energy type level, calculate the proportion of different energies such as electricity, fuel, and coal in the total energy loss respectively;

[0119] Let the equipment have a proportion in the energy loss of (where by calculating the equipment obtained from the ratio of the energy consumption to the total energy loss, which is used to analyze the relative importance of each device in energy loss, identify the devices with relatively large energy losses, and thus take targeted energy-saving measures);

[0120] Process step The contribution of energy loss to (where determined by the ratio of the energy consumption of the process step to the total energy loss, which is used to evaluate the proportion of different process steps in energy loss and provide a basis for optimizing the process flow and reducing energy loss);

[0121] Energy type The proportion in the total energy loss is (where obtained by calculating the ratio of the loss amount of the energy type to the total energy loss amount, which is used to analyze the contribution of different energy types in energy loss and helps to formulate reasonable energy management strategies, such as optimizing the energy structure, etc.);

[0122] Step S4: Cost accounting: Calculate the electricity cost based on the electricity charge pricing method of the power company and the data of the power monitor, calculate the fuel cost according to the data of the fuel flowmeter and the fuel unit price, and summarize to obtain the total energy cost of the mine and analyze the proportion of each energy cost; The specific steps are as follows:

[0123] Step S4-1: Electricity cost accounting:

[0124] Analysis of electricity pricing method and data acquisition:

[0125] Obtain relevant information on the electricity charge pricing method from the power company, determine whether it includes pricing items such as basic electricity charge, peak-valley electricity charge, and power factor adjustment electricity charge, and the specific pricing rules for each item;

[0126] Obtain the electricity consumption data from the power monitor, including the electricity consumption in different time periods (peak period, valley period, normal period); Ensure the accuracy and integrity of the power monitor data, and if there is data missing or abnormal, conduct a timely investigation and repair;

[0127] Electricity cost calculation (single pricing method):

[0128] If the electricity pricing method is only a single unit price pricing, let the electricity unit price be ( represents the price per unit of electricity), and the total electricity consumption is ( represents the total electricity consumption of the mine within a certain period), then the electricity cost ( Indicates the mine power cost calculated according to the single unit price pricing method);

[0129] If the power pricing method includes the basic electricity charge , peak-valley electricity charge, and power factor adjustment electricity charge When:

[0130] Calculation of peak-valley electricity charge: Let the unit price during the peak period be ( Indicates the price per unit of electricity during the peak period), and the electricity consumption during the peak period is ; The unit price during the valley period is ( Indicates the price per unit of electricity during the valley period), and the electricity consumption during the valley period is ; The unit price during the normal period is ( Indicates the price per unit of electricity during the normal period), and the electricity consumption during the normal period is ; Then the peak-valley electricity charge

[0131] ( Indicates the peak-valley electricity charge part calculated according to the unit prices and electricity consumptions in different peak-valley periods);

[0132] Power factor adjustment electricity charge ( Indicates the power factor adjustment cost generated due to factors such as power factor. The specific calculation method varies according to local regulations and power company regulations and is usually related to factors such as power factor and electricity consumption) is determined according to the power factor adjustment coefficient and calculation method provided by the power company;

[0133] Power cost ;

[0134] Step S4-2: Fuel cost accounting:

[0135] Fuel data collection and unit price determination:

[0136] Obtain the total fuel consumption data through the fuel flowmeter ( Indicates the total amount of fuel consumed by the mine within a certain period), and ensure that the flowmeter measurement is accurate and the data transmission is normal;

[0137] Determine the fuel unit price ( Indicates the price per unit of fuel), and the fuel unit price can be determined according to the market purchase price or the contract price signed with the supplier. Consider price fluctuation factors and, if necessary, update the unit price data regularly;

[0138] Fuel cost calculation:

[0139] Fuel cost ( (indicating the cost generated by the fuel consumption in the mine);

[0140] Step S4-3: Aggregation and analysis of the total energy cost:

[0141] Calculation of the total energy cost:

[0142] Calculate the total energy cost of the mine (where is the cost of other energy sources such as coal and natural gas, and the calculation method is similar to that of electricity and fuel costs, which is calculated according to the unit price and total consumption of the corresponding energy source, (indicating the total cost of all energy consumed in the mine));

[0143] Analysis of the proportion of each energy cost:

[0144] Calculate the proportion of the electricity cost ( (indicating the proportion of the electricity cost in the total energy cost));

[0145] Calculate the proportion of the fuel cost ( (indicating the proportion of the fuel cost in the total energy cost));

[0146] Calculate the proportion of other energy costs (Calculate the proportion for each other energy source separately, indicating the proportion of the

[0147] th other energy cost in the total energy cost));

[0148] By analyzing the proportion of each energy cost, understand the energy consumption structure of the mine, find out the energy types with relatively high cost proportions, and provide a basis for energy management and cost control; for example, if the proportion of the electricity cost is too high, measures such as optimizing the operation mode of electrical equipment, adopting energy-saving equipment, or exploring the utilization of renewable energy can be considered to reduce the electricity cost;

[0149] Step S5-1: Optimize the equipment operation parameters using the genetic algorithm:

[0150] Determine the decision variables and coding method:

[0151] Analyze the key operating parameters that affect the energy consumption and energy utilization efficiency of the equipment, such as the working frequency, power setting, operating time, etc. of the equipment, and determine these parameters as decision variables;

[0152] Select a suitable coding method according to the characteristics of the decision variables, such as binary coding or real number coding; Binary coding is suitable for discrete decision variables. Divide the value range of each decision variable into several intervals and represent each interval with a binary number; Real number coding directly uses real numbers to represent the values of decision variables and is suitable for continuous decision variables. In this method, a suitable coding method can be selected according to the actual nature of the equipment operating parameters. The equipment operating parameter coding adopts binary coding or real number coding method (where binary coding converts the parameter value into a binary digital string, which is convenient for genetic operations in the genetic algorithm; real number coding directly uses the actual numerical value of the parameter for operations, and can represent the parameter more accurately in some cases);

[0153] Construct a fitness function:

[0154] Construct a fitness function with the lowest energy consumption cost per unit product and the highest energy utilization efficiency as the optimization objectives (where, is the fitness function value, which is used to evaluate the quality of an individual (i.e., a set of equipment operating parameter combinations); and are weight coefficients, which are used to balance the importance of the energy consumption cost per unit product and the energy utilization efficiency in the optimization objectives, and can be set according to the actual situation of the mine and management priorities, represents the weight of the energy consumption cost per unit product in the fitness function, represents the weight of the energy utilization efficiency in the fitness function; is the energy consumption cost per unit product, which is an important indicator to measure the economic operation of the equipment; is the energy utilization efficiency, which reflects the effective utilization degree of energy by the equipment);

[0155] Initialize the population:

[0156] Randomly generate an initial population according to the coding method and value range of the decision variables; The population size is determined according to the complexity of the problem and computing resources, generally ranging from dozens to hundreds; Each individual represents a set of equipment operating parameter combinations, and the individuals in the initial population should be as evenly distributed as possible in the solution space to increase the possibility of finding the global optimal solution;

[0157] Genetic operations:

[0158] Selection operation: Adopt roulette wheel selection operation (where, is the individual the probability of being selected, For an individual 's fitness function value, by calculating the ratio of the fitness function value of each individual to the sum of the fitness function values of all individuals in the population, the probability of an individual being selected is determined. The higher the fitness, the greater the probability of being selected, so that excellent individuals have more opportunities to participate in subsequent genetic operations);

[0159] Crossover operation: Select single-point crossover operation or multi-point crossover operation; for binary coding, the single-point crossover operation randomly selects a crossover point in the coding strings of two parent individuals, and exchanges the genes after the crossover point to generate two new offspring individuals; the multi-point crossover operation selects multiple crossover points for gene exchange; for real-number coding, the crossover operation can generate offspring individuals by weighted averaging the decision variables of two parent individuals; the crossover probability Generally ranges from 0.6 to 0.9, controlling the frequency of the crossover operation. An appropriate crossover probability helps to introduce new gene combinations in the population and increase the diversity of solutions;

[0160] Mutation operation: Adopt basic bit mutation operation; for binary coding, randomly select some bits in the individual coding string for inversion operation (i.e., 0 becomes 1, 1 becomes 0); for real-number coding, randomly perturb the value of one or some decision variables within the value range of the decision variables; the mutation probability Is generally small, ranging from 0.001 to 0.1. The mutation operation is mainly used to prevent the algorithm from falling into a local optimal solution. By introducing a small amount of random mutation, the algorithm has the opportunity to jump out of the local optimal region and explore a wider solution space;

[0161] Iterative optimization:

[0162] Perform iterative search according to the predetermined number of iterations; in each iteration, perform selection, crossover, and mutation operations in sequence to generate a new population, and then calculate the fitness function value of each individual in the new population; as the iteration progresses, the individuals in the population gradually evolve towards the optimal solution, and the fitness function value continuously increases; when the predetermined number of iterations is reached or other termination conditions are met (such as the change in the fitness function value for several consecutive generations is less than the set threshold), stop the iteration and output the optimal equipment operation parameter combination, which is the parameter setting that makes the equipment performance reach a better state under the current optimization goal;

[0163] Step S5-2: Optimize the energy distribution path using the particle swarm optimization algorithm:

[0164] Coding and initialization:

[0165] Encode the energy distribution path as the particle position in the particle swarm optimization algorithm (where the particle position represents the distribution ratio or distribution method of energy among different devices, technological processes, or energy storage facilities, and through encoding, the actual energy distribution path is converted into a numerical form that can be processed by the algorithm);

[0166] Randomly initialize the positions and velocities of the particle swarm; the size M of the particle swarm is determined according to the problem size and computing resources, and is generally similar to the population size in the genetic algorithm; the position vector of each particle represents a possible energy distribution path, and the velocity vector determines the moving direction and speed of the particle in the search space; during initialization, the positions and velocities are randomly generated within a reasonable value range to ensure that the particles have a certain degree of dispersion in the solution space to cover more possible solutions;

[0167] Determine the optimization objective and fitness function:

[0168] Take the minimum energy loss as the optimization objective and construct a fitness function; the fitness function value is directly related to the energy loss amount, and the smaller the energy loss, the smaller the fitness function value (the specific function form can be determined according to the calculation method and model of the energy loss. For example, the energy loss amount can be directly used as the fitness function value, or through some transformations, the fitness function is made more easily processed and convergent during the optimization process);

[0169] Set the algorithm parameters:

[0170] Set the inertia weight 、learning factors and ; the inertia weight controls the influence degree of the particle's previous velocity on the current velocity, generally taking values between 0 and 1. A larger is beneficial to global search, and a smaller is beneficial to local search; the learning factors and respectively determine the influence degrees of the particle's own optimal position and the global optimal position on the particle velocity update. Usually around, and they jointly guide the particle to move towards the optimal solution direction in the search space;

[0171] Iteratively update the particle state:

[0172] According to the particle velocity update formula

[0173] ,

[0174] where, and are the velocities of the particle at the th and th iterations respectively, is the inertia weight, and are the learning factors, and is a random number between is the individual optimal position of particle at the -th iteration, is the global optimal position of the swarm at the -th iteration, and are the positions of particle at the -th and -th iterations respectively;

[0175] For each particle, calculate the fitness function value corresponding to its new position and compare it with the individual historical optimal fitness value and the swarm historical optimal fitness value; if the fitness value of the new position is better, update the individual optimal position and the swarm optimal position (if the fitness value of the current position of the particle is less than its individual historical optimal fitness value, update the current position to the individual optimal position; if the fitness value of the current position of the particle is less than the swarm historical optimal fitness value, update the current position to the swarm optimal position);

[0176] Termination condition judgment:

[0177] Repeat step 4 until the termination condition is met; the termination condition can be reaching the predetermined maximum number of iterations, or the swarm optimal fitness value has no obvious improvement in consecutive several iterations (i.e., the change is less than the set threshold); when the termination condition is met, output the swarm optimal position, and the energy allocation path corresponding to this position is the optimized energy allocation scheme, which can minimize or approach the minimum state of energy loss;

[0178] Step S5-3: Use the LSTM time series prediction model to predict energy demand and cost:

[0179] Data preparation and preprocessing:

[0180] Collect historical energy cost data, production data (such as production volume, equipment operation time, processing volume, etc.) and influencing factor data (such as market energy price fluctuations, seasonal factors, production process adjustments, etc.) as input variables (where historical energy cost data is used to reflect the relationship between past energy consumption and cost and is the basis for predicting future costs; production data is closely related to energy consumption, and by analyzing the historical relationship between production data and energy cost, the influence law of production activities on energy demand and cost can be explored; influencing factor data covers potential influencing factors of external environment and internal production changes on energy cost, which helps to improve the accuracy of prediction);

[0181] Before the input model, normalize the production planning information (including planned extraction volume , planned beneficiation volume , planned equipment operation duration , etc.); normalization is to map data of different magnitudes to a specific interval, such as the [0,1] or [-1,1] interval, with the aim of eliminating the influence of the dimension between data, enabling the model to converge more stably and quickly during training, and improving the prediction performance of the model);

[0182] Construct the LSTM model structure:

[0183] Determine the structure of the input layer, hidden layer, and output layer of the LSTM model; the number of input layer nodes is determined according to the number of input variables, and each input variable corresponds to an input node; the hidden layer can be set with one or more layers, and the number of hidden layer nodes is determined through experiments or experience, generally between dozens and hundreds. The hidden layer is used to extract features and patterns in the data; the number of output layer nodes is determined according to the prediction target. In this method, if predicting energy demand and cost simultaneously, the output layer can be set with two nodes to respectively output the predicted value of energy demand and the predicted value of cost (where the LSTM cell plays a key role in memorizing and processing time series information in the model. Through the gating mechanism, it controls the forgetting, updating, and output of information, thereby being able to effectively process data with time series characteristics);

[0184] Model parameter initialization:

[0185] Initialize the weight matrix and bias vector of the LSTM cell; including the input gate weight matrix , the forget gate weight matrix , the output gate weight matrix , the candidate memory cell weight matrix and the corresponding bias vectors , , , (These weight matrices and bias vectors are important parameters in the LSTM model. They determine the processing method and learning ability of the model for input data. The selection of the initial values will affect the training effect and convergence speed of the model. Usually, a random initialization method is adopted, and these parameters are continuously adjusted through the backpropagation algorithm during training to enable the model to better fit the data);

[0186] Model training:

[0187] Divide the historical data into a training set and a validation set. The training set is used for learning the model parameters, and the validation set is used to evaluate the performance of the model and prevent overfitting;

[0188] For each sample in the training set, input the data step by step in time, and calculate the input gate of the LSTM cell at time input gate where is the value of the input gate, which determines how much of the input information at the current time can enter the memory cell, is the sigmoid function that compresses the calculation result between 0 and 1, is the weight matrix of the input gate, is the output of the hidden layer at the previous time, is the input at the current time, is the bias vector of the input gate), forget gate ( is the weight matrix of the forget gate, is the bias vector of the forget gate), output gate (the output gate determines how much of the information in the memory cell can be output to the hidden layer at the current time, is the weight matrix of the output gate, is the bias vector of the output gate), candidate memory cell (the candidate memory cell is used to generate new information that needs to be updated to the memory cell at the current time, is the weight matrix of the candidate memory cell, is the bias vector of the candidate memory cell), and then update the memory cell (where represents element-wise multiplication, and the memory cell integrates the forgetting of the information in the memory cell at the previous time and the update of the new information at the current time), and finally calculate the output of the hidden layer ;

[0189] According to the error between the predicted output and the actual output (such as mean squared error MSE or mean absolute error MAE, etc.), use the backpropagation algorithm to calculate the gradient, and update the weight matrix and bias vector of the LSTM cell through gradient descent or other optimization algorithms (such as Adam optimization algorithm); during the training process, continuously adjust the model parameters to gradually reduce the error until the predetermined training stop condition is reached (such as the number of training epochs reaches the set value, the error of the validation set no longer decreases, or the minimum error threshold is reached, etc.);

[0190] Model prediction and evaluation:

[0191] Using the trained LSTM model and combining with the production planning information (which has been normalized), predict the energy demand and cost under different future production plans and market conditions; compare and evaluate the prediction results with the actual data (if there is some future actual data for comparison) or the results of other benchmark prediction methods. The evaluation metrics can include Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), etc., to measure the accuracy and reliability of the model prediction; according to the evaluation results, if the model performance is not ideal, the model structure, parameters can be further adjusted or the data volume can be increased, etc. to improve the model and enhance the prediction accuracy, providing a more valuable reference basis for the energy management and production decision-making of the mine;

[0192] Step S6: Visualization and Decision Support: Develop a visualization interface to display equipment energy consumption, energy consumption of the process flow, and energy cost data; automatically generate an energy management decision support report based on the cost accounting and optimization analysis results and push it to the mine management personnel. The specific steps are as follows:

[0193] Step S6-1: Visualization Interface Development and Data Display:

[0194] Select visualization tools and technologies:

[0195] According to the actual needs and technical environment of the mine, select appropriate visualization tools or development frameworks, such as libraries like Matplotlib, Seaborn, Plotly in Python, or use professional commercial visualization software (such as Tableau, PowerBI, etc.); these tools provide rich chart types and interactive functions, capable of meeting the visualization display requirements of different data;

[0196] Data connection and acquisition:

[0197] Establish a connection between the visualization interface and the data storage system (such as a relational database, a distributed file system, etc.), and obtain relevant data such as equipment energy consumption, energy consumption of the process flow, and energy cost from the data storage system (ensure the real-time or timeliness of the data, set a reasonable data acquisition mechanism according to the data update frequency, for example, query the latest data from the database regularly);

[0198] Chart design and layout:

[0199] Design appropriate chart types according to data characteristics and analysis purposes; for equipment energy consumption data, bar charts can be used to show the energy consumption comparison of different equipment over a period of time, or line charts can be used to display the change trend of the energy consumption of a single equipment over time; the energy consumption of the process flow can be presented by combining a flow chart with energy consumption data annotation to visually show the energy consumption distribution of each process link; energy cost data is suitable for using pie charts to show the proportion of different energy costs in the total cost, or bar charts to compare the changes in energy costs in different time periods;

[0200] Design the layout of the visualization interface, reasonably arrange different charts on the interface, and ensure that the information is clear and easy to understand; elements such as titles, axis labels, legends, etc. can be added to enhance the readability of the charts; at the same time, consider setting interactive functions, such as mouse hovering to display data details, zooming and panning the charts to view different time periods or data ranges, etc., to facilitate data exploration and analysis by mine management personnel;

[0201] Data visualization implementation:

[0202] Use the selected visualization tool to visually display the obtained data according to the designed chart types and layouts; according to the time dimension of the data (such as daily, weekly, monthly, yearly, etc.) and classification dimensions such as equipment and process links, aggregate, group, and transform the data to meet the display requirements of different charts; for example, summarize the daily equipment energy consumption data into monthly data for drawing monthly energy consumption trend charts;

[0203] Optimize the visualization effect, adjust visual elements such as colors, fonts, line styles, etc., to make the charts beautiful and conform to the visual norms of mining enterprises; ensure that the charts can be normally displayed on different devices (such as computer monitors, tablets, mobile phones, etc.) and have good readability to facilitate management personnel to view data anytime and anywhere;

[0204] Step S6-2: Generation and push of decision support reports:

[0205] Report template design:

[0206] Design an energy management decision support report template according to the content and format requirements of the cost accounting and optimization analysis results; the report template should include parts such as a cover, table of contents, abstract, detailed analysis content, conclusions and suggestions, etc.; in the detailed analysis content, cover the cost accounting results (such as details of each energy cost, total cost change trend, etc.), optimization analysis results (such as comparison before and after optimization of equipment operation parameters, optimization effect of energy distribution paths, future energy demand and cost forecasts, etc.), and visually display them in combination with charts and data;

[0207] Report content generation:

[0208] Extract relevant data for cost accounting and optimization analysis from the data storage system, and fill the data into the corresponding chapters and charts according to the format requirements of the report template; automatically generate the text description part, such as summarizing the reasons for cost changes, the implementation effects of optimization measures, the analysis of future energy trends, etc. The text description should be concise, clear, and logical, and be able to accurately convey key information;

[0209] Add data interpretation and analysis to the report to help mine managers understand the meaning and potential problems behind the data; for example, compare the energy consumption of different equipment with the industry average level, analyze the impact of changes in the proportion of energy costs on the enterprise's profit, etc., and provide in-depth information required for decision-making for managers;

[0210] Report push settings:

[0211] Determine the way and frequency of report push, such as choosing methods like email, SMS, or internal system message push (select a suitable push method according to the work habits of mine managers and the convenience of information acquisition to ensure that the report can be delivered to managers in a timely manner); set the push time, for example, push the energy management report of the previous week on Monday morning every week, or push the detailed analysis report of the previous month at the beginning of each month, so that managers can regularly obtain the latest energy management information;

[0212] Configure the push system to ensure that the report can be accurately sent to the specified manager's account or device; for email push, set the email subject, body format, and attachments (such as PDF or Excel format files of the report); for SMS push, control the SMS length and highlight key information; for internal system message push, ensure that the message is displayed prominently in the mine management system and provide a convenient link to view the full text of the report;

[0213] Report feedback and improvement:

[0214] Collect feedback from mine managers on the report, understand their satisfaction with the report content, format, and push method, as well as their needs for further improvement; according to the feedback, optimize and adjust the report template, generated content, and push settings, and continuously improve the quality and practicality of the decision support report to better serve the energy management decision-making process of the mine; for example, if managers hope to add specific analysis dimensions or chart types to the report, modify the report generation system in a timely manner to meet user needs;

[0215] Step S7: Feedback and continuous optimization: Regularly collect actual energy consumption, costs, and equipment operation data for comparison with the system prediction results, collect information on equipment failures, production process adjustments, and market energy price fluctuations, and optimize and adjust the energy loss model, cost accounting model, and optimization algorithm based on the comparison and collected information. The specific steps are as follows:

[0216] Step S7-1: Data collection and comparison:

[0217] Regular data collection:

[0218] Set a fixed data collection period, such as weekly, monthly or quarterly, and determine a suitable period according to the actual situation of mine production and the data change frequency (the collection period should be able to timely reflect the dynamic changes of energy consumption and equipment operation, and will not increase unnecessary workload and system burden due to too frequent data collection); within each collection period, obtain the actual energy consumption, cost and equipment operation data from various monitoring devices in the mine (such as smart meters, fuel flow meters, sensors, etc.) and the cost accounting system to ensure the accuracy and integrity of the data (conduct a preliminary quality inspection on the collected data, such as checking the rationality and integrity of the data, eliminating obvious error or missing data points, and for a small amount of missing data, appropriate interpolation methods can be used for supplementation);

[0219] Comparison with the prediction results:

[0220] Extract the prediction results in aspects such as energy consumption, cost and equipment operation for the corresponding period from the system (these prediction results are generated by the prediction models in the previous steps, such as the prediction of energy demand and cost by the LSTM time series prediction model, and the energy consumption prediction after optimizing the equipment operation parameters based on the optimization algorithm, etc.); compare the actual collected data with the prediction results one by one, and calculate the deviation values of each item of data, such as absolute deviation, relative deviation, etc. (absolute deviation = actual value - predicted value, relative deviation = (actual value - predicted value) / predicted value × 100%, through the calculation of the deviation value, the deviation degree between the prediction result and the actual situation can be intuitively understood); analyze the reasons for the deviation, which may include the limitations of the prediction model, the external environment changes not being fully considered (such as sudden market energy price fluctuations, abnormal climate conditions affecting equipment operation efficiency, etc.), equipment aging or failures resulting in abnormal increase in energy consumption, etc. (the analysis of the reasons for the deviation needs to comprehensively consider multiple factors and conduct in-depth exploration in combination with the actual situation of mine production and the equipment operation status);

[0221] Step S7-2: Information collection:

[0222] Collection of equipment failure information:

[0223] Establish a mechanism for equipment failure monitoring and reporting. Through the built-in fault diagnosis system of the equipment (if any), feedback from on-site operators, and regular equipment inspection records, obtain equipment failure information in a timely manner (the equipment failure information should include details such as the time of failure, equipment name, failure type, and severity of the failure to accurately analyze the impact of the failure on energy consumption and production); classify and organize equipment failures, count the occurrence frequency and impact scope of different types of failures, and analyze the relationship between failures and increased energy consumption (for example, the failure of some key equipment may lead to the stagnation or inefficient operation of the entire production process, thus significantly increasing energy consumption. Analyzing this relationship can provide a targeted basis for subsequent optimization and adjustment).

[0224] Collection of production process adjustment information:

[0225] Maintain close communication with the mine production department to obtain relevant information on production process adjustments in a timely manner, such as improvements in the production process, introduction of new equipment or new technologies, changes in production tasks, etc. (Understand the background, purpose, and specific implementation content of the production process adjustment, as well as the changes in the production process and equipment operation mode before and after the adjustment); record the time nodes of the production process adjustment and analyze its impact on energy consumption, cost, and equipment operation (The production process adjustment may change the load characteristics of the equipment, the energy demand structure, and production efficiency, thereby affecting energy loss and cost accounting. It is necessary to accurately evaluate these impacts to consider the process adjustment factors in model optimization).

[0226] Collection of market energy price fluctuation information:

[0227] Pay attention to the dynamics of the energy market. Through subscribing to energy price information platforms, maintaining contact with energy suppliers, or referring to industry reports, etc., collect market energy price fluctuation information (Obtain price change data of the main energy sources used in the mine, such as electricity, fuel, coal, etc., including the amplitude of price increase or decrease, time period, and price trend prediction, etc.); analyze the direct and indirect impacts of market energy price fluctuations on the mine's energy costs (such as price fluctuations may prompt the mine to adjust its energy procurement strategy, optimize its energy use structure, and thus affect equipment operation parameters and production process arrangements), and provide a basis for market price factors for the optimization of the cost accounting model.

[0228] Step S7-3: Optimization and adjustment of the model and algorithm:

[0229] Optimization of the energy loss model:

[0230] Optimize and adjust the energy loss model based on the data comparison results and the information collected; if it is found that the deviation between the actual energy loss and the model prediction is large and mainly caused by changes in the equipment operating state or external environmental factors, it may be necessary to re-evaluate and correct the parameters in the equipment energy consumption model (such as the relevant parameters in the power characteristic function, load impact function, and environmental impact correction function) to more accurately reflect the energy consumption characteristics of the equipment under actual working conditions (for example, if the power decreases due to equipment aging, the parameters in the power characteristic function need to be adjusted accordingly; if the environmental temperature is higher than the model assumption value for a long time, affecting the heat dissipation of the equipment and increasing energy consumption, the environmental impact correction function needs to be optimized); for the energy consumption model of the process flow, if the energy consumption relationship of each link equipment changes after the production process is adjusted, update the equipment energy consumption accumulation relationship and auxiliary energy consumption calculation method in the process flow energy consumption model in a timely manner (ensure that the process flow energy consumption model can adapt to the energy consumption situation after the process change); at the same time, optimize the loss calculation method and weight allocation of equipment, process flow links, and energy types in the model according to the change of the proportion of each part of the loss in the energy loss decomposition model, so that the energy loss model is closer to the actual energy loss situation in the production process;

[0231] Optimization of the cost accounting model:

[0232] Optimize the cost accounting model according to the market energy price fluctuation information and the actual cost data comparison results; if the energy price fluctuates frequently and has a great impact on the cost, add a price fluctuation adjustment factor to the cost accounting model to make the cost calculation more timely and accurately reflect the market price changes (for example, establish a dynamic correlation model between the electricity cost and the real-time electricity price fluctuation, and update the electricity cost calculation in a timely manner according to the electricity price adjustment); combine the analysis of the impact of production process adjustment on the cost, and adjust the cost calculation parameters related to the production process in the cost accounting model (such as the energy consumption cost distribution coefficient of different process links, the correlation between equipment maintenance cost and process change, etc.) to ensure that the cost accounting can accurately reflect the actual cost change after the process adjustment; at the same time, optimize the calculation method of other cost items in the cost accounting model (such as considering the impact of equipment failure repair cost on the total cost and incorporating it into the cost accounting model to make the cost accounting more comprehensive);

[0233] Improvement of the optimization algorithm:

[0234] Evaluate the performance of genetic algorithms, particle swarm optimization algorithms, etc. in the process of optimizing equipment operation parameters and energy distribution paths based on data comparison and analysis results; if the optimization results fail to meet the expected effects or new optimization requirements are found in actual production, improve the optimization algorithms; for example, adjust parameters such as the coding method, crossover probability, and mutation probability in the genetic algorithm to improve the search efficiency and global optimization ability of the algorithm (find the parameter combination most suitable for the actual situation of the mine by comparing the performance of the algorithm under different parameter settings through experiments); for the particle swarm optimization algorithm, optimize the value-taking strategies of the inertia weight and learning factor, or improve the particle position and velocity update formula to enable the algorithm to converge to the optimal solution faster and more accurately (make targeted improvements to the algorithm based on its performance in actual applications and combined with the characteristics of the mine energy system); at the same time, continuously introduce new optimization algorithms or technologies (such as research on the application potential of deep learning algorithms in energy management), compare and integrate them with existing algorithms, explore optimization methods more suitable for mine energy loss balance management, and improve the mine energy utilization efficiency and cost control level; during the optimization and adjustment process, fully test and verify the new models and algorithms to ensure their stability and effectiveness, and avoid introducing new problems or errors due to optimization and adjustment; verification can be carried out by means of historical data backtesting, simulation, and small-scale pilot applications, and further improve the models and algorithms according to the verification results to form a virtuous cycle of continuous optimization, and continuously enhance the scientificity and accuracy of mine energy management.

[0235] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for cost statistics based on mine energy loss balance, characterized by: The following steps are involved: Step S1, data collection and transmission: Install smart meters as power monitors at the power equipment in the mine, set fuel flow meters and equip fuel level sensors on fuel consumption equipment, deploy temperature sensors, humidity sensors, pressure sensors in the mine area, and install operating status sensors on the equipment, and transmit the data collected by all sensors to the data processing center through wired and wireless networks; Step S2: Data preprocessing and storage: In the data processing center, anomaly detection methods are used to remove abnormal data points based on data statistical laws and equipment operation logic, and interpolation algorithms are used to supplement missing data. Data is stored in relational databases and distributed file systems according to equipment type, production process, energy type, and time dimension. Step S3: Energy loss model construction: for each equipment in the mine, the equipment energy consumption model is constructed by comprehensively considering the equipment power characteristics, load influence and environmental factors; the mine production process is analyzed, and the process energy consumption model is constructed based on the accumulated energy consumption of equipment in each link and the auxiliary energy consumption calculation; the energy loss cost is obtained by subtracting the effective output energy consumption from the total energy input of the mine, and an energy loss decomposition model is established according to the equipment, process link and energy type; Step S4: Cost accounting model is used for cost accounting: the electricity cost is calculated according to the electricity price calculation method of the power company and the data of the power monitoring instrument, the fuel cost is calculated according to the fuel flow meter data and the unit price of fuel, the total energy cost of the mine is summarized and the proportion of each energy cost is analyzed; Step S5: Optimization analysis: Use genetic algorithm to optimize equipment operating parameters, with the lowest unit product energy consumption cost and the highest energy utilization efficiency as the optimization goal; use particle swarm optimization algorithm to optimize the energy distribution path, with the minimum energy loss as the optimization goal; Use the LSTM time series forecasting model combined with production planning information to predict energy demand and cost under different future production plans and market conditions; Step S6: Visualization and decision support: Develop a visualization interface to display equipment energy consumption, process energy consumption and energy cost data; Automatically generate energy management decision support reports based on cost accounting and optimization analysis results and push them to mine managers; Step S7: Feedback and continuous optimization: Regularly collect actual energy consumption, cost and equipment operation data and compare them with system prediction results, collect information on equipment failures, production process adjustments and market energy price fluctuations, and optimize and adjust energy loss models, cost accounting models and optimization algorithms based on the comparison and collection of information.

2. The method for cost statistics based on mine energy loss balance according to claim 1, characterized in that: The anomaly detection method is based on The anomaly detection method based on the principle is , calculate its mean and standard deviation , like or , it is determined as abnormal data and removed; the interpolation algorithm is a cubic spline interpolation algorithm.

3. The method for cost statistics based on mine energy loss balance according to claim 1, characterized in that: The device energy consumption model is constructed as follows: Assume that the device power characteristic function is , the load influence function is , the environmental impact correction function is , then the equipment energy consumption model in, is the time variable, is the load variable, is the environment variable vector, Indicates that the device is , and The energy consumption under the conditions, the environmental variable vector includes temperature, humidity, pressure and altitude; the energy consumption model of the process flow is constructed as follows: The energy consumption of the device is , the auxiliary energy consumption is , then the process energy consumption model , represents the total energy consumption of the process, Indicates the number of equipment in the process flow.

4. The method for cost statistics based on mine energy loss balance according to claim 1 is characterized by: The calculation method of the electricity cost is: Assume that the unit price of electricity is The total power consumption is , electricity cost , when the electricity pricing method includes basic electricity charges , peak and valley electricity charges and power factor adjustment electricity charges The peak-valley electricity fee includes the peak-period unit price. , Peak power consumption , Off-peak hours unit price , off-peak hours , time period unit price Electricity consumption during normal hours , electricity cost ; The fuel cost accounting method is: Assume the fuel unit price is The total fuel consumption is , fuel costs The total energy cost is calculated as ,in, For other energy costs.

5. The method for cost statistics based on mine energy loss balance according to claim 1, characterized in that: The genetic algorithm is applied in the following way: the equipment operation parameter coding adopts binary coding or real number coding, and the fitness function is constructed with the lowest unit product energy consumption cost and the highest energy utilization efficiency as the optimization goal. ,in, and is the weight coefficient, is the energy cost per unit product, For energy efficiency, select the operation by roulette wheel , single-point crossover operation or multi-point crossover operation, basic bit mutation operation, iteratively searching for the optimal device operating parameter combination according to a predetermined number of iterations, wherein, For individuals The probability of being selected, For population size.

6. The method for cost statistics based on mine energy loss balance according to claim 5 is characterized by: The particle swarm optimization algorithm is applied as follows: the energy distribution path is encoded as the particle position in the particle swarm optimization algorithm, the minimum energy loss is taken as the optimization goal, and the particle speed update formula is: , the particle position update formula is ,in, and Particles In the Second and The speed of iterations, is the inertia weight, and is the learning factor, and for A random number, For particles In the The individual optimal position of the iteration, For the group The global optimal position of the iteration, and Particles In the Second and The position of the iteration, initialize the position and velocity of the particle swarm, and set the inertia weight Learning Factor and .

7. The method for cost statistics based on mine energy loss balance according to claim 6 is characterized by: The LSTM time series prediction model is applied in the following way: historical energy cost data, production data and influencing factor data are used as input variables. Before inputting the model, production planning information including planned mining volume , Planned beneficiation volume , Planned equipment operating time Perform normalization processing and assume that the LSTM unit is at time The input gate ,in, is the input gate weight matrix, is the hidden layer output at the previous moment, Input for the current moment, is the input gate bias vector, is the sigmoid function, the forget gate ,in, is the forget gate weight matrix, is the bias vector of the forget gate, the output gate ,in, is the output gate weight matrix, is the output gate bias vector, candidate memory unit ,in, is the candidate memory unit weight matrix, is the candidate memory unit bias vector, memory unit ,in, Represents element-wise multiplication, the hidden layer output , by adjusting the LSTM unit weights and biases through learning and training of historical data, and combining production planning information to predict energy demand and cost under different future production plans and market conditions.

8. The method for cost statistics based on mine energy loss balance according to claim 1, characterized in that: The visualization interface display forms include bar charts, line charts and pie charts; the decision support report push methods include email, mobile phone text messages or system internal message push.

Images