Intelligent optimization method for efficient coal mining

Abstract

The invention discloses an intelligent optimization method for efficient coal mining, and the method comprises the following steps: constructing a coal mining full-process energy consumption monitoring system: respectively deploying energy consumption sensors on mining equipment and auxiliary equipment, the mining equipment comprises a coal mining machine, a scraper conveyor and a hydraulic support, the auxiliary equipment comprises a ventilator and a drainage pump, and the ventilator is connected with the drainage pump; the method comprises the following steps: acquiring instantaneous power and accumulated power consumption data of equipment operation, air volume energy consumption of a ventilation system and flow energy consumption data of a drainage system in real time, and forming a full-flow energy consumption monitoring data set. An energy consumption redundancy link is accurately recognized by combining an energy consumption-yield correlation model, then the operation time period of high-energy-consumption equipment is dynamically adjusted through a peak-valley energy consumption optimization algorithm, and a redundancy recognition-accurate regulation and control energy consumption optimization link is formed by matching a motor frequency conversion speed regulation technology and a hydraulic system pressure self-adaptive regulation technology.

Description

Technical Field

[0001] This invention belongs to the field of coal mining technology, and in particular relates to an intelligent optimization method for efficient coal mining. Background Technology

[0002] In the current coal mining sector, fully mechanized mining (longwall mining) has become the mainstream technology, widely employing core equipment such as coal mining machines, scraper conveyors, and hydraulic supports, along with auxiliary systems such as ventilation fans and drainage pumps to achieve large-scale production. To ensure mining efficiency, existing technologies mostly use fixed equipment operating parameters (such as motor rated speed and hydraulic support fixed pressure) to organize production. Some mines estimate energy consumption by manually recording equipment operating time and make preliminary adjustments to the start-up and shutdown times of some equipment based on peak and off-peak electricity prices. At the same time, for different coal seams (thick coal seams, thin coal seams) or mine types (high gas, rock burst), suitable specialized equipment is selected. However, the overall focus remains on equipment functional compatibility, with manual experience used to determine the direction of parameter adjustments during the mining process to ensure basic production continuity and safety, and to meet the industry's basic demand for raw coal production.

[0003] However, existing coal mining technologies are ill-suited to the current development needs of high efficiency, low consumption, and adaptability to multiple scenarios, exhibiting significant limitations: In energy consumption management, reliance on manual energy consumption estimation leads to low data accuracy, fixed parameter operation cannot dynamically adapt to changes in operating conditions, and identification of energy consumption redundancy is difficult, making it hard to achieve a 15%-20% reduction in unit energy consumption; In terms of scenario adaptation, there is a lack of dynamic response mechanisms for geological conditions, gas concentration, rock bursts, and other operating conditions, and specialized equipment can only meet the basic requirements of a single scenario, resulting in long optimization cycles when switching between scenarios; In terms of operational stability and intelligence, manual adjustments based on experience are prone to equipment failure due to parameter mismatch, and the lack of data-driven closed-loop control logic makes it impossible to achieve linkage between abnormal operating conditions and equipment control, and the high labor costs and low decision-making efficiency make it difficult to promote the upgrading of the mining process towards refinement and intelligence, thus restricting the improvement of the overall benefits of coal mining. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides an intelligent optimization method for efficient coal mining, which solves the problems of high energy consumption, poor adaptability, low intelligence and poor efficiency in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A smart optimization method for efficient coal mining, comprising the following steps:

[0007] S1. Construct a full-process energy consumption monitoring system for coal mining: Deploy energy consumption sensors on mining equipment and auxiliary equipment respectively. The mining equipment includes coal mining machines, scraper conveyors, and hydraulic supports. The auxiliary equipment includes ventilators and drainage pumps. Collect data on the instantaneous power and cumulative power consumption of the equipment in real time, as well as the air volume energy consumption of the ventilation system and the flow energy consumption of the drainage system, to form a full-process energy consumption monitoring dataset.

[0008] S2. Establish an energy consumption-output correlation model: Based on the full-process energy consumption monitoring data collected in S1 and the raw coal output data for the corresponding time period, the raw coal output data includes the coal cutting amount of the coal mining machine and the conveying amount of the scraper conveyor. Depending on the amount of data in the mining scenario, a multiple linear regression algorithm or a random forest algorithm is selected to construct an energy consumption-output correlation model. When the amount of data is small, the multiple linear regression algorithm is used, and when the amount of data is large, the random forest algorithm is used. The mapping relationship between energy consumption and output is analyzed through this model to identify redundant energy consumption links.

[0009] S3. Construct a peak-valley energy consumption optimization algorithm: Obtain peak-valley electricity price time period division data of the power grid, which includes the specific time intervals and corresponding electricity prices of peak, flat and valley periods. Collect the load peak data of the underground mining system through the energy consumption monitoring system of S1. The load peak data of the underground mining system includes the total power peak of the equipment and the load peak of the auxiliary system in each time period. Input the power grid peak-valley electricity price data and the underground load peak data into the peak-valley energy consumption optimization algorithm.

[0010] S4. Dynamically adjust the operating time of high-energy-consuming equipment: Based on the calculation results of the S3 peak-valley energy consumption optimization algorithm, non-critical process equipment is scheduled to operate in the valley section of the power grid. The non-critical process equipment includes the no-load debugging equipment of the transfer machine and the non-emergency transportation equipment of the auxiliary transportation equipment. The full-load operation of key mining equipment is scheduled in the flat section of the power grid. The key mining equipment includes the coal mining machine and the hydraulic support, so as to avoid high-energy-consuming equipment from operating in the peak section of the power grid.

[0011] S5. Adaptive Energy Consumption Adjustment of Equipment: Based on the optimal energy consumption range identified by the S2 energy consumption-output correlation model, the motor speed of the core mining equipment is dynamically adjusted through motor frequency conversion speed regulation technology. The core mining equipment includes a coal mining machine and a scraper conveyor. At the same time, the hydraulic system pressure of the hydraulic support is adjusted in real time through hydraulic system pressure adaptive adjustment technology.

[0012] S6. Energy consumption optimization effect feedback and model iteration: Collect energy consumption data and production data after the implementation of S4 and S5, compare them with the predicted values ​​of the S2 energy consumption-production correlation model, calculate the reduction rate of energy consumption per unit of raw coal, the preset threshold is 15%, if the preset threshold is not reached, adjust the model parameters and algorithm weight coefficients, and iterate until the reduction rate of energy consumption per unit of raw coal stabilizes between 15% and 20%.

[0013] Preferably, the energy consumption sensor in S1 adopts an explosion-proof design to adapt to the high gas and high humidity environment underground. The data acquisition frequency is not less than once per minute. This acquisition frequency can meet the needs of real-time capture of equipment energy consumption fluctuations. Data transmission adopts 5G technology or industrial Ethernet technology to ensure that energy consumption data is uploaded to the ground control center in real time, providing immediate data support for subsequent model construction and algorithm optimization.

[0014] Preferably, the input parameters of the energy consumption-output correlation model in S2 also include geological condition parameters, including coal seam thickness and coal seam hardness. Different coal seam thicknesses and hardnesses directly affect the operating resistance of mining equipment, thereby changing the correlation between energy consumption and output. By introducing geological condition parameters, the correlation between energy consumption and output under different geological environments can be corrected, thereby improving the accuracy of identifying energy consumption redundancy links.

[0015] Preferably, the peak-valley energy consumption optimization algorithm described in S3 also introduces the energy consumption cost parameter for equipment start-up and shutdown. High-energy-consuming equipment will generate additional energy consumption during start-up and shutdown. When high-energy-consuming equipment switches between peak and valley periods, the energy consumption loss during the start-up and shutdown process is calculated to avoid the additional energy consumption caused by frequent start-up and shutdown, and to ensure that the overall energy consumption of the adjusted operating period is optimal.

[0016] Preferably, the motor frequency conversion speed regulation technology described in S5 adopts a vector control method with a speed regulation range of 5Hz to 50Hz. This speed regulation range can cover the operating requirements of the mining equipment from low load to full load, and meet the energy consumption adjustment requirements under different production targets. The hydraulic system pressure adaptive regulation technology collects pressure data in real time through pressure sensors installed on the hydraulic support column, and the adjustment response time does not exceed 0.5 seconds. This response time can quickly match the changes in roof pressure, avoid energy waste or safety risks caused by pressure regulation lag, and ensure the real-time and accurate energy consumption regulation.

[0017] Preferably, the full-process energy consumption monitoring dataset in S1 also includes equipment operating temperature data and equipment operating vibration data. Excessive equipment operating temperature or abnormal vibration will increase equipment operating energy consumption. By collecting these two types of data, we can help determine the impact of equipment operating status on energy consumption, further improve the energy consumption monitoring system, and provide more comprehensive data basis for S2 to identify energy consumption redundancy links.

[0018] Preferably, after identifying the energy consumption redundancy link in S2, an energy consumption redundancy link analysis report is generated. The analysis report includes the specific equipment of the energy consumption redundancy link, the amount of energy consumption redundancy, and the cause of the occurrence. This report can clarify the key objects and directions for subsequent energy consumption optimization and provide data support for adjusting the operating time of high energy consumption equipment in S4 and performing adaptive adjustment of equipment energy consumption in S5.

[0019] Preferably, when dynamically adjusting the operating time of high-energy-consuming equipment in S4, the scheduling of underground workers is taken into account to avoid the disconnect between equipment operating time and personnel operation, thereby achieving coordinated optimization of equipment operation and personnel operation and further improving overall mining efficiency.

[0020] Preferably, historical energy consumption optimization data is introduced during the iterative optimization process in S6. The historical energy consumption optimization data includes energy consumption optimization parameters and energy consumption optimization effects under different mining scenarios. By comparing and analyzing historical data with current data, the shortcomings of the current optimization scheme can be quickly identified, improving the efficiency and accuracy of model iterative optimization and shortening the time to achieve the target energy consumption reduction.

[0021] Preferably, the method also includes a step of visualizing the energy consumption optimization effect, which displays the reduction in unit raw coal energy consumption, the changes in energy consumption of each piece of equipment, and the distribution of energy consumption at different times in the form of charts, intuitively presenting the actual effect of the S4 and S5 optimization measures, making it easier for staff to quickly grasp the dynamics of energy consumption optimization, and providing a reference for S6 iterative optimization and subsequent mining decisions.

[0022] The technical effects and advantages of the intelligent optimization method for efficient coal mining of this invention are as follows:

[0023] 1. This invention constructs a full-process energy consumption monitoring system covering mining equipment and auxiliary systems, accurately identifies redundant energy consumption links by combining an energy consumption-output correlation model, and then dynamically adjusts the operating time of high-energy-consuming equipment through peak-valley energy consumption optimization algorithms. Combined with motor frequency conversion speed regulation and hydraulic system pressure adaptive adjustment technology, a redundancy identification-precise control energy consumption optimization link is formed, which ultimately achieves a stable reduction of 15%-20% in unit raw coal energy consumption, solving the problems of extensive energy consumption control and limited energy-saving effect of traditional mining methods.

[0024] 2. This invention achieves scenario-based adaptation through subordinate technical features: It introduces geological condition parameters (coal seam thickness, hardness) to correct the energy consumption-production correlation model, accurately adapting to working conditions with large geological fluctuations in thin coal seams and avoiding redundant energy consumption misjudgments; it introduces peak-valley algorithms to optimize equipment start-up and shutdown energy consumption cost parameters, adapting to the needs of continuous operation of gas extraction pumps and frequent equipment start-ups and shutdowns in high-gas mines, reducing additional energy consumption; it improves the adjustment response speed of the hydraulic system and introduces micro-vibration monitoring linkage, adapting to working conditions with sudden changes in roof pressure in rockburst mines, avoiding equipment overload; it calls historical energy consumption optimization data to accelerate model iteration, adapting to working conditions with frequent switching of multiple coal seams and shortening the optimization cycle. Compared to traditional methods that are only applicable to simple and conventional working conditions, this invention can cover mainstream mine types such as thick coal seams, thin coal seams, high gas, rockburst, and multiple coal seams, significantly improving its universality.

[0025] 3. The adaptive adjustment technology in this invention can adjust the motor speed and hydraulic pressure in real time according to the coal seam hardness and roof pressure, avoiding equipment failure and shutdown caused by overload or underload. The correlation model of energy consumption-output-operating conditions (gas concentration, micro-vibration energy) can realize the linkage between abnormal operating conditions and equipment control (such as simultaneously reducing the load of the coal mining machine and increasing the load of the extraction pump when the gas concentration exceeds the standard), reducing safety risks. The iterative optimization mechanism continuously compares actual and predicted energy consumption data, dynamically corrects model parameters and control strategies, ensures the long-term stability of energy consumption optimization effects, and reduces operational fluctuations caused by parameter mismatch. Compared with traditional methods that rely on manual experience and are prone to failure due to fixed parameters, this invention significantly reduces the equipment overload failure rate and the risk of safety accidents, and improves mining continuity.

[0026] 4. This invention's peak-valley energy consumption optimization algorithm, combined with grid peak-valley electricity price dispatching equipment, can reduce the operating time of high-energy-consuming equipment during high-electricity-price periods, directly reducing electricity costs. Historical data iteration technology shortens the energy consumption optimization cycle during multi-coal-seam switching, reducing high-energy-consumption losses during switching periods. Data-driven automated control replaces the traditional model of manually estimating energy consumption and adjusting parameters based on experience, reducing labor costs and cost waste caused by human error. Simultaneously, reduced equipment downtime and stable mining efficiency ensure that raw coal production targets are met, further improving overall economic benefits.

[0027] 5. This invention achieves a transformation in coal mining from being driven by manual experience to being driven by data intelligence through a closed-loop logic of data acquisition, model building, algorithm optimization, automatic control, and effect feedback: the energy consumption monitoring system enables real-time data acquisition and transmission, replacing manual recording; the correlation model and optimization algorithm enable accurate identification of energy redundancy and automatic generation of control strategies, replacing manual judgment; visualization and multi-level decision support (implicit in the technical logic) assist staff in accurately grasping the operational status and improving decision-making efficiency. Compared with the extensive management of traditional mining, this invention promotes the upgrading of coal mining towards intelligence and refinement, providing technical support for efficient and green mining. Attached Figure Description

[0028] Figure 1 This is a flowchart illustrating the implementation of an intelligent optimization method for efficient coal mining proposed in this invention. Detailed Implementation

[0029] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0030] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include," "contain," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "includes..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0031] refer to Figure 1 This invention provides an intelligent optimization method for efficient coal mining. It is designed for typical working conditions such as comprehensive mechanized mining of thick coal seams, efficient mining of thin coal seams, and safe mining in high-gas mines. The invention adopts the energy consumption monitoring-model optimization-adaptive adjustment technology scheme. All core equipment used (coal mining machine, sensors, variable frequency motors, etc.) meet safety standards, ensuring the safety of underground operations and the feasibility of the technical solution.

[0032] Example 1

[0033] This embodiment provides an intelligent optimization method for efficient coal mining, which is used as the basis for conventional thick coal seam (coal seam thickness 6-8m) mining. The specific implementation includes:

[0034] Implementation scenario:

[0035] In a certain coal mine in region A, the No. 3 coal seam is 7.2m thick and dips at 8°. It adopts fully mechanized top coal caving technology and has a planned daily raw coal output of 5000t. The peak and valley periods of the power grid are as follows: peak period 8:00-12:00, 18:00-22:00 (electricity price 0.85 yuan / kWh), flat period 6:00-8:00, 12:00-18:00, 22:00-24:00 (electricity price 0.52 yuan / kWh), and valley period 0:00-6:00 (electricity price 0.28 yuan / kWh).

[0036] Purpose of implementation:

[0037] Verify the feasibility of the basic scheme of full-process energy consumption monitoring - energy consumption-output model construction - peak-valley energy consumption optimization - equipment adaptive adjustment in conventional thick coal seam mining, achieve a 15%-20% reduction in unit raw coal energy consumption, and reduce electricity costs through peak-shifting scheduling.

[0038] Implementation steps:

[0039] S1. Establish a full-process energy consumption monitoring system:

[0040] Mining equipment deployment: The coal mining machine is MG500 / 1130-WD type, the scraper conveyor is SGZ1000 / 1400 type, and the hydraulic support is ZY12000 / 28 / 63 type; the auxiliary equipment is FBCDZ-8-No.28 type ventilation fan and MD450-60×9 type drainage pump.

[0041] Energy consumption sensor selection: KXY127 intrinsically safe energy consumption sensor for mining (explosion-proof rating ExdIMb) is used and installed at the power input of the above equipment, with a sampling frequency of 1 time / minute; at the same time, GFY15 mining wind speed sensor (for collecting air volume energy consumption) is installed at the air outlet of the ventilation fan and LD3200 mining electromagnetic flow meter (for collecting flow energy consumption) is installed at the outlet of the drainage pump. The data is uploaded to the ground control center (configured with Advantech IPC-610L industrial computer) through a 5G mining base station (KT6500 type).

[0042] S2. Establish an energy consumption-output correlation model:

[0043] Data collection period: 7 consecutive days of data collection, acquiring 10,080 sets of energy consumption data (average daily energy consumption of coal mining machine is about 8,500 kWh, scraper conveyor is 6,200 kWh, and ventilation fan is 4,800 kWh) and corresponding production data (average daily actual production is 4,980 t).

[0044] Algorithm selection: Due to the large amount of data (10080 groups), the Random Forest algorithm (implemented based on the Python sklearn library, with 100 decision trees and feature dimensions including equipment power, mining speed, and coal seam hardness) was selected to construct an energy consumption-output correlation model. The main energy consumption redundancy links were identified as the scraper conveyor running idle (average 1.2 hours per day, energy redundancy of 180kWh) and the ventilation fan supplying excessive air (air volume 15% higher than actual demand, energy redundancy of 720kWh).

[0045] S3. Construct a peak-valley energy consumption optimization algorithm:

[0046] Input data: peak and valley electricity price data of the power grid, peak load data of underground mine (maximum total power of 1200kW during peak period, 950kW during flat period, and 700kW during valley period), and introduce the energy consumption cost parameters of equipment start-up and shutdown (energy consumption of coal mining machine start-up and shutdown is about 30kWh / time, scraper conveyor is 25kWh / time).

[0047] Algorithm output: High energy consumption equipment operation schedule planning - Key equipment (coal mining machine, hydraulic support) is scheduled to operate at full load during the flat period (average 10 hours per day), non-critical equipment (transfer conveyor no-load commissioning, auxiliary transportation equipment) is scheduled to operate during the valley period (average 4 hours per day), and only necessary auxiliary equipment such as ventilation fans and drainage pumps are retained during the peak period (operating at 70% load).

[0048] S4-S5. Dynamic adjustment and adaptive regulation:

[0049] Equipment time period adjustment: Execute according to the algorithm output. In the valley section (0:00-6:00), start the transfer machine for no-load debugging (complete chain tension and lubrication checks). In the level section (6:00-8:00), start the coal mining machine (coal cutting speed set to 8m / min) and hydraulic support (moving step distance 0.8m).

[0050] Adaptive energy consumption adjustment: The motor uses a YVP280M-4 vector control variable frequency motor (speed range 5-50Hz). When the coal cutting resistance of the coal mining machine increases (coal seam hardness increases from 25MPa to 30MPa), the motor speed decreases from 45Hz to 38Hz (energy consumption decreases from 180kW to 152kW). The hydraulic support column is equipped with a CYT-60 mining pressure sensor. When the roof pressure increases from 35MPa to 42MPa, the hydraulic system pressure is adaptively adjusted from 38MPa to 45MPa (response time 0.3 seconds) to avoid overload or underload of the support.

[0051] S6. Iterative Optimization and Results Verification:

[0052] Iteration process: After the first week of implementation, the unit raw coal energy consumption was 8.2 kWh / t, which did not reach the 15% reduction target (the original traditional method energy consumption was 9.8 kWh / t). The weight coefficient of coal seam hardness in the random forest model was adjusted from 0.15 to 0.22, and the energy consumption weight of peak-valley algorithm start-up and shutdown was increased from 0.1 to 0.15.

[0053] Stable operation: After three weeks of continuous optimization, a stable equipment operation and adjustment strategy was established.

[0054] Implementation results:

[0055] The unit raw coal energy consumption has been steadily reduced to 8.0 kWh / t, a decrease of 18.4% compared to traditional mining methods; the average daily electricity cost has been reduced from 48,000 yuan to 36,000 yuan, saving an average of 12,000 yuan per day; the accuracy rate of energy consumption redundancy identification has reached over 90%; the idle running time of the scraper conveyor has been shortened to 0.3 hours / day; and the air supply redundancy of the ventilation fan has been reduced to less than 5%, meeting the needs of efficient and low-consumption mining of conventional thick coal seams.

[0056] Example 2

[0057] This embodiment provides an intelligent optimization method for efficient coal mining, applicable to the adaptation of geological parameters in thin coal seam (1.2-1.5m thick) mining. Specific implementation details include:

[0058] Implementation Scenarios

[0059] In a certain coal mine in region B, the No. 10 thin coal seam is 1.3m thick and dips at 12°. It adopts the thin coal seam fully mechanized mining technology and has a planned daily output of 2000t. The coal seam hardness fluctuates greatly (18-32MPa) and the roof is relatively broken. It is prone to abnormal fluctuations in energy consumption due to changes in geological conditions.

[0060] Purpose of implementation:

[0061] This addresses the issues of inaccurate energy consumption redundancy identification due to geological condition fluctuations and additional energy consumption caused by roof fracturing in thin coal seam mining. It improves the adaptability of the energy consumption-production model to geological parameters and accelerates the response speed of hydraulic support pressure adjustment, ensuring low energy consumption and safety in thin coal seam mining.

[0062] Implementation steps:

[0063] S1. Energy consumption monitoring system adaptation:

[0064] Using the energy consumption sensor and data transmission scheme of Example 1, an additional ZJ30DB logging-while-drilling instrument is installed on the cutting section of the coal mining machine to collect coal seam thickness (1.3m±0.1m) and coal seam hardness (18-32MPa) data in real time and upload them to the ground control center simultaneously.

[0065] S2. Optimization of the energy consumption-output correlation model:

[0066] Input parameter supplement: Based on the model of Example 1, the geological parameters of coal seam thickness and coal seam hardness are added. The model mapping relationship is corrected through data training. When the coal seam hardness is >28MPa, the energy consumption coefficient of the coal mining machine increases from 1.0 to 1.2 (that is, the energy consumption increases by 20% under the same output); when the coal seam thickness is <1.2m, the conveying efficiency coefficient of the scraper conveyor is reduced to 0.9 (to avoid overload energy consumption).

[0067] Redundancy identification and optimization: By analyzing the correlation between geological parameters and energy consumption data, we can distinguish between high energy consumption caused by equipment failure and high energy consumption caused by changes in geological conditions, thus avoiding misjudgment and shutdown.

[0068] S3-S4. Peak-valley optimization and equipment adjustment:

[0069] The peak-valley energy consumption optimization algorithm follows the logic of Example 1. Taking into account the low power of thin coal seam equipment (such as low-body coal mining machines), the off-peak operation time of non-critical equipment (such as coal seam cleaning equipment) is extended to 6 hours / day (valley period 0:00-6:00).

[0070] S5. Adaptive Adjustment Enhancement:

[0071] Hydraulic support adjustment: In response to the characteristics of roof breakage, DBW10B electromagnetic relief valves are selected to shorten the hydraulic system pressure adjustment response time from 0.3 seconds to 0.2 seconds; at the same time, pressure sensors are installed on the top beam of the support to monitor the roof contact pressure in real time and prevent roof collapse due to insufficient pressure.

[0072] Coal mining machine speed regulation: The coal cutting speed is dynamically adjusted according to the change in coal seam hardness. When the hardness is >30MPa, the coal cutting speed is reduced from 6m / min to 4.5m / min to reduce motor overload energy consumption.

[0073] S6. Iterative Optimization:

[0074] Based on 10 days of operational data, the weight of geological parameters in the model was adjusted (from 20% to 30%) to improve the model's adaptability to thin coal seam conditions.

[0075] Implementation results:

[0076] Energy consumption per unit of raw coal is reduced to 7.5 kWh / t, a decrease of 18.5% compared to the traditional thin coal seam mining method (9.2 kWh / t); the accuracy rate of energy consumption redundancy identification is improved from 78% to 92%, avoiding equipment downtime of 3 times per month due to misjudgment of geological conditions; the risk of roof collapse is reduced by 60%, and no additional energy consumption is generated due to roof problems, which is suitable for the mining needs of thin coal seams with large geological fluctuations.

[0077] Example 3

[0078] This embodiment provides an intelligent optimization method for efficient coal mining, applicable to high-gas mines (gas content 12-15 mg / m³). 3 The implementation of start-up and shutdown energy consumption control for / t) mining operations includes the following specific implementation details:

[0079] Implementation scenario:

[0080] A high-gas coal mine in region C has a coal seam gas content of 13.5 m³. 3 / t, adopting a fully mechanized mining + gas extraction coordinated process, with a planned daily output of 3000t; the gas extraction pump needs to run continuously, and the coal mining machine needs to be started and stopped frequently due to fluctuations in gas concentration, which easily generates additional start-stop energy consumption; the peak and valley electricity prices of the power grid are consistent with those of Example 1.

[0081] Purpose of implementation:

[0082] To address the issues of excessive energy consumption caused by frequent start-ups and shutdowns of equipment in high-gas mines, and poor coordination between gas extraction and mining equipment, the energy consumption of gas extraction and mining equipment is optimized by reducing the number of start-ups and shutdowns through peak-valley scheduling logic, thereby reducing overall energy consumption.

[0083] Implementation steps:

[0084] S1. Coordinated monitoring of energy consumption and gas concentration:

[0085] Energy consumption monitoring: Energy consumption sensors are deployed on the coal mining machine, gas extraction pump (2BE1503-0BY4 type), and ventilation fan, with a data collection frequency of 1 time / minute;

[0086] Gas monitoring: KG9701 gas sensors are installed at the working face to collect gas concentration data in real time (threshold 0.8%), and the data is uploaded in conjunction with energy consumption data.

[0087] S2. Construction of the energy consumption-output-gas correlation model:

[0088] Based on the model in Example 1, a new gas concentration parameter is added to construct a three-dimensional correlation model. When the gas concentration is >0.6%, the energy consumption of the coal mining machine is allowed to increase by 10% (to avoid forced shutdown), and the gas extraction pump is linked to increase the load.

[0089] S3. Peak-valley energy consumption optimization algorithm upgrade:

[0090] Start-up and shutdown energy consumption parameters are introduced: the energy consumption of equipment start-up and shutdown is statistically analyzed (45kWh / time for gas extraction pump and 32kWh / time for coal mining machine). A start-up and shutdown energy consumption cost threshold is added to the algorithm - when the peak-valley electricity price difference is <0.3 yuan / kWh, the equipment operating period is not switched (to avoid frequent start-up and shutdown).

[0091] Coordinated scheduling logic: Set the gas extraction pump as the priority equipment to avoid extraction interruption due to peak shifting; the operating hours of the coal mining machine are staggered with the peak load of the gas extraction pump (peak hours for extraction pump: 10:00-14:00, peak hours for coal mining machine: 14:00-18:00).

[0092] S4. Equipment Co-operation Control:

[0093] Gas-equipment linkage: When the gas concentration is >0.7%, the coal mining machine operates at reduced load (from 80% to 60%), while the gas extraction pump load is increased simultaneously (from 70% to 90%) to avoid frequent start-ups and shutdowns of the coal mining machine;

[0094] Time period adjustment: The peak-valley switching of the gas extraction pump is cancelled (originally planned to switch from the peak segment to the valley segment). The coal mining machine will only be scheduled to operate at full load during the flat segment (12:00-18:00) and at non-full load during the peak segment (8:00-12:00).

[0095] S5. Adaptive Adjustment:

[0096] Adjust the power of the coal mining machine according to the load changes of the gas extraction pump. When the gas extraction pump load is greater than 85%, the power of the coal mining machine is reduced by 15% to avoid forced shutdown when the total load exceeds the limit.

[0097] S6. Iterative Optimization:

[0098] Based on 15 days of operating data, the start-stop energy consumption cost threshold was adjusted (from 0.3 yuan / kWh to 0.35 yuan / kWh) to reduce ineffective switching.

[0099] Implementation results:

[0100] Energy consumption per unit of raw coal was reduced to 8.8 kWh / t, a 19.3% reduction compared to the traditional method (10.9 kWh / t); the number of equipment start-ups and shutdowns was reduced from an average of 8 times per day to 3 times, resulting in a reduction of 420 kWh / day in extra energy consumption during start-ups and shutdowns; the number of times gas concentration exceeded the standard was reduced from 5 times / week to 1 time / week, and no coal mining machine was forced to shut down due to gas problems, achieving a synergy between safety and low energy consumption in high-gas mines.

[0101] Example 4

[0102] This embodiment provides an intelligent optimization method for efficient coal mining, used for rapid response adjustment in rockburst-prone mines. Specific implementation details include:

[0103] Implementation scenario:

[0104] A certain rockburst-prone mine in region D has a coal seam thickness of 4.5m and a rockburst hazard level of medium. The planned daily output is 3500t. The roof pressure fluctuates greatly (40-55MPa), and it is necessary to quickly adjust the equipment operation status to avoid rockburst risks. Traditional adjustment is slow and may lead to equipment overload or shutdown.

[0105] Purpose of implementation:

[0106] To address the problem of equipment overload and slow adjustment response caused by sudden changes in roof pressure in mines prone to rock bursts, resulting in production stoppages and energy consumption, we can improve the equipment adjustment response speed and strengthen the pressure-energy consumption linkage control to reduce the additional energy consumption caused by rock bursts and ensure continuous mining.

[0107] Implementation steps:

[0108] S1. Collaborative monitoring of energy consumption and impact early warning:

[0109] Energy consumption monitoring: Deploy high-frequency energy consumption sensors (sampling frequency 10 times / second) on coal mining machines, hydraulic supports, and scraper conveyors;

[0110] Impact warning: Install a microseismic monitoring system (YCS500 type) to collect microseismic energy in real time (threshold 10). 5 J), synchronously monitor the top plate pressure (CYT-60 sensor).

[0111] S2. Construction of the energy consumption-pressure-microseismic correlation model:

[0112] An energy consumption regulation model is constructed using microseismic energy and roof pressure as core parameters—when microseismic energy > 105 When the pressure of the J plate or top plate exceeds 50 MPa, a rapid adjustment command is triggered.

[0113] S3. Peak-valley optimization adaptation:

[0114] Considering the risk of rock bursts, and to avoid operating the equipment at full load during peak periods (which can easily lead to the accumulation of rock bursts), the coal mining machine will be scheduled to operate at full load during the flat periods (14:00-20:00), with only 50% load maintained during peak periods.

[0115] S4. Quick Response Adjustment:

[0116] Variable frequency speed control for motor: The coal mining machine uses a YVP315L2-4 type vector control variable frequency motor (speed range 5-50Hz). When micro-vibration energy > 10 is detected... 5 At time J, the motor speed rapidly drops from 42Hz to 25Hz (response time 0.8 seconds), and the energy consumption drops from 165kW to 98kW;

[0117] Hydraulic support adjustment: The sampling frequency of the column pressure sensor is increased to 10 times / second. When the pressure on the top plate rises from 40MPa to 55MPa, the hydraulic system pressure is adjusted from 42MPa to 58MPa within 0.4 seconds, and the support force is increased by 40% simultaneously to prevent the support from deforming.

[0118] S5. Iterative Optimization:

[0119] Based on 20 days of operational data, the linkage delay between impact warning and energy consumption adjustment was optimized (reduced from 1 second to 0.5 seconds), improving response timeliness.

[0120] Implementation results:

[0121] Energy consumption per unit of raw coal was reduced to 8.3 kWh / t, a 21.0% reduction compared to the traditional method (10.5 kWh / t); the number of shutdowns due to rock bursts was reduced from 4 times / month to 1 time / month, and energy consumption losses during shutdowns were reduced by 60%; the equipment overload failure rate was reduced from 15% to 3%, and the deformation of hydraulic supports was controlled within 5 mm, meeting the safe and low-energy consumption mining requirements of mines prone to rock bursts.

[0122] Example 5

[0123] This embodiment provides an intelligent optimization method for efficient coal mining, which is used for iterative implementation based on historical data from multi-coal seam mining. Specific implementation details include:

[0124] Implementation scenario:

[0125] A multi-seam coal mine in region E is simultaneously mining seams No. 2 (5m thick, 25-30MPa hardness) and No. 5 (3m thick, 18-22MPa hardness), with a planned total daily output of 6000t. Coal seam switching is frequent (2-3 times per month), and traditional models need to be retrained for 14 days to adapt to the new coal seams, resulting in high energy consumption during the switching period.

[0126] Purpose of implementation:

[0127] To address the issues of slow model iteration and lagging energy consumption optimization during multi-coal seam switching, historical mining data is introduced to accelerate model iteration while simultaneously enabling visualization of energy consumption effects. This facilitates rapid adjustment of mining strategies and shortens the energy consumption optimization cycle during coal seam switching.

[0128] Implementation steps:

[0129] S1. Establishment of a multi-coal-seam energy consumption monitoring system:

[0130] Energy consumption monitoring equipment identical to that in Example 1 was deployed in the No. 2 and No. 5 coal seam working faces to establish a coal seam-equipment-energy consumption correlation database and store historical data (120,000 sets in the past year).

[0131] S2. Model building based on historical data:

[0132] Historical data retrieval: Extract the energy consumption-production model parameters of coal seam No. 2 (100 random forest decision trees, hardness weight 25%) and the variable frequency motor speed regulation curve of coal seam No. 5 (speed 38Hz at hardness 25MPa).

[0133] Model migration: When switching to coal seam No. 5, the model is initialized based on historical data. Only 3 days of new data are needed to complete the training, and there is no need to rebuild it.

[0134] S3. Peak-valley optimization adaptation:

[0135] Peak-valley scheduling is adjusted according to the power differences of equipment in different coal seams: the coal mining machine in coal seam No. 2 has a high power (1130kW) and is scheduled to operate at full load in the flat section; the coal mining machine in coal seam No. 5 has a low power (800kW) and can maintain 70% load operation in the peak section to reduce the pressure of off-peak scheduling.

[0136] S4. Adaptive adjustment of parameter migration:

[0137] The adaptation parameters of coal seam hardness, motor speed, roof pressure, and support pressure from historical data are directly transferred to the new coal seam, with only minor adjustments (±10%) based on actual working conditions. For example, when the hardness of coal seam No. 5 is 20MPa, the motor speed is slightly adjusted from 38Hz to 36Hz.

[0138] S5. Visualization of energy consumption optimization effects:

[0139] Software deployment: KingView 7.5 software is used to display the energy consumption change curves, peak and valley time energy consumption distribution pie charts, and unit energy consumption reduction trend lines of each device in real time on the ground control center and the intrinsically safe display screen (KJD220 type) in the mine.

[0140] Decision support: Staff can quickly identify energy consumption anomalies (such as a sudden 15% increase in energy consumption of the scraper conveyor in coal seam No. 5) through a visual interface and complete parameter adjustments within 2 hours.

[0141] S6. Iterative Optimization:

[0142] The historical database is updated monthly based on the operational data of the two coal seams to optimize the adaptation accuracy of model migration (error reduced from 8% to 5%).

[0143] Implementation results:

[0144] The time to achieve energy consumption optimization standards during multi-coal seam switching was shortened from 14 days to 5 days, a reduction of 64%; the unit raw coal energy consumption during the switching period decreased from 9.1 kWh / t to 7.8 kWh / t, and the energy consumption during the stable period remained at 7.6-7.9 kWh / t; the efficiency of staff in discovering and resolving abnormal energy consumption problems through the visual interface was improved by 80%, and the energy consumption loss caused by the lag in parameter adjustment was reduced by 3,000 kWh per month.

[0145] Comparative Example 1

[0146] This comparative example provides information on traditional coal mining methods, including:

[0147] Implementation scenario:

[0148] The No. 3 coal seam of a certain coal mine in a certain region A, which is the same as in Example 1, adopts the traditional fully mechanized mining technology, with a planned daily output of 5,000 tons, and the peak and valley periods of the power grid are the same as in Example 1.

[0149] Implementation method:

[0150] No energy consumption monitoring: Energy consumption is estimated solely by manually recording the equipment's operating time (error ±15%), without real-time data acquisition and analysis;

[0151] Model-free optimization: The coal mining machine and scraper conveyor are fixed to full-load operation during peak periods (8:00-12:00, 18:00-22:00), and non-critical equipment (transfer conveyor, auxiliary transportation equipment) operate synchronously with the main equipment, without peak-shifting scheduling;

[0152] No adaptive adjustment: The motor speed is fixed at 50Hz and the hydraulic support pressure is fixed at 40MPa, and it does not adjust with changes in coal seam hardness or roof pressure;

[0153] No iterative optimization: The equipment operating status is adjusted solely based on human experience, without data-driven parameter optimization.

[0154] Implementation results:

[0155] The unit raw coal energy consumption is 9.8 kWh / t, which is 22.5% higher than that of Example 1 (8.0 kWh / t); the average daily electricity cost is 48,000 yuan, which is 12,000 yuan more than that of Example 1; the average daily additional energy consumption for equipment start-up and shutdown is 650 kWh, which is more than three times that of Example 1; the accuracy rate of energy consumption redundancy identification is only 45%, the scraper conveyor idle running time is 1.2 hours / day, and the ventilation fan air supply redundancy is 15%, which have not been effectively optimized, highlighting the disadvantages of high energy consumption and low adaptability of traditional methods.

[0156] Compared with Examples 1-5 and Comparative Example 1, this invention, based on the common scenarios of coal mining and using the comparative example (traditional coal mining method) as a benchmark, integrates the core differences of Examples 1-5 (the method of this invention) in four aspects: energy consumption optimization effect, scenario adaptability, technical logic, and actual benefits, as detailed below:

[0157] Regarding energy consumption reduction, the comparative example lacks systematic optimization, with the unit raw coal energy consumption remaining fixed at 9.8 kWh / t. Examples 1-5 all achieved reductions of over 15%, with Example 1 (conventional thick coal seam) reducing to 8.0 kWh / t (a decrease of 18.4%), Example 2 (thin coal seam) reducing to 7.5 kWh / t (a decrease of 18.5%), Example 3 (high-gas mine) reducing to 8.8 kWh / t (a decrease of 19.3%), and Example 4 (rockburst mine) reducing to 8.3 kWh / t (a decrease of 21.0%). Example 5 (multi-coal seam) reduced from 9.1 kWh / t to 7.8 kWh / t during the switching period (a decrease of 14.3%) and maintained at 7.6-7.9 kWh / t during the stable period, all achieving the core energy-saving targets. The comparative example has no room for energy saving.

[0158] In terms of scenario adaptability, the comparative example is only suitable for simple and routine working conditions. When faced with complex scenarios such as geological fluctuations in thin coal seams, start-up and shutdown of high-gas equipment, sudden pressure changes due to rockbursts, and switching between multiple coal seams, problems such as misjudgment of energy consumption redundancy identification and equipment overload shutdown are likely to occur. Examples 1-5 specifically address the pain points of different scenarios: Example 2 improves the redundancy identification accuracy from 78% to 92% by adding geological parameters (coal seam thickness / hardness); Example 3 reduces equipment start-up and shutdown by 5 times / day through gas-energy consumption linkage; Example 4 reduces the number of production shutdowns by 3 times / month through 0.4-second hydraulic response; Example 5 shortens the switching period from 14 days to 5 days through historical data migration, achieving full scenario adaptability, while the comparative example has no scenario adaptability capability.

[0159] Technically, the comparative model relies on manual experience, lacks real-time monitoring (energy consumption estimation error ±15%), model optimization (equipment parameters are fixed), and iterative closed-loop operation. Examples 1-5 all adopt a monitoring-modeling-optimization-adjustment-iterative closed-loop logic: real-time data is obtained through explosion-proof sensors (collection frequency 1 time / minute-10 times / second), a correlation model is built using algorithms such as random forest, combined with peak and valley electricity prices, geological / gas / microseismic parameter optimization strategies, and then executed through variable frequency motors (5-50Hz), rapid hydraulic adjustment, etc. Finally, the parameters are iteratively optimized, such as adjusting the model weights in Example 1 and updating the historical database in Example 5, forming a data-driven dynamic optimization. The comparative model lacks any technical closed loop.

[0160] In terms of actual benefits, the comparative example has an average daily electricity cost of 48,000 yuan, an equipment start-up and shutdown energy consumption of 650 kWh / day, and significant losses due to downtime caused by malfunctions; Example 1 saves an average daily electricity cost of 12,000 yuan, Example 3 reduces start-up and shutdown energy consumption by 420 kWh / day, Example 4 reduces the equipment overload failure rate from 15% to 3%, and Example 5 improves anomaly handling efficiency by 80% through a visual interface. The overall benefits are significant, while the comparative example has no additional benefits.

[0161] In summary, the method of this invention, through closed-loop technical logic and full-scenario adaptability design, achieves significant reduction in energy consumption and improvement in efficiency compared with traditional methods, and has strong industrial application value.

[0162] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of protection of the claims.

[0163] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A smart optimization method for efficient coal mining, characterized in that, The method includes the following steps: S1. Construct a full-process energy consumption monitoring system for coal mining: Deploy energy consumption sensors on mining equipment and auxiliary equipment respectively. The mining equipment includes coal mining machines, scraper conveyors, and hydraulic supports. The auxiliary equipment includes ventilators and drainage pumps. Collect data on the instantaneous power and cumulative power consumption of the equipment in real time, as well as the air volume energy consumption of the ventilation system and the flow energy consumption of the drainage system, to form a full-process energy consumption monitoring dataset. S2. Establish an energy consumption-output correlation model: Based on the full-process energy consumption monitoring data collected in S1 and the raw coal output data for the corresponding time period, the raw coal output data includes the coal cutting amount of the coal mining machine and the conveying amount of the scraper conveyor. Depending on the amount of data in the mining scenario, a multiple linear regression algorithm or a random forest algorithm is selected to construct an energy consumption-output correlation model. When the amount of data is small, the multiple linear regression algorithm is used, and when the amount of data is large, the random forest algorithm is used. The mapping relationship between energy consumption and output is analyzed through this model to identify redundant energy consumption links. S3. Construct a peak-valley energy consumption optimization algorithm: Obtain peak-valley electricity price time period division data of the power grid, which includes the specific time intervals and corresponding electricity prices of peak, flat and valley periods. Collect the load peak data of the underground mining system through the energy consumption monitoring system of S1. The load peak data of the underground mining system includes the total power peak of the equipment and the load peak of the auxiliary system in each time period. Input the power grid peak-valley electricity price data and the underground load peak data into the peak-valley energy consumption optimization algorithm. S4. Dynamically adjust the operating time of high-energy-consuming equipment: Based on the calculation results of the S3 peak-valley energy consumption optimization algorithm, non-critical process equipment is scheduled to operate in the valley section of the power grid. The non-critical process equipment includes the no-load debugging equipment of the transfer machine and the non-emergency transportation equipment of the auxiliary transportation equipment. The full-load operation of key mining equipment is scheduled in the flat section of the power grid. The key mining equipment includes the coal mining machine and the hydraulic support, so as to avoid high-energy-consuming equipment from operating in the peak section of the power grid. S5. Adaptive Energy Consumption Adjustment of Equipment: Based on the optimal energy consumption range identified by the S2 energy consumption-output correlation model, the motor speed of the core mining equipment is dynamically adjusted through motor frequency conversion speed regulation technology. The core mining equipment includes a coal mining machine and a scraper conveyor. At the same time, the hydraulic system pressure of the hydraulic support is adjusted in real time through hydraulic system pressure adaptive adjustment technology. S6. Energy consumption optimization effect feedback and model iteration: Collect energy consumption data and production data after the implementation of S4 and S5, compare them with the predicted values ​​of the S2 energy consumption-production correlation model, calculate the reduction rate of energy consumption per unit of raw coal, the preset threshold is 15%, if the preset threshold is not reached, adjust the model parameters and algorithm weight coefficients, and iterate until the reduction rate of energy consumption per unit of raw coal stabilizes between 15% and 20%.

2. The intelligent optimization method for efficient coal mining as described in claim 1, characterized in that, The energy consumption sensor described in S1 adopts an explosion-proof design, which is suitable for high gas and high humidity environments underground. The data acquisition frequency is no less than once per minute. This acquisition frequency can meet the needs of real-time capture of equipment energy consumption fluctuations. Data transmission adopts 5G technology or industrial Ethernet technology to ensure that energy consumption data is uploaded to the ground control center in real time, providing immediate data support for subsequent model building and algorithm optimization.

3. The intelligent optimization method for efficient coal mining as described in claim 1, characterized in that, The input parameters of the energy consumption-output correlation model described in S2 also include geological condition parameters, such as coal seam thickness and coal seam hardness. Different coal seam thicknesses and hardnesses directly affect the operating resistance of mining equipment, thereby changing the correlation between energy consumption and output. By introducing geological condition parameters, the correlation between energy consumption and output under different geological environments can be corrected, thereby improving the accuracy of identifying energy consumption redundancy links.

4. The intelligent optimization method for efficient coal mining as described in claim 1, characterized in that, The peak-valley energy consumption optimization algorithm described in S3 also introduces the energy consumption cost parameter for equipment start-up and shutdown. High-energy-consuming equipment will generate additional energy consumption during start-up and shutdown. When high-energy-consuming equipment switches between peak and valley periods, the energy consumption loss during the start-up and shutdown process is calculated to avoid the additional energy consumption caused by frequent start-up and shutdown, and to ensure that the overall energy consumption of the adjusted operating period is optimal.

5. The intelligent optimization method for efficient coal mining as described in claim 1, characterized in that, The motor frequency conversion speed regulation technology described in S5 adopts a vector control method with a speed regulation range of 5Hz to 50Hz. This speed regulation range can cover the operating requirements of mining equipment from low load to full load, and meet the energy consumption adjustment requirements under different production targets. The hydraulic system pressure adaptive regulation technology collects pressure data in real time through pressure sensors installed on the hydraulic support column. The adjustment response time is no more than 0.5 seconds. This response time can quickly match the changes in roof pressure, avoid energy waste or safety risks caused by pressure regulation lag, and ensure the real-time and accurate energy consumption regulation.

6. The intelligent optimization method for efficient coal mining as described in claim 1, characterized in that, The full-process energy consumption monitoring dataset mentioned in S1 also includes equipment operating temperature data and equipment operating vibration data. Excessive equipment operating temperature or abnormal vibration will increase equipment operating energy consumption. By collecting these two types of data, we can help determine the impact of equipment operating status on energy consumption, further improve the energy consumption monitoring system, and provide more comprehensive data basis for S2 to identify energy consumption redundancy links.

7. The intelligent optimization method for efficient coal mining as described in claim 6, characterized in that, After identifying energy-consumption redundancy links in S2, an energy-consumption redundancy link analysis report is generated. The analysis report includes the specific equipment involved in the energy-consumption redundancy link, the amount of energy-consumption redundancy, and the cause of the redundancy. This report can clarify the key objects and directions for subsequent energy consumption optimization and provide data support for adjusting the operating time of high-energy-consuming equipment in S4 and for adaptive adjustment of equipment energy consumption in S5.

8. The intelligent optimization method for efficient coal mining as described in claim 1, characterized in that, When dynamically adjusting the operating hours of high-energy-consuming equipment in S4, the scheduling of underground workers is taken into account to avoid the disconnect between equipment operating hours and personnel operations, thereby achieving coordinated optimization of equipment operation and personnel operations and further improving overall mining efficiency.

9. The intelligent optimization method for efficient coal mining as described in claim 1, characterized in that, Historical energy consumption optimization data is introduced during the iterative optimization process in S6. This historical energy consumption optimization data includes energy consumption optimization parameters and energy consumption optimization effects under different mining scenarios. By comparing and analyzing historical data with current data, the shortcomings of the current optimization scheme can be quickly identified, improving the efficiency and accuracy of model iterative optimization and shortening the time to achieve the target energy consumption reduction.

10. The intelligent optimization method for efficient coal mining as described in claim 1, characterized in that, The method also includes a step to visualize the energy consumption optimization effect, which displays the reduction in unit raw coal energy consumption, the changes in energy consumption of each piece of equipment, and the distribution of energy consumption at different times in the form of charts, intuitively presenting the actual effect of the S4 and S5 optimization measures, making it easier for staff to quickly grasp the dynamics of energy consumption optimization, and providing a reference for S6 iterative optimization and subsequent mining decisions.

Images