Coal mine fully mechanized working face intelligent operation online evaluation system and method based on dynamic correction of geological conditions

Abstract

The application relates to the technical field of intelligent coal mining, in particular to a coal mine fully-mechanized coal mining face intelligent operation online evaluation method based on dynamic correction of geological conditions, which comprises the following steps: collecting geological data of a working face and operation data of key equipment of the working face, obtaining key equipment automatic operation monitoring indexes of the fully-mechanized coal mining face, and a fully-mechanized coal mining face automatic operation index; correcting the key indexes under a standard condition based on geological conditions; calculating the key indexes under the influence of geological conditions based on the corrected key indexes, and calculating the fully-mechanized coal mining face automatic operation index based on the key indexes, the automatic operation monitoring indexes and the fully-mechanized coal mining face automatic operation index; correcting the key indexes under the standard condition and the key equipment automatic operation monitoring indexes of the fully-mechanized coal mining face, optimizing the fully-mechanized coal mining face automatic operation index, grading the operation level of the intelligent fully-mechanized coal mining face, and feeding back the evaluation result. The application can automatically quantify and strip the influence of geological condition differences, and realizes fair performance comparison between working faces.

Description

Technical Field

[0001] This application relates to the field of intelligent coal mining technology, specifically to a real-time online evaluation method and system for the operational efficiency of fully mechanized mining faces, and in particular, an online evaluation system and method for intelligent operation of fully mechanized coal mining faces based on dynamic correction of geological conditions. Background Technology

[0002] With the deepening of intelligent coal mine construction, the evaluation of the operational level of fully mechanized mining faces is shifting from qualitative and static acceptance to quantitative and dynamic assessment. Currently, several typical technical approaches exist in the industry, but all have certain limitations: (1) Competition- or acceptance-based indicator system model: This model constructs a quantitative evaluation system that includes core indicators such as automation rate and human intervention rate, and innovatively addresses geological differences by setting different tracks and introducing a geological complexity coefficient (K value). However, its data mainly relies on manual reporting and periodic on-site verification, which cannot achieve normalized and real-time online evaluation. Moreover, its geological compensation (K value) is mainly used for total score addition and is not deeply integrated with the dynamic calculation process of the operation indicators. It cannot accurately quantify the dynamic impact of different specific geological factors (such as soft rock base and large dip angle) on specific operation indicators (such as automation rate and human intervention rate).

[0003] (2) Classification and benchmarking model based on direct data acquisition: This model automatically collects equipment operation data through the system interface, realizing real-time calculation and ranking of indicators such as automation rate and intervention rate. However, its evaluation method mainly compares the data of working faces of the same mining height type horizontally, lacking scientific correction for more detailed geological condition differences (such as dip angle, structure, roof and floor) within the working face. For working faces containing multiple complex geological conditions, the fairness of the evaluation results needs to be improved.

[0004] (3) Simple self-evaluation mode based on key signal determination: This method collects a few key state signals, with simple logic and fully automatic statistics, ensuring the objectivity of the data. However, its evaluation index is singular and cannot comprehensively and accurately reflect the independent operating status of different subsystems such as supports and coal mining machines, resulting in limited evaluation depth; it does not consider differences in geological conditions and cannot support a refined and fair evaluation. Summary of the Invention

[0005] The technical problem that this invention aims to solve is that existing technologies have not been able to simultaneously address the three core issues of normalized online evaluation, objective and automated data processing, and fair and detailed comparison across geological conditions.

[0006] Therefore, this invention provides an online evaluation system and method for intelligent operation of fully mechanized coal mining faces based on dynamic correction of geological conditions. It can automatically quantify and isolate the influence of differences in geological conditions, and achieve fair performance comparison across working faces.

[0007] The technical solution adopted by this invention to solve its technical problem is: An online evaluation method for intelligent operation of fully mechanized coal mining faces based on dynamic correction of geological conditions includes the following steps: S1 collects geological data from the working face and classifies the geological conditions of the working face; S2 collects operational data from key equipment on the longwall mining face and obtains automated operation monitoring indicators for key equipment on the longwall mining face through key indicators. These automated operation monitoring indicators include the automated operation index of the longwall mining face. ; S3 is a key indicator based on modified benchmark conditions according to geological conditions; S4 calculates the acceptable automation operation index of fully mechanized mining faces under the influence of geological conditions based on modified key indicators. and based on , , Calculate the automation operation index of the fully mechanized mining face ,in The automation operation index of a fully mechanized mining face under benchmark conditions; S5 optimizes the automation operation index of the fully mechanized mining face based on key indicators under the conditions of reduced manpower efficiency, advanced conditions, and operational data correction benchmarks, as well as the automation operation monitoring indicators of key equipment in the fully mechanized mining face. ; S6 is based on the automation operation index of fully mechanized mining faces. The operational level of intelligent fully mechanized mining faces is evaluated in a graded manner, and the evaluation results are fed back.

[0008] Furthermore, the key indicators include the automation rate of hydraulic supports. Hydraulic support manual intervention rate Automation rate of coal mining machines Human intervention rate of coal mining machines Number of workers at the working face .

[0009] Furthermore, the key automated operation monitoring indicators for the fully mechanized mining face also include the overall automation rate of the fully mechanized mining face. Comprehensive manual intervention rate at fully mechanized mining faces And the overall automation rate (OAR) of the fully mechanized mining face, among which, , , , For stent weighting coefficient; This is the weighting coefficient for coal mining machinery.

[0010] Furthermore, in step S3, an adjustment coefficient is defined based on geological conditions. ,in, This represents the effect of the condition on the automation rate. The expected reduction coefficient This represents the rate of artificial intervention under this condition. The expected increase coefficient.

[0011] Furthermore, in step S3, the key index adjusted by the adjustment coefficient influenced by geological conditions is expressed as follows: ; ; , , , , The range is within the interval [0,1].

[0012] Furthermore, in step S4, the acceptable automated operation index of the fully mechanized mining face under the influence of geological conditions is... .

[0013] Furthermore, in step S4, the automation operation index of the fully mechanized mining face... .

[0014] Furthermore, in step S5, the weighting coefficient is based on the efficiency of reducing manpower. Optimization methods include: Data preparation: Extract valid data samples from all working faces within a certain period from the platform. Each sample includes: the calculated comprehensive automation level index of the support structure. Comprehensive automation level indicators of coal mining machines And the corresponding performance indicators, including the number of workers on the work surface. ; Correlation analysis: Calculate separately and correlation coefficient ,as well as and correlation coefficient ; Weight optimization calculation: The correlation coefficient is normalized and used as the basis for optimizing the weights. The normalized result is obtained. , ; Smooth iteration: Iterative updates are performed using exponential smoothing. ,in, This is a smoothing factor (e.g., 0.2) used to control the update magnitude.

[0015] Furthermore, in step S5, based on the benchmark conditions of advanced levels... Rolling update methods include: In each geological condition classification combination, the top 5%-10% of working faces are selected as the benchmark working faces for the current period based on their corrected index FAI and original operating data. Analysis of the actual performance of these benchmark working faces under their own geological conditions , , , Value to evaluate the advanced level of the working face update .

[0016] An online evaluation system for intelligent operation of fully mechanized coal mining faces based on dynamic correction of geological conditions includes: A data acquisition and communication module, which is used to acquire equipment operation data on the working surface; The geological conditions management module is used to provide geological conditions data for the working face. The operation indicator calculation module is connected to the data acquisition and communication module to acquire equipment data and calculate equipment operation monitoring indicators. The geological correction model calculation module is connected to the geological condition management module and the operation index calculation module. Based on the geological condition correction equipment operation monitoring index, the automated operation index (FAI) of the fully mechanized mining face is obtained.

[0017] The beneficial effects of this invention are: (1) It has made the evaluation process more normalized, objective and efficient, and solved the problems of reliance on manual labor and poor timeliness.

[0018] This invention achieves fully automated, real-time direct acquisition of core operational data by establishing a standardized data interface with the equipment, and utilizes a rule engine to automatically identify key events such as "automatic tracking" and "human intervention." This fundamentally replaces the data acquisition methods in existing competition or acceptance models that rely on manual entry and on-site verification.

[0019] Therefore, the method and tools provided by this patent can provide management departments with a low-cost, high-frequency monitoring tool that is routine (such as automatic operation by shift or day), objective (eliminating human interference), and efficient (without the need to organize a large number of manual on-site work), realizing a continuous "health check" of the working face's operating status.

[0020] (2) It has achieved refined and fair evaluation across working faces, and solved the problems of distorted evaluation results and misaligned incentives caused by differences in geological conditions.

[0021] The core of this invention lies in constructing a dynamic correction model of "geological conditions - expected performance". First, geological conditions are refined into multiple quantifiable "key constraint factors" (such as steep dip angle and soft rock base); second, a quantitative influence coefficient on the automation rate (α) and intervention rate (β) is preset for each factor; finally, the expected operational level under specific geological conditions is dynamically calculated through the model. Based on this, the Operating Actual Index (OAI) is corrected to obtain the Standardized Index (FAI).

[0022] This mechanism transforms the evaluation standard from a "one-size-fits-all" approach to a "dynamic and personalized one." On working faces with poor geological conditions, in order to achieve the same FAI level, the system allows for a lower absolute OAI value. This scientifically eliminates the influence of objective geological constraints, enabling the evaluation results to fairly reflect the management level and effort of different mines under their own objective conditions. This, in turn, stimulates the intrinsic motivation of mines of all conditions to "make good use" of the intelligent system, and solves the unfairness problem caused by simple horizontal benchmarking.

[0023] (3) An evaluation index system with both depth and operability was constructed, which solved the problems of rough evaluation and vague diagnosis.

[0024] This invention does not use an oversimplified single indicator, but independently calculates the automation rate (ar) and manual intervention rate (mr) of hydraulic supports and coal mining machines. From two dimensions and four core indicators, it can clearly distinguish between "whether the system is in use" (ar) and "how well it is used" (mr).

[0025] This design enables in-depth diagnostic capabilities in the evaluation results. Managers can not only see an overall FAI score, but also drill down to find out whether the problem lies in poor support following the machine (AR support too low or MR support too high) or unstable coal cutting by the coal mining machine (AR coal cutting too low or MR coal cutting too high). This provides clear data guidance for accurately locating system shortcomings and carrying out targeted optimizations (such as adjusting following parameters and upgrading the cutting model), promoting the deepening of intelligent systems from "having functions" to "having superior functions."

[0026] (4) A data-driven management closed loop of “monitoring-evaluation-diagnosis-optimization” has been formed, which has improved the efficiency of production management.

[0027] This invention combines online evaluation with an intelligent diagnostic suggestion module. After calculating the FAI and each sub-indicator, the system automatically compares the actual values ​​with the geologically corrected expected values, identifies the indicator with the largest deviation, and associates it with its geological condition characteristics.

[0028] This allows the system to evolve from a simple "measuring instrument" into an "intelligent advisor," automatically generating preliminary diagnoses and optimization suggestions such as, "Due to the high intervention rate of the support due to soft rock floor, it is recommended to strengthen floor management or discuss adaptive supports." This significantly reduces the analytical burden on managers, accelerates the decision-making process from problem identification to solution formulation, promotes the transformation and upgrading of coal mine production management towards digitalization, refinement, and prevention, and ultimately translates evaluation into tangible productivity improvements.

[0029] (5) It provides a data foundation for the dynamic evolution and parameter optimization of the standard system, and ensures the long-term scientific nature of the evaluation system.

[0030] During operation, the system described in this invention will continuously accumulate a large number of paired samples of "geological conditions - actual operating data". This real data provides the possibility for iterative optimization of the baseline values ​​(ar*, mr*) and geological influence coefficients (α, β) in the model (corresponding to another patent).

[0031] This makes the entire evaluation system a learnable and evolving intelligent system that can dynamically adjust the evaluation benchmarks as the industry as a whole advances in technology, always maintaining its advanced and scientific nature, and avoiding the problem of static standards becoming ineffective over time. Attached Figure Description

[0032] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0033] Figure 1 This is a schematic diagram of the intelligent online evaluation system of the present invention.

[0034] Figure 2 This is a schematic diagram illustrating the implementation process of the intelligent online evaluation method in this invention.

[0035] Figure 3 This is a schematic diagram of the list of operation evaluation data of the autonomous region's intelligent fully mechanized mining face, displayed by the visualization unit in this invention.

[0036] Figure 4 This is a schematic diagram showing the intelligent fully mechanized mining face operation evaluation details displayed by the report generation unit in this invention. Detailed Implementation

[0037] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, illustrating only the basic structure of the invention, and therefore only show the components relevant to the invention.

[0038] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, features defined with "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0039] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances. An intelligent online evaluation system for fully mechanized coal mining faces based on dynamic correction of geological conditions includes a data acquisition and communication module, a geological condition management module, an operation index calculation module, a geological correction model calculation module, a comprehensive evaluation and visualization module, a diagnosis and optimization suggestion module, and a system management module.

[0040] The data acquisition and communication module is used to acquire operating data of key equipment on the working surface. The data acquisition and communication module includes a device interface unit, a data parsing unit, and an event recognition engine. The equipment interface unit supports data communication with various brands and models of hydraulic support electro-hydraulic control systems, coal mining machine control systems, and working face transportation control systems. It supports multiple industrial protocols such as OPC UA, Modbus TCP, and Profinet to obtain the operating condition data and work data of each device. The data parsing unit parses, verifies, and aligns the timestamps of the collected raw data; The event recognition engine has a built-in rule base that identifies core production events from the data stream in real time.

[0041] The geological condition management module includes a geological feature library, a working face archive unit, and an influence matrix management unit, providing working environment data for equipment management. The geological feature library stores a standardized geological condition feature index system and quantitative standards; the working face archive unit establishes and maintains a geological condition feature vector for each working face; and the influence matrix management unit stores and maintains the geological condition influence quantification matrix M, supporting online adjustment by experts and version management.

[0042] The performance indicator calculation module includes an indicator calculation engine and a data cache and storage unit. The indicator calculation engine is connected to the data acquisition and communication module to acquire device data and calculate device-level performance monitoring indicators. The data cache and storage unit caches real-time calculation results and persistently stores historical data.

[0043] The geological correction model calculation module is connected to the geological condition management module and the operational index calculation module. The geological correction model calculation module includes a benchmark model library, a correction coefficient calculation unit, and a model optimization unit. The benchmark model library stores the benchmark operating performance model P0 and the benchmark comprehensive operating index. ; The correction coefficient calculation unit queries the geological feature vector G of the working face. Calculate the expected performance level and expected comprehensive operating index. and correction factor K; The model optimization unit is connected to the data acquisition and communication module. Based on the historical operating data of the equipment, it uses machine learning algorithms to continuously optimize the coefficients of the influence matrix M.

[0044] The comprehensive evaluation and visualization module includes an index calculation unit, a rating unit, a visualization display unit, and a report generation unit. The index calculation unit calculates the actual automated operation index (OAI) and the corrected automated operation index (FAI) of the fully mechanized mining face. The rating unit classifies operational levels based on FAI values; The visualization unit provides web and mobile visualization interfaces to display real-time data, historical trends, benchmark rankings, diagnostic reports, etc. The report generation unit automatically generates daily, weekly, and monthly analytical reports.

[0045] The diagnosis and optimization suggestion module includes a problem pattern library, a measure knowledge base, an intelligent diagnosis unit, and a suggestion generation unit. The problem pattern library stores common runtime problem patterns and diagnostic rules; The measures knowledge base stores optimization measures for different geological conditions and operational problems; The intelligent diagnostic unit compares actual and expected indicators to automatically identify operational shortcomings. It is recommended that the generated unit combine geological conditions and problem diagnosis results to generate personalized optimization suggestions.

[0046] The system management module includes user access control, configuration management, and data security units: user access control supports multi-level user roles and access control; configuration management manages system parameters, calculation cycles, threshold settings, etc.; and the data security unit ensures the security of data transmission and storage.

[0047] Each module is connected through the enterprise's internal network or private network. The data acquisition module is deployed at the coal mine site (and can be integrated with the existing centralized control system server), while the other modules can be deployed in the ground data center or cloud platform, and exchange data and call services through standardized API interfaces.

[0048] An online evaluation method for intelligent operation of fully mechanized coal mining faces based on dynamic correction of geological conditions is proposed, and its evaluation process is as follows: (1) Data access and initialization: The coal mine completes the data connection of the intelligent system and fills in basic information such as the geological conditions of the working face on the platform.

[0049] (2) Real-time data collection: The platform automatically collects operational monitoring data and performs cleaning and verification.

[0050] (3) Indicator calculation: The system automatically calculates relevant operating indicators based on the collected data.

[0051] (4) Grading: based on Scores are automatically assigned, and evaluation levels are determined.

[0052] (5) Results release: A monthly working face operation evaluation report will be generated.

[0053] (6) Feedback and improvement: Based on the evaluation results, the coal mine analyzes the weak links, formulates and implements improvement measures to form a closed-loop management of "evaluation-feedback-improvement".

[0054] Specifically, the evaluation method includes the following steps: Step S1: Construct a feature vector library of geological conditions at the working face. S1.1 Obtain working environment data The equipment operating environment data includes the geological conditions of the working face. The classification of geological conditions is the basis for implementing differentiated evaluation. Based on the survey data, this plan proposes six key constraints that significantly restrict the intelligent operation of fully mechanized mining, as follows: Table 1 Key Constraints

[0055] The geological properties of each working face are described by all its key constraints, forming a standardized geological condition file, which provides a basis for subsequent accurate matching of evaluation standards.

[0056] S1.2 Constructing Geological Condition Feature Vectors For each fully mechanized mining face to be evaluated, a digital geological profile is established. This profile consists of a set of predefined geological condition characteristic indicators, forming a multi-dimensional geological condition feature vector, which is stored in the working face profile unit. Geological condition characteristic indicators include, but are not limited to: Coal seam occurrence characteristic indicators include: coal seam thickness type (extremely thin, thin, medium thick, thick, extra thick), coal seam dip angle classification (gently dipping, dipping, steeply dipping), and coal seam stability (stable, relatively stable, unstable, extremely unstable). Geological structural characteristics indicators include the degree of fault development, fold complexity, and density of collapse columns, which are classified into simple, medium, complex, and extremely complex levels according to the "Detailed Rules for Coal Mine Geological Work". Top and bottom plate condition indicators: including the stability level of the top plate (stable, moderately stable, unstable), and the lithology and bearing capacity of the bottom plate (hard, medium-hard, soft). Mining process characteristics include: mining method (one-time full-height mining, top coal caving mining) and working face layout (strike longwall, dip longwall). Geological indicators of hazards include gas level (low gas, high gas, coal and gas outburst), hydrogeological type (simple, medium, complex, extremely complex), and rock burst hazard (none, weak, medium, strong).

[0057] Each indicator is quantified into standardized feature values, forming a geological condition feature vector G = (g1, g2, ..., g...). n ), where g i This represents the value of the i-th geological condition characteristic index.

[0058] Step S2: Real-time automatic acquisition of raw equipment operation data and identification of core events. Establish a data communication interface with the intelligent fully mechanized coal mining system (including the electro-hydraulic control system of hydraulic supports, the coal mining machine control system, the working face transportation system, and the personnel positioning system) to achieve fully automatic, real-time acquisition of key runtime sequence data, specifically including: Equipment status timing signals: Coal mining machine operating status (automatic / manual mode, traction speed, drum position), hydraulic support control mode (automatic follow-up / manual control), support action (lifting column, lowering column, moving support, pushing conveyor) trigger signals, support pressure data; Personnel location data: Identification and timestamps of personnel entering the work area and end area during the production shift; Production system status signals: emulsion pump station start / stop status, working face conveyor operation status.

[0059] Based on a predefined rules engine, the following core production events are identified in real time from the above time-series data stream: Automatic cutting event of coal mining machine: When the coal mining machine is in "memory cutting" or "planned cutting" automatic mode and the traction speed is greater than the set threshold, the automatic cutting time will start to accumulate; when it switches to manual mode or the speed is lower than the threshold, the event ends.

[0060] Coal mining machine manual intervention event: If a coal mining machine remote control operation signal or HMI interface manual adjustment command is detected during the automatic cutting process, it is marked as a manual intervention.

[0061] Automatic hydraulic support following event: When the coal mining machine passes the support position, and the support automatically completes the "lowering the support-moving the support-raising the support" cycle within the set time window without human intervention, it is counted as a successful automatic following event.

[0062] Manual intervention event for hydraulic support: If manual operation (including operation of adjacent supports or remote intervention) is detected during automatic follow-up or after automatic follow-up fails, it is counted as one manual intervention.

[0063] Step S3: Calculate equipment-level operation monitoring indicators Online evaluation indicators for intelligent fully mechanized mining faces are core tools for measuring the effectiveness of intelligent operation. This design, based on the principles of systematicity, measurability, and guidance, focuses on core process data regarding "whether the system is in use" and "whether the operation is smooth," and constructs an evaluation index for the automation rate of hydraulic supports (…). ), hydraulic support manual intervention rate ( ), Coal mining machine automation rate ( ), Coal mining machine manual intervention rate ( ), number of workers at the working face (including end face) Five key indicators were used to calculate the automation operation monitoring indicators for key equipment in the fully mechanized mining face. These indicators included the overall automation rate of the fully mechanized mining face (...). ), Comprehensive manual intervention rate of fully mechanized mining face ( ), Overall Automation Rate (OAR) of Longwall Mining Face, Automation Operation Index of Longwall Mining Face ( By automatically and in real-time acquiring data from existing intelligent systems in coal mines, subjective judgment is avoided.

[0064] S3.1 Key Indicator Calculation S3.1.1 Automation rate of hydraulic supports ( ) Automation rate of hydraulic supports ( The ratio refers to the proportion of hydraulic supports passed by the coal mining machine during coal mining operations when the hydraulic support automation control function is enabled, out of the total number of hydraulic supports passed by the coal mining machine. This ratio directly measures the degree of normalized use of the intelligent following function of the support system. The higher the ratio, the better the level of automation application.

[0065] The calculation formula is as follows:

[0066] In the formula, the number of automated follow-up support shifts is the number of hydraulic supports that the coal mining machine passes through when the hydraulic supports are under automated control during coal mining operations. Total number of passes for the coal mining machine – the total number of hydraulic supports that the coal mining machine passes over during coal mining operations.

[0067] S3.1.2 Manual intervention rate of hydraulic supports ( ) Manual intervention rate of hydraulic supports ( This refers to the proportion of manual intervention required for hydraulic supports during coal mining operations, when the hydraulic supports are under automated control, relative to the total number of hydraulic supports passed by the coal mining machine. This ratio reflects the proportion of automated operation where manual intervention is still necessary for correction or compensation. A smaller value indicates a stronger system adaptability and more stable operation.

[0068] The calculation formula is as follows:

[0069] In the formula, "automatic follow-up support shift" refers to the number of hydraulic supports manually moved during coal mining operations when the hydraulic supports are under automated control, expressed as a unit support. Total number of passes by the coal mining machine – During coal mining operations, under the automated control function of the hydraulic supports, the total number of hydraulic supports passed by the coal mining machine, expressed as a unit of support.

[0070] S3.1.3 Coal mining machine automation rate ( ) Automation rate of coal mining machines ( The ratio () refers to the proportion of hydraulic supports passed by the coal mining machine under automated control during coal mining operations, out of the total number of hydraulic supports passed by the machine. This ratio directly measures the degree of routine use of intelligent coal cutting functions such as memory cutting or planned cutting. A higher ratio indicates a better level of automation.

[0071] The calculation formula is as follows:

[0072] In the formula, "automatic coal cutting passes through" refers to the number of hydraulic supports that the coal mining machine passes through under automated control during coal mining operations, expressed as a unit of support. Total number of coal mining machine operations – the total number of hydraulic supports that the coal mining machine passes over during coal mining operations, expressed as a unit of support.

[0073] S3.1.4 Coal mining machine manual intervention rate ( ) Manual intervention rate of coal mining machines ( This refers to the ratio of the number of hydraulic supports passed by the coal mining machine during manual remote control operation to the total number of hydraulic supports passed by the coal mining machine under automated control. This ratio reflects the degree of manual intervention required during intelligent coal cutting due to geological changes, model inaccuracies, and other reasons. The smaller the value, the stronger the system's self-adaptability and the more stable its operation.

[0074] The calculation formula is as follows:

[0075] In the formula, the number of manual remote control operation frames refers to the number of hydraulic supports that the coal mining machine passes through during coal mining operations, expressed as a unit frame. Total number of automated coal cutting passes – the total number of hydraulic supports passed by the coal mining machine in the automated control state during coal mining operations, expressed as a unit of support.

[0076] S3.1.5 Number of workers on the working face ( ) Number of workers at the working face ( This refers to the average positional data of personnel within the work area (including the end points) during a production shift. This indicator is used to verify whether intelligent systems have truly reduced the number of personnel working in hazardous areas and is a standard for measuring effectiveness.

[0077] The calculation method is as follows:

[0078] In the formula, —The number of personnel at the work site (including the end) during a specific time period (without a change in the number of personnel) within the statistical period, expressed in person; —The duration corresponding to the number of people, in minutes.

[0079] Calculation of Automated Operation Monitoring Indicators for Key Equipment in S3.2 Longwall Mining Face S3.2.1 Comprehensive automation rate of fully mechanized mining face ( ) The overall automation rate of fully mechanized mining faces ( The value is a weighted average of the automation rate of hydraulic supports and the automation rate of coal mining machines. This indicator is used to comprehensively measure the degree of automation coverage in the two core processes of support and cutting. The higher the value, the higher the overall degree of automation of the working face and the better the foundation for the routine application of intelligent systems.

[0080] The calculation formula is as follows:

[0081] In the formula, —Stent weighting coefficient; — Coal mining machinery weighting coefficient.

[0082] Note: The following movement of hydraulic supports is the foundation and prerequisite for ensuring the safety and continuous advancement of the working face. The stability and coverage of its automated operation have a more direct and significant impact on overall efficiency. To reflect the fundamental nature of support following, the support weight coefficient is 0.7, the coal mining machine weight coefficient is 0.3, and so on.

[0083] S3.2.2 Comprehensive manual intervention rate of fully mechanized mining face ( ) Comprehensive manual intervention rate in fully mechanized mining faces ( This is the weighted average of the manual intervention rate for hydraulic supports and coal mining machines. This indicator reflects the frequency with which manual intervention is still required for correction or adjustment during automated operation. A lower value indicates stronger system adaptability and stability, and smoother automated operation.

[0084] The calculation formula is as follows:

[0085] S3.2.3 Overall automation rate of fully mechanized mining face ( ) Overall automation rate of fully mechanized mining faces ( ) is in the overall automation rate ( Based on the above, this is the net value after deducting efficiency losses caused by human intervention. This indicator more accurately reflects the level of "effective automation" after deducting ineffective or inefficient automation. The higher the value, the better the overall effectiveness of the work surface in balancing automation coverage and operational quality.

[0086] The calculation formula is as follows:

[0087] S3.2.4 Automation Operation Index of Longwall Mining Face ( ) Automated operation index of working face ( The index is a quantitative measure of the overall automation level of a single working face. It directly reflects the absolute operating status of the intelligent fully mechanized mining system and is independent of geological conditions.

[0088] The calculation method is as follows:

[0089] Step S4: Construct a dynamic correction model for geological conditions To fairly and scientifically reflect the objective constraints of different geological conditions on the operational performance of the intelligent system in the evaluation, this scheme introduces a geological condition correction mechanism. The overall approach is: First, define a model of the advanced operational level that the intelligent system should achieve under ideal (benchmark) geological conditions; Secondly, based on the actual geological conditions of a specific working face, the adverse effects are quantified to calculate the "acceptable" expected operating level under those geological conditions. Finally, the OAI represents the actual operating level of the working face. The OAI is compared with the expected level under the geological conditions to obtain a standardized and comparable final evaluation index (evaluated using FAI).

[0090] In this way, working faces with different mining difficulties can have their "effort level" and "intelligent application effectiveness" measured on the same scale, thereby creating positive incentives.

[0091] S4.1 Establish a benchmark operating performance model S4.1.1 Baseline Operation Model The benchmark operating model P0 defines the theoretical operating level that a mature working face, which fully utilizes advanced intelligent technologies, should achieve under ideal or simply simple geological conditions. It serves as an ideal reference for evaluation and is primarily used to calculate benchmark values ​​for geological condition corrections.

[0092] The target values ​​under the baseline conditions are recommended as follows (which can be adjusted according to industry best practices):

[0093]

[0094]

[0095]

[0096] According to the weights set in step S3.2.1 ( , ), calculate the comprehensive indicators under the benchmark model: (1) Target automation rate of fully mechanized mining face under benchmark conditions:

[0097] (2) Target human intervention rate of fully mechanized mining face under benchmark conditions:

[0098] (3) Overall automation rate of fully mechanized mining face under benchmark conditions:

[0099] (4) Target automation operation index of fully mechanized mining face under benchmark conditions:

[0100] S4.2: Construct a geological condition influence quantification matrix M to calculate the specific expected performance level of the working face. To quantify the impact of geological conditions on automated operation, a pair of adjustment coefficients is assigned to each type of key indicator. ), matrix M includes adjustment coefficients .in, This represents the effect of the condition on the automation rate ( The expected reduction coefficient (negative impact) This represents the effect of the condition on the rate of artificial intervention ( The expected increase coefficient (positive impact) is based on industry experience and survey data, and can be optimized in the future based on data accumulation.

[0101] Table 2. Adjustment Coefficients for Key Constraints

[0102] Step S5: Calculate the corrected standardized operating index For a working face with a geological condition set G, the acceptable operational model under the influence of geological conditions is calculated as follows: S5.1 Calculate the baseline target value under geological constraints Based on all the geological constraints of the working face, the α and β coefficients are summarized, and the baseline target values ​​are adjusted.

[0103]

[0104]

[0105]

[0106]

[0107] Note: The calculation results must be constrained within the interval [0,1], where i represents the i-th key constraint.

[0108] S5.2 Calculate the expected comprehensive operating index under the influence of geological conditions ( )

[0109]

[0110] This represents a relatively good level of operation that is "acceptable" or "theoretically achievable" under the specific geological conditions of the working face, after scientific prediction.

[0111] S5.3 Calculation of the corrected automated operation index of the fully mechanized mining face ( ) use This represents the final revised automation operation index of the fully mechanized mining face, calculated as follows:

[0112] The essence is to measure the actual operating index of the working face ( ), and its expected index under geological conditions ( After normalizing the ratio, it is then mapped back to the benchmark index. On the scale of ). This indicates that the actual operation is better than expected under these geological conditions; This indicates that the expected outcome has been achieved; This indicates that expectations have not been met. All working surfaces All values ​​are based on a fair consideration of geological differences and are aligned with a unified baseline. Compare them.

[0113] Step S6: Evaluate the dynamic optimization of model parameters The correction coefficient K in this evaluation system includes the weighting coefficient ( ), geological adjustment coefficient ( ) and benchmark target value ( The initial settings of these parameters primarily rely on the experience of industry experts and preliminary research, constituting theoretical "prior values." However, whether these parameters accurately reflect the contribution of different automation stages to the ultimate goals of "reducing manpower, increasing safety, and improving efficiency," and whether they precisely quantify the objective constraints of various geological conditions, still requires verification and calibration using actual operational data. Deviations in parameter settings will directly affect the fairness of the evaluation results and the effectiveness of their guiding role. To address this issue, we plan to utilize the real operational data accumulated on the platform to establish a data-driven dynamic parameter optimization mechanism. This mechanism aims to continuously monitor and analyze the data to allow model parameters to evolve from "experience-based static settings" to "effectiveness-based dynamic optimization," ensuring that the evaluation system always scientifically and accurately reflects and guides the improvement of intelligent operation levels.

[0114] S6.1 Weighting coefficients based on the efficiency of reducing manpower ( Optimization methods Initial weighting coefficients for the support and coal mining machine ( , This is based on the theoretical judgment of the fundamental and safety importance of support operations. However, whether this weighting ratio best reflects the core practical goal of "reducing manpower" requires data verification. Under different coal mines and processes, the effects of support automation and coal mining machinery automation on reducing the number of workers at the working face ( The actual contribution may differ.

[0115] Statistical analysis of historical data revealed that the "comprehensive automation level of hydraulic supports" and "comprehensive automation level of coal mining machines" were correlated with the "number of workers on the working face (…)" The association strength and relevance of ")" are used to deduce and optimize the weighting coefficients in reverse. and The goal is to make the weight allocation more accurately reflect the contribution of automation in each process to the effectiveness of "reducing manpower," and to strengthen the guiding role of evaluation in reducing manpower and increasing efficiency.

[0116] The specific method is as follows: (1) Data preparation: Extract valid data samples from all working faces within a certain period (such as a quarter) from the platform. Each sample contains: the calculated comprehensive automation level index of the support structure. Comprehensive automation level indicators of coal mining machines And the corresponding effectiveness indicator: number of workers on the working face ( ).

[0117] (2) Correlation analysis: Calculate the correlations separately. and correlation coefficient ,as well as and correlation coefficient The correlation coefficient is calculated using the existing Spearman rank correlation coefficient method. The absolute value of the correlation coefficient reflects the degree to which the level of automation in this process affects the reduction of manpower.

[0118] (3) Weight optimization calculation: The correlation coefficient is normalized and used as the basis for weight optimization. A simplified optimization formula is as follows:

[0119]

[0120] This formula means that the level of automation in a particular step is more closely related to the effectiveness of reducing manpower, and that step will be given a higher weight in the overall evaluation.

[0121] (4) Smoothing iteration: To avoid drastic changes in weights due to fluctuations in single-period data, exponential smoothing is used for iterative updates:

[0122] in, This is a smoothing factor (e.g., 0.2) used to control the update magnitude.

[0123] S6.2 Geological adjustment coefficient based on equipment operation data ( Calibration method Initial geological adjustment coefficient ( The table is based on qualitative experience and case studies, and may not be able to accurately quantify the impact of each geological condition on the automation rate. ) and intervention rate ( The actual magnitude of the impact needs to be determined. For example, whether the estimate that a "large tilt angle" condition increases the intervention rate by 12% is universally applicable requires verification with large datasets.

[0124] Overall approach and expected results: The working faces will be grouped according to a single geological condition (e.g., "with steep dip" group vs. "without steep dip" control group), and key operational indicators between the groups will be compared. , , , The statistical differences were used to empirically measure the impact of the geological conditions, thereby calibrating the data. and Coefficients. The goal is to make the geological correction model more closely reflect objective reality and improve the horizontal fairness of the evaluation.

[0125] The specific method is as follows: (1) Division of control group and data screening: For a specific geological condition to be calibrated (such as "soft rock base"), all working face data with the same geological conditions are selected from the database as the experimental group, and a batch of working face data that do not have such geological conditions but are similar in other major geological conditions are selected as the control group.

[0126] (2) Analysis of differences in indicators: The differences between the experimental group and the control group were calculated respectively. , , , The average of these four indicators.

[0127] (3) Coefficient calculation and calibration: Impact coefficient on automation rate : Calculate the experimental group relative to the control group Average percentage decrease. For example, the control group. The average decrease was 85%, and the experimental group's was 70%. Therefore, the observed decrease rate was (85% - 70%) / 85% ≈ 17.6%. Compare this observed value with the initial... The values ​​(e.g., -0.12) are compared and calibrated according to certain rules (e.g., taking the weighted average of the observed values ​​and the initial values).

[0128] Impact coefficient of intervention rate : Calculate the experimental group relative to the control group Average increase rate. For example, the control group. The average increase was 10%, and the experimental group's was 22%. Therefore, the observed increase rate was (22% - 10%) / 10% = 120%. This observed rate was then compared with the initial... The value (e.g., +0.15) is compared for calibration.

[0129] (4) Multiple regression-assisted calibration: For complex situations involving multiple intertwined geological conditions, a multiple linear regression model can be used. or As the dependent variable, regression is performed with multiple geological conditions (converted into 0 / 1 dummy variables or degree variables) as independent variables. The magnitude and direction of the regression coefficients can be directly used as calibration. and This is an important basis.

[0130] S6.3 Benchmark target value based on advanced level ( Rolling update method Benchmark target value (e.g.) =0.95) represents the advanced level under ideal conditions. With the popularization of intelligent technologies, the improvement of operator proficiency, and the enhancement of equipment reliability, the industry's actual "advanced level" will dynamically rise. A fixed benchmark target value may lead to an excessively low evaluation ceiling, failing to continuously incentivize innovation and breakthroughs.

[0131] Establish a benchmark management mechanism to regularly (e.g., annually) identify the "benchmark working face" with the best actual performance under various geological conditions. Use its high-level operational data as a reference to progressively and continuously update the benchmark target values ​​applicable throughout the region. The goal is to ensure that the "full score" of the evaluation system keeps pace with industry technological progress and continuously leads the level of intelligent operation to a higher level.

[0132] Detailed method description: (1) Selection of benchmark working faces: In each geological condition classification combination (major categories may be appropriately merged), based on its modified index FAI and original operating data, the top 5%-10% of working faces are selected as the current period's "benchmark working faces". Ensure the advanced nature, representativeness and data authenticity of the benchmarks.

[0133] (2) Benchmark data extraction and analysis: Analyze the actual performance of these benchmark working faces under their own geological conditions. , , , These values ​​represent the "realistically advanced level" achievable under such conditions at the current stage, since they have done their best within their objective limitations.

[0134] (3) The target value update calculation can be performed in multiple ways. This embodiment provides two different methods: the target value update calculation is performed using method A or method B. Method A (Quantitation Method): Calculate a certain index (e.g., ...) for all benchmark working faces. The upper quartile (75th percentile) of the target area. This value means that 25% of the benchmark working surfaces have reached this level or above, making them strong candidates for a new round of benchmark target values.

[0135] Method B (Trend Extrapolation): Plot the curve of the historical baseline value of the indicator over time, combine it with the trend of technological progress, and use linear or curve fitting to perform appropriate forward-looking extrapolation to determine the new target value.

[0136] (4) Prudent updating and release: The updating of benchmark target values ​​should be relatively cautious to avoid frequent and large changes. A "small steps, quick progress" strategy can be adopted, with each update not exceeding 5%. The updated target values ​​need to be reviewed by experts and then uniformly released and applied at the beginning of the new evaluation cycle to ensure the stability and authority of the evaluation standards.

[0137] Step S7: Execution Level Grading and Visualization Based on the corrected fully mechanized mining face automation operation index ( The operational level of intelligent fully mechanized mining faces is divided into four levels: Grade A (Excellent): ≥90 indicates that the intelligent system at the working face operates efficiently, with in-depth automation and minimal human intervention, reaching a leading level within the limits of geological conditions.

[0138] Grade B (Good): 80≤ <90. This indicates that the intelligent system is operating stably, the automation functions are being used effectively, and it has a good foundation for routine operation.

[0139] Grade C (Qualified): 60≤ <80. This indicates that the intelligent system has basically achieved operation, but the level of automation or stability needs to be improved, and there is still a lot of manual intervention.

[0140] Grade D (Needs improvement): <60. This indicates that the intelligent system is not performing well and the automation functions are not being effectively utilized, requiring significant improvement.

[0141] The evaluation rating will serve as an important basis for assessing the level of intelligent operation in coal mines, providing policy support, and recognizing outstanding achievements.

[0142] The operational data is analyzed and displayed through visualization units. Figure 3 , 4 This is an example image for a statistical analysis page.

[0143] Furthermore, based on the evaluation results, the coal mine analyzes the weak links, formulates and implements improvement measures, forming a closed-loop management of "evaluation-feedback-improvement".

[0144] In summary, based on the above online evaluation system, this application has the following functions: (1) To achieve fully automatic, real-time and continuous data collection and calculation of the core indicators of the working face operation, so as to ensure the objectivity and high frequency of evaluation; (2) To achieve refined, process-oriented and quantitative processing of differences in complex geological conditions, by constructing a dynamic "geological conditions-expected performance" model, to establish personalized evaluation benchmarks for each working face, thereby achieving fairness correction at the source of index calculation; (3) Construct a monitoring index system that can independently and accurately reflect the operating status of the two major systems, coal mining machine and hydraulic support, to ensure that the evaluation results have in-depth diagnostic capabilities; (4) Ultimately, scientific and fair routine performance benchmarking will be achieved across working faces with different geological conditions, and the evaluation results will be automatically linked to operational shortcomings, providing accurate and dynamic data support and guidance for the optimization and upgrading of intelligent systems and production management decisions.

[0145] Based on the above-described preferred embodiments of the present invention, and through the foregoing description, those skilled in the art can make various changes and modifications without departing from the inventive concept. The technical scope of this invention is not limited to the contents of the specification, but must be determined by the scope of the claims.

Claims

1. An online evaluation method for intelligent operation of fully mechanized coal mining faces based on dynamic correction of geological conditions, characterized in that, Includes the following steps: S1 collects geological data from the working face and classifies the geological conditions of the working face; S2 collects operational data from key equipment on the longwall mining face and obtains automated operation monitoring indicators for key equipment on the longwall mining face through key indicators. These automated operation monitoring indicators include the automated operation index of the longwall mining face. ; S3 is a key indicator based on modified benchmark conditions according to geological conditions; S4 calculates the acceptable automation operation index of fully mechanized mining faces under the influence of geological conditions based on modified key indicators. and based on , , Calculate the automation operation index of the fully mechanized mining face ,in The automation operation index of a fully mechanized mining face under benchmark conditions; S5 optimizes the automation operation index of the fully mechanized mining face based on key indicators under the conditions of reduced manpower efficiency, advanced conditions, and operational data correction benchmarks, as well as the automation operation monitoring indicators of key equipment in the fully mechanized mining face. ; S6 is based on the automated operation index of fully mechanized mining faces. The operational level of intelligent fully mechanized mining faces is evaluated in a graded manner, and the evaluation results are fed back.

2. The online evaluation method for intelligent operation of fully mechanized coal mining faces based on dynamic correction of geological conditions as described in claim 1, characterized in that, The key indicators include the automation rate of hydraulic supports. Hydraulic support manual intervention rate Automation rate of coal mining machines Human intervention rate of coal mining machines .

3. The online evaluation method for intelligent operation of fully mechanized coal mining faces based on dynamic correction of geological conditions according to claim 2, characterized in that, The key automated operation monitoring indicators for fully mechanized mining faces also include the overall automation rate of the fully mechanized mining face. Comprehensive manual intervention rate at fully mechanized mining faces And the overall automation rate (OAR) of the fully mechanized mining face, among which, , , , For stent weighting coefficient; This is the weighting coefficient for coal mining machinery.

4. The online evaluation method for intelligent operation of fully mechanized coal mining faces based on dynamic correction of geological conditions as described in claim 1, characterized in that, In step S3, an adjustment coefficient is defined based on geological conditions. ,in, This represents the effect of the condition on the automation rate. The expected reduction coefficient This represents the rate of artificial intervention under this condition. The expected increase coefficient.

5. The online evaluation method for intelligent operation of fully mechanized coal mining faces based on dynamic correction of geological conditions according to claim 4, characterized in that, In step S3, the key indicators adjusted by the adjustment coefficient influenced by geological conditions are expressed as follows: ; ; , , , , The range is within the interval [0,1].

6. The online evaluation method for intelligent operation of fully mechanized coal mining faces based on dynamic correction of geological conditions according to claim 5, characterized in that, In step S4, the acceptable automation operation index of the fully mechanized mining face under the influence of geological conditions is determined. .

7. The online evaluation method for intelligent operation of fully mechanized coal mining faces based on dynamic correction of geological conditions according to claim 6, characterized in that, In step S4, the automation operation index of the fully mechanized mining face is... .

8. The online evaluation method for intelligent operation of fully mechanized coal mining faces based on dynamic correction of geological conditions according to claim 1, characterized in that, In step S5, the weighting coefficient is based on the efficiency of reducing manpower. Optimization methods include: Data preparation: Extract valid data samples from all working faces within a certain period from the platform. Each sample includes: the calculated comprehensive automation level index of the support structure. Comprehensive automation level indicators of coal mining machines And the corresponding performance indicators, including the number of workers on the work surface. ; Correlation analysis: Calculate separately and correlation coefficient ,as well as and correlation coefficient ; Weight optimization calculation: The correlation coefficient is normalized and used as the basis for optimizing the weights. The normalized result is obtained... , ; Smooth iteration: Iterative updates are performed using exponential smoothing. ,in, This is a smoothing factor (e.g., 0.2) used to control the update magnitude.

9. The online evaluation method for intelligent operation of fully mechanized coal mining faces based on dynamic correction of geological conditions according to claim 1, characterized in that, In step S5, based on the benchmark conditions of advanced levels... Rolling update methods include: In each geological condition classification combination, the top-ranked working face is selected as the benchmark working face for the current period based on its corrected index FAI and original operating data. Analysis of the actual performance of these benchmark working faces under their own geological conditions , , , Value to evaluate the advanced level of the working face update .

10. An online evaluation system for intelligent operation of fully mechanized coal mining faces based on dynamic correction of geological conditions, characterized in that, include: A data acquisition and communication module, which is used to acquire equipment operation data on the working surface; The geological conditions management module is used to provide geological conditions data for the working face. The operation indicator calculation module is connected to the data acquisition and communication module to acquire equipment data and calculate equipment operation monitoring indicators. The geological correction model calculation module is connected to the geological condition management module and the operation index calculation module. Based on the geological condition correction equipment operation monitoring index, the automated operation index (FAI) of the fully mechanized mining face is obtained.

Images