Construction method of adaptive cutting guide control system of coal mining machine based on digital twinning

Abstract

The invention provides a construction method of a self-adaptive cutting guide control system of a coal mining machine based on digital twinning, and relates to the technical field of self-adaptive cutting of coal mining machines. The method specifically comprises the following steps: designing a complex dirt band thin coal seam coal mining machine cutting state sensing method and a complex dirt band thin coal seam coal mining machine self-adaptive control strategy; the method comprises the following steps: based on a complex dirt band thin coal seam coal mining machine cutting state sensing method and a complex dirt band thin coal seam coal mining machine self-adaptive control strategy, establishing a complex dirt band thin coal seam coal mining machine self-adaptive cutting digital twinborn model for simulating the self-adaptive cutting process of the complex dirt band thin coal seam coal mining machine; and constructing a mechanism characteristic life prediction model driven by a digital model and a digital twinborn monitoring model for the adaptive cutting dynamic reliability of the coal mining machine for the complex dirt band thin coal seam, wherein the model is used for evaluating the reliability of the adaptive cutting process of the coal mining machine for the complex dirt band thin coal seam in real time. According to the invention, the adaptive capacity of the coal mining machine to the complex dirt band thin coal seam can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of adaptive cutting of coal shearers, and in particular to a method for constructing an adaptive cutting guidance and control system of a coal shearer based on digital twins. Background Art

[0002] To promote the intelligent development of the coal mining process, the status of the equipment cluster at the coal mining machine working face can gradually be transparently monitored. However, for the mining process of thin coal seams with complex and diverse geological conditions, the full-process intelligent safety decision-making and autonomous judgment of high-reliability operation throughout the life cycle of the coal mining machine still require the online participation of operators. In addition, due to the spatial characteristics of the geological structure of thin coal seams, the adaptive guidance and cutting system of thin coal seam coal mining machines places higher requirements on the coordination of knowledge in multiple disciplines such as mechanics, electrical, hydraulics, and control, as well as the fusion performance of multi-source heterogeneous data information. Digital twins are based on the modeling of multi-source heterogeneous data. It is a new concept and system architecture for controlling physical processes. Its main feature is the adaptive ability and flexibility of the elements closely related to the twin process and the physical process to change with the changes in the physical process. It is crucial to the research and application of intelligent power transmission systems for complex interbedded thin coal seams with gangue. Therefore, in order to achieve intelligent, safe and efficient coal mining, the technical architecture and key technologies of the intelligent mining face based on digital twins, the system framework construction and the collaborative evolution of virtual and real data have been proposed one after another. However, there is still a lack of in-depth research and effective implementation methods for the virtual-real collaborative control and dynamic and highly reliable operation of the power transmission system of the coal mining machine in complex thin coal seams.

[0003] The dynamic process of intelligently and efficiently cutting and breaking coal and rock containing interbedded gangue by a shearer is characterized by non-equilibrium, nonlinearity, time-varying nature, and strong coupling. Furthermore, constructing a digital twin model of the power transmission system for intelligently cutting interbedded gangue by a shearer in thin coal seams involves the integration of knowledge from multiple disciplines. Currently, the main bottleneck is the structural evolution of highly efficient thin coal seam shearers. The adaptive improvement of these machines is influenced by factors such as diverse heterogeneous information, motion parameters, and dynamic control strategies for control systems. The complex and diverse occurrence conditions of thin coal seams, as well as the structural weaknesses of the shearer in responding to their environment, all lead to significant differences in the coupling relationships between the physical model, virtual model, decision model, and interaction model. Summary of the Invention

[0004] In response to the above-mentioned shortcomings of the existing technology, the present invention, based on the concept of digital twin technology, proposes a method for constructing an adaptive cutting and control system of a coal mining machine based on digital twin. The method aims to utilize the dynamic system characteristics of the coal mining machine during the adaptive cutting process, develop an intelligent power transmission system, and open up new fields and applications for intelligent coal mining machines.

[0005] The present invention proposes a method for constructing a guidance and control system for a coal mining machine adaptively cutting complex thin coal seams with gangue based on digital twins, comprising:

[0006] Design a cutting state perception method and adaptive control strategy for shearers in complex thin coal seams with gangue;

[0007] Based on the cutting state perception method of the shearer in complex thin coal seams with gangue and the adaptive control strategy of the shearer in complex thin coal seams with gangue, a digital twin model of the shearer in complex thin coal seams with gangue is established to simulate the adaptive cutting process of the shearer in complex thin coal seams with gangue.

[0008] Based on the digital twin model of the adaptive cutting of the coal shearer in complex thin coal seams with gangue, a digital-analog-driven mechanism characteristic life prediction model and a digital twin monitoring model of the dynamic reliability of the adaptive cutting of the coal shearer in complex thin coal seams with gangue are constructed to evaluate the reliability of the adaptive cutting process of the coal shearer in complex thin coal seams with gangue in real time.

[0009] Furthermore, the specific contents of the cutting state perception method of the coal shearer with complex design and thin coal seam with gangue are as follows:

[0010] Through a virtual simulation experiment based on the cutting vibration mechanism of a thin coal seam coal shearer, the cutting process of the thin coal seam coal shearer under different combinations of coal-rock ratios, different coal-rock structures, and different coal-rock hardnesses was simulated. Based on the simulation results, a nonlinear correlation model between the coal-rock cutting state and the vibration signal of the thin coal seam coal shearer was constructed. The nonlinear correlation model between the coal-rock cutting state and the vibration signal of the thin coal seam coal shearer was represented by a one-dimensional vibration acceleration curve.

[0011] A customized information transformation model is used to convert the one-dimensional vibration acceleration curve into a two-dimensional time-frequency spectrum image. Data analysis is then used to extract the cross-term features of the two-dimensional time-frequency spectrum image. The physical significance of the two-dimensional time-frequency spectrum image is then verified by comparing the extracted cross-term features with the physical phenomena during the shearer cutting process.

[0012] Using the feature information processing module, the two-dimensional time-frequency spectrum image processed by the information transformation customized model is fused with the multi-source data information image obtained according to the distribution of the structural changes of any complex interbedded coal seam. The generated multi-source data information fusion image is used to build a basic data sample library for cutting state recognition.

[0013] A cutting state classification and recognition model is constructed using the cutting state recognition basic data sample library.

[0014] Furthermore, the specific contents of the adaptive control strategy of the complex thin coal seam with gangue are as follows:

[0015] Define the performance indicators of the shearer for complex thin coal seams with gangue, including cutting area, productivity, cutting specific energy consumption, cutting resistance, load fluctuation coefficient and coal charging rate;

[0016] Define the motion parameters of the complex thin coal seam shearer, including: traction speed v q and speed n;

[0017] The multi-task Gaussian algorithm is used to fit the fitting surfaces and fitting errors of various performance indicators and shearer motion parameters, and the functional equations of various performance indicators and shearer motion parameters are obtained to construct a comprehensive performance indicator evaluation model.

[0018] The constraints of the shearer's motion parameters were defined based on actual working conditions. Based on the thin-seam shearer drum auxiliary design and load calculation software, the comprehensive performance index evaluation model was divided into several regions along the cutting direction. Within each region, a segmented fitting method was used to approximate the constraints of the shearer's motion parameters.

[0019] The optimization objectives are to maximize the cutting area, productivity, and coal loading rate, while minimizing the cutting specific energy consumption, cutting resistance, and load fluctuation coefficient. Based on the theory of approximate ideal solution sorting, the kinematic parameter combinations of the shearer under different working conditions are used as evaluation objects, and the performance index is used as the evaluation index. An n*m decision matrix is ​​established between the evaluation objects and the evaluation index, and then forward and standardized. This matrix generates the optimal kinematic parameter combinations of the shearer under different working conditions. n represents the number of evaluation objects, and m represents the number of evaluation indexes.

[0020] A mechanical-electrical-hydraulic-control coupling model is constructed based on the optimal motion parameter combination of the coal mining machine under different working conditions, and a control sequence is designed based on the constructed mechanical-electrical-hydraulic-control coupling model; wherein the control sequence is: a control strategy of the coal mining machine based on a control model in which the drum speed takes precedence over the traction speed, a control model in which the traction speed takes precedence over the drum speed, and a coordinated control model;

[0021] A model associating the control strategy with the coal seam structure and movement parameters is established based on the designed control sequence, so as to automatically select the optimal control strategy based on the coal seam structure and movement parameters;

[0022] The deep reinforcement learning method is used to optimize the model that associates the control strategy with the coal seam structure and motion parameters, and an adaptive control model is obtained, which is used to generate an adaptive cutting optimal control strategy according to actual working conditions.

[0023] Furthermore, the digital twin model of the adaptive cutting of the shearer in complex thin coal seams with gangue includes: a physical perception layer, a virtual simulation layer, a twin decision layer and a data interaction layer;

[0024] The physical perception layer is used to construct the physical structure system of the coal mining equipment and to perform intelligent monitoring of the physical structure system of the coal mining equipment by designing multiple physical sensors, so as to obtain the working status information of the coal mining equipment in complex and thin coal seams in real time;

[0025] The virtual simulation layer is used to construct a high-precision three-dimensional twin model of a dynamic, complex, thin coal seam with gangue. By combining the working status information of the coal mining machine in the complex, thin coal seam with gangue acquired in real time, an adaptive control model is used to generate an adaptive cutting optimal control strategy for adaptively adjusting and controlling the action of the coal mining machine physical structure system in the physical perception layer.

[0026] The twin decision layer is used to optimize the cutting process of the shearer in complex thin coal seams with gangue by identifying the cutting state of the shearer in real time through the cutting state classification and recognition model based on the working state information obtained by the physical perception layer and the dynamic high-precision three-dimensional twin model of complex thin coal seams with gangue constructed by the virtual simulation layer;

[0027] The data interaction layer is used to transmit and interact data between the physical perception layer, the virtual simulation layer, and the twin decision layer to achieve dynamic adjustment of the adaptive cutting of the coal mining machine in complex thin coal seams with gangue.

[0028] Furthermore, the physical perception layer is constructed as follows: the physical perception layer includes three parts: a coal mining machine physical structure system, a multi-physical sensor design, and a data acquisition system; wherein the coal mining machine physical structure system is a coal mining machine adaptive cutting control comprehensive test bench designed based on similarity theory and cutting experiments;

[0029] The design method of the multi-physical sensor is as follows: through dynamic analysis of the load pattern of key components of the coal mining machine cutting part, the sensing force points are determined, and the layout of the multi-physical sensor is designed according to the sensing force points; the sensors are arranged according to the layout of the multi-physical sensor, and according to the cutting state sensing method of the coal mining machine with complex gangue and thin coal seams, a spiral drum cutting vibration sensing system, a square head vibration sensing system and a rocker arm vibration sensing system are constructed to obtain the posture parameter information of the coal mining machine with complex gangue and thin coal seams in real time, and the multi-source data information collected in real time by each physical sensor during the coal mining machine cutting process is used to identify the cutting state of the coal mining machine with thin coal seams, so as to realize dynamic monitoring of the coal mining machine cutting complex thin coal seams; wherein the posture parameter information includes: traction speed, rotation speed and rocker arm adjustment height;

[0030] The posture parameter information of the complex thin coal seam with gangue and the multi-source data information collected by multiple physical sensors are used as the working state information of the complex thin coal seam with gangue;

[0031] The data acquisition system is used to monitor and record the operating parameters of the coal mining machine adaptive cutting control comprehensive test bench and the working status data collected in real time by multiple physical sensors.

[0032] Furthermore, the method for constructing the virtual simulation layer is as follows: coal and rock samples are collected from typical working faces and tested for physical and mechanical properties, the physical property parameters of the coal and rock mass are determined based on discrete elements, and a discrete element model of the coal and rock mass is constructed. Based on the application programming interface (API) technology, the discrete element model of the coal and rock mass is modified by compiling a replacement API for multiple particle type clusters, thereby constructing a dynamic, complex, and high-precision three-dimensional twin model of thin coal seams with interbedded gangue, which can correct and replace particle sets in real time.

[0033] Based on the real-time acquired posture parameter information of the shearer in complex and thin coal seams, the shearer's cutting action is simulated and the dynamic complex and thin coal seams with gangue and gangue are corrected and replaced in real time. A high-precision three-dimensional twin model of the complex and thin coal seams with gangue is constructed based on the adaptive control strategy of the shearer in complex and thin coal seams using multi-source data information collected by multiple physical sensors. The adaptive control model is used to generate the shearer's adaptive cutting optimal control strategy. The shearer's adjustment action is virtually executed according to the generated adaptive cutting optimal control strategy to generate the expected working status information.

[0034] Feedback of the virtually executed adjustment action to the physical perception layer guides the coal mining machine's physical structure system to perform actions, obtains the working status information after the action, and evaluates the effectiveness of the adaptive cutting optimal control strategy by comparing the expected working status information with the working status information after the action. The adaptive cutting optimal control strategy is adjusted based on the evaluation results, and then the adjustment action of the coal mining machine is virtually executed again to form a closed-loop control process.

[0035] A coal-rock coupling model of a shearer's rigid-flexible coupling virtual prototype is established, and the shearer's hydraulic system and electronic control system are integrated into the virtual simulation layer. Interface technology is used to achieve interconnection between models, determine the input and output of each model, and perform joint simulation to simulate the cutting process of a shearer in complex thin coal seams with interbedded gangue.

[0036] Furthermore, the twin decision layer is constructed by using the discrete element model of the coal and rock mass constructed in the virtual simulation layer as a basis, and constructing a test model of the coal seam cut by the coal mining machine by changing the position, thickness and rock properties of the interlayer of the coal and rock mass discrete element model in the virtual simulation layer. The test model is used to analyze the force law, vibration characteristics and pick state of the spiral drum in the coal mining machine when cutting coal and rock, and to construct a model of the formation process of coal rock crushing, collapse, flow and coupling surface interface pressure in the process of the coal mining machine system cutting the interlayer of coal and rock, which is used for the coal rock crushing, collapse, flow and interface pressure formation in the coal mining machine cutting process.

[0037] Based on the construction of a model of the coal rock crushing, collapse, flow and the formation of the interface pressure of the coupling surface during the process of cutting the coal rock with gangue by the coal shearer system, a cutting state classification and recognition model is constructed by using the cutting state perception method of the coal shearer in the complex thin coal seam with gangue, which is used to monitor the cutting state of the coal shearer in the thin coal seam.

[0038] During the shearer cutting process in complex thin coal seams with gangue, the coal rock flow velocity field characteristics are obtained by extracting the running speed and displacement parameters of coal rock particles, and the dynamic load distribution of the shearer is simulated by optimizing the running speed and displacement parameters of coal rock particles.

[0039] According to the characteristics of the coal rock flow velocity field and the dynamic load distribution of the coal shearer, the cutting process of the coal shearer in complex thin coal seams with gangue is simulated using the virtual simulation layer, and the cutting state classification and recognition model is used to identify the cutting state of the coal shearer in real time. According to the recognition results and the working state information obtained from the physical perception layer, the cutting parameters and cutting path are dynamically adjusted to optimize the cutting process of the coal shearer in complex thin coal seams with gangue.

[0040] Furthermore, the method for constructing the data interaction layer is as follows: for the multiple physical sensors set in the physical perception layer, each physical sensor is regarded as a sensor node, a cluster head node is selected and a clustering strategy is adopted to divide all the sensor nodes into different clusters; a network topology structure adapted to the underground scenario is designed, a routing protocol is formulated according to the network topology structure and the clustering strategy, a multi-objective algorithm is adopted to optimize the routing protocol, the network topology structure is optimized by clustering, optimizing the cluster head and constructing a fitness function model, and the optimized network topology structure is used as the communication structure of the data interaction layer; and the loading of the routing protocol is completed by reading the external file of the import model of the real-time information of the coal and rock cutting status.

[0041] Furthermore, the method for constructing the digital-analog driven mechanism characteristic life prediction model is as follows:

[0042] A multi-domain collaborative coupling simulation method was used to measure the wear of shearer picks and spiral blades in different interbedded coal seams. Based on the measured wear, the wear distribution characteristics of the picks and spiral blades in different interbedded coal seams were analyzed.

[0043] Based on the wear distribution characteristics of shearer picks and spiral blades in different interbedded coal seams, the single factor method was used to analyze the effects of coal rock compressive strength, drum structural parameters, and shearer kinematic parameters on spiral drum wear.

[0044] The operating data of shearers in complex and thin coal seams with gangue in different interbedded coal seams were collected as historical big data, including cutting parameters, cutting damage, cutting impact signal frequency, and cutting time. A big data model of cutting parameters, cutting damage, cutting impact signal frequency, and cutting time was constructed based on the results of single-factor analysis. The big data model was then used to fit the historical big data to generate an initial life prediction curve for shearers in complex and thin coal seams with gangue.

[0045] Real-time acquisition of acceleration signals and operating data of shearers in complex thin coal seams with gangue, and use of big data models to generate current life prediction curves for shearers in complex thin coal seams with gangue;

[0046] Based on the digital model-driven method, the life attenuation characteristics of the coal mining machine are mined. According to the generated initial life prediction curve and current life prediction curve, the meta-learning theory is used to adjust the big data model and the fitted historical life prediction curve is corrected in real time in combination with the life attenuation characteristics.

[0047] Furthermore, the method for constructing the digital twin monitoring model of the adaptive cutting dynamic reliability of the complex thin coal seam with gangue is as follows:

[0048] The shearer's cutting process under different coal seam conditions was simulated using a rigid-flexible coupling virtual prototype model in the virtual simulation layer. The structural characteristics of the shearer during real-time service were obtained based on the simulation results. These structural characteristics were used to identify the focus areas of key components in the shearer's cutting section, and state functions for the maximum stress and maximum amplitude of key components were established.

[0049] Based on the state functions of the maximum stress and maximum amplitude of key components, the stress reliability, frequency reliability, and amplitude reliability of key components are evaluated using stress-intensity interference theory, resonance failure theory, and reliability sensitivity theory. Furthermore, the reliability of the design variables of key parts of the shearer cutting section is evaluated through sensitivity analysis and used as the reliability sensitivity index of the shearer adaptive cutting system.

[0050] Based on the Copula function, the historical failure data of key parts of the shearer cutting part and the simulation results are used to establish the failure mode correlation and key component correlation, and the reliability of key components and the reliability of the shearer adaptive cutting system are obtained. The reliability of key components and the reliability of the shearer adaptive cutting system are used as the reliability indicators of the shearer adaptive cutting system.

[0051] Based on the simulation results, the equivalent stress index of the key parts of the shearer cutting part and the dynamic characteristic index of the shearer are obtained;

[0052] A comprehensive performance evaluation model for the dynamic reliability of the shearer's adaptive cutting process for complex interbedded coal and rock is constructed using the equivalent stress index of the shearer's key parts, the state functions of the maximum stress and maximum amplitude of the key parts, the stress reliability, frequency reliability, and amplitude reliability of the key parts, the system reliability sensitivity index, the system reliability index, and the shearer's dynamic characteristic index. Based on the genetic algorithm theory, the comprehensive performance evaluation model for the dynamic reliability of the shearer's adaptive cutting process for complex interbedded coal and rock is implemented with genetic encoding, fitness analysis, and multi-generation evolution to obtain the natural frequencies of the shearer's key parts, which are used to optimize the shearer's key parts and the shearer's adaptive cutting system.

[0053] The shearer's historical cutting data, cutting parameters, and reliability evaluation data are obtained and integrated through multi-domain collaborative control technology. The integrated data is used to train a particle swarm optimization long short-term memory (PSO)-LSTM model to obtain a predictive model for evaluating the reliability of key components and the shearer's adaptive cutting system.

[0054] This prediction model is used to build a digital twin monitoring model for the dynamic reliability of adaptive cutting of coal shearers in complex thin coal seams with gangue. The model is used to optimize key components and the adaptive cutting system of the coal shearer according to the evaluation results of the prediction model, and to realize real-time evaluation and monitoring of the dynamic reliability of key components and the adaptive cutting of the coal shearer in the process of adaptive cutting of coal shearers in complex thin coal seams with gangue.

[0055] The beneficial effects of adopting the above technical solution are:

[0056] The method of the present invention is based on the concept of digital twin technology. It adopts a method combining on-site test sampling, virtual prototype technology, multi-domain modeling and collaborative simulation and experimental analysis to establish a multi-domain deep fusion experimental system for multi-source heterogeneous data in the adaptive control cutting process of a coal mining machine in complex thin coal seams with gangue; constructs a mechanical-electrical-hydraulic-control integrated virtual prototype coupling theory and method of the discrete element bonding contact model of the coal rock mass and the coal mining machine power transmission system, takes the bidirectionally coupled coal rock cutting simulation data flow as the main line, and uses accurate characterization of the coal mining machine cutting state information data and reasonable data information processing rules as means, combined with big data analysis to design a coal mining machine cutting state perception model with high accuracy and strong adaptability to thin coal seams; takes the coal mining machine cutting state perception and decision-making control method as the approach, designs an adaptive cutting guidance and control system that enhances the coordination of the data twin of the coal mining machine in complex thin coal seams with gangue by using heterogeneous data information, and improves the coal mining machine's adaptability to complex thin coal seams with gangue.

[0057] The method of the present invention establishes a guidance and control system for coal mining machines to adaptively cut complex thin coal seams with gangue, which integrates physical models, virtual models, decision models and interactive models. This is also an important measure to ensure the optimal comprehensive performance of coal mining machines in thin coal seams under complex geological conditions and to protect the safety and reliability of coal mining machines under changes in external loads. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 Schematic diagram of the intelligent, efficient, and reliable cutting and control digital twin system for structural evolution in this embodiment;

[0059] Figure 2 This is a flow chart of the cutting state perception of a shearer in a complex thin coal seam with gangue in this embodiment;

[0060] Figure 3This is a flow chart of the optimization design of the adaptive control strategy for the shearer in complex thin coal seams with gangue in this embodiment;

[0061] Figure 4 Schematic diagram of the digital space for adaptive cutting of a shearer in a complex thin coal seam with gangue in this embodiment;

[0062] Figure 5 Schematic diagram of the mechanism characteristic life prediction model of digital analog drive in this embodiment;

[0063] Figure 6 Schematic diagram of the digital twin monitoring model for the adaptive cutting dynamic reliability of a coal mining machine in complex thin coal seams with gangue in this embodiment. DETAILED DESCRIPTION

[0064] For ease of understanding of the present application, the specific embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings and embodiments. The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thoroughly and comprehensively understood.

[0065] This implementation method takes anisotropic complex interbedded thin coal seam coal mining machine as the research object, constructs the adaptive cutting guidance and control mechanism and reliability evaluation digital twin model modeling method affected by the synergistic coupling characteristics of mechanical-electrical-hydraulic-control multi-fields, carries out the coal mining machine cutting state perception affected by multi-source data information, different geometric and kinematic parameters-multi-generation evolution structure-health state performance-reliability data model cross-boundary optimization design, and finally forms a set of structural evolution intelligent, efficient and reliable cutting control digital twin system, such as Figure 1 shown.

[0066] A method for constructing a digital twin-based adaptive cutting control system for a coal mining machine is provided in this embodiment. Figure 2 As shown, the method includes the following processes:

[0067] Design a cutting state perception method for a coal shearer in complex thin coal seams with gangue and an adaptive control strategy for a coal shearer in complex thin coal seams with gangue.

[0068] The specific contents of the design of the cutting state perception method of the shearer in the complex thin coal seam with gangue are as follows:

[0069] Through a virtual simulation experiment based on the cutting vibration mechanism of a thin coal seam coal shearer, the cutting process of the thin coal seam coal shearer under the combination of different coal-rock ratios, different coal-rock structures, and different coal-rock hardnesses is simulated, and a nonlinear correlation model between the coal-rock cutting state and the vibration signal of the thin coal seam coal shearer is constructed based on the simulation results; wherein the nonlinear correlation model between the coal-rock cutting state and the vibration signal of the thin coal seam coal shearer is represented by a one-dimensional curve of vibration acceleration.

[0070] In this embodiment, if Figure 2 As shown in the figure, a virtual simulation experiment based on the cutting vibration mechanism of a thin coal seam shearer is conducted to analyze the influence of different coal-rock ratios, different coal-rock structures, and different coal-rock hardness on the time domain information of the vibration signal received by the shearer cutting part during the cutting process. Specifically, different combinations of coal-rock ratios, different coal-rock structures, and different coal-rock hardness are set. Through a virtual simulation experiment based on the cutting vibration mechanism of a thin coal seam shearer, a one-dimensional vibration acceleration curve is obtained and the time domain information is extracted. Based on the extracted time domain information, a nonlinear correlation model is constructed to reflect the relationship between the coal-rock cutting state of the thin coal seam shearer and its corresponding vibration signal.

[0071] The one-dimensional vibration acceleration curve is converted into a two-dimensional time-frequency spectrum image using a customized information transformation model. The cross-term features of the two-dimensional time-frequency spectrum image are extracted using a data analysis method. The physical significance of the two-dimensional time-frequency spectrum image is verified by comparing the extracted cross-term features with the physical phenomena during the shearer cutting process.

[0072] In this embodiment, if Figure 2 As shown in the figure, based on the STFT stationary transformation theory of time-domain to frequency-domain features, a one-dimensional vibration acceleration curve is converted into a two-dimensional time-frequency spectrum image through three steps: segmenting the non-stationary vibration signal, transforming multiple stationary signals, and fitting the signal using a window covering method. Data analysis methods are used to analyze the cross-term features in the transformed image. By suppressing the interference terms in the cross-term features and verifying them with the retained cross-term features, the transformed two-dimensional time-frequency spectrum image accurately reflects the physical process of coal-rock cutting by a thin coal seam shearer, preventing the loss of identification feature information, verifying the physical meaning of the image itself, and realizing the design of a customized model structure for information conversion. The analysis results show that the STFT transformation effectively preserves the time-frequency resolution of the rocker housing vibration information, highlighting the characteristic information of energy clusters, and clearly distinguishing the distribution patterns of energy characteristics under different operating conditions.

[0073] Using the feature information processing module, the two-dimensional time-frequency spectrum image processed by the information transformation customized model is fused with the multi-source data information image obtained that conforms to the distribution of structural changes of arbitrarily complex interbedded coal seams, and the generated multi-source data information fusion image is used to build a basic data sample library for cutting state recognition.

[0074] In this embodiment, based on the information transformation customization model, a multi-source data information image fusion design method that conforms to the distribution of structural changes of arbitrarily complex interbedded coal seams is constructed, the feature information processing module is modeled, and the construction of the basic data sample library for cutting state recognition is completed to provide accurate original samples for the augmentation of recognition system data.

[0075] The feature information processing module is used to fuse the two-dimensional time-frequency spectrum image processed by the information transformation customized model with the multi-source data information image obtained that conforms to the distribution of structural changes of any complex interbedded coal seam, and the specific content of the basic data sample library for cutting state recognition is constructed using the generated multi-source data information fusion image:

[0076] The feature information processing module includes: a feature detail fusion model and a feature detail augmentation model.

[0077] The two-dimensional time-frequency spectrum image processed by the customized information transformation model and the multi-source data information image obtained that conforms to the distribution of structural changes of arbitrarily complex interbedded coal seams are input into the feature detail fusion model. The nonlinear and multi-level morphological wavelet fusion algorithm is used to decompose the two-dimensional time-frequency spectrum image and all the multi-source data information images and extract image features respectively. Image fusion is performed based on the extracted image features to generate a multi-source data information fusion image and annotate the coal-rock cutting status of the multi-source data information fusion image. The annotated multi-source data information fusion image is used as the basic data sample.

[0078] The basic data samples are input into the feature detail augmentation model. Based on the generative adversarial network (GANs) model, the model structure parameters of the generator and the discriminator are set. The generator generates new data samples based on the basic data samples, and the discriminator is used to distinguish the new data samples generated by the generator from the basic data samples. A gradient penalty mathematical model is defined to train the generator and the discriminator to obtain trained generators and discriminators.

[0079] The gradient penalty mathematical model is expressed as:

[0080]

[0081] Where GP represents the gradient penalty term; γ represents the penalty coefficient; represents the expectation of the sampling point a' on the distribution P; (a' is the sampling point distributed in the synthetic data sample; is the gradient expression of the discriminator.

[0082] In this embodiment, if Figure 2 As shown, the appropriate wavelet basis and number of decomposition levels are selected to fuse the two-dimensional time-frequency spectrum image processed by the customized information transformation model with the multi-source data information image that conforms to the distribution of structural variations in arbitrarily complex interbedded coal seams. For the feature detail augmentation model, a gradient penalty mathematical model based on image data robustness theory is defined to satisfy the distribution of detail features. The Lipschitz function is used to constrain coherence and verify the imbalance of weight distribution. The Wasserstein distance is used as a criterion for evaluating sample types to provide evaluation data for predicting system stability performance.

[0083] The basic data samples are input into the trained generator and discriminator to obtain new basic data samples, and the basic data samples and the new basic data samples are used to build a basic data sample library for cutting state recognition.

[0084] A cutting state classification and recognition model is constructed using the cutting state recognition basic data sample library.

[0085] The method for constructing the cutting state classification and recognition model is as follows: selecting a convolutional neural network that meets the requirements of the cutting state classification task and adding a classification layer at the end of the convolutional neural network to construct a cutting state classification and recognition model for identifying the cutting state category of the sample data by extracting features from the input sample data, and setting the initial convolution parameters and pooling parameters in the cutting state classification and recognition model; selecting training sets of different data volumes from the cutting state recognition basic data sample library, using different data sets to train the same cutting state classification and recognition model, using the particle swarm algorithm to optimize the cutting state classification and recognition model to obtain the optimized cutting state classification and recognition model, and recording the classification accuracy and root mean square error of the cutting state classification and recognition models trained by different data sets at the same time, and evaluating the performance of the cutting state classification and recognition model under different data conditions by analyzing the linear relationship between the data volume and the classification accuracy and root mean square error of the cutting state classification and recognition model, thereby selecting the optimal cutting state classification and recognition model.

[0086] In this embodiment, if Figure 2 As shown in the figure, the multi-source data information fusion image is used as the database replacement model of the multi-target recognition algorithm, and the variables of the convolution parameters and pooling parameters of the feature extraction and recognition classification structure are further established to achieve the two goals of accuracy and mean root mean square error of recognition classification in perception performance. By analyzing the linear relationship between the input of the augmented model data volume and the output of the recognition model result, the correlation between the recognition response and the model structure and database volume is verified.

[0087] The specific contents of the adaptive control strategy of the complex thin coal seam shearer with gangue are as follows:

[0088] The performance indicators of the shearer for complex thin coal seams with gangue are defined, including cutting area, productivity, cutting specific energy consumption, cutting resistance, load fluctuation coefficient and coal charging rate.

[0089] Define the shearer motion parameters for complex thin coal seams with gangue, including: traction speed v q and speed n.

[0090] The multi-task Gaussian algorithm is used to fit the fitting surfaces and fitting errors of various performance indicators and shearer motion parameters, and the functional equations of various performance indicators and shearer motion parameters are obtained. A comprehensive performance indicator evaluation model is constructed, which is expressed as:

[0091] S(v q ,n)=av q 2 -bv q n+cn 2 +dv q -en+f (2)

[0092] Where S represents the comprehensive performance index evaluation function; a, b, c, d, e, and f represent the weights of each performance index respectively.

[0093] The constraints of the shearer's motion parameters are defined according to actual working conditions. Based on the thin coal seam shearer drum auxiliary design and load calculation software, the comprehensive performance index evaluation model is divided into several regions along the cutting direction. In each region, the constraints of the shearer's motion parameters are approximated using a segmented fitting method.

[0094] The constraints are expressed as:

[0095] X=(x1,x2) T =(v q ,n) T (3)

[0096] Where X represents the constraint condition; x1 and x2 are both constraint items.

[0097] The optimization objectives are defined as maximizing the cutting area, productivity and coal loading rate, and minimizing the cutting specific energy consumption, cutting resistance and load fluctuation coefficient. Based on the theory of approximate ideal solution sorting, the shearer motion parameter combinations under different working conditions are taken as evaluation objects, and the performance indicators are taken as evaluation indicators. An n*m decision matrix between the evaluation objects and the evaluation indicators is established, and forward and normalized processing is performed to generate the optimal motion parameter combinations of the shearer under different working conditions. Here, n represents the number of evaluation objects, and m represents the number of evaluation indicators.

[0098] A mechanical-electrical-hydraulic-control coupling model is constructed according to the optimal motion parameter combination of the coal mining machine under different working conditions, and a control sequence is designed according to the constructed mechanical-electrical-hydraulic-control coupling model; wherein the control sequence is: the drum speed takes precedence over the traction speed control model, the traction speed takes precedence over the drum speed control model and the coordinated control model coal mining machine control strategy.

[0099] According to the designed control sequence, a model associating the control strategy with the coal seam structure and movement parameters is established to automatically select the optimal control strategy according to the coal seam structure and movement parameters.

[0100] The deep reinforcement learning method is used to optimize the model that associates the control strategy with the coal seam structure and motion parameters, and an adaptive control model is obtained, which is used to generate an adaptive cutting optimal control strategy according to actual working conditions.

[0101] In this embodiment, if Figure 3 As shown in the figure, a comprehensive performance index evaluation model of thin coal seam shearer is constructed based on multi-objective parameter optimization design theory, and a multi-task Gaussian algorithm is used to fit the cutting area, productivity, cutting energy consumption, cutting resistance, load fluctuation coefficient, coal loading rate and shearer motion parameters (v q -n) and the fitting surface and fitting error between them, the functional equations between each performance and the shearer motion parameters are obtained. Based on the thin coal seam shearer drum auxiliary design and load calculation software, the comprehensive performance index evaluation model is divided into several areas along the cutting direction. The thickness, position and hardness of the gangue layer in different intervals are different. The constraint conditions of the shearer motion parameters are approximated by the segmented fitting method. With the maximum cutting area, productivity and coal loading rate, and the minimum cutting energy consumption, cutting resistance and load fluctuation coefficient as the optimization goals, based on the theory of approximate ideal solution sorting, an n*m decision matrix between the above evaluation objects and evaluation indicators is established, and it is subjected to forward and standardization processing to clarify the optimal and worst solutions corresponding to each optimization goal, so as to obtain the optimal combination of shearer motion parameters under different working conditions, that is, directly taking the optimal solution corresponding to each optimization goal. The constructed mechanical-electrical-hydraulic-control coupling model is used to design the control sequence. Based on the changes in the performance indicators of the coal mining machine during the adjustment process, the control strategies of the coal mining machine using the drum speed priority over traction speed control model, the traction speed priority over drum speed control model and the collaborative control model are clarified. A model is formed to associate the control strategy with the coal seam structure and performance parameters. The applicability and rationality of the motion parameter control strategy for the optimal comprehensive performance of the coal mining machine in various complex interbedded thin coal seams are obtained. Based on deep learning theory, a deep reinforcement learning adaptive control model is constructed to obtain the optimal control strategy for adaptive cutting.

[0102] Based on the cutting state perception method of the coal shearer in complex thin coal seams with gangue and the adaptive control strategy of the coal shearer in complex thin coal seams with gangue, an adaptive cutting digital twin model of the coal shearer in complex thin coal seams with gangue is established to simulate the adaptive cutting process of the coal shearer in complex thin coal seams with gangue.

[0103] The digital twin model of the adaptive cutting of the complex thin coal seam shearer with gangue includes: a physical perception layer, a virtual simulation layer, a twin decision layer and a data interaction layer.

[0104] In this embodiment, if Figure 4 As shown in the figure, taking the MG2×55 / 250-BWD complex interbedded thin coal seam shearer as the research object, a digital twin model of the shearer's adaptive cutting is established. The model structure includes four levels: physical perception layer, virtual simulation layer, twin decision layer, and data interaction layer. The digital space of the shearer's adaptive cutting in complex interbedded thin coal seams is constructed based on three-dimensional models, virtual scenes, and behavioral logic principles.

[0105] The physical perception layer is used to construct the physical structure system of the coal mining equipment and to perform intelligent monitoring of the physical structure system of the coal mining equipment by designing multiple physical sensors, so as to obtain the working status information of the coal mining equipment in complex and thin coal seams in real time;

[0106] The working status information includes: posture parameter information of the complex gangue-interposed thin coal seam coal mining machine and multi-source data information collected by multiple physical sensors; wherein the posture parameter information includes: traction speed, rotation speed and rocker arm adjustment height.

[0107] In this embodiment, through the design of the physical structure system of the coal mining machine equipment, the relationship between multiple physical sensors and information fusion and the data acquisition system, the current thin coal seam coal mining process of complex interbedded coal and rock, which mainly relies on manual observation, is transformed into intelligent information acquisition, while strengthening the deep integration of information.

[0108] The method for constructing the physical perception layer is as follows: the physical perception layer includes three parts, namely: a coal mining machine physical structure system, a multi-physical sensor design and a data acquisition system; wherein the coal mining machine physical structure system is a coal mining machine adaptive cutting control comprehensive test bench designed based on similarity theory and cutting experiments.

[0109] In this embodiment, according to the disclosed design method of the comprehensive test bench for adaptive cutting control of coal mining machines, a comprehensive test bench for adaptive cutting control of coal mining machines is designed and developed according to similarity theory and cutting experiments. The comprehensive test bench consists of a mechanical system, a hydraulic system, an electrical system, a data acquisition and transmission system, a test bench control and monitoring system, and a host machine; the mechanical system consists of a coal wall clamping device, a cutting device, and a cable conveying device; the coal wall clamping device includes an experimental gantry and a base; the cutting device includes: a spiral drum, a rocker arm, a sliding platform, and a guide rail; the spiral drum is based on the MG2×55 / 250-BWD thin coal seam coal mining machine spiral drum as a prototype, and a drum similarity model is established; the hydraulic system consists of a top clamping cylinder acting on the coal wall, left and right side clamping cylinders and a push cylinder, a sliding platform lateral propulsion cylinder, a sliding platform traction cylinder, a rocker arm height adjustment cylinder, a drum drive motor, and auxiliary components such as a pump station; the electrical system includes a motor control pump motor, a main motor, a filter motor, and a cooling fan.

[0110] The design method of the multi-physical sensor is as follows: through dynamic analysis of the load-bearing rules of key components of the coal mining machine cutting part, the sensing force points are determined, and the layout of the multi-physical sensors is designed according to the sensing force points; the sensors are arranged according to the layout of the multi-physical sensor, and according to the cutting state perception method of the coal mining machine with complex gangue and thin coal seams, a spiral drum cutting vibration perception system, a square head vibration perception system and a rocker arm vibration perception system are constructed to obtain the posture parameter information of the coal mining machine with complex gangue and thin coal seams in real time, and the multi-source data information collected in real time by each physical sensor during the coal mining machine cutting process is used to identify the cutting state of the thin coal seam coal mining machine, so as to realize dynamic monitoring of the coal mining machine cutting complex thin coal seams.

[0111] The layout of the multi-physical sensors is as follows: for the coal mining machine adaptive cutting control comprehensive test bench, a torque sensor and a vibration acceleration transmitter are installed between the drum and the hydraulic motor to monitor the motor speed, torque and vibration characteristics during the drum cutting of coal and rock; a magnetostrictive displacement sensor is installed at the tail end of the traction cylinder to measure the traction speed; pressure transmitters are installed on the coal wall clamping cylinder, traction cylinder, height adjustment cylinder, accumulator, pump station, motor circuit and transverse propulsion locking cylinder respectively to measure the pressure of the coal wall clamping cylinder, traction cylinder, height adjustment cylinder, accumulator, pump station, motor circuit and transverse propulsion locking cylinder.

[0112] In this embodiment, the spiral drum, square head, and rocker arm are all key components of the shearer's cutting unit. Using the previously described method for sensing the cutting state of a shearer with complex, thin coal seams, a spiral drum cutting vibration sensing system, a square head vibration sensing system, and a rocker arm vibration sensing system are formed. A torque sensor and a vibration acceleration transmitter are installed between the drum and the hydraulic motor to comprehensively test the motor speed, torque, and vibration characteristics during the drum's coal and rock cutting process. The cutting state of the thin coal seam shearer is identified using multi-source sensor data as characteristic parameters. A magnetostrictive displacement sensor installed at the tail end of the traction cylinder is combined with the time taken for the traction process to determine the traction speed of the test bench shearer. Pressure transmitters are used to measure the pressures of the coal wall clamping cylinder, traction cylinder, height adjustment cylinder, accumulator, pump station, motor circuit, and lateral thrust locking cylinder. These measurement results are combined to dynamically monitor the shearer's cutting process of complex, thin coal seams.

[0113] The data acquisition system is used to monitor and record the operating parameters of the coal mining machine adaptive cutting control comprehensive test bench and the working status data collected in real time by multiple physical sensors.

[0114] In this embodiment, if Figure 4As shown, the existing data acquisition system is used to monitor and record the operating parameters of the coal mining machine adaptive cutting control comprehensive test bench and the working status data collected in real time by multiple physical sensors.

[0115] The virtual simulation layer is used to construct a high-precision three-dimensional twin model of a dynamic, complex, and thin coal seam with gangue. By combining the working status information of the coal mining machine in the complex, thin coal seam with gangue obtained in real time, an adaptive control model is used to generate an adaptive cutting optimal control strategy for adaptively adjusting and controlling the action of the physical structure system of the coal mining machine in the physical perception layer.

[0116] The method for constructing the virtual simulation layer is as follows: coal and rock samples are collected from typical working faces and their physical and mechanical properties are tested, the physical property parameters of the coal and rock mass are determined based on discrete elements, and a discrete element model of the coal and rock mass is constructed. Based on the application programming interface (API) technology, the discrete element model of the coal and rock mass is corrected by compiling a replacement API for a cluster of multiple particle types, and a dynamic, complex, and thin coal seam with interbedded gangue is constructed with high precision three-dimensional twin model that can correct and replace particle sets in real time.

[0117] In this embodiment, if Figure 4 As shown, for Yanzhou Coal's Yangcun Mine and Datong Coal's Tashan Mine, typical working face coal samples containing complex interlayers, hard nodules, and faults of varying hardness and number of layers were selected according to sampling standards for physical and mechanical property testing. This was done to determine the coal and rock mass physical parameters based on discrete element methods, including intrinsic material parameters, basic contact parameters, and contact model parameters. By integrating Application Program Interface technology, a replacement API for multiple particle clusters was compiled. This replacement API enabled real-time model correction, dynamically adjusting the particle set in the model based on the operating status of the shearer and the actual response of the coal and rock mass. Through behavioral logic programming, interactive simulation between the shearer and the coal and rock model was achieved, simulating the shearer's cutting process under different coal seam conditions. A high-precision 3D twin model of complex interlayered thin coal seams was constructed, allowing for real-time correction and replacement of particle sets, achieving high-fidelity restoration of complex interlayered thin coal seams.

[0118] According to the real-time acquired posture parameter information of the shearer in complex and thin coal seams with gangue, the cutting action of the shearer is simulated and the dynamic high-precision three-dimensional twin model of the complex and thin coal seams with gangue is corrected and replaced in real time. Based on the adaptive control strategy of the shearer in complex and thin coal seams with gangue, an adaptive control model is constructed using multi-source data information collected by multiple physical sensors. The adaptive control model is used to generate the adaptive cutting optimal control strategy of the shearer. According to the generated adaptive cutting optimal control strategy, the adjustment action of the shearer is virtually executed to generate the expected working status information.

[0119] The adjustment action performed virtually is fed back to the physical perception layer to guide the physical structure system of the coal mining machine to perform actions, and the working status information after the action is obtained. The effectiveness of the adaptive cutting optimal control strategy is evaluated by comparing the expected working status information with the working status information after the action. The adaptive cutting optimal control strategy is adjusted according to the evaluation results, and then the adjustment action of the coal mining machine is virtually executed again to form a closed-loop control process.

[0120] In this embodiment, if Figure 4 As shown in the figure, by obtaining the attitude parameter information of the coal mining machine, the corresponding action simulation is completed in the virtual simulation layer, including speed regulation and height adjustment. Then, the adaptive control model is used to virtually execute the adjustment action to adjust the attitude and position of the coal mining machine in the physical perception layer. That is, the traction speed and rotation speed of the coal mining machine and the height of the rocker arm are adjusted in real time according to the structural distribution of the coal seam to realize closed-loop adaptive adjustment control.

[0121] A coal-rock coupling model of a shearer's rigid-flexible coupling virtual prototype is established, and the shearer's hydraulic system and electronic control system are integrated into the virtual simulation layer. Interface technology is used to achieve interconnection between models, determine the input and output of each model, and perform joint simulation to simulate the cutting process of a shearer in complex thin coal seams with interbedded gangue.

[0122] In this embodiment, if Figure 4 As shown, a coal-cutting coupled model of a rigid-flexible coupled virtual prototype of a coal mining machine, a hydraulic system and an electronic-control system are established, and the interconnection between the system models is realized based on the interface technology, and the input and output of each system model are determined, and joint simulation is performed.

[0123] The twin decision layer is used to optimize the cutting process of the shearer in complex thin coal seams with gangue by identifying the cutting state of the shearer in real time through the cutting state classification and recognition model based on the working state information obtained by the physical perception layer and the dynamic high-precision three-dimensional twin model of complex thin coal seams with gangue constructed by the virtual simulation layer.

[0124] The method for constructing the twin decision layer is as follows: using the discrete element model of the coal and rock mass constructed in the virtual simulation layer as a basis, by changing the position, thickness and rock properties of the interlayer of the coal and rock mass discrete element model in the virtual simulation layer to construct a test model of the coal seam cut by the coal shearer, and using this test model to analyze the force law, vibration characteristics and tooth state of the spiral drum cutting the coal and rock in the coal shearer, and constructing a process model of coal rock crushing, collapse, flow and coupling surface interface pressure formation in the process of the coal shearer system cutting the interlayer of coal and rock, which is used for coal rock crushing, collapse, flow and interface pressure formation in the coal shearer cutting process.

[0125] Based on the construction of a model of coal rock crushing, collapse, flow and the formation of coupling surface interface pressure during the process of cutting coal rock with gangue by a coal shearer system, a cutting state perception method for shearers in thin coal seams with complex gangue is used to construct a cutting state classification and recognition model for monitoring the cutting state of shearers in thin coal seams.

[0126] In this embodiment, if Figure 4 As shown in the figure, a discrete element model containing different interlayer hardness structures was used as the basis. By changing the location, thickness, and rock properties of the interlayer, a test model for shearer cutting coal seams was constructed. The test model of shearer cutting coal seams was used to analyze the force law, vibration characteristics, and pick state of the spiral drum cutting coal rock. A model was constructed for the formation of coal rock crushing, collapse, flow, and coupling surface interface pressure during the shearer system cutting interlayer coal rock. A thin coal seam shearer cutting state perception, recognition, and monitoring model was constructed based on a multi-source data information fusion network model. The model includes three modules: data generation, accuracy evaluation, and online monitoring. It is used to realize multi-mode recognition and monitoring of thin coal seam shearer cutting state under different data sources.

[0127] During the cutting process of a shearer in a complex thin coal seam with gangue, the coal rock flow velocity field characteristics are obtained by extracting the running speed and displacement parameters of coal rock particles. The dynamic load distribution of the shearer is simulated by optimizing the running speed and displacement parameters of coal rock particles.

[0128] According to the characteristics of the coal rock flow velocity field and the dynamic load distribution of the coal shearer, the cutting process of the coal shearer in complex thin coal seams with gangue is simulated using the virtual simulation layer, and the cutting state classification and recognition model is used to identify the cutting state of the coal shearer in real time. According to the recognition results and the working state information obtained from the physical perception layer, the cutting parameters and cutting path are dynamically adjusted to optimize the cutting process of the coal shearer in complex thin coal seams with gangue.

[0129] In this embodiment, if Figure 4 As shown, the velocity and displacement parameters of coal rock particles are extracted to obtain the characteristics of the coal rock flow velocity field, including velocity magnitude, direction, and change trend. A program to optimize the velocity and displacement parameters of coal rock particles is developed to obtain the dynamic load distribution of the shearer. Simulation provides the digital twin model with a data stream, namely cutting parameters and cutting paths, thereby improving the accuracy of the twin model, enabling real-time monitoring of the shearer's cutting status during the cutting process, and optimizing motion parameters to make the cutting process more efficient.

[0130] The data interaction layer is used to transmit and interact data between the physical perception layer, the virtual simulation layer, and the twin decision layer to achieve dynamic adjustment of the adaptive cutting of the coal mining machine in complex thin coal seams with gangue.

[0131] The data interaction layer is constructed as follows: for the multiple physical sensors set in the physical perception layer, each physical sensor is regarded as a sensor node, a cluster head node is selected, and a clustering strategy is adopted to divide all sensor nodes into different clusters; a network topology structure adapted to the underground scenario is designed, a routing protocol is formulated according to the network topology structure and the clustering strategy, a multi-objective algorithm is adopted to optimize the routing protocol, the network topology structure is optimized by clustering, optimizing cluster heads, and constructing a fitness function model, and the optimized network topology structure is used as the communication structure of the data interaction layer; and the routing protocol is loaded by reading an external file of an import model of real-time information on the coal and rock cutting status.

[0132] In this embodiment, if Figure 4 As shown, the data interaction layer model is centered around a large number of sensor nodes, integrated with a host computer and switches. The model is divided into a transmission data model and an interaction data model, effectively connecting the underground physical perception layer, the central control system's twin decision-making layer, and the surface virtual simulation layer. To improve the timeliness of information transmission network systems and reduce system energy consumption, this paper analyzes the inherent characteristics of wireless sensor networks, such as their large scale, self-organization, and high fault tolerance. Taking into account constraints such as the underground coal mine working environment and the distribution patterns of sensor nodes, a network topology suitable for underground scenarios, namely the communication structure of the data interaction layer, is designed. A multi-objective algorithm is used to improve the routing protocol. By clustering, optimizing cluster heads, and constructing a fitness function model, nodes are ensured to quickly find the optimal transmission path during information transmission. A model for importing real-time information on coal and rock cutting status is established. The routing protocol is loaded by reading an external file containing the imported model, resulting in a highly efficient and low-loss data interaction layer model.

[0133] Based on the digital twin model of the adaptive cutting of the coal shearer in complex thin coal seams with gangue, a digital-analog-driven mechanism characteristic life prediction model and a digital twin monitoring model of the dynamic reliability of the adaptive cutting of the coal shearer in complex thin coal seams with gangue are constructed to evaluate the reliability of the adaptive cutting process of the coal shearer in complex thin coal seams with gangue in real time.

[0134] The method for constructing the digital model-driven mechanism characteristic life prediction model is as follows:

[0135] The multi-domain collaborative coupling simulation method is used to measure the wear of the picks and spiral blades of the coal shearer in different coal seams with gangue. Based on the measured wear, the wear distribution characteristics of the picks and spiral blades of the coal shearer in different coal seams with gangue are analyzed.

[0136] Based on the wear distribution characteristics of shearer picks and spiral blades in different interbedded coal seams, the single factor method was used to analyze the effects of coal rock compressive strength, drum structural parameters, and shearer kinematic parameters on spiral drum wear.

[0137] The operating data of the shearer in complex and thin coal seams with gangue are collected in different gangue-interbedded coal seams as historical big data, including cutting parameters, cutting damage, cutting impact signal frequency and cutting time. A big data model of cutting parameters, cutting damage, cutting impact signal frequency and cutting time is constructed based on the results of single factor analysis. The big data model is then used to fit the historical big data to generate an initial life prediction curve for the shearer in complex and thin coal seams with gangue.

[0138] The acceleration signals and operating data of the shearer in complex and thin coal seams with gangue are collected in real time, and the current life prediction curve of the shearer in complex and thin coal seams with gangue is generated using the big data model.

[0139] Based on the digital model-driven method, the life attenuation characteristics of the coal mining machine are mined. According to the generated initial life prediction curve and current life prediction curve, the meta-learning theory is used to adjust the big data model and the fitted historical life prediction curve is corrected in real time in combination with the life attenuation characteristics.

[0140] In this embodiment, if Figure 5 As shown in the figure, the existing multi-domain collaborative coupling simulation method is used to measure the wear distribution characteristics of the picks and spiral blades of coal mining machines in different interbedded coal seams. Based on the single-factor method, the influence of coal rock compressive strength, drum structural parameters, and coal mining machine kinematic parameters on spiral drum wear is analyzed. The big data model of cutting parameters, cutting damage, cutting impact signal frequency, and cutting time is determined. Based on this, the initial life prediction curve of the coal mining machine in thin coal seams is derived by fitting the historical big data curve. Based on the real-time acceleration signal and the mechanism model obtained above, the meta-learning theory is combined with the big data model to predict and correct the historical life prediction curve in real time. Based on the digital model-driven mining of the coal mining machine life attenuation characteristics, a digital model-driven mechanism characteristic life prediction model is established.

[0141] The method for constructing the digital twin monitoring model of the adaptive cutting dynamic reliability of the complex thin coal seam with gangue is as follows:

[0142] The coal-rock cutting coupling model of the shearer rigid-flexible coupling virtual prototype in the virtual simulation layer is used to simulate the cutting process of the shearer under different coal seam conditions. The structural characteristics of the shearer in real-time service are obtained based on the simulation results. The structural characteristics are used to identify the focus areas of the key parts of the shearer cutting part, and the state functions of the maximum stress and maximum amplitude of the key components are established.

[0143] Based on the state functions of the maximum stress and maximum amplitude of key components, the stress reliability, frequency reliability and amplitude reliability of key components are evaluated respectively using the stress-intensity interference theory, resonance failure theory and reliability sensitivity theory. Then, the reliability of the design variables of the key parts of the coal shearer cutting part is evaluated through sensitivity analysis and used as the reliability sensitivity index of the coal shearer adaptive cutting system.

[0144] Based on the Copula function, the historical failure data of key parts of the shearer cutting part and the simulation results are used to establish the failure mode correlation and key component correlation. The reliability of key components and the reliability of the shearer adaptive cutting system are obtained. The reliability of key components and the reliability of the shearer adaptive cutting system are used as the reliability indicators of the shearer adaptive cutting system.

[0145] Based on the simulation results, the equivalent stress index of the key parts of the coal mining machine cutting part and the dynamic characteristic index of the coal mining machine are obtained.

[0146] A comprehensive performance evaluation model for the dynamic reliability of the shearer in the process of adaptive cutting of complex coal and rock with gangue is constructed using the equivalent stress indicators of the key parts of the shearer cutting part, the state functions of the maximum stress and maximum amplitude of the key parts, the stress reliability, frequency reliability and amplitude reliability of the key parts, the system reliability sensitivity index, the system reliability index and the dynamic characteristic index of the shearer. Based on the genetic algorithm theory, the comprehensive performance evaluation model for the dynamic reliability of the shearer in the process of adaptive cutting of complex coal and rock with gangue is implemented with genetic encoding, fitness analysis and multi-generation evolution to obtain the natural frequencies of the key parts of the shearer cutting part and the adaptive cutting system of the shearer.

[0147] In this embodiment, if Figure 6 As shown in the figure, based on the structural characteristics of a shearer during real-time service, the focus areas of key components in the shearer's cutting section were identified. The relationship between the focus areas and the maximum amplitude of key components in the shearer's cutting section was fitted using MATLAB, and state functions for the maximum stress and maximum amplitude of key components were established to simulate the stress and vibration conditions of these components during service. Combining stress-strength interference theory, resonance failure theory, and reliability sensitivity theory, the stress reliability, frequency reliability, and amplitude reliability of key components were analyzed, as well as the reliability sensitivity of design variables. Based on Copula functions, the correlation between failure modes and key components was established, resulting in the reliability of key components and the reliability of the shearer's adaptive cutting system. A comprehensive dynamic reliability performance evaluation model for the shearer's adaptive cutting of complex interbedded coal and rock was constructed by combining the equivalent stress indicators of key components, the state functions of the maximum stress and maximum amplitude of key components, the stress reliability, frequency reliability, and amplitude reliability of key components, the system reliability sensitivity index, the system reliability index, and the dynamic characteristics index of the shearer. Genetic encoding, fitness analysis, and multi-generational evolution were then applied to the model to achieve the evolutionary design of key components and the system.

[0148] The historical cutting data, cutting parameters and reliability evaluation data of the shearer are obtained and integrated through multi-domain collaborative control technology. The fused data is used to train the particle swarm optimization long short-term memory (PSO-LSTM) model, and a prediction model is obtained for evaluating the reliability of key components and the adaptive cutting system of the shearer.

[0149] This prediction model is used to build a digital twin monitoring model for the dynamic reliability of adaptive cutting of coal shearers in complex thin coal seams with gangue. The model is used to optimize key components and the adaptive cutting system of the coal shearer according to the evaluation results of the prediction model, and to realize real-time evaluation and monitoring of the dynamic reliability of key components and the adaptive cutting of the coal shearer in the process of adaptive cutting of coal shearers in complex thin coal seams with gangue.

[0150] In this embodiment, if Figure 6 As shown in the figure, a digital twin monitoring model for the dynamic reliability of adaptive cutting of a coal mining machine in complex thin coal seams with gangue is built. Through multi-domain collaborative control technology, virtual simulation data and historical cutting data are integrated, and the cutting parameters and dynamic reliability evaluation data of the coal mining machine are combined. The particle swarm optimization long short-term memory PSO-LSTM neural network algorithm is used as an alternative model of the multi-objective genetic algorithm. The cutting parameters and reliability evaluation data are written into the PSO-LSTM neural network algorithm. The reliability of key components and systems is evaluated through the algorithm simulation results, and real-time evaluation and monitoring of the dynamic reliability of key components and systems in the adaptive cutting process are achieved.

[0151] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope defined by the claims of the present invention.

Claims

1. A method for constructing an adaptive cutting guidance and control system for a coal mining machine based on digital twins, characterized in that: The method includes the following steps: Design a cutting state perception method and adaptive control strategy for shearers in complex thin coal seams with gangue; Based on the cutting state perception method of the shearer in complex thin coal seams with gangue and the adaptive control strategy of the shearer in complex thin coal seams with gangue, a digital twin model of the shearer in complex thin coal seams with gangue is established to simulate the adaptive cutting process of the shearer in complex thin coal seams with gangue. Based on the digital twin model of the adaptive cutting of the coal shearer in complex thin coal seams with gangue, a digital-analog-driven mechanism characteristic life prediction model and a digital twin monitoring model of the dynamic reliability of the adaptive cutting of the coal shearer in complex thin coal seams with gangue are constructed to evaluate the reliability of the adaptive cutting process of the coal shearer in complex thin coal seams with gangue in real time.

2. A method for constructing a coal mining machine adaptive cutting guidance and control system based on digital twin according to claim 1, characterized in that: The specific contents of the design of the cutting state perception method of the shearer in the complex thin coal seam with gangue are as follows: Through a virtual simulation experiment based on the cutting vibration mechanism of a thin coal seam coal shearer, the cutting process of the thin coal seam coal shearer under different combinations of coal-rock ratios, different coal-rock structures, and different coal-rock hardnesses was simulated. Based on the simulation results, a nonlinear correlation model between the coal-rock cutting state and the vibration signal of the thin coal seam coal shearer was constructed. The nonlinear correlation model between the coal-rock cutting state and the vibration signal of the thin coal seam coal shearer was represented by a one-dimensional vibration acceleration curve. A customized information transformation model is used to convert the one-dimensional vibration acceleration curve into a two-dimensional time-frequency spectrum image. Data analysis is then used to extract the cross-term features of the two-dimensional time-frequency spectrum image. The physical significance of the two-dimensional time-frequency spectrum image is then verified by comparing the extracted cross-term features with the physical phenomena during the shearer cutting process. Using the feature information processing module, the two-dimensional time-frequency spectrum image processed by the information transformation customized model is fused with the multi-source data information image obtained according to the distribution of the structural changes of any complex interbedded coal seam. The generated multi-source data information fusion image is used to build a basic data sample library for cutting state recognition. A cutting state classification and recognition model is constructed using the cutting state recognition basic data sample library.

3. The method for constructing a coal mining machine adaptive cutting guidance and control system based on digital twin according to claim 2, characterized in that: The specific contents of the adaptive control strategy of the complex thin coal seam shearer with gangue are as follows: Define the performance indicators of the shearer for complex thin coal seams with gangue, including cutting area, productivity, cutting specific energy consumption, cutting resistance, load fluctuation coefficient and coal charging rate; Define the motion parameters of the complex thin coal seam shearer, including: traction speed v q and speed n; The multi-task Gaussian algorithm is used to fit the fitting surfaces and fitting errors of various performance indicators and shearer motion parameters, and the functional equations of various performance indicators and shearer motion parameters are obtained to construct a comprehensive performance indicator evaluation model. The constraints of the shearer's motion parameters were defined based on actual working conditions. Based on the thin-seam shearer drum auxiliary design and load calculation software, the comprehensive performance index evaluation model was divided into several regions along the cutting direction. Within each region, a segmented fitting method was used to approximate the constraints of the shearer's motion parameters. The optimization objectives are to maximize the cutting area, productivity, and coal loading rate, while minimizing the cutting specific energy consumption, cutting resistance, and load fluctuation coefficient. Based on the theory of approximate ideal solution sorting, the kinematic parameter combinations of the shearer under different working conditions are used as evaluation objects, and the performance index is used as the evaluation index. An n*m decision matrix is ​​established between the evaluation objects and the evaluation index, and then forward and standardized. This matrix generates the optimal kinematic parameter combinations of the shearer under different working conditions. n represents the number of evaluation objects, and m represents the number of evaluation indexes. A mechanical-electrical-hydraulic-control coupling model is constructed based on the optimal motion parameter combination of the coal mining machine under different working conditions, and a control sequence is designed based on the constructed mechanical-electrical-hydraulic-control coupling model; wherein the control sequence is: a control strategy of the coal mining machine based on a control model in which the drum speed takes precedence over the traction speed, a control model in which the traction speed takes precedence over the drum speed, and a coordinated control model; A model associating the control strategy with the coal seam structure and movement parameters is established based on the designed control sequence, so as to automatically select the optimal control strategy based on the coal seam structure and movement parameters; The deep reinforcement learning method is used to optimize the model that associates the control strategy with the coal seam structure and motion parameters, and an adaptive control model is obtained, which is used to generate an adaptive cutting optimal control strategy according to actual working conditions.

4. The method for constructing a digital twin-based adaptive cutting guidance and control system for a coal mining machine according to claim 3, characterized in that: The digital twin model of the adaptive cutting of the complex thin coal seam with gangue includes: a physical perception layer, a virtual simulation layer, a twin decision layer and a data interaction layer; The physical perception layer is used to construct the physical structure system of the coal mining equipment and to perform intelligent monitoring of the physical structure system of the coal mining equipment by designing multiple physical sensors, so as to obtain the working status information of the coal mining equipment in complex and thin coal seams in real time; The virtual simulation layer is used to construct a high-precision three-dimensional twin model of a dynamic, complex, thin coal seam with gangue. By combining the working status information of the coal mining machine in the complex, thin coal seam with gangue acquired in real time, an adaptive control model is used to generate an adaptive cutting optimal control strategy for adaptively adjusting and controlling the action of the coal mining machine physical structure system in the physical perception layer. The twin decision layer is used to optimize the cutting process of the shearer in complex thin coal seams with gangue by identifying the cutting state of the shearer in real time through the cutting state classification and recognition model based on the working state information obtained by the physical perception layer and the dynamic high-precision three-dimensional twin model of complex thin coal seams with gangue constructed by the virtual simulation layer; The data interaction layer is used to transmit and interact data between the physical perception layer, the virtual simulation layer, and the twin decision layer to achieve dynamic adjustment of the adaptive cutting of the coal mining machine in complex thin coal seams with gangue.

5. The method for constructing a digital twin-based adaptive cutting control system for a coal mining machine according to claim 4, characterized in that: The construction method of the physical perception layer is as follows: the physical perception layer includes three parts: coal machine physical structure system, multi-physical sensor design and data acquisition system; The coal mining machine physical structure system is a coal mining machine adaptive cutting control comprehensive test bench designed based on similarity theory and cutting experiments; The design method of the multi-physical sensor is as follows: through dynamic analysis of the load pattern of key components of the coal mining machine cutting part, the sensing force points are determined, and the layout of the multi-physical sensor is designed according to the sensing force points; the sensors are arranged according to the layout of the multi-physical sensor, and according to the cutting state sensing method of the coal mining machine with complex gangue and thin coal seams, a spiral drum cutting vibration sensing system, a square head vibration sensing system, and a rocker arm vibration sensing system are constructed to obtain the posture parameter information of the coal mining machine with complex gangue and thin coal seams in real time, and the multi-source data information collected in real time by each physical sensor during the coal mining machine cutting process is used to identify the cutting state of the coal mining machine with thin coal seams, thereby realizing dynamic monitoring of the coal mining machine cutting complex thin coal seams; The posture parameter information includes: traction speed, rotation speed and rocker arm adjustment height; The posture parameter information of the complex thin coal seam with gangue and the multi-source data information collected by multiple physical sensors are used as the working state information of the complex thin coal seam with gangue; The data acquisition system is used to monitor and record the operating parameters of the coal mining machine adaptive cutting control comprehensive test bench and the working status data collected in real time by multiple physical sensors.

6. The method for constructing a digital twin-based adaptive cutting control system for a coal mining machine according to claim 5, characterized in that: The virtual simulation layer is constructed by collecting coal and rock samples from a typical working face and testing their physical and mechanical properties. Discrete element-based physical parameters of the coal and rock mass are determined, and a discrete element model of the coal and rock mass is constructed. Based on application programming interface (API) technology, the discrete element model of the coal and rock mass is modified by compiling a replacement API for multiple particle clusters. This results in a dynamic, complex, and high-precision three-dimensional twin model of thin coal seams with interbedded gangue, which can modify and replace particle sets in real time. Based on the real-time acquired posture parameter information of the shearer in complex and thin coal seams, the shearer's cutting action is simulated and the dynamic complex and thin coal seams with gangue and gangue are corrected and replaced in real time. A high-precision three-dimensional twin model of the complex and thin coal seams with gangue is constructed based on the adaptive control strategy of the shearer in complex and thin coal seams using multi-source data information collected by multiple physical sensors. The adaptive control model is used to generate the shearer's adaptive cutting optimal control strategy. The shearer's adjustment action is virtually executed according to the generated adaptive cutting optimal control strategy to generate the expected working status information. Feedback of the virtually executed adjustment action to the physical perception layer guides the coal mining machine's physical structure system to perform actions, obtains the working status information after the action, and evaluates the effectiveness of the adaptive cutting optimal control strategy by comparing the expected working status information with the working status information after the action. The adaptive cutting optimal control strategy is adjusted based on the evaluation results, and then the adjustment action of the coal mining machine is virtually executed again to form a closed-loop control process. A coal-rock coupling model of a shearer's rigid-flexible coupling virtual prototype is established, and the shearer's hydraulic system and electronic control system are integrated into the virtual simulation layer. Interface technology is used to achieve interconnection between models, determine the input and output of each model, and perform joint simulation to simulate the cutting process of a shearer in complex thin coal seams with interbedded gangue.

7. The method for constructing a coal mining machine adaptive cutting guidance and control system based on digital twin according to claim 6, characterized in that: The twin decision layer is constructed by using the discrete element model of the coal and rock mass constructed in the virtual simulation layer as a basis, and constructing a test model of the coal seam cut by a shearer by changing the position, thickness, and rock properties of the interlayer of the coal and rock mass discrete element model in the virtual simulation layer. The test model is used to analyze the force law, vibration characteristics, and pick state of the spiral drum in the coal shearer when cutting coal and rock, and a model of the formation process of coal rock crushing, collapse, flow, and coupling surface interface pressure during the process of the coal shearer system cutting the interlayer of coal and rock is constructed, which is used to analyze the coal rock crushing, collapse, flow, and interface pressure formation during the coal shearer cutting process. Based on the construction of a model of the coal rock crushing, collapse, flow and the formation of the interface pressure of the coupling surface during the process of cutting the coal rock with gangue by the coal shearer system, a cutting state classification and recognition model is constructed by using the cutting state perception method of the coal shearer in the complex thin coal seam with gangue, which is used to monitor the cutting state of the coal shearer in the thin coal seam. During the shearer cutting process in complex thin coal seams with gangue, the coal rock flow velocity field characteristics are obtained by extracting the running speed and displacement parameters of coal rock particles, and the dynamic load distribution of the shearer is simulated by optimizing the running speed and displacement parameters of coal rock particles. According to the characteristics of the coal rock flow velocity field and the dynamic load distribution of the coal shearer, the cutting process of the coal shearer in complex thin coal seams with gangue is simulated using the virtual simulation layer, and the cutting state classification and recognition model is used to identify the cutting state of the coal shearer in real time. According to the recognition results and the working state information obtained from the physical perception layer, the cutting parameters and cutting path are dynamically adjusted to optimize the cutting process of the coal shearer in complex thin coal seams with gangue.

8. The method for constructing a coal mining machine adaptive cutting guidance and control system based on digital twin according to claim 7, characterized in that: The data interaction layer is constructed as follows: for the multiple physical sensors set in the physical perception layer, each physical sensor is regarded as a sensor node, a cluster head node is selected, and a clustering strategy is adopted to divide all sensor nodes into different clusters; a network topology structure adapted to the underground scenario is designed, a routing protocol is formulated according to the network topology structure and the clustering strategy, a multi-objective algorithm is adopted to optimize the routing protocol, the network topology structure is optimized by clustering, optimizing cluster heads, and constructing a fitness function model, and the optimized network topology structure is used as the communication structure of the data interaction layer; and the routing protocol is loaded by reading an external file of an import model of real-time information on the coal and rock cutting status.

9. The method for constructing a digital twin-based adaptive cutting guidance and control system for a coal mining machine according to claim 8, characterized in that: The method for constructing the digital model-driven mechanism characteristic life prediction model is as follows: A multi-domain collaborative coupling simulation method was used to measure the wear of shearer picks and spiral blades in different interbedded coal seams. Based on the measured wear, the wear distribution characteristics of the picks and spiral blades in different interbedded coal seams were analyzed. Based on the wear distribution characteristics of shearer picks and spiral blades in different interbedded coal seams, the single factor method was used to analyze the effects of coal rock compressive strength, drum structural parameters, and shearer kinematic parameters on spiral drum wear. The operating data of shearers in complex and thin coal seams with gangue in different interbedded coal seams were collected as historical big data, including cutting parameters, cutting damage, cutting impact signal frequency, and cutting time. A big data model of cutting parameters, cutting damage, cutting impact signal frequency, and cutting time was constructed based on the results of single-factor analysis. The big data model was then used to fit the historical big data to generate an initial life prediction curve for shearers in complex and thin coal seams with gangue. Real-time acquisition of acceleration signals and operating data of shearers in complex thin coal seams with gangue, and use of big data models to generate current life prediction curves for shearers in complex thin coal seams with gangue; Based on the digital model-driven method, the life attenuation characteristics of the coal mining machine are mined. According to the generated initial life prediction curve and current life prediction curve, the meta-learning theory is used to adjust the big data model and the fitted historical life prediction curve is corrected in real time in combination with the life attenuation characteristics.

10. A method for constructing a coal mining machine adaptive cutting guidance and control system based on digital twins according to claim 9, characterized in that: The method for constructing the digital twin monitoring model of the adaptive cutting dynamic reliability of the complex thin coal seam with gangue is as follows: The shearer's cutting process under different coal seam conditions was simulated using a rigid-flexible coupling virtual prototype model in the virtual simulation layer. The structural characteristics of the shearer during real-time service were obtained based on the simulation results. These structural characteristics were used to identify the focus areas of key components in the shearer's cutting section, and state functions for the maximum stress and maximum amplitude of key components were established. Based on the state functions of the maximum stress and maximum amplitude of key components, the stress reliability, frequency reliability, and amplitude reliability of key components are evaluated using stress-intensity interference theory, resonance failure theory, and reliability sensitivity theory. Furthermore, the reliability of the design variables of key parts of the shearer cutting section is evaluated through sensitivity analysis and used as the reliability sensitivity index of the shearer adaptive cutting system. Based on the Copula function, the historical failure data of key parts of the shearer cutting part and the simulation results are used to establish the failure mode correlation and key component correlation, and the reliability of key components and the reliability of the shearer adaptive cutting system are obtained. The reliability of key components and the reliability of the shearer adaptive cutting system are used as the reliability indicators of the shearer adaptive cutting system. Based on the simulation results, the equivalent stress index of the key parts of the shearer cutting part and the dynamic characteristic index of the shearer are obtained; A comprehensive performance evaluation model for the dynamic reliability of the shearer's adaptive cutting process for complex interbedded coal and rock is constructed using the equivalent stress index of the shearer's key parts, the state functions of the maximum stress and maximum amplitude of the key parts, the stress reliability, frequency reliability, and amplitude reliability of the key parts, the system reliability sensitivity index, the system reliability index, and the shearer's dynamic characteristic index. Based on the genetic algorithm theory, the comprehensive performance evaluation model for the dynamic reliability of the shearer's adaptive cutting process for complex interbedded coal and rock is implemented with genetic encoding, fitness analysis, and multi-generation evolution to obtain the natural frequencies of the shearer's key parts, which are used to optimize the shearer's key parts and the shearer's adaptive cutting system. The shearer's historical cutting data, cutting parameters, and reliability evaluation data are obtained and integrated through multi-domain collaborative control technology. The integrated data is used to train a particle swarm optimization long short-term memory (PSO)-LSTM model to obtain a predictive model for evaluating the reliability of key components and the shearer's adaptive cutting system. This prediction model is used to build a digital twin monitoring model for the dynamic reliability of adaptive cutting of coal shearers in complex thin coal seams with gangue. The model is used to optimize key components and the adaptive cutting system of the coal shearer according to the evaluation results of the prediction model, and to realize real-time evaluation and monitoring of the dynamic reliability of key components and the adaptive cutting of the coal shearer in the process of adaptive cutting of coal shearers in complex thin coal seams with gangue.

Images