Logical operation verification system for intelligent lubrication system of coal mining equipment

By building a dynamic coupling network and an adaptive fuzzy logic decision tree, the problem of insufficient data in the intelligent lubrication system of coal mining equipment is solved, and more efficient and safe equipment monitoring and lubrication management are achieved, which improves the overall performance of the system and intelligence level.

CN118655781BInactive Publication Date: 2024-11-15SHANDONG JIKUANG LUNENG COAL POWER CO LTD YANGCHENG COAL MINE
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411109759.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-14
Publication Date
2024-11-15
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The monitoring and logic operation verification methods of existing coal mining equipment intelligent lubrication systems have problems such as one-sided data, lack of dynamic adaptability of logic rules, poor real-time data processing, and insufficient interaction analysis between equipment, resulting in insufficient monitoring efficiency and security.

Method used

By constructing multi-dimensional sensor data tensors, performing nonlinear transformation and wavelet noise reduction, establishing a dynamic coupling network, calculating fractal dimensions, generating an adaptive fuzzy logic decision tree, and introducing logical consistency indicators to fully capture the operating status of the device and between devices. Interaction to realize logical operation verification of intelligent lubrication system.

Benefits of technology

The monitoring and logical operation verification capabilities of the intelligent lubrication system of coal mining equipment have been improved, the operating efficiency and safety of the system have been improved, the equipment maintenance and management have been optimized, and the intelligence level and adaptability of the system have been enhanced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118655781B_ABST
    Figure CN118655781B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of logic operation verification technology, and further to a logic operation verification system for an intelligent lubrication system for coal mining equipment. The logic operation verification method comprises: step 1: initializing the operating parameters of each device of the automated coal mining face; step 2: constructing a data tensor of a multidimensional sensor based on the operating data collected by each sensor group; performing nonlinear transformation and wavelet noise reduction on the data tensor to obtain preprocessed data; step 3: constructing a dynamic coupling network reflecting the interaction between devices based on the preprocessed data; and then calculating the fractal dimension of the dynamic coupling network; step 4: generating an adaptive fuzzy logic decision tree based on the dynamic coupling network and the corresponding fractal dimension. The present invention determines whether to start the intelligent lubrication system through the results of the logic operation verification, which can ensure that the equipment is lubricated when actually needed, improve lubrication efficiency and system safety, and optimize equipment maintenance management.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of logic operation verification, and in particular relates to a logic operation verification system for an intelligent lubrication system of coal mining equipment. Background Art

[0002] In modern coal mining, the application of intelligent lubrication systems for coal mining equipment has become increasingly common. Coal mining equipment includes coal cutters, hydraulic supports, and scraper conveyors. When these equipment operate in a high-intensity working environment, they need frequent lubrication to reduce friction and wear to ensure the normal operation of the equipment. However, the startup and operation of the lubrication system is not a simple timed operation, but depends on the real-time operating status of the equipment and the results of logical operation verification.

[0003] The intelligent lubrication system of coal mining equipment includes coal mining machines, hydraulic supports, scraper conveyors, transfer machines, crushers and belt conveyors. The automated operation of these equipment has greatly improved the efficiency and safety of coal mining. However, as the number and complexity of equipment increase, it becomes particularly important to ensure that these equipment can operate efficiently and in a coordinated manner. This requires us to monitor the operating status of the equipment in real time and verify the logical operation to ensure its safety and reliability during operation. In the prior art, the equipment monitoring and logical operation verification methods of automated coal mining faces mainly rely on traditional monitoring methods and simple logical rules. Although these methods have improved the monitoring efficiency of equipment to a certain extent, there are still some significant problems and limitations.

[0004] First, traditional monitoring methods mostly rely on a single sensor or a simple combination of sensors to obtain equipment operation data. These sensors usually include temperature sensors, vibration sensors, current sensors, and voltage sensors. These sensors can only provide equipment operation information in a single dimension or a small number of dimensions, and it is difficult to fully reflect the comprehensive operation status of the equipment. With the increase in equipment complexity, single sensor data cannot effectively capture the complex interactive relationship between equipment, resulting in the one-sidedness and limitations of monitoring data. Secondly, the existing logic operation verification method mainly relies on preset fixed logic rules. These rules are usually established based on experience and simple logical relationships and lack dynamic adaptability. In practical applications, the operating environment of coal mining working face equipment is complex and changeable, and fixed logic rules are difficult to adapt to these changes, resulting in reduced accuracy and reliability of logic operation verification. For example, when the equipment operating environment changes, the preset logic rules may not be updated and adjusted in time, resulting in inaccurate verification results, and may even miss equipment fault warnings. In addition, existing monitoring and verification systems generally have insufficient data processing capabilities. With the increase in the number of sensors and the amount of data, traditional data processing methods are difficult to efficiently process and analyze massive data. Poor real-time performance and data processing lag have become important factors affecting system performance. The lack of data processing capabilities not only affects the efficiency of monitoring and verification, but also limits the scalability and adaptability of the system. Furthermore, the monitoring system in the existing technology lacks in-depth analysis and modeling of the interaction between devices. The interaction and collaborative work between devices are crucial to the operation of the entire coal mining system. Most existing systems only focus on the operating status of a single device and ignore the dynamic coupling relationship between devices. This isolated monitoring method makes it difficult to discover potential problems and optimization space in the system, limiting the improvement of the overall performance of the system. Summary of the invention

[0005] The main purpose of the present invention is to provide a logic operation verification system for the intelligent lubrication system of coal mining equipment, which significantly improves the monitoring and logic operation verification capabilities of the intelligent lubrication system of coal mining equipment. By comprehensively capturing the operating status of the equipment, deeply analyzing the interactions between the equipment, generating a flexible and adaptive logic decision tree, and introducing scientific logic consistency indicators, the present invention not only improves the operating efficiency and safety of the system, but also provides strong support for intelligent and automated coal mining face management. By deciding whether to start the intelligent lubrication system based on the results of the logic operation verification, it can ensure that the equipment is lubricated when actually needed, improve lubrication efficiency and system safety, optimize equipment maintenance management, improve the level of system intelligence, and promote sustainable development.

[0006] In order to solve the above problems, the technical solution of the present invention is achieved as follows:

[0007] A logic operation verification system for an intelligent lubrication system of coal mining equipment, the system comprising: a logic operation verification part and a control part; the logic operation verification part is used to perform logic operation verification on various equipment of an automated coal mining working face to obtain a logic operation verification result, specifically including:

[0008] Step 1: Initialize the operating parameters of each device of the automated coal mining face; install a corresponding sensor group in each device, each sensor group includes multiple sensors, and collects the operating parameters of the corresponding device in real time;

[0009] Step 2: Based on the operating data collected by each sensor group, a data tensor of a multi-dimensional sensor is constructed; nonlinear transformation and wavelet denoising are performed on the data tensor to obtain preprocessed data;

[0010] Step 3: Based on the preprocessed data, a dynamic coupling network reflecting the interaction between devices is constructed; and then the fractal dimension of the dynamic coupling network is calculated;

[0011] Step 4: Generate an adaptive fuzzy logic decision tree according to the dynamic coupling network and the corresponding fractal dimension; calculate the depth of the adaptive fuzzy logic decision tree, and then calculate the logic consistency index according to the depth of the adaptive fuzzy logic decision tree, and compare the logic consistency index with the set standard value to determine whether it passes the logic operation verification;

[0012] The control part is used to start the intelligent lubrication system to provide lubrication for various equipment when the result of the logic operation verification is passed.

[0013] Furthermore, the equipment of the automated coal mining face includes at least: coal mining machines, hydraulic supports, scraper conveyors, transfer machines, crushers and belt conveyors; the number and types of operating data between equipment are the same; the operating data includes at least: voltage, current, load, number of working cycles, operating time, vibration frequency and temperature.

[0014] Furthermore, suppose there are devices, and the total running data of each device is Class, the time limit is , then the multidimensional sensor data tensor constructed in step 2 Use the following formula to express it:

[0015] ;

[0016] in, and All are subscript indexes; It is The sensor group of the device is at time The first Class operation data; , and The indexes are Dimensions, Indexes Standard basis vectors for dimension and time dimensions; Represents a tensor product.

[0017] Furthermore, in step 2, the data tensor is subjected to nonlinear transformation and wavelet denoising by the following formula to obtain the preprocessed data: :

[0018] ;

[0019] in, and They are Fourier transform and inverse Fourier transform respectively; is the number of layers of wavelet decomposition; is the unit tensor; For the The learning rate of the layer; and Respectively The wavelet transform and inverse wavelet transform of the layer; soft is the soft threshold function, defined as , is the independent variable, is the set soft threshold; For the Adaptive threshold parameters of the layer; is the total number of data points; For the Noise level estimation of the layer; is the tensor decomposition function, is the element-wise product.

[0020] Furthermore, the tensor decomposition function Use the following formula to express it:

[0021] ;

[0022] in, is the core tensor; ReLU is the rectified linear unit activation function; , and They are the factor matrix of the first dimension, the factor matrix of the second dimension, and the factor matrix of the third dimension respectively; , and are the tensor products along the first dimension, the second dimension, and the third dimension respectively; Noise level estimation of the layer Use the following formula to express it:

[0023] ;

[0024] Among them, MAD is the median absolute deviation; Adaptive threshold parameters for layers Use the following formula to express it:

[0025] ;

[0026] Among them, erf is the error function.

[0027] Furthermore, in the dynamic coupling network reflecting the interaction between devices constructed based on the preprocessed data in step 3, the coupling strength between each device is expressed by the following formula:

[0028] ;

[0029] in, Indicates the device and equipment In time The coupling strength; For equipment In time Preprocessed data; For equipment In time Preprocessed data; MI is the mutual information function; For equipment and equipment The physical distance between is the spatial attenuation constant, controlling the effect of distance on the coupling strength; is the steepness parameter of the logistic function; is the midpoint parameter of the logistic function; For equipment and equipment The Granger causality index between is calculated using the following formula:

[0030] ;

[0031] Among them, var is the variance function; For a given hour conditional variance.

[0032] Furthermore, in step 3, the fractal dimension of the dynamic coupling network is calculated using the following formula: :

[0033] ;

[0034] in, is the scale parameter; for The generalized box counting function under scale; Tr is the trace of the matrix, that is, the sum of the main diagonal elements; is the eigenvalue vector of the coupling strength matrix; the coupling strength matrix is ​​based on is a matrix with elements; Eigenvalue vector The elements; is the eigenvalue vector The number of eigenvalues ​​in .

[0035] Furthermore, in step 4, the depth of the adaptive fuzzy logic decision tree is calculated using the following formula: :

[0036] ;

[0037] in, is the preset adaptive adjustment coefficient.

[0038] Furthermore, in step 4, the following formula is used to calculate the logical consistency index according to the depth of the adaptive fuzzy logic decision tree:

[0039] ;

[0040] in, It is the complexity index of adaptive fuzzy logic decision tree; is the scaling parameter; is the hierarchical index of the decision tree; For the The number of decision features of the decision tree of the layer; is the gamma function.

[0041] Furthermore, the complexity index of adaptive fuzzy logic decision tree Use the following formula to calculate:

[0042] ;

[0043] in, is a second-order polylogarithmic function;

[0044] ;

[0045] in, is the fractal dimension function, which is expressed using the following formula:

[0046] ;

[0047] No. The number of decision features in the decision tree of the layer Use the following formula to express it:

[0048] ;

[0049] in, is the subscript index.

[0050] The logic operation verification system for the intelligent lubrication system of coal mining equipment of the present invention has the following beneficial effects: the present invention deeply analyzes the interaction and dynamic changes between devices by constructing a dynamic coupling network and calculating fractal dimensions. Traditional monitoring methods often ignore the complex interaction relationship between devices, while the present invention concretizes the coupling strength and interaction relationship between devices through a dynamic coupling network. The calculation of fractal dimensions further quantifies the complexity of the system and provides a scientific basis for understanding the dynamic coupling relationship between devices. This method not only reveals the interaction mechanism between devices, but also provides important parameter support for generating an adaptive fuzzy logic decision tree, so that the decision tree can more accurately reflect the operation logic of the system. The introduction of the logic consistency index provides a comprehensive and scientific evaluation standard for the logic operation verification of the system. The logic operation verification in the traditional method often lacks systematicity and comprehensiveness, while the present invention comprehensively evaluates whether the logic operation of the system meets the predetermined standard by calculating the logic consistency index, comprehensively considering the coupling strength between devices, the depth and complexity of the decision tree and other factors. This scientific evaluation method not only improves the accuracy of the logic operation verification, but also can timely discover potential problems in the system, warn of equipment failures and abnormalities, and improve the safety and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A schematic flow chart of a method for executing a logic operation verification part of a logic operation verification system for an intelligent lubrication system for coal mining equipment provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0053] Embodiment 1:

[0054] refer to Figure 1 , a logic operation verification system for an intelligent lubrication system of coal mining equipment, the system comprising: a logic operation verification part and a control part; the logic operation verification part is used to perform logic operation verification on various equipment of an automated coal mining working face to obtain a logic operation verification result, specifically including:

[0055] Step 1: Initialize the operating parameters of each device of the automated coal mining face; install a corresponding sensor group in each device, each sensor group includes multiple sensors, and collects the operating parameters of the corresponding device in real time;

[0056] By acquiring the operating data of the equipment in a comprehensive and real-time manner, an accurate and reliable foundation is provided for subsequent data processing and logic operation verification. The sensor group consists of multiple types of sensors, each of which monitors specific operating parameters. For example, the temperature sensor can monitor the temperature changes of the equipment in real time, the vibration sensor can record the vibration frequency and amplitude of the equipment, and the current and voltage sensors can capture the electrical operating status of the equipment. These sensors work together to ensure that the collected data can fully reflect the operating status and environmental changes of the equipment. The installation and initialization process of the sensor group includes selecting the appropriate type and number of sensors to ensure that the key operating parameters of the equipment are covered, and these sensors need to be integrated with the control system of the equipment to achieve real-time transmission and processing of data. In this way, the sensor group can provide multi-dimensional and high-precision operating data, thus laying a solid foundation for subsequent logic operation verification. The operating data collected in real time includes not only instantaneous values, but also historical data of the equipment under different operating conditions. These data can help analyze the operating mode of the equipment, identify potential anomalies and faults, and provide necessary input for the construction of dynamic coupling networks. In addition, the configuration of the sensor group also needs to consider the transmission and storage of data. The data collected by the sensor needs to be transmitted to the central control system through a reliable communication network for further processing and analysis. In this process, it is necessary to ensure the integrity and accuracy of the data to avoid data distortion caused by transmission delay or packet loss. To this end, redundant sensor configuration and advanced data verification algorithms can be used to improve the reliability of data transmission. Through the initialization of step 1, the operating status of the intelligent lubrication system of the coal mining equipment is fully monitored, and the multi-dimensional data provided by the sensor group provides a rich source of information for subsequent data processing and logic operation verification. These data can not only reflect the current status of the equipment, but also predict the future operation trend of the equipment through the analysis of historical data, thereby providing a basis for the dynamic adjustment and optimization of logical operations. For example, in the data collected by the sensor, if the temperature or vibration frequency of a certain device is found to be abnormal, early warning and processing can be carried out in time to prevent the occurrence of equipment failure. In practical applications, the installation and initialization of the sensor group also need to consider the complex environmental factors of the coal mining face. The coal mining face usually has a harsh environment with dust, vibration, high temperature and other factors, so the selection and installation of the sensor needs to have good environmental resistance. At the same time, the maintenance and calibration of the sensor are also crucial. Only by maintaining the high accuracy and stability of the sensor can the reliability of the collected data be ensured. Through these measures, it is ensured that the equipment on the automated coal mining face can continuously and stably provide high-quality operating data under harsh environmental conditions, providing a solid foundation for subsequent logical operation verification.

[0057] Step 2: Based on the operating data collected by each sensor group, a data tensor of a multi-dimensional sensor is constructed; nonlinear transformation and wavelet denoising are performed on the data tensor to obtain preprocessed data;

[0058] In the automated coal mining face, the equipment operating parameters collected by the sensor group in real time include not only single data points at each time point, but also the distribution of these parameters in space and time. By organizing these data into multidimensional tensors, the high-dimensional characteristics of the data can be fully utilized to provide a comprehensive and detailed description of the equipment operating status. This data tensor structure can not only reflect the operating status of a single device, but also reveal the relationship and dynamic changes between different devices, providing a multi-level and multi-dimensional data basis for subsequent logical operation verification. Next, the data tensor is subjected to nonlinear transformation and wavelet denoising. The purpose of nonlinear transformation is to remap the original data by applying nonlinear functions, thereby highlighting the important features and patterns in the data. The operating data of the intelligent lubrication system of coal mining equipment is usually highly nonlinear and complex. Through nonlinear transformation, these complex dynamic characteristics can be better captured and characterized, providing more representative data for subsequent data analysis. Wavelet denoising is to remove the noise components in the data and extract effective signals reflecting the real equipment operating status. In the complex environment of coal mining working face, the data collected by sensors will inevitably be disturbed by various noises, such as mechanical vibration, environmental noise, etc. If these noises are not processed, they may seriously affect the subsequent logical operation verification results. The wavelet denoising method effectively removes noise by decomposing and reconstructing signals, improves the signal-to-noise ratio of the data, and makes the preprocessed data more accurate and reliable. The quality of the preprocessed data directly affects the construction of the dynamic coupling network and the generation of the adaptive fuzzy logic decision tree in the subsequent steps. Therefore, the nonlinear transformation and wavelet denoising processing in step 2 are not only a data cleaning process, but also to ensure the efficient application of data in logical operation verification. Through preprocessing, purer and more distinctive data are obtained, so that the dynamic coupling network can more accurately reflect the interaction relationship between devices, providing a solid data foundation for logical operation verification. At the same time, the application of these preprocessed data in the adaptive fuzzy logic decision tree can also improve the accuracy and effectiveness of the decision tree, so that it can more truly reflect the operating status and logical relationship of the equipment in the calculation and comparison of logical consistency indicators.

[0059] Step 3: Based on the preprocessed data, a dynamic coupling network reflecting the interaction between devices is constructed; and then the fractal dimension of the dynamic coupling network is calculated;

[0060] The operation of each device on the automated coal mining face is not only independent, but also interrelated. In such a complex system, the interaction between each device has an important impact on the overall operation status of the system. By preprocessing the data, the relationship between the devices can be extracted and represented as a dynamic coupling network. In this network, each node represents a device, and the edge represents the coupling relationship between the devices. The strength of the coupling relationship can be quantified by the correlation and dependency between the devices, thus forming a complex network that reflects the dynamic interaction between the devices. The construction of the dynamic coupling network not only helps to understand the interaction between the devices, but also reveals the hidden structure and dynamic changes within the system. For example, by analyzing the nodes and edges in the network, key devices and important interaction relationships can be identified, and potential bottlenecks and failure points can be discovered. This is crucial for the logical operation verification of the automated coal mining face, because only by deeply understanding the interaction between the devices can the logical consistency and operational rationality of the system be accurately judged. Next, calculating the fractal dimension of the dynamic coupling network is an important means to further analyze the complexity of the system. The fractal dimension is an indicator used to describe the geometric structure of a complex system, which can reflect the self-similarity and complexity of the system. In the dynamic coupling network of the automated coal mining face, the fractal dimension can be used to quantify the complexity of the network, thereby evaluating the complexity of the interaction between devices and the stability of the system operation state. By calculating the fractal dimension, the geometric characteristics of the network can be obtained and its impact on the system logic operation verification can be further analyzed.

[0061] The calculation process of fractal dimension involves box counting and scale analysis of the dynamic coupling network. Specifically, by dividing the network and counting the minimum number of boxes required to cover the network, the fractal characteristics of the network can be obtained. This characteristic can not only quantify the complexity of the network, but also reveal the self-similar structure within the system. For the logic operation verification of the automated coal mining face, the fractal dimension provides an important reference indicator for judging the complexity and stability of the system. For example, if the fractal dimension is high, it means that the interaction between the devices is more complex, and the logic operation of the system may be more difficult to verify, requiring more detailed analysis and verification. Based on the analysis results of the dynamic coupling network and fractal dimension, an adaptive fuzzy logic decision tree can be further generated. This process aims to deal with uncertainty and dynamic changes in the system by constructing a decision tree model that combines fuzzy logic and adaptive algorithms. The adaptive fuzzy logic decision tree can not only accurately reflect the interaction between devices, but also adapt to the dynamic changes of the system, thereby providing more reliable logic operation verification results. In this process, the depth and structure of the decision tree depend on the analysis results of the dynamic coupling network and fractal dimension, thereby ensuring the logical consistency and operational rationality of the decision tree. Finally, by calculating the depth and logic consistency index of the adaptive fuzzy logic decision tree, it is possible to evaluate whether the logical operation of the system has passed the verification. The logic consistency index is used to measure the logic consistency and stability of the decision tree to ensure that the operation of the system complies with the predetermined logic rules and standards. By comparing the logic consistency index with the set standard value, it is possible to determine whether the logical operation of the system meets the requirements, thereby achieving comprehensive verification and optimization of the intelligent lubrication system of coal mining equipment.

[0062] Step 4: Generate an adaptive fuzzy logic decision tree based on the dynamic coupling network and the corresponding fractal dimension; calculate the depth of the adaptive fuzzy logic decision tree, and then calculate the logic consistency index based on the depth of the adaptive fuzzy logic decision tree, and compare the logic consistency index with the set standard value to determine whether it passes the logic operation verification.

[0063] First, the generation of the adaptive fuzzy logic decision tree is based on the analysis results of the dynamic coupling network and fractal dimension. The dynamic coupling network reveals the complex interaction relationship between the intelligent lubrication systems of coal mining equipment, while the fractal dimension quantifies the complexity and self-similarity of these relationships. By inputting this information into the decision tree model, an adaptive fuzzy logic decision tree that reflects the interaction and dynamic changes between equipment can be constructed. Fuzzy logic has unique advantages in processing uncertainty and fuzzy information, and can effectively cope with the complex operating environment and changeable operating conditions of the coal mining face. The adaptive algorithm enables the decision tree to be dynamically adjusted according to real-time data, improving the flexibility and adaptability of the decision tree. The generated adaptive fuzzy logic decision tree not only contains the interaction information between equipment, but also combines the complexity analysis results of the dynamic coupling network and fractal dimension, so that the decision tree has higher accuracy and reliability. In the process of logical operation verification, each node of the decision tree represents a fuzzy logic rule, and the path represents the operating logic of the equipment. In this way, the operating relationship and logic rules between equipment can be described comprehensively and meticulously, providing a detailed decision basis for logical operation verification.

[0064] Next, the depth of the adaptive fuzzy logic decision tree is calculated to evaluate the complexity of the decision tree and the length of the decision path. The depth of the decision tree directly reflects the longest path length from the root node to the leaf node, representing the complexity of the decision process. In the logical operation verification of the intelligent lubrication system of coal mining equipment, the depth of the decision tree not only reflects the complexity of the interaction between the equipment, but also reveals the complexity of the logical operation process. By calculating the depth of the decision tree, the logical complexity of the system can be quantified, providing a basis for the calculation of the logical consistency index. The calculation of the logical consistency index is the core of the logical operation verification. The logical consistency index is used to measure the logical consistency and stability of the adaptive fuzzy logic decision tree, ensuring that each logical path of the decision tree is reasonable and complies with the predetermined rules. By analyzing the depth of the decision tree and the logical rules of each layer, the logical consistency index of the entire decision tree can be calculated. The logical consistency index not only reflects the logical relationship within the decision tree, but also reveals the rationality and stability of the equipment operation logic. In the logical operation verification of the intelligent lubrication system of coal mining equipment, the logical consistency index is a key parameter for evaluating the system operation status and the rationality of the logical operation. Finally, comparing the calculated logical consistency index with the set standard value is the final step to determine whether the logical operation verification has passed. The standard value is pre-set according to the system's operating requirements and safety standards. By comparing the logic consistency index with the standard value, it can be determined whether the system's logical operation meets the predetermined standard. If the logic consistency index is higher than the standard value, it indicates that the system's logical operation consistency is good and has passed the logic operation verification; conversely, if the logic consistency index is lower than the standard value, it indicates that the system has problems with inconsistent or unstable logic operations and needs further adjustment and optimization. In practical applications, through the detailed analysis and calculation of the above steps, the logical operation of the intelligent lubrication system of coal mining equipment can be comprehensively and accurately evaluated. The generation of the adaptive fuzzy logic decision tree and the calculation of the logic consistency index not only provide a detailed basis for logic operation verification, but also reveal the interaction and dynamic changes between equipment, providing a strong guarantee for the safe operation of the system. Through the logic operation verification, the logical inconsistency problems in the system can be discovered and corrected in a timely manner, improving the safety and stability of the system.

[0065] The control part is used to start the intelligent lubrication system to provide lubrication for various equipment when the result of the logic operation verification is passed.

[0066] Before the logical operation verification is passed, the system will monitor and analyze the operating parameters of each device in the coal mining face in real time. The data collected by the sensor group can fully understand the workload, wear and lubrication status of the equipment. If the lubrication system is started directly by timing or preset conditions, it may lead to unnecessary lubrication, increase operating costs and difficulty in equipment maintenance. Through logical operation verification, it is ensured that the system is started only when the equipment really needs lubrication to avoid waste of resources and over-lubrication. The logical operation verification process involves nonlinear transformation and wavelet noise reduction processing of multi-dimensional sensor data tensors to obtain accurate equipment operation status data. These pre-processed data construct a dynamic coupling network that reflects the interaction between devices, and calculate its fractal dimension to generate an adaptive fuzzy logic decision tree. Through this complex data processing and analysis method, the lubrication needs of the equipment can be accurately judged and the lubrication efficiency can be improved. Only when the logical operation verification result passes and confirms that the equipment is in a state that requires lubrication, the intelligent lubrication system is started to ensure the best lubrication effect. In the coal mining face, equipment failure will not only lead to production stagnation, but also may cause safety accidents. The logical operation verification method can detect potential failure risks in advance through a detailed analysis of the equipment operation parameters. For example, abnormal operating parameters of a certain equipment may indicate that it needs lubrication. If lubrication is not performed in time, it may cause the equipment to overheat, wear and even fail. After the logical operation verification is passed, the lubrication system is started, and preventive lubrication can be performed before a major failure of the equipment occurs, reducing the risk of equipment failure and improving the safety of the overall system. Traditional equipment lubrication management is usually based on fixed time intervals or the experience of operators. This method is prone to untimely lubrication or over-lubrication. The logical operation verification method uses intelligent analysis methods and combines the real-time operation data of the equipment to make scientific decisions and optimize the lubrication management process. This data-driven maintenance strategy not only improves the operating reliability of the equipment, but also extends the service life of the equipment and reduces maintenance costs. The intelligent lubrication system of coal mining equipment reflects the characteristics of intelligent manufacturing in the era of Industry 4.0 through the logical operation verification method. The system comprehensively applies advanced technologies such as sensor technology, data analysis, fuzzy logic and decision trees to realize the intelligent and automated management of equipment lubrication. This lubrication strategy based on intelligent verification can dynamically adapt to changes in the operating status of the equipment and adjust the lubrication plan in real time, reflecting the high intelligence level of the system and significantly improving the overall production efficiency and equipment maintenance level.

[0067] Embodiment 2: The equipment of the automated coal mining face includes at least: a coal mining machine, a hydraulic support, a scraper conveyor, a transfer machine, a crusher and a belt conveyor; the quantity and type of operating data between the equipment are the same; the operating data includes at least: voltage, current, load, number of working cycles, operating time, vibration frequency and temperature.

[0068] Specifically, first of all, the coal mining machine is one of the core equipment of the coal mining face, and its main task is to cut and crush the coal seam. The coal mining machine will generate a large amount of operating data during the working process, such as voltage, current and load data. These data reflect the working status and performance of the coal mining machine. For example, voltage and current can reveal the operating status of the electrical system, while load data can show the workload and cutting efficiency of the coal mining machine. In addition, the number of working cycles and running time of the coal mining machine are also very important. These data can be used to evaluate the working efficiency and equipment health of the coal mining machine. Vibration frequency and temperature data can be used to monitor the mechanical state of the coal mining machine and discover potential faults and problems in advance. Hydraulic support is another important equipment on the coal mining face. Its main function is to support and protect the coal mining face and prevent the roof from collapsing. The operating data of the hydraulic support also includes voltage, current, load, number of working cycles, running time, vibration frequency and temperature. These data can reflect the working status and support effect of the hydraulic support. For example, voltage and current data can reveal the operating status of the hydraulic system, and load data can show the support strength and workload of the support. The number of working cycles and running time can be used to evaluate the working efficiency and service life of hydraulic supports, while the vibration frequency and temperature data can monitor the mechanical state of hydraulic supports and detect potential faults and problems in advance. Scraper conveyors, transfer machines, crushers and belt conveyors are transportation and processing equipment on automated coal mining faces. These equipment also generate a large amount of data during operation. The operating data of these equipment also includes voltage, current, load, number of working cycles, running time, vibration frequency and temperature. For example, the voltage and current data of scraper conveyors and belt conveyors can reveal the operating status of the electrical system, and the load data can show the workload and transportation efficiency of the conveyor. The number of working cycles and running time can be used to evaluate the working efficiency and service life of the equipment, while the vibration frequency and temperature data can monitor the mechanical state of the equipment and detect potential faults and problems in advance. Through unified operation data collection, the data between these equipment can be effectively compared and analyzed. Since the number and type of operation data between equipment are the same, a complete equipment operation data network can be formed. These data networks can not only reflect the operating status of a single device, but also reveal the relationship and dynamic changes between equipment. For example, by analyzing these data, we can find out whether the abnormal operation of a certain device will affect the operation of other devices, thereby revealing the coupling relationship and synergy between devices. These data play a vital role in the process of logical operation verification. Through comprehensive analysis and processing of these data, a dynamic coupling network reflecting the interaction between devices can be constructed and its fractal dimension can be calculated. The adaptive fuzzy logic decision tree constructed based on these data can reflect the complex logical relationship and dynamic changes between devices.The calculation of the logic consistency index depends on the accuracy and completeness of these data. By comparing the logic consistency index with the set standard value, it can be determined whether the logical operation of the device meets the predetermined standard, thereby achieving the purpose of logic operation verification.

[0069] Example 3: Assume that there are devices, and the total running data of each device is Class, the time limit is , then the multidimensional sensor data tensor constructed in step 2 Use the following formula to express it:

[0070] ;

[0071] in, and All are subscript indexes; It is The sensor group of the device is at time The first Class operation data; , and The indexes are Dimensions, Indexes Standard basis vectors for dimension and time dimensions; Represents a tensor product.

[0072] Specifically, the smoothing part The purpose is to reduce the noise and abnormal fluctuations in the data. Taking time derivatives The processing of can better capture the changing trend and dynamic characteristics of the data. As a normalization factor, it ensures the smoothness and consistency of the processed data at different time points, thereby improving the reliability and stability of the data. This process is particularly important for data collection in the complex environment of automated coal mining faces, because equipment operation data is often affected by a variety of environmental factors, and directly using the original data may lead to inaccurate analysis results. Then, through the tensor product The formula combines different devices and different types of data in the time dimension to form a high-dimensional data tensor This tensor structure not only preserves the multi-class data of each device at different time points, but also reveals the complex relationships of these data in space and time. Specifically, the standard basis vectors , and Represents device index, data type index and time index respectively. Through the tensor product method, these different dimensional data can be effectively integrated to form a complete high-dimensional data structure. In the process of logical operation verification, the multi-dimensional sensor data tensor constructed It plays a vital role. First, by integrating the equipment operation data into a high-dimensional tensor, the interaction and dynamic changes between devices can be captured more comprehensively. This multi-dimensional data representation method enables in-depth analysis of the equipment's operating status and the discovery of potential anomalies and problems. Secondly, by further processing and analyzing the tensor, a dynamic coupling network reflecting the interaction between devices can be constructed, and its fractal dimension can be calculated. These analysis results provide an important basis for the subsequent generation of an adaptive fuzzy logic decision tree. The generation of an adaptive fuzzy logic decision tree depends on high-quality input data. The construction of a multi-dimensional sensor data tensor can ensure the comprehensiveness and accuracy of the input data. This data structure can not only reflect the operating status of a single device, but also reveal the relationship and dynamic changes between devices, making the generated decision tree more accurate and reliable. Each node of the decision tree represents a fuzzy logic rule, and the path represents the operating logic of the device. In this way, the operating relationship and logic rules between devices can be described comprehensively and meticulously, providing a detailed decision basis for the verification of logical operations. By calculating the depth and logic consistency index of the adaptive fuzzy logic decision tree, it is possible to evaluate whether the logical operation of the system has passed the verification. The logical consistency index is used to measure the logical consistency and stability of the decision tree, ensuring that each logical path of the decision tree is reasonable and complies with the predetermined rules. By analyzing and comparing the logical consistency index, it is possible to determine whether the logical operation of the system meets the requirements, thereby achieving comprehensive verification and optimization of the intelligent lubrication system of coal mining equipment.

[0073] Example 4: In step 2, the data tensor is subjected to nonlinear transformation and wavelet denoising by the following formula to obtain preprocessed data: :

[0074] ;

[0075] in, and They are Fourier transform and inverse Fourier transform respectively; is the number of layers of wavelet decomposition; is the unit tensor; For the The learning rate of the layer; and Respectively The wavelet transform and inverse wavelet transform of the layer; soft is the soft threshold function, defined as , is the independent variable, is the set soft threshold; For the Adaptive threshold parameters of the layer; is the total number of data points; For the Noise level estimation of the layer; is the tensor decomposition function, is the element-wise product.

[0076] Specifically, the formula uses Fourier transform and inverse Fourier transform to realize the conversion of data between time domain and frequency domain. Able to convert raw data tensors Converting from the time domain to the frequency domain, in the frequency domain, the frequency characteristics of the data are more obvious, which is helpful for further signal processing. After the data is converted to the frequency domain, it is easier to apply the wavelet transform for multi-scale analysis. Inverse Fourier transform Then convert the processed frequency domain data back to the time domain to ensure that the preprocessed data In the frequency domain, the formula introduces the wavelet transform and inverse wavelet transform , these transformations are used to decompose and reconstruct data at multiple levels. The advantage of wavelet transform lies in its multi-resolution analysis capability, which can effectively decompose the different frequency components in the data, thereby identifying and extracting the main features in the data. In practical applications, wavelet transform can adapt to the local characteristics of the data and is particularly suitable for processing data in the complex environment of automated coal mining faces. Through multi-level wavelet decomposition, the frequency components of the data can be analyzed more carefully, thereby performing more effective noise reduction and feature extraction. The soft threshold function is used in the formula To process the coefficients after wavelet transformation, the definition of soft threshold function is This function is used to perform threshold processing on the wavelet coefficients to remove noise in the data. By setting appropriate threshold parameters , which can effectively filter out high-frequency noise while retaining the main features of the signal. This step is crucial in noise reduction processing, because the data of automated coal mining faces are often interfered by environmental noise, and this method must be used to improve the signal-to-noise ratio of the data. After wavelet noise reduction processing, the formula is The function performs nonlinear transformation, which is used to further enhance the characteristics of the data. The purpose of nonlinear transformation is to amplify subtle changes in the data and make important features more prominent. This step can improve the resolution and recognition of the data, thereby providing more clear and reliable input data for subsequent logical operation verification. The unit tensor in the formula and learning rate It also plays an important regulatory role. Unit tensor As a benchmark, ensure that the data is standardized during the transformation, and the learning rate It is used to adjust the amplitude of transformation at each level to ensure the stability and effectiveness of the preprocessing process. By setting a reasonable learning rate, adaptive transformation and processing can be achieved at different levels, further improving the quality of data preprocessing. In addition, the tensor decomposition function in the formula It also plays an important role in the data preprocessing process. Tensor decomposition is used to decompose high-dimensional data tensors into multiple low-dimensional components, which facilitates data analysis and processing. Through tensor decomposition, data redundancy can be effectively reduced and data processing efficiency can be improved. This process combines wavelet denoising and nonlinear transformation to make the final preprocessed data It has higher quality and better feature representation ability. During the logic operation verification process, preprocess the data It is an important basis for subsequent steps. High-quality preprocessed data can more accurately reflect the operating status of the equipment and provide reliable data support for the construction of the dynamic coupling network and the calculation of the fractal dimension. The dynamic coupling network is used to reveal the interaction and dynamic changes between equipment, while the fractal dimension quantifies the geometric characteristics of these complex relationships. These analysis results directly affect the generation of adaptive fuzzy logic decision trees and the calculation of logical consistency indicators. Through high-quality data preprocessing, the accuracy and reliability of logical operation verification can be ensured, thereby effectively evaluating the operating logic and operation rationality of the intelligent lubrication system of coal mining equipment.

[0077] Example 5: Tensor decomposition function Use the following formula to express it:

[0078] ;

[0079] in, is the core tensor; ReLU is the rectified linear unit activation function; , and They are the factor matrix of the first dimension, the factor matrix of the second dimension, and the factor matrix of the third dimension respectively; , and are the tensor products along the first dimension, the second dimension, and the third dimension respectively; Noise level estimation of the layer Use the following formula to express it:

[0080] ;

[0081] Among them, MAD is the median absolute deviation; Adaptive threshold parameters for layers Use the following formula to express it:

[0082] ;

[0083] Among them, erf is the error function.

[0084] Specifically, the tensor decomposition function The principle is to decompose complex multidimensional data tensors so that the main features of the data can be extracted and retained. The core tensors involved in the formula are and the factor matrix , , The data are combined together through tensor products and then processed by the rectified linear unit (ReLU) activation function to form a new data tensor. This method uses tensor decomposition technology to represent high-dimensional data as low-dimensional components by decomposition, greatly reducing the redundancy of the data and enhancing the feature representation of the data. The ReLU activation function further ensures that the nonlinear characteristics of the data are preserved, making the preprocessed data more representative and accurate when performing logical operation verification. In the noise level estimation process, the median absolute deviation (MAD) is used to calculate the noise level . This process estimates the noise intensity in the data by transforming the data through a wavelet transform and then calculating its MAD value. The advantage of this method is that MAD is a robust statistic that can effectively resist the influence of extreme values ​​and outliers, thereby providing a stable noise estimate. This is particularly important for data processing in complex environments such as automated coal mining faces, because sensor data is often interfered by various environmental noises. Through this robust noise estimation method, the noise in the data can be more accurately identified and removed. Adaptive threshold parameters The calculation of takes into account the number of layers of wavelet decomposition and the total number of data points, and forms a dynamically adjusted threshold through the combination of error function (erf) and logarithmic function. This threshold plays a key role in the soft threshold processing process and can be adjusted according to the specific data characteristics to achieve the best noise reduction effect. The design of adaptive threshold enables flexible processing of noise at different levels, which not only retains the main characteristics of the signal, but also effectively removes high-frequency noise and improves the overall quality of the data. In the process of logical operation verification, these preprocessing steps are the basis for ensuring data accuracy and reliability. High-quality preprocessed data can not only more accurately reflect the operating status of the equipment, but also reveal the mutual relationship and dynamic changes between the equipment. This is crucial for building a dynamic coupling network and calculating the fractal dimension, because these analysis results directly affect the generation of adaptive fuzzy logic decision trees and the calculation of logical consistency indicators. Through high-quality data preprocessing, logical operation verification can more accurately evaluate the operating logic and operation rationality of the intelligent lubrication system of coal mining equipment, ensuring the safety and stability of the system.

[0085] Embodiment 6: In the dynamic coupling network reflecting the interaction between devices constructed based on the preprocessed data in step 3, the coupling strength between each device is expressed by the following formula:

[0086] ;

[0087] The coupling strength in the formula It is obtained through a variety of complex calculation steps, reflecting the device and equipment In time First, the mutual information (MI) function It is used to quantify the degree of information sharing between the preprocessed data of two devices. Mutual information is an indicator to measure the dependency between two random variables. The larger the value, the more information sharing between the two variables. In the automated coal mining face, this dependency can reflect the collaborative work and mutual influence between the devices, thus providing an important basis for the subsequent logical operation verification. At the same time, in the formula This part is used to standardize the mutual information results. By calculating the difference between the data of the two devices, the influence of the mutual information is adjusted. This standardization process ensures that the coupling strength depends not only on the absolute value of information sharing, but also takes into account the difference between the data, making the calculation of the coupling strength more balanced and reasonable. In addition, the physical distance and the spatial decay constant The introduction of enables the formula to reflect the influence of the geographical location between devices on the coupling strength. The part represents the distance attenuation factor. As the physical distance increases, the coupling strength decays exponentially. This consideration is particularly important for automated coal mining faces, because in real environments, the physical distance between devices can significantly affect the strength of their interaction. By introducing the spatial attenuation constant , the formula can more realistically reflect the actual interaction between devices. Furthermore, the Logistic function is introduced into the formula to adjust the influence based on the Granger causality (GC) indicator. By comparing the conditional and unconditional variances, we quantify the and equipment Specifically, if the device The data can significantly reduce the equipment The prediction error of the device About equipment Granger causality exists. The Logistic function part of the formula By parameters and Adjusting the steepness and midpoint position of the Logistic function allows the influence of causal relationships to be flexibly adjusted. This step ensures that the coupling strength depends not only on static data dependencies, but also takes into account dynamic causal influences, making the results more comprehensive and accurate. In the specific logic operation verification process, these calculation steps and considerations enable the dynamic coupling network to accurately reflect the complex interactions between devices. By constructing such a network, the coupling strength and mutual influence between devices can be fully captured, providing rich information for subsequent analysis and verification. For example, when it is found that the coupling strength between certain devices is abnormally high or low, the reasons behind it can be further explored to identify potential failures or optimization points, thereby improving the operating efficiency and safety of the entire system.

[0088] in, Indicates the device and equipment In time The coupling strength; For equipment In time Preprocessed data; For equipment In time Preprocessed data; MI is the mutual information function; For equipment and equipment The physical distance between is the spatial attenuation constant, controlling the effect of distance on the coupling strength; is the steepness parameter of the logistic function; is the midpoint parameter of the logistic function; For equipment and equipment The Granger causality index between is calculated using the following formula:

[0089] ;

[0090] Among them, var is the variance function; For a given hour conditional variance.

[0091] Specifically, in the logic operation verification system for the intelligent lubrication system of coal mining equipment, the Granger Causality (GC) index plays a vital role in the dynamic coupling network. This index quantifies the causal relationship between devices, reveals the mutual influence and information transmission path between devices, and thus provides a deep basis for logic operation verification. Granger causality is based on time series data to determine whether the operating status of a device can be predicted by the past status of another device, that is, whether there is a causal relationship between the devices. Granger causality index is calculated by comparing the device The conditional variance and unconditional variance of quantify the causal relationship. Specifically, the conditional variance Indicates that on a given device When the data is Variance of; unconditional variance The equipment The variance of itself. Through the formula , it can be concluded that If the value is significantly greater than zero, it means that the device Data on the device There is a significant predictive ability, that is, there is a Granger causal relationship. In the automated coal mining face, the operating status of the equipment is often interrelated. Through Granger causality analysis, it is possible to identify which equipment has a significant causal relationship, thereby revealing the internal operating mechanism of the system. For example, there may be a significant causal relationship between the coal mining machine and the hydraulic support, because the operating status of the coal mining machine directly affects the workload and stability of the hydraulic support. Through this causal analysis, we can better understand the interaction between equipment and optimize the operation strategy of the system. In the process of logical operation verification, the role of Granger causality indicators is particularly important. First, by quantifying the causal relationship between equipment, the key equipment and key paths in the system can be identified. These key equipment and paths play a core role in the system, and ensuring their normal operation is a prerequisite for the stable operation of the entire system. For example, if it is found that a certain equipment has a significant Granger causal relationship with multiple other equipment, then this equipment may be a key equipment in the system, and special attention should be paid to its operating status and maintenance. Secondly, Granger causality analysis can also help identify potential faults and anomalies. By monitoring the changes in Granger causality indicators, abnormal fluctuations in the causal relationship between equipment can be discovered in time, which may indicate potential equipment failures. For example, if the Granger causality between the coal mining machine and the hydraulic support suddenly weakens, it may mean that there is a problem with the operating status of the coal mining machine, which affects the stability of the hydraulic support. Through this early warning mechanism, maintenance and adjustments can be carried out before the failure occurs to avoid system operation interruptions and safety accidents. In addition, Granger causality indicators can also be used to optimize the control strategy of the equipment. In the automated coal mining face, the operating status of each device is coordinated through a complex control system. Through Granger causality analysis, the dynamic interaction relationship between equipment can be better understood, thereby optimizing the control strategy and improving the overall operating efficiency of the system. For example, by adjusting the operating parameters of the coal mining machine, the working state of the hydraulic support can be optimized, thereby improving the efficiency and safety of the entire coal mining work.

[0092] Example 7: In step 3, the fractal dimension of the dynamic coupling network is calculated using the following formula: :

[0093] ;

[0094] in, is the scale parameter; for The generalized box counting function under scale; Tr is the trace of the matrix, that is, the sum of the main diagonal elements; is the eigenvalue vector of the coupling strength matrix; the coupling strength matrix is ​​based on is a matrix with elements; Eigenvalue vector The elements; is the eigenvalue vector The number of eigenvalues ​​in .

[0095] Specifically, first of all, As a scale parameter, it is the basis for calculating fractal dimension. part, reflecting the Time Equipment and The sum of the coupling strengths between the two devices is summed up over all pairs of devices to obtain the overall coupling strength of the entire network at a specific point in time. This sum is used as a benchmark to measure the overall complexity of the network when calculating the fractal dimension. In order to capture the self-similarity characteristics of the network, a logarithmic transformation is used in the formula, that is, and Through this transformation, the distribution characteristics of the network at different scales can be analyzed, thus revealing its fractal characteristics. The slope of the ratio provides the rate of change of the network at different scales, which is crucial to understanding the geometric complexity of the network. In further calculations, the formula introduces the generalized box counting function The logarithmic derivative of , to reflect the rate of change of the network at different scales. The introduction of this derivative term enhances the formula's ability to quantify network complexity, ensuring that the fractal dimension is not just a static geometric feature, but also takes into account the dynamic changes of the network at different scales. This dynamic change is particularly important for the logical operation verification of automated coal mining faces, because the interactions between equipment are often dynamic and changing. Only by considering these changes can the operating status of the system be accurately evaluated. In order to fully reflect the complexity of the network, the formula also combines the eigenvalues ​​of the coupling strength matrix The trace of the eigenvalue vector and the sum of the eigenvalues It is used to further adjust the calculation of fractal dimension. The coupling strength matrix is ​​based on the Granger causality index The matrix of elements reflects the causal relationship between devices. By introducing the calculation of eigenvalues, the formula can quantify the overall level and distribution characteristics of coupling strength, which is crucial for understanding the intrinsic structure and dynamic characteristics of the network. The calculation result provides a key complexity indicator for logical operation verification. Through this indicator, the complexity of the interaction between devices can be quantified, and potential problems and optimization space that may exist in the system can be identified. For example, a higher fractal dimension may indicate that the coupling relationship between devices is complex and changeable, reflecting the high dynamics and potential instability of the system. In this case, further verification and analysis may reveal that specific devices or interaction relationships need to be optimized or adjusted, thereby improving the overall stability and operating efficiency of the system. In addition, the changing trend of the fractal dimension can also be used to monitor the operating status and health of the system. During the logical operation verification process, continuous monitoring of the changes in the fractal dimension can promptly detect abnormal changes, thereby warning of possible equipment failures or system instability. For example, if the fractal dimension suddenly increases over a period of time, this may mean that the interactions within the system have become more complex and unstable, requiring further investigation and processing. Through these analyses, the fractal dimension It provides a comprehensive and dynamic complexity index, making the logical operation verification of the intelligent lubrication system of coal mining equipment more accurate and scientific. Combined with the fractal dimension of the dynamic coupling network, we can deeply understand the relationship and dynamic characteristics between equipment, so as to achieve more efficient and safe system management and optimization. In the whole verification process, the application of fractal dimension not only improves the transparency of the system, but also enhances the controllability of the system, providing strong support for the intelligent management of the automated coal mining face.

[0096] Example 8: In step 4, the depth of the adaptive fuzzy logic decision tree is calculated using the following formula: :

[0097] ;

[0098] in, is the preset adaptive adjustment coefficient.

[0099] Specifically, in the formula, the depth of the decision tree The fractal dimension The logarithmic operation of the coupling strength is combined with the average value and the adaptive adjustment coefficient Specifically, the formula first takes the fractal dimension With the preset adjustment factor The binary logarithm of the ratio , and take its upper limit This part of the calculation determines the basic decision tree depth. Fractal dimension It reflects the complexity of the interaction between devices. Therefore, by performing logarithmic operations on it, this complexity can be converted into the base depth of the decision tree, so that the decision tree can reflect the overall complexity of the system. Next, the product term in the formula is used to further adjust the depth of the decision tree so that it can adaptively adapt to the coupling strength between each device. This product term reflects the overall level of interaction between devices in the entire system by averaging the coupling strength of each device. Specifically, for each device , the formula calculates its relationship with all other devices The sum of the coupling strengths , and normalized to the average coupling strength of each device. , the formula can capture the coupling characteristics and dynamic changes of the entire system. In the process of logical operation verification, the depth of the decision tree It is a key parameter that directly affects the complexity and accuracy of the decision tree. By combining the fractal dimension and coupling strength, the formula ensures that the depth of the decision tree can dynamically adapt to the complexity of the system, avoiding the problem of being too shallow or too deep. If the decision tree is too shallow, it may not be able to capture the complex relationships in the system, resulting in inaccurate verification results; if the decision tree is too deep, it may lead to excessive computational complexity, reducing the real-time performance and efficiency of the system. The adaptive fuzzy logic decision tree can optimize the computational efficiency while ensuring the verification accuracy by dynamically adjusting the depth, thereby improving the overall performance of the system. In addition, the adaptive adjustment coefficient The formula plays a role in balancing complexity and practical application needs. The value of can control the basic depth of the decision tree to adapt to different application scenarios and needs. In practical applications, The choice of can be adjusted according to factors such as specific equipment type, system complexity and computing resources, so as to ensure that the decision tree can perform optimally in different environments. In this way, the logical operation verification of the intelligent lubrication system of coal mining equipment can more accurately evaluate and verify the operating status of the system. The depth of the decision tree directly affects the accuracy and efficiency of the logical operation verification. The adaptive depth calculated by the above formula can ensure that the decision tree has sufficient complexity to reflect the dynamic characteristics of the system and maintains a high computing efficiency, thereby achieving efficient and reliable logical operation verification.

[0100] Embodiment 9: In step 4, the following formula is used to calculate the logic consistency index according to the depth of the adaptive fuzzy logic decision tree:

[0101] ;

[0102] in, It is the complexity index of adaptive fuzzy logic decision tree; is the scaling parameter; is the hierarchical index of the decision tree; For the The number of decision features of the decision tree of the layer; is the gamma function.

[0103] Specifically, the logical consistency index in the formula It is calculated through several key parts. First, the formula contains The term is used to quantify the sum of squares of the coupling strength between devices. This part reflects the interaction strength between the devices in the system. The calculation method of the sum of squares enhances the influence of high coupling strength, so that in the logical consistency evaluation, the devices with high coupling strength have a greater contribution to the overall evaluation results. This part is achieved through Standardization is performed to make the results have consistent dimensions, which is convenient for further calculation and comparison. Item, introduces the complexity index of adaptive fuzzy logic decision tree through logistic regression function Complexity Index Reflecting the complexity of the decision tree, the introduction of the logistic regression function makes the influence of complexity on the logical consistency index present a smooth change. As a scaling parameter, it is used to adjust the influence of complexity on the logical consistency index. When the complexity of the decision tree is high, the value of this part will approach zero. Conversely, when the complexity is low, the value of this part will approach 1, thereby adjusting the overall consistency index. The item is the depth of the adaptive fuzzy logic decision tree. Number of devices The logarithmic ratio of is introduced into the calculation. By comparing the depth of the decision tree and the logarithm of the number of devices, the adaptability of the decision tree depth relative to the system scale can be evaluated. Ideally, the depth of the decision tree should have a reasonable proportional relationship with the number of devices. This part of the calculation can ensure that the depth of the decision tree is not too shallow or too deep, thereby maintaining the rationality of the system's logical operation verification. Gamma function The introduction of further adjusts the impact of decision tree depth on logical consistency indicators. The gamma function provides a continuous adjustment method, making the decision tree depth smoother and more natural when affecting consistency indicators. Through the gamma function, the impact of depth on logical consistency indicators can be refined to ensure that changes in decision tree depth can be more reasonably reflected in logical consistency indicators. The number of decision features in each layer of the decision tree is calculated to reflect the impact of the number of features in each layer on the logical consistency index. This ensures that the impact of the number of features at different levels can be evenly reflected in the overall index. By taking the geometric mean of the number of features at each level, the hierarchical structure and feature distribution of the decision tree can be comprehensively reflected, thereby further refining the logical consistency evaluation.

[0104] In practical applications, these complex calculation steps ensure the logical consistency index It can fully and accurately reflect the operating logic of the intelligent lubrication system of coal mining equipment. In a complex automated coal mining face, the interaction between equipment is dynamic and complex. Through the above formula, these dynamic interaction relationships can be captured and quantified, thus providing a scientific basis for logical operation verification. Logical consistency index The calculation of plays a vital role in the logic operation verification. First, by calculating the sum of the squares of the coupling strengths between devices, it ensures that the influence of strong interactions between devices can be fully reflected. This part of the calculation enhances the contribution of high coupling strength devices to the overall evaluation results, ensuring that the key role of high coupling strength devices in the logic operation verification is fully reflected. Secondly, the introduction of the logistic regression function, through the complexity index The complexity of the decision tree is quantified. The logistic regression function makes the influence of complexity on the logical consistency index change smoothly, and the parameter The degree of this influence is adjusted. This method can ensure that the complexity of the decision tree can be reasonably reflected in the logic operation verification, avoiding the adverse impact of too high or too low complexity on the verification results. Again, by comparing the depth of the decision tree and number of devices The logarithmic ratio of the decision tree depth can be used to evaluate the adaptability of the decision tree depth relative to the system scale. This part of the calculation ensures that the depth of the decision tree will not be too shallow or too deep, and maintains the rationality and scientificity of the system's logical operation verification. In addition, the introduction of the gamma function ensures that the change in depth can be more reasonably reflected in the consistency index by continuously adjusting the impact of the decision tree depth on the logical consistency index. In this way, the logical consistency index more smoothly and naturally reflects the impact of the decision tree depth, making the verification results more accurate and scientific. Finally, by calculating the number of decision features of each layer of the decision tree, the logical consistency evaluation can be refined to ensure that the impact of the number of features at different levels is evenly reflected in the overall index. The standardization of the number of features at each layer ensures that the hierarchical structure and feature distribution of the decision tree can be fully reflected in the logical consistency index through the geometric mean method.

[0105] Example 10: Complexity index of adaptive fuzzy logic decision tree Use the following formula to calculate:

[0106] ;

[0107] in, is a second-order polylogarithmic function;

[0108] ;

[0109] in, is the fractal dimension function, which is expressed using the following formula:

[0110] ;

[0111] No. The number of decision features in the decision tree of the layer Use the following formula to express it:

[0112] ;

[0113] in, is the subscript index.

[0114] Specifically, in the logic operation verification system for the intelligent lubrication system of coal mining equipment, Example 10 proposes a complex mathematical model for calculating the complexity index of the adaptive fuzzy logic decision tree This indicator plays a key role in the logic operation verification process, and evaluates the system's operating status and optimization potential by quantifying the complexity of the decision tree. Complexity index of adaptive fuzzy logic decision tree The calculation formula of combines multiple factors, reflecting the hierarchical structure of the decision tree, the change in fractal dimension, and the number of decision features. First, The term is used to reflect the growth characteristics of the number of nodes in each layer of the decision tree. As the number of nodes increases, it increases exponentially, which means that the complexity of the decision tree is higher at higher levels. However, in order to avoid the excessive influence of higher levels on the overall complexity, the formula is introduced The fractal dimension is attenuated by the high-level complexity, so that the influence of high-level complexity on the overall index can be reasonably controlled. Rate of change is another key factor in the formula. By approximating the first and second order derivatives, the formula can capture the subtle changes in fractal dimension at different levels. This change reflects the complexity differences of the system at different levels, ensuring that the complexity index of the decision tree can dynamically adapt to the actual state of the system. The expression introduces periodic changes through The term is used to simulate the fluctuation of complexity with the level. In this way, the fractal dimension not only reflects the static complexity of the system, but also captures the dynamic change characteristics, making the complexity index more accurate and comprehensive.

[0115] Second-order polylogarithmic function The formula provides a smooth adjustment function. This function can maintain smoothness and continuity when adjusting complexity, avoiding calculation errors caused by mutations or discontinuities. This is particularly important for logical operation verification of complex systems, because smooth complexity changes can better reflect the actual operating status of the system, thereby improving the accuracy and reliability of verification. In addition, the calculation of the number of decision features at each level in the formula cannot be ignored. The number of decision features in the layer The formula combines the number of combinations and the probability distribution, by It expresses the complexity of the decision features at each layer. This part reflects the amount of information that each layer of nodes needs to process, and the contribution of different nodes to the overall complexity at different levels. In this way, the formula ensures that the number of features at different levels can be evenly reflected in the complexity index, thereby avoiding the excessive impact of the abnormal number of features at a certain layer on the overall complexity assessment. In the process of logical operation verification, the complexity index of the adaptive fuzzy logic decision tree It provides a comprehensive evaluation tool for the operating status of the system. First, by quantifying the complexity of the decision tree, we can identify the key levels and features in the system and find potential optimization points. For example, if the complexity of a certain layer is significantly higher than that of other layers, this may mean that there is redundancy or unnecessary complexity in that layer. The complexity can be reduced by simplifying the decision rules or optimizing feature selection, thereby improving the overall efficiency of the system. In addition, complexity indicators can also be used to monitor the operating health of the system. By continuously tracking By monitoring changes in the complexity of the system, we can detect abnormal fluctuations in system complexity in a timely manner, thereby warning of potential failures or performance degradation. For example, if the complexity index increases rapidly in a short period of time, this may indicate that abnormal interactions have occurred within the system or that the decision tree structure has changed irrationally, requiring further inspection and adjustment.

[0116] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A logical operation verification system for an intelligent lubrication system of coal mining equipment, characterized in that: The system includes: a logic operation verification part and a control part; the logic operation verification part is used to perform logic operation verification on each device of the automated coal mining working face to obtain the logic operation verification result, which specifically includes: Step 1: Initialize the operating parameters of each device of the automated coal mining face; install a corresponding sensor group in each device, each sensor group includes multiple sensors, and collects the operating parameters of the corresponding device in real time; Step 2: Based on the operating data collected by each sensor group, a data tensor of a multi-dimensional sensor is constructed; nonlinear transformation and wavelet denoising are performed on the data tensor to obtain preprocessed data; Step 3: Based on the preprocessed data, a dynamic coupling network reflecting the interaction between devices is constructed; and then the fractal dimension of the dynamic coupling network is calculated; Step 4: Generate an adaptive fuzzy logic decision tree according to the dynamic coupling network and the corresponding fractal dimension; calculate the depth of the adaptive fuzzy logic decision tree, and then calculate the logic consistency index according to the depth of the adaptive fuzzy logic decision tree, and compare the logic consistency index with the set standard value to determine whether it passes the logic operation verification; The control part is used to start the intelligent lubrication system to provide lubrication for each device when the result of the logic operation verification is passed; The equipment of the automated coal mining face at least includes: coal mining machine, hydraulic support, scraper conveyor, transfer machine, crusher and belt conveyor; the number and type of operation data between the equipment are the same; the operation data at least includes: voltage, current, load, number of working cycles, operation time, vibration frequency and temperature; Assume a total of devices, and the total running data of each device is Class, the time limit is , then the multidimensional sensor data tensor constructed in step 2 Use the following formula to express it: ; in, and All are subscript indexes; It is The sensor group of the device is at time The first Class operation data; , and The indexes are Dimensions, Indexes Standard basis vectors for dimension and time dimensions; represents tensor product; In step 2, the data tensor is subjected to nonlinear transformation and wavelet denoising by the following formula to obtain the preprocessed data: : ; in, and They are Fourier transform and inverse Fourier transform respectively; is the number of layers of wavelet decomposition; is the unit tensor; For the The learning rate of the layer; and Respectively The wavelet transform and inverse wavelet transform of the layer; soft is the soft threshold function, defined as , is the independent variable, is the set soft threshold; For the Adaptive threshold parameters of the layer; is the total number of data points; For the Noise level estimation of the layer; is the tensor decomposition function, is the element-wise product; Tensor decomposition function Use the following formula to express it: ; in, is the core tensor; ReLU is the rectified linear unit activation function; , and They are the factor matrix of the first dimension, the factor matrix of the second dimension, and the factor matrix of the third dimension respectively; , and are the tensor products along the first dimension, the second dimension, and the third dimension respectively; Noise level estimation of the layer Use the following formula to express it: ; Among them, MAD is the median absolute deviation; Adaptive threshold parameters for layers Use the following formula to express it: ; Among them, erf is the error function.

2. The logic operation verification system for the intelligent lubrication system of coal mining equipment according to claim 1, characterized in that: In step 3, based on the preprocessed data, in the dynamic coupling network reflecting the interaction between devices, the coupling strength between each device is expressed by the following formula: ; in, Indicates the device and equipment In time The coupling strength; For equipment In time Preprocessed data; For equipment In time Preprocessed data; MI is the mutual information function; For equipment and equipment The physical distance between is the spatial attenuation constant, controlling the effect of distance on the coupling strength; is the steepness parameter of the logistic function; is the midpoint parameter of the logistic function; For equipment and equipment The Granger causality index between is calculated using the following formula: ; Among them, var is the variance function; For a given hour conditional variance.

3. The logic operation verification system for the intelligent lubrication system of coal mining equipment according to claim 2, characterized in that: In step 3, the fractal dimension of the dynamic coupling network is calculated using the following formula: : ; in, is the scale parameter; for The generalized box counting function under scale; Tr is the trace of the matrix, that is, the sum of the main diagonal elements; is the eigenvalue vector of the coupling strength matrix; the coupling strength matrix is ​​based on is a matrix with elements; Eigenvalue vector The elements; is the eigenvalue vector The number of eigenvalues ​​in .

4. The logic operation verification system for the intelligent lubrication system of coal mining equipment according to claim 3, characterized in that: In step 4, the depth of the adaptive fuzzy logic decision tree is calculated using the following formula: : ; in, is the preset adaptive adjustment coefficient.

5. The logic operation verification system for the intelligent lubrication system of coal mining equipment according to claim 4, characterized in that: In step 4, the following formula is used to calculate the logical consistency index according to the depth of the adaptive fuzzy logic decision tree: ; in, It is the complexity index of adaptive fuzzy logic decision tree; is the scaling parameter; is the hierarchical index of the decision tree; For the The number of decision features of the decision tree of the layer; is the gamma function.

6. The logic operation verification system for the intelligent lubrication system of coal mining equipment according to claim 4, characterized in that: Complexity index of adaptive fuzzy logic decision tree Use the following formula to calculate: ; in, is a second-order polylogarithmic function; ; in, is the fractal dimension function, which is expressed using the following formula: ; No. The number of decision features in the decision tree of the layer Use the following formula to express it: ; in, is the subscript index.