Intelligent control system and method of ocean engineering gear processing machine tool

Abstract

The invention discloses an intelligent control system for an ocean engineering gear processing machine tool, which relates to the technical field of intelligent manufacturing of ocean engineering equipment and comprises a data acquisition, analysis, decision making, execution, diagnosis, interaction and storage management module, a quantum sensor is used for data acquisition, and sensitivity is improved; analyzing and introducing a graph neural network, and mining potential information; optimizing a decision fusion genetic algorithm; magnetic suspension driving is adopted for execution, and precision is improved; diagnosis is combined with an expert system and a fault tree; vR and AR technologies are interactively introduced; distributed account books are used for storage, safety is guaranteed, all the modules cooperate, and efficient, intelligent and accurate machining control is achieved. According to the method, the machining precision, efficiency and reliability of the ocean engineering gear are improved, the advanced technology is adopted, data collection is more accurate, analysis is deeper, decision making is more optimized, execution is more accurate, fault diagnosis is faster, man-machine interaction is improved, data safety is guaranteed, cost is reduced, and manufacturing and development of ocean engineering equipment are promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent manufacturing of marine engineering equipment, and in particular to an intelligent control system and method for a marine engineering gear processing machine tool. Background Art

[0002] Marine engineering has extremely stringent requirements on the quality and performance of gears. Its working environment is complex and it is subjected to huge loads and impacts. Traditional gear processing machine tools have exposed many problems when facing such demands. The processing accuracy of machine tools is difficult to meet the high-precision requirements of marine engineering for gears. During the processing, factors such as tool wear, vibration, and thermal deformation will cause problems such as gear tooth profile error and pitch error, affecting the transmission stability and service life of the gears. Moreover, traditional machine tools lack the ability to monitor and intelligently control the processing process in real time, and are unable to adjust parameters in time according to the processing conditions. Once a processing abnormality occurs, it often causes a large amount of waste and waste of resources.

[0003] With the development of intelligent manufacturing technology, some processing machine tools have begun to introduce intelligent control concepts, but in the field of marine engineering gear processing, the existing intelligent control systems are still insufficient. The existing data collection methods are limited, and the accuracy and reliability of sensors are difficult to adapt to the harsh conditions of the marine environment, resulting in the inability of the collected data to accurately reflect the subtle changes in the processing process. The data analysis method is also relatively simple, making it difficult to conduct a comprehensive and in-depth analysis of complex processing data, and it is impossible to accurately predict the processing quality and detect potential faults in a timely manner. At the same time, the intelligent decision-making and control execution links lack synergy, and the decision-making plan cannot be efficiently and accurately converted into the actual action of the machine tool, affecting the processing efficiency and quality.

[0004] In addition, in terms of fault diagnosis and maintenance, traditional methods rely on manual experience and simple detection methods, which makes it difficult to quickly and accurately locate the root cause of the fault, and maintenance work is often delayed, resulting in long machine tool downtime and affecting production progress. Moreover, the existing processing system lacks effective human-computer interaction methods and data management methods, making it difficult for operators to intuitively and conveniently obtain machine tool information and set parameters, and the security and sharing of data cannot be effectively guaranteed. Therefore, it is of great practical significance to develop an intelligent control system and method suitable for marine engineering gear processing machine tools. Summary of the invention

[0005] The intelligent control system and method of the marine engineering gear processing machine tool proposed in the present invention are used to solve the problems mentioned in the above-mentioned prior art.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solution: an intelligent control system for a marine engineering gear processing machine tool, comprising the following modules: Data acquisition module: Use displacement, vibration, temperature, and pressure sensors to collect gear processing data. The sampling frequency is based on the formula f s =k× Dynamic adjustment, where v is the tool cutting speed, p is the machining accuracy level, and k is the empirical coefficient; quantum sensing technology is used to capture changes in physical quantities; Data analysis module: Use deep learning algorithms to build a hybrid model based on convolutional neural networks and long short-term memory networks, extract features and recognize patterns from collected data, and establish a processing quality prediction model Q=f(D), where Q is the processing quality index and D is the data vector; introduce graph neural networks to mine potential information from data; Intelligent decision-making module: Combines preset processing parameters and quality standards, uses fuzzy decision-making algorithms, and Determine the decision-making plan, is the factor weight, To correspond to fuzzy rules; fusion genetic algorithm optimizes fuzzy decision parameters; Control execution module: receives control instructions from the intelligent decision-making module, adjusts machine tool parameters, introduces magnetic suspension drive technology, and reduces mechanical friction and transmission errors; Fault diagnosis module: real-time monitoring of machine tool status, using fault feature extraction and fault classification algorithms to analyze data, and establish a fault dictionary F={f 1 ,f 2 ,...,f n}, where f i For the i-th fault type; combine the expert system and fault tree analysis method to analyze the root cause of the fault; Human-machine interaction module: provides a human-machine interaction interface, supports operators to input operating parameters through touch screen or voice commands, and displays machine tool information on the interface; introduces VR and AR technologies, operators can immersively experience the machine tool operation status through VR devices, and view the machine tool status in the actual scene through AR devices; Data storage and management module: Store the collected information in the database, use data encryption technology to ensure security, and use data mining algorithms to analyze historical data; use distributed ledger technology to ensure that the data cannot be tampered with and is traceable.

[0007] Furthermore, it also includes an adaptive learning module, which uses a reinforcement learning algorithm to automatically adjust the decision rules and parameters of the intelligent decision-making module according to real-time feedback during the processing. This module also introduces a meta-learning mechanism to learn new processing tasks and environments, so that the system can achieve optimal performance in different processing scenarios.

[0008] Furthermore, it also includes a remote monitoring and maintenance module, which connects the machine tool to the remote server through the industrial Internet to realize remote maintenance of the machine tool. The operator obtains the machine tool operation information through the mobile phone APP or computer terminal; 5G communication technology is used to transmit data, and at the same time, edge computing technology is used to process local data.

[0009] Furthermore, the sensors in the data acquisition module use multi-sensor fusion technology to fuse data from different types of sensors. The fusion technology uses a fusion algorithm based on Bayesian reasoning to perform weighted fusion on data from different sensors.

[0010] Furthermore, the deep learning model in the data analysis module adopts transfer learning technology, using models pre-trained in other processing tasks to adapt to the characteristics of marine engineering gear processing. The module also adopts federated learning technology to train the model without leaking the data privacy of each participant.

[0011] Furthermore, the servo control system in the control execution module adopts a fuzzy-proportional integral differential composite control algorithm, which combines the flexibility of fuzzy control and the accuracy of PID control to improve the stability of parameter adjustment. The composite control algorithm introduces an adaptive adjustment mechanism to automatically adjust the parameters of fuzzy control and PID control according to the machine tool operating status and processing tasks.

[0012] Furthermore, the method of the intelligent control system of the marine engineering gear processing machine tool comprises the following steps: S1: Data acquisition: Start the data acquisition module, dynamically set the sensor sampling frequency according to the principle of adapting to the processing accuracy, collect tool displacement, machine tool vibration, cutting temperature and cutting force data in the gear processing process in real time, and use quantum sensing technology to improve the accuracy and anti-interference ability of data acquisition; S2: Data analysis: The collected data is transferred to the data analysis module, and a hybrid model based on CNN, LSTM and GNN is used to perform feature extraction and pattern recognition to predict the gear processing quality; S3: Intelligent decision-making: The data analysis module sends the analysis results to the intelligent decision-making module, which combines the preset processing parameters and quality standards and uses the fuzzy decision-making algorithm optimized by the genetic algorithm to comprehensively determine the decision-making plan based on multiple factors; S4: Control execution: The intelligent decision-making module sends the decision plan to the control execution module, which adjusts the machine tool's tool feed speed, spindle speed, cutting depth and other parameters in real time according to the instructions, and uses magnetic suspension drive technology to improve motion control accuracy; S5: Fault diagnosis: The fault diagnosis module monitors the machine tool operation status in real time, uses the fault feature extraction and classification algorithm combined with the expert system and fault tree analysis method, and diagnoses the fault and analyzes the root cause by comparing the fault features with the fault dictionary; S6: Human-machine interaction: The operator inputs operating parameters and queries processing information through the human-machine interaction module that introduces VR and AR technologies. The module displays the machine tool's operating status, processing quality, and fault information in real time. S7: Data storage and management: The data storage and management module stores the collected data, analysis results, decision-making plans and fault information in a database using distributed ledger technology, uses data encryption technology to ensure data security, and uses data mining algorithms to analyze historical data.

[0013] Furthermore, after the data collection step, a data preprocessing step is also included to filter, reduce noise and normalize the collected data, and use a multi-sensor fusion algorithm based on Bayesian reasoning to improve data quality and availability.

[0014] Furthermore, in the intelligent decision-making step, if the decision result exceeds the preset safety range, the system will automatically trigger the alarm mechanism and take safety measures such as emergency shutdown. At the same time, the system will initiate an emergency decision-making plan and quickly generate a temporary solution based on historical data and real-time conditions.

[0015] Furthermore, after the data storage and management steps, it also includes data feedback and optimization steps. According to the data mining results and processing quality feedback, the processing parameters and intelligent decision-making rules are optimized and adjusted, and the meta-learning mechanism and federated learning technology are used to accelerate the optimization process.

[0016] Compared with the prior art, the present invention has the following beneficial effects: In terms of data collection, the use of quantum sensing technology and multi-sensor fusion technology has greatly improved the sensitivity of sensors and the accuracy of data. It can accurately capture subtle changes in the processing process and provide a reliable basis for subsequent analysis.

[0017] By introducing graph neural networks, transfer learning, and federated learning technologies, the data analysis module can mine data information more comprehensively and deeply, significantly improve the accuracy of processing quality predictions, discover potential problems in advance, and reduce scrap rates.

[0018] The intelligent decision-making module integrates genetic algorithms to optimize fuzzy decision parameters, and can quickly formulate the best decision plan in a complex environment to ensure the efficiency and stability of the processing process. The control execution module adopts magnetic suspension drive technology and adaptive adjustment fuzzy-PID composite control algorithm, which effectively improves the accuracy and stability of machine tool motion control and significantly improves the accuracy and surface quality of gear processing.

[0019] The fault diagnosis module combines expert systems and fault tree analysis methods to not only quickly locate faults, but also deeply analyze the root causes of faults, provide comprehensive guidance for maintenance, and reduce downtime. The human-computer interaction module introduces VR and AR technologies to provide operators with a more intuitive and convenient operating experience, improving the accuracy and efficiency of operations.

[0020] The data storage and management module uses distributed ledger technology to ensure data security and traceability, and realize data sharing and collaborative work among multiple departments. At the same time, the adaptive learning module and meta-learning mechanism enable the system to continuously adapt to new processing tasks and environments and continuously optimize performance. Overall, this patented system improves the accuracy, efficiency and reliability of marine engineering gear processing, reduces production costs, and strongly promotes the development of marine engineering equipment manufacturing. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A schematic block diagram of the intelligent control system of the marine engineering gear processing machine tool proposed by the present invention; Figure 2 A bar chart comparing the machining accuracy of the intelligent control system and method for the marine engineering gear machining machine tool proposed by the present invention; Figure 3 A line chart comparing the processing efficiency of the intelligent control system and method for the marine engineering gear processing machine tool proposed by the present invention; Figure 4 A pie chart comparing the fault diagnosis time of the intelligent control system and method for the marine engineering gear processing machine tool proposed in the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0023] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0024] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. In addition, the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, and it can be the internal connection of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0025] Reference Figure 1-4 :An intelligent control system for marine engineering gear processing machine tools, including the following modules: Data acquisition module: Install high-precision displacement sensors, vibration sensors, temperature sensors and pressure sensors at key locations of marine engineering gear processing machines. The sensor sampling frequency is calculated according to the formula f s =k× Determine, where v is the tool cutting speed, which can be calculated from the spindle speed and tool diameter of the machine tool; p is the machining accuracy level, which is set according to the design requirements of marine engineering gears; k is the empirical coefficient, which ranges from 10 to 20. For example, when the tool cutting speed v = 100m / min, the machining accuracy level p = 5, and the empirical coefficient k = 15, the sampling frequency At the same time, quantum sensing technology is used to utilize the characteristics of quantum states to improve the sensitivity and anti-interference ability of the sensor, ensuring that the collected data such as tool displacement, machine tool vibration, cutting temperature and cutting force are accurate and reliable.

[0026] Data analysis module: Receives data transmitted by the data acquisition module and uses deep learning algorithms to analyze the data. A hybrid model based on convolutional neural network (CNN), long short-term memory network (LSTM) and graph neural network (GNN) is used for analysis. CNN is used to extract local features of data, LSTM processes the time series information of data, and GNN considers the complex correlation between data. The processing quality prediction model Q=f(D) is established, where Q is the processing quality index and D is the collected data vector, to predict the gear processing quality. The model is trained using historical processing data, and the model parameters are continuously optimized to improve the accuracy of processing quality prediction.

[0027] Intelligent decision-making module: The intelligent decision-making module receives the results of the data analysis module, combines the preset processing parameters and quality standards, and uses the fuzzy decision-making algorithm to make decisions. The algorithm considers the comprehensive influence of multiple factors and solves the fuzzy rule library. Determine the decision-making plan, is the weight of the ith factor, is the fuzzy rule corresponding to the i-th factor. At the same time, the genetic algorithm is integrated to optimize the parameters of the fuzzy decision and quickly find the optimal decision solution in a complex and changeable processing environment. For example, when the predicted value of the processing quality deviates from the preset standard, the intelligent decision module adjusts the tool feed speed, spindle speed and other parameters according to the fuzzy rules and genetic algorithm.

[0028] Control execution module: The control execution module receives the control instructions issued by the intelligent decision-making module and makes real-time adjustments to the machine tool's tool feed speed, spindle speed, cutting depth and other parameters. The magnetic suspension drive technology is used to reduce mechanical friction and transmission errors, and achieve smoother and more precise motion control. At the same time, the servo control system adopts a fuzzy-proportional integral differential (PID) composite control algorithm, combining the flexibility of fuzzy control and the accuracy of PID control, and introduces an adaptive adjustment mechanism to automatically adjust the parameters of fuzzy control and PID control according to the machine tool's operating status and processing tasks, ensuring the accuracy and response speed of parameter adjustment.

[0029] Fault diagnosis module: real-time monitoring of the machine tool's operating status, using fault feature extraction algorithm and fault classification algorithm to analyze the collected data. Establish a fault dictionary F = {f 1 ,f 2 ,...,f n}, where f i For the i-th fault type, by comparing the fault characteristics with the fault dictionary, the fault can be diagnosed quickly and accurately and the root cause can be analyzed. For example, when the vibration sensor detects abnormal vibration, the fault diagnosis module analyzes the possible causes of the fault according to the fault tree, such as tool wear, bearing damage, etc., and gives corresponding maintenance suggestions through the expert system.

[0030] Human-machine interaction module: The human-machine interaction module provides a friendly human-machine interaction interface, supporting operators to input operating parameters and query processing information through touch screen, keyboard or voice commands. With the introduction of virtual reality (VR) and augmented reality (AR) technologies, operators can immersively experience the machine tool operation status through VR devices, and intuitively view machine tool parameters and fault prompts in actual scenes through AR devices. For example, operators wearing VR devices can observe the gear processing process in all directions and find potential problems; using AR glasses to scan machine tool parts can display detailed information and current status of the parts.

[0031] Data storage and management module: The data storage and management module stores the collected data, analysis results, decision-making plans and fault information in a database using distributed ledger technology (such as blockchain). Data encryption technology is used to ensure data security, and data mining algorithms are used to analyze historical data to provide a basis for optimizing processing technology. Distributed ledger technology ensures that data cannot be tampered with and is traceable, and enables data sharing and collaborative work among multiple departments. For example, the quality inspection department can view the data in the processing process through blockchain for quality traceability and analysis.

[0032] The present invention also includes an adaptive learning module, which uses a reinforcement learning algorithm to automatically adjust the decision rules and parameters of the intelligent decision module according to real-time feedback and historical data during the processing process, thereby improving the adaptability and intelligence level of the system. The module also introduces a meta-learning mechanism, which can quickly learn new processing tasks and environments, reduce learning time and cost, and enable the system to quickly achieve optimal performance in different processing scenarios.

[0033] The present invention also includes a remote monitoring and maintenance module, which connects the machine tool to the remote server through the industrial Internet to achieve remote monitoring, fault diagnosis and maintenance of the machine tool. Operators can obtain the operating status and processing information of the machine tool anytime and anywhere through a mobile phone APP or a computer terminal. This module uses 5G communication technology to achieve high-speed, low-latency data transmission, ensuring the real-time nature of remote monitoring and control. At the same time, edge computing technology is used to perform preliminary processing of data locally to reduce the burden on the cloud server.

[0034] In the present invention, the data acquisition module deeply applies multi-sensor fusion technology, and organically integrates multiple types of sensors such as displacement sensors, vibration sensors, temperature sensors, and pressure sensors. During the gear processing process, multi-dimensional data such as tool displacement, equipment vibration frequency, temperature fluctuation in the processing area, and cutting pressure value are synchronously collected, and fusion processing is performed on heterogeneous data obtained by different sensors. The fusion process adopts a fusion algorithm based on Bayesian reasoning, which fully considers the uncertainty of sensor data caused by environmental interference, device accuracy differences and other factors, and conducts confidence assessment on each sensor data through a probability model. Then, a reasonable weighted calculation is implemented based on the assessment results to fuse multi-source data into more accurate comprehensive data. This technical solution not only effectively reduces the error interference of a single sensor, but also significantly improves the accuracy and reliability of data acquisition through optimization at the algorithm level, providing high-quality data support for subsequent data analysis and decision-making modules.

[0035] In the present invention, in the data analysis module, the deep learning model deeply applies the transfer learning technology. First, a basic model that has been pre-trained with large-scale data in related fields such as mechanical manufacturing and precision machining is selected. The network structure of the model is optimized and adjusted according to the particularity of the marine engineering gear processing scene (such as complex load conditions and special material processing characteristics). By freezing the basic layer parameters and fine-tuning the feature extraction layer, the model can quickly adapt to the characteristic pattern of the gear processing data. This process greatly shortens the training cycle and improves efficiency compared to training from scratch. At the same time, it allows the model to capture the key features of tasks such as gear processing quality prediction and defect identification more quickly, and optimizes performance. In addition, the module introduces federated learning technology, and unites multiple data subjects such as machine tool manufacturers, processing companies, and scientific research institutions to achieve "data available but invisible" under the technical guarantees of differential privacy protection and homomorphic encryption. All parties participate in model training based on local gear processing data, and complete joint optimization through encrypted parameter interaction. This model aggregates multi-source heterogeneous data, enriches the diversity of model training samples, enables the model to learn more complex processing scenario features, significantly enhances generalization capabilities, and improves prediction accuracy under different processing equipment and process conditions. At the same time, it strictly adheres to data privacy boundaries and achieves the dual goals of data collaboration and security protection.

[0036] In the present invention, the servo control system in the control execution module adopts a fuzzy-proportional integral differential (PID) composite control algorithm, combining the flexibility of fuzzy control and the accuracy of PID control to improve the stability and accuracy of parameter adjustment. The composite control algorithm introduces an adaptive adjustment mechanism, which can automatically adjust the parameters of fuzzy control and PID control according to the operating status of the machine tool and the processing task, and achieve a better control effect.

[0037] The present invention comprises the following steps: Data collection: Start the data collection module, dynamically set the sensor sampling frequency according to the principle of matching the processing accuracy, and collect data such as tool displacement, machine tool vibration, cutting temperature and cutting force during gear processing in real time. Use quantum sensing technology to improve the accuracy and anti-interference ability of data collection.

[0038] Data analysis: The collected multi-source data such as displacement, vibration, temperature, etc. are transmitted to the data analysis module. A hybrid model integrating convolutional neural network (CNN), long short-term memory network (LSTM) and graph neural network (GNN) is used to extract features and recognize patterns based on data spatial characteristics, temporal changes and correlation relationships, and finally accurately predict the gear processing quality.

[0039] Intelligent decision-making: The data analysis module sends the analysis results to the intelligent decision-making module. The intelligent decision-making module combines the preset processing parameters and quality standards, and uses the fuzzy decision-making algorithm optimized by the fusion genetic algorithm to comprehensively determine the decision-making plan based on multiple factors.

[0040] Control execution: The intelligent decision-making module sends the decision plan to the control execution module. The control execution module adjusts the machine tool's tool feed speed, spindle speed, cutting depth and other parameters in real time according to the instructions, and uses magnetic suspension drive technology and adaptive fuzzy-PID composite control algorithm to improve motion control accuracy.

[0041] Fault diagnosis: The fault diagnosis module monitors the machine tool operating status in real time, uses a fault feature extraction and classification algorithm that combines an expert system and a fault tree analysis method, and compares the fault features with the fault dictionary to quickly and accurately diagnose the fault and analyze the root cause.

[0042] Human-machine interaction: Operators use VR / AR technology to create immersive interactive scenes, supporting multiple forms of interaction such as gestures and voice. Operators can intuitively input parameters and query processing information in a three-dimensional virtual scene. This module uses real-time rendering technology to dynamically present the machine tool's operating status, processing quality, and fault information, achieving efficient human-machine collaboration that integrates virtual and real.

[0043] Data storage and management: The data storage and management module stores the collected data, analysis results, decision-making plans and fault information in a database using distributed ledger technology, uses data encryption technology to ensure data security, and uses data mining algorithms to analyze historical data.

[0044] In the present invention, a data preprocessing step is added after the data collection step, and the original data is subjected to spatiotemporal noise suppression by combining adaptive Kalman filtering and wavelet noise reduction algorithms, and the dimensional differences of multi-source sensor data are eliminated by combining the Z-score standardization method. A dynamic fusion model is constructed based on Bayesian reasoning, and the confidence of each sensor data is quantified by probability density estimation. A weighted fusion strategy is used to generate high-precision comprehensive data, which effectively improves data integrity and feature expression capabilities, and provides a reliable data basis for subsequent analysis and decision-making.

[0045] In the present invention, in the intelligent decision-making step, if the decision result exceeds the preset safety range, the system will automatically trigger the alarm mechanism and take safety measures such as emergency shutdown. At the same time, the system will start the emergency decision plan and quickly generate a temporary solution based on historical data and real-time conditions to reduce losses.

[0046] In the present invention, after the data storage and management steps, a data feedback and optimization step is also included to optimize and adjust the processing parameters and intelligent decision-making rules according to the data mining results and processing quality feedback. The meta-learning mechanism and federated learning technology are used to accelerate the optimization process and improve the overall performance and adaptability of the system.

[0047] The above are only preferred specific implementation modes of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solutions and inventive concepts of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An intelligent control system for marine engineering gear processing machine tools, characterized in that: Includes the following modules: Data acquisition module: Use displacement, vibration, temperature, and pressure sensors to collect gear processing data. The sampling frequency is based on the formula f s =k× Dynamic adjustment, where v is the tool cutting speed, p is the machining accuracy level, and k is the empirical coefficient; quantum sensing technology is used to capture changes in physical quantities; Data analysis module: Use deep learning algorithms to build a hybrid model based on convolutional neural networks and long short-term memory networks, extract features and recognize patterns from collected data, and establish a processing quality prediction model Q=f(D), where Q is the processing quality index and D is the data vector; introduce graph neural networks to mine potential information from data; Intelligent decision-making module: Combines preset processing parameters and quality standards, uses fuzzy decision-making algorithms, and Determine the decision-making plan, is the factor weight, To correspond to fuzzy rules; fusion genetic algorithm optimizes fuzzy decision parameters; Control execution module: receives control instructions from the intelligent decision-making module, adjusts machine tool parameters, introduces magnetic suspension drive technology, and reduces mechanical friction and transmission errors; Fault diagnosis module: real-time monitoring of machine tool status, using fault feature extraction and fault classification algorithms to analyze data, and establish a fault dictionary F={f1,f2,...,f n }, where f i For the i-th fault type; analyze the root cause of the fault by combining the expert system and the fault tree analysis method; Human-machine interaction module: provides a human-machine interaction interface, supports operators to input operating parameters through touch screen or voice commands, and displays machine tool information on the interface; introduces VR and AR technologies, operators can immersively experience the machine tool operation status through VR devices, and view the machine tool status in the actual scene through AR devices; Data storage and management module: Store the collected information in the database, use data encryption technology to ensure security, and use data mining algorithms to analyze historical data; use distributed ledger technology to ensure that the data cannot be tampered with and is traceable.

2. The intelligent control system for marine engineering gear processing machine tools according to claim 1 is characterized in that: It also includes an adaptive learning module, which uses a reinforcement learning algorithm to automatically adjust the decision rules and parameters of the intelligent decision-making module based on real-time feedback during the processing. This module also introduces a meta-learning mechanism to learn new processing tasks and environments, so that the system can achieve optimal performance in different processing scenarios.

3. The intelligent control system for marine engineering gear processing machine tools according to claim 1 is characterized in that: It also includes a remote monitoring and maintenance module, which connects the machine tool to the remote server through the industrial Internet to achieve remote maintenance of the machine tool. The operator obtains the machine tool operation information through the mobile phone APP or computer terminal; 5G communication technology is used to transmit data, and at the same time, edge computing technology is used to process local data.

4. The intelligent control system for marine engineering gear processing machine tools according to claim 1 is characterized in that: The sensors in the data acquisition module adopt multi-sensor fusion technology to fuse the data of different types of sensors. The fusion technology adopts a fusion algorithm based on Bayesian reasoning to perform weighted fusion on the data of different sensors.

5. The intelligent control system for marine engineering gear processing machine tools according to claim 1 is characterized in that: The deep learning model in the data analysis module adopts transfer learning technology, using models pre-trained in other processing tasks to adapt to the characteristics of marine engineering gear processing. The module also adopts federated learning technology to train the model without leaking the data privacy of each participant.

6. The intelligent control system for marine engineering gear processing machine tools according to claim 1 is characterized in that: The servo control system in the control execution module adopts a fuzzy-proportional integral differential composite control algorithm, which combines the flexibility of fuzzy control and the accuracy of PID control to improve the stability of parameter adjustment. The composite control algorithm introduces an adaptive adjustment mechanism to automatically adjust the parameters of fuzzy control and PID control according to the machine tool operating status and processing tasks.

7. A method for applying the intelligent control system of a marine engineering gear processing machine tool according to any one of claims 1 to 6, characterized in that: The following steps are involved: S1: Data acquisition: Start the data acquisition module, dynamically set the sensor sampling frequency according to the principle of adapting to the processing accuracy, collect tool displacement, machine tool vibration, cutting temperature and cutting force data in the gear processing process in real time, and use quantum sensing technology to improve the accuracy and anti-interference ability of data acquisition; S2: Data analysis: The collected data is transferred to the data analysis module, and a hybrid model based on CNN, LSTM and GNN is used to perform feature extraction and pattern recognition to predict the gear processing quality; S3: Intelligent decision-making: The data analysis module sends the analysis results to the intelligent decision-making module, which combines the preset processing parameters and quality standards and uses the fuzzy decision-making algorithm optimized by the genetic algorithm to comprehensively determine the decision-making plan based on multiple factors; S4: Control execution: The intelligent decision-making module sends the decision plan to the control execution module, which adjusts the tool feed speed, spindle speed, and cutting depth of the machine tool in real time according to the instructions, and uses magnetic suspension drive technology to improve motion control accuracy; S5: Fault diagnosis: The fault diagnosis module monitors the machine tool operation status in real time, uses the fault feature extraction and classification algorithm combined with the expert system and fault tree analysis method, and diagnoses the fault and analyzes the root cause by comparing the fault features with the fault dictionary; S6: Human-machine interaction: The operator inputs operating parameters and queries processing information through the human-machine interaction module that introduces VR and AR technologies. The module displays the machine tool's operating status, processing quality, and fault information in real time. S7: Data storage and management: The data storage and management module stores the collected data, analysis results, decision-making plans and fault information in a database using distributed ledger technology, uses data encryption technology to ensure data security, and uses data mining algorithms to analyze historical data.

8. The method of the intelligent control system of the marine engineering gear processing machine tool according to claim 7 is characterized in that: After the data collection step, a data preprocessing step is also included to filter, reduce noise and normalize the collected data, and a multi-sensor fusion algorithm based on Bayesian reasoning is used to improve data quality and availability.

9. The method of the intelligent control system of the marine engineering gear processing machine tool according to claim 7, characterized in that: In the intelligent decision-making step, if the decision result exceeds the preset safety range, the system will automatically trigger the alarm mechanism and take emergency shutdown. At the same time, the system will activate the emergency decision-making plan and quickly generate a temporary solution based on historical data and real-time conditions.

10. The method of intelligent control system of marine engineering gear processing machine tool according to claim 7, characterized in that: After the data storage and management steps, there are also data feedback and optimization steps. According to the data mining results and processing quality feedback, the processing parameters and intelligent decision-making rules are optimized and adjusted, and the meta-learning mechanism and federated learning technology are used to accelerate the optimization process.

Images