Processing roller and drying roller control system of spinning machine
By deploying sensors and machine learning models on spinning machines, real-time monitoring and adjustment of parameters of processing rollers and drying rollers, the lack of real-time adjustment and fault prediction in the prior art is solved, and the reliability and production efficiency of the equipment are improved. Reduces maintenance costs and manual operation dependency.
Patent Information
- Application Number
- CN202411435997.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-15
- Publication Date
- 2025-01-07
AI Technical Summary
The existing spinning machine's processing roller and drying roller control systems lack real-time adjustment capabilities and fault prediction mechanisms, resulting in production interruptions and high maintenance costs, and are highly dependent on manual operations, affecting product quality and production efficiency.
Using sensors, data acquisition units and central processing units, combined with machine learning modules and user interfaces, the parameters of processing rollers and drying rollers are monitored and adjusted in real time, and fault prediction and health monitoring are carried out through support vector machines and long and short-term memory network models, providing Real-time alerts and remote monitoring capabilities reduce manual operation dependencies and improve device reliability.
The stability and repetition of the fiber processing process are achieved, maintenance costs and production interruptions caused by equipment failures are reduced, production efficiency and product quality are improved, and operating costs are reduced.
Smart Images
Figure CN119272132A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of textile machinery, in particular to a control system for a processing roller and a drying roller of a spinning machine. Background Art
[0002] In the textile industry, the control system of the spinning machine's process rollers and drying rollers is a key production equipment, and its performance directly affects the quality and production efficiency of the final product. During the spinning process, accurate control of the process rollers and drying rollers is essential to ensure the quality and performance of the fiber. Since these processes are highly dependent on the precise adjustment of the equipment, the control system of the equipment must be able to accurately monitor and adjust various operating parameters, such as temperature, drawing speed and drying conditions.
[0003] In the prior art, although many spinning machines use automated control systems to monitor and adjust the operating parameters of the processing rollers and drying rollers, these systems usually rely on traditional control algorithms, which often cannot fully adapt to the rapid changes in the production environment. In addition, existing systems often lack the ability to predict equipment failures and cannot identify potential equipment problems in advance, such as abnormal vibration or temperature increase, which may lead to production interruptions and high maintenance costs.
[0004] The main problem of the existing technology is its limited adaptability and predictive maintenance capabilities. Although the existing systems can perform basic monitoring and control functions, they usually cannot adjust the processing parameters in real time to cope with sudden changes in production, and lack effective fault prediction mechanisms, which limits their ability to maintain product quality consistency and reduce production interruptions under high-standard market demands. In addition, the excessive reliance on manual operation further increases the instability of production efficiency and the risk of operating errors. Therefore, there is an urgent need to develop a more efficient and intelligent spinning machine control system to solve the above problems. Summary of the invention
[0005] In view of the deficiencies in the prior art, the present invention provides a control system for processing rollers and drying rollers of a spinning machine, which solves the problem that the traditional system cannot adjust processing parameters in real time to cope with sudden changes in production and lacks an effective fault prediction mechanism.
[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A control system for a processing roller and a drying roller of a spinning machine, comprising: A sensor disposed on the treatment roll and the drying roll, the sensor being adapted to measure at least one parameter related to the operation of the spinning machine; a data acquisition unit, connected to the sensor, adapted to receive and pre-process the parameters, including converting analog signals into digital signals and performing data normalization; a central processing unit configured with a machine learning module for executing a prediction algorithm based on received operating parameters to predict the operating condition and maintenance needs of the equipment; A user interface for displaying prediction results and receiving user input to adjust operating parameters of the process roller and the drying roller.
[0007] Preferably, the sensor comprises a temperature sensor and a vibration sensor, wherein the temperature sensor is a thermocouple type for monitoring the surface temperature of the processing roller and the drying roller during processing, and the vibration sensor is an accelerometer for monitoring the vibration frequency and amplitude related to the operating status of the equipment.
[0008] Preferably, the data acquisition unit further comprises an analog-to-digital converter, which is used to convert the analog signal received from the sensor into a digital signal and perform data normalization processing, wherein the data normalization comprises calculating the Z-score of each data point according to the following formula:
[0009] in are the raw data points received from the sensor, is the mean value of the data set, is the standard deviation.
[0010] Preferably, the machine learning module of the central processing unit uses a support vector machine algorithm for fault prediction and health monitoring, and the algorithm is trained and executed based on the following formula:
[0011] in is the weight vector learned from the training data, is the input feature vector, is the learned bias term, is the predicted output, and the training step involves using the historical running data as the training set and adjusting by minimizing the prediction error and .
[0012] Preferably, the central processing unit is further configured with a module for performing principal component analysis, which is used to extract key features from the operating parameters. The key feature extraction step includes calculating the covariance matrix of each feature and then finding the eigenvectors of the covariance matrix. These eigenvectors represent the direction of the maximum variance in the data and are used to optimize the performance of the support vector machine algorithm.
[0013] Preferably, the user interface further comprises a real-time alarm system for sending an alarm to an operator when the predicted maintenance demand reaches a threshold, the real-time alarm system being activated by: Monitor maintenance demand indicators output by the long short-term memory network model; When the indicator exceeds the preset threshold, an alarm is automatically triggered and the user is prompted to perform necessary maintenance operations through the graphical user interface.
[0014] Preferably, the system further comprises a remote monitoring module, which allows monitoring and adjustment of operating parameters of the processing roller and the drying roller from a remote location via the Internet, the remote monitoring module comprising: A secure authentication system to ensure that only authorized users can access and modify parameters; Data encryption transmission ensures data security during the transmission of operating parameters.
[0015] Preferably, the data acquisition unit further includes a fault detection logic, which is used to automatically diagnose potential hardware faults based on parameter anomalies received from the sensor, and the fault detection logic includes: Analyze temperature and vibration data for unusual patterns; Predefined anomaly thresholds are used to determine whether a fault condition exists and provide a fault indication on the user interface.
[0016] Preferably, the central processing unit is further configured with an adaptive learning module capable of learning and adapting to new operating conditions, which automatically adjusts the parameters of the prediction model based on continuously received new data to improve the accuracy of the prediction and the overall performance of the system.
[0017] Preferably, the central processing unit is further configured with a module for dynamic energy-saving optimization, which automatically adjusts the energy usage of the equipment according to the current production efficiency and energy consumption data to maximize energy efficiency. The specific steps include: Monitor real-time energy consumption data; Automatically adjusts process and drying roller speed and temperature settings based on preset energy efficiency targets.
[0018] How it works: The system uses advanced sensing technology, data processing unit, central processing unit and user interface to ensure efficient and reliable spinning operations. In this system, temperature sensors and vibration sensors are deployed on the processing rollers and drying rollers to monitor key operating parameters in real time. The temperature sensor is a thermocouple type, which is responsible for monitoring the temperature of the roller surface to maintain the optimal temperature conditions for the spinning process; the vibration sensor uses an accelerometer to monitor the vibration condition of the equipment and promptly detect the signs of equipment failure. The data acquisition unit includes an analog-to-digital converter (ADC), which is responsible for converting analog signals into digital signals and performing data normalization. This processing step normalizes the data by calculating the Z-score, the formula is in represents the original data point, is the average value, is the standard deviation. Normalization ensures the consistency and comparability of data and provides accurate input for subsequent analysis. The system's central processing unit has a built-in machine learning module that uses support vector machine (SVM) and long short-term memory network (LSTM) models to analyze the collected data and perform fault prediction and maintenance demand prediction. These predictions are based on historical and real-time data, and are continuously optimized through machine learning models to improve the accuracy of predictions and the operating efficiency of equipment. The user interface is designed as a graphical user interface (GUI), providing intuitive data display and operation control, including real-time data flow, historical trend analysis and early warning information. The real-time alarm system automatically triggers an alarm based on the maintenance demand indicators output by the LSTM model when these indicators exceed the preset threshold, and prompts the user to perform necessary maintenance operations through the GUI, thereby improving the reliability and safety of the equipment. In addition, the system includes a remote monitoring module that allows remote monitoring and adjustment of equipment operating parameters via the Internet. The module includes secure authentication and data encryption transmission to ensure data security and authorized access to operations. The fault detection logic further enhances the system's automated monitoring capabilities, and can automatically diagnose hardware faults based on abnormal patterns in sensor data and provide fault indications on the user interface in a timely manner. The central processing unit is also equipped with an adaptive learning module and an energy optimization module, which automatically adjust the parameters of the prediction model based on the new data continuously received, and adjust the energy use of the equipment according to the real-time energy consumption data to maximize energy efficiency. This dynamic adjustment not only improves the efficiency of energy use, but also reduces operating costs.
[0019] The present invention provides a control system for a processing roller and a drying roller of a spinning machine. The control system has the following beneficial effects: 1. The present invention ensures the stability and repeatability of the fiber processing process by accurately monitoring and automatically adjusting key parameters such as the temperature and speed of the processing roller and the drying roller. This fine control helps to maintain the consistency of product quality and reduce quality problems caused by fluctuations in processing conditions, thereby meeting high-standard market demands.
[0020] 2. Through real-time data monitoring and advanced prediction algorithms, the present invention can promptly identify potential equipment problems, such as abnormal vibration or temperature rise, so as to implement preventive maintenance measures. This not only extends the service life of the equipment, but also significantly reduces the maintenance costs and production interruptions caused by sudden failures.
[0021] 3. The automated and intelligent control system of the present invention reduces the reliance on manual operation and improves the efficiency of the production process. Through the adaptive learning algorithm, the system can optimize operating parameters based on historical data and real-time feedback, achieving faster production cycles and higher raw material utilization. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] Figure 1 It is the main framework diagram of the present invention; Figure 2 It is a flow chart of the medium pressure processing unit of the present invention. DETAILED DESCRIPTION
[0023] 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.
[0024] Example: Please see attached Figure 1 and 2 The embodiment of the present invention provides a control system for a processing roller and a drying roller of a spinning machine, comprising: A sensor disposed on the processing roller and the drying roller, the sensor being adapted to measure at least one parameter related to the operation of the spinning machine; a data acquisition unit connected to the sensor and adapted to receive and pre-process parameters, including converting analog signals into digital signals and performing data normalization; a central processing unit configured with a machine learning module for executing a prediction algorithm based on received operating parameters to predict the operating condition and maintenance needs of the equipment; A user interface for displaying prediction results and receiving user input to adjust operating parameters of the process roller and the drying roller.
[0025] In this embodiment, the system deploys temperature sensors and vibration sensors on each processing roller and drying roller. The temperature sensor is a thermocouple type because it responds quickly and accurately to high temperatures and is suitable for monitoring the high temperature environment of the processing roller. The thermocouple is installed at the position where the roller is most likely to contact the fiber. The vibration sensor uses a highly sensitive accelerometer fixed to the non-rotating part of the roller to reduce mechanical interference and improve measurement accuracy. This sensor deployment method can capture key operating data in real time, providing a basis for subsequent data processing and analysis.
[0026] Data acquisition unit In this embodiment, the data acquisition unit is responsible for receiving analog signals from the sensor and converting them into digital signals for further processing. A high-precision analog-to-digital converter (ADC) is used to ensure the accuracy of signal conversion and avoid data loss during transmission.
[0027] CPU and machine learning In this embodiment, the central processing unit has built-in advanced machine learning modules, including support vector machines (SVM) and long short-term memory networks (LSTM). The SVM model is used to quickly identify and classify equipment states, such as normal, attention-required, and faulty. The training process of the model includes selecting a suitable kernel function and adjusting the penalty parameter C and the kernel parameter γ to optimize the classification boundary. The LSTM model is used to process and predict time series-based data. Its ability lies in capturing long-term dependencies in the data, and it is very suitable for predicting the future state and maintenance needs of the equipment. The complexity of LSTM lies in its internal state update mechanism, which controls the long-term transmission and memory of information through the gating unit.
[0028] user interface In this embodiment, the graphical user interface (GUI) is designed as an intuitive operation platform that supports touch screen and physical button operation. The interface display includes real-time data stream, historical data analysis, early warning system and maintenance prompts. Users can view the equipment status, adjust operating parameters, or respond to maintenance suggestions proposed by the system through simple interactive operations. The design of the GUI focuses on user experience, allowing operators to easily manage the complex system of the spinning machine even without a deep technical background.
[0029] Through the specific description of the above technical solutions, we have explained in detail each step from sensor deployment to user interface, and demonstrated how to optimize the performance and maintenance of spinning machines by integrating advanced monitoring technologies and intelligent algorithms. The technical selection of each step is to ensure the efficiency and reliability of the entire system, while simplifying the operation process, reducing human errors, and improving production efficiency. Through real-time data monitoring and intelligent data analysis, the system can prevent unexpected downtime, extend equipment life, and improve energy efficiency through automated adjustments. In addition, the intuitive design of the user interface ensures that technicians can easily manage this complex system and respond instantly to various operating conditions. Overall, the implementation of these technical solutions not only improves the operating efficiency and product quality of the spinning machine, but also brings significant economic benefits and operational convenience.
[0030] The sensors include temperature sensors and vibration sensors, wherein the temperature sensors are of the thermocouple type and are used to monitor the surface temperature of the processing roller and the drying roller during the process, while the vibration sensors are accelerometers and are used to monitor the vibration frequency and amplitude related to the operating status of the equipment.
[0031] The data acquisition unit further includes an analog-to-digital converter for converting analog signals received from the sensor into digital signals and performing data normalization processing, wherein data normalization includes calculating the Z-score of each data point according to the following formula:
[0032] in are the raw data points received from the sensor, is the mean value of the data set, is the standard deviation.
[0033] The machine learning module of the central processing unit uses a support vector machine algorithm for fault prediction and health monitoring. The algorithm is trained and executed based on the following formula:
[0034] in is the weight vector learned from the training data, is the input feature vector, is the learned bias term, is the predicted output, and the training step involves using the historical running data as the training set and adjusting by minimizing the prediction error and .
[0035] The central processing unit is further configured with a module for performing principal component analysis to extract key features from the operating parameters. The key feature extraction step includes calculating the covariance matrix of each feature and then finding the eigenvectors of the covariance matrix. These eigenvectors represent the direction of the maximum variance in the data and are used to optimize the performance of the support vector machine algorithm.
[0036] The user interface further includes a real-time alert system for sending an alert to the operator when the predicted maintenance requirement reaches a threshold, the real-time alert system being activated by: Monitor maintenance demand indicators output by the long short-term memory network model; When the indicator exceeds the preset threshold, an alarm is automatically triggered and the user is prompted to perform necessary maintenance operations through the graphical user interface.
[0037] The system further includes a remote monitoring module that allows monitoring and adjustment of operating parameters of the process roller and the drying roller from a remote location via the Internet, the remote monitoring module comprising: A secure authentication system to ensure that only authorized users can access and modify parameters; Data encryption transmission ensures data security during the transmission of operating parameters.
[0038] The data acquisition unit further includes fault detection logic for automatically diagnosing potential hardware faults based on parameter anomalies received from the sensor, the fault detection logic including: Analyze temperature and vibration data for unusual patterns; Predefined anomaly thresholds are used to determine whether a fault condition exists and provide a fault indication on the user interface.
[0039] The central processing unit is further configured with an adaptive learning module capable of learning and adapting to new operating conditions, which automatically adjusts the parameters of the prediction model based on new data continuously received to improve the accuracy of the prediction and the overall performance of the system.
[0040] The central processing unit is further configured with a module for dynamic energy-saving optimization, which automatically adjusts the energy usage of the equipment to maximize energy efficiency based on current production efficiency and energy consumption data. The specific steps include: Monitor real-time energy consumption data; Automatically adjusts process and drying roller speed and temperature settings based on preset energy efficiency targets.
[0041] In a preferred embodiment, real-time data collection and feedback mechanism In this embodiment, the control system of the processing roller and drying roller of the spinning machine is designed to have advanced data collection and real-time feedback capabilities to monitor the equipment status and adjust the operating parameters according to the real-time data.
[0042] Sensor Network Deployment Type and Configuration: Multiple types of sensors are deployed on the process and drying rollers, including temperature sensors (thermocouples), vibration sensors (accelerometers), and other sensors that may be required, such as humidity sensors and pressure sensors.
[0043] Position and Installation: Temperature sensors are installed at key locations where the rollers contact the fiber to monitor temperature changes during processing in real time; vibration sensors are installed on the main load-bearing structure of the equipment to detect abnormal vibrations or equipment imbalance.
[0044] Data collection and transmission Analog to digital conversion: Use a high-precision analog to digital converter (ADC) to convert the analog signal collected from the sensor into a digital signal. This step is critical to accurately capture the raw data of the sensor and avoid losses during the signal conversion process.
[0045] Wireless data transmission: Use industrial wireless networks (such as Wi-Fi or dedicated frequency bands) to transmit data to the central processing unit in real time. This ensures the speed and reliability of data transmission and supports the system to respond quickly to dynamic changes.
[0046] Real-time data processing and feedback generation Data preprocessing: Before the data reaches the central processing unit, necessary preprocessing, such as filtering and denoising, is performed to improve the quality of the data. Normalization is also performed in this step, using Z-score standardization to ensure comparability of data across different devices and time periods.
[0047] Real-time analysis and decision-making: Use advanced data analysis techniques (such as time series analysis and machine learning algorithms) to process the collected data. Based on the real-time analysis results, the system automatically generates operational suggestions or automatically adjusts equipment parameters.
[0048] Feedback Mechanisms and User Interfaces Dynamic Feedback System: The system displays data and analysis results in real time through a graphical user interface, including any warning or alarm information. The interface is user-friendly and supports operators to quickly understand the equipment status and make decisions.
[0049] User interaction: Operators can evaluate and manually adjust system suggestions through the interface, or directly adopt automatically adjusted parameter settings. In addition, the system supports remote access capabilities, allowing technical teams to monitor and adjust equipment from any location.
[0050] In a preferred embodiment, the integration of the adaptive learning adjustment algorithm In this embodiment, the machine learning module of the central processing unit is further enhanced to include an adaptive learning adjustment algorithm. This algorithm is particularly suitable for dynamically changing production environments and can automatically adjust the parameters of the prediction model based on real-time feedback. This process not only enhances the accuracy of the model, but also improves the responsiveness and efficiency of the system.
[0051] Real-time data collection and feedback mechanism The system continuously collects operating data of the processing roller and drying roller, such as temperature, vibration, etc. through the deployed sensors.
[0052] After the real-time data is converted by the ADC, it is standardized through normalization processing in preparation for further analysis.
[0053] Adaptive Adjustment of Model Parameters Parameter update rule: The update of model parameters is based on the gradient descent method, and the adjustment includes the learning rate and model weights The update formula is as follows:
[0054] in, is the current weight, is the learning rate, is the gradient of the loss function L with respect to the weights.
[0055] Adaptive learning rate adjustment: Adopt Adam optimizer or other advanced optimization algorithms to automatically adjust the learning rate of each parameter based on the estimation of historical gradient and quadratic gradient.
[0056]
[0057] in, is the adaptive learning rate at time step t, is the root mean square of the estimated quadratic gradient is a small constant added for numerical stability.
[0058] Continuous performance evaluation and optimization Use cross-validation to regularly evaluate the performance of your model, especially under new production conditions.
[0059] Performance feedback is used to further tune model parameters, such as adjusting regularization terms to avoid overfitting.
[0060] Practical application integration into control systems The output of the adaptive algorithm is used to adjust the operating parameters of the process and drying rollers, such as temperature settings and speeds, in real time to maximize production efficiency and reduce energy consumption.
[0061] The system provides instant feedback and visual adjustment suggestions through a graphical user interface (GUI), allowing operators to intuitively understand the results of model adjustments.
[0062] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A control system for a treatment roller and a drying roller of a spinning machine, characterized in that: include: A sensor disposed on the treatment roll and the drying roll, the sensor being adapted to measure at least one parameter related to the operation of the spinning machine; a data acquisition unit, connected to the sensor, adapted to receive and pre-process the parameters, including converting analog signals into digital signals and performing data normalization; a central processing unit configured with a machine learning module for executing a prediction algorithm based on received operating parameters to predict the operating condition and maintenance needs of the equipment; A user interface for displaying prediction results and receiving user input to adjust operating parameters of the process roller and the drying roller.
2. A control system for a treatment roller and a drying roller of a spinning machine according to claim 1, characterized in that: The sensors include a temperature sensor and a vibration sensor, wherein the temperature sensor is a thermocouple type for monitoring the surface temperature of the processing roller and the drying roller during processing, and the vibration sensor is an accelerometer for monitoring the vibration frequency and amplitude related to the operating status of the equipment.
3. A control system for a treatment roller and a drying roller of a spinning machine according to claim 1, characterized in that: The data acquisition unit further includes an analog-to-digital converter, which is used to convert the analog signal received from the sensor into a digital signal and perform data normalization processing, wherein the data normalization includes calculating the Z-score of each data point according to the following formula: in are the raw data points received from the sensor, is the mean value of the data set, is the standard deviation.
4. A control system for a treatment roller and a drying roller of a spinning machine according to claim 1, characterized in that: The machine learning module of the central processing unit uses a support vector machine algorithm for fault prediction and health monitoring. The algorithm is trained and executed based on the following formula: in is the weight vector learned from the training data, is the input feature vector, is the learned bias term, is the predicted output, and the training step involves using the historical running data as the training set and adjusting by minimizing the prediction error and .
5. A control system for a treatment roller and a drying roller of a spinning machine according to claim 1, characterized in that: The central processing unit is further configured with a module for performing principal component analysis, which is used to extract key features from the operating parameters. The key feature extraction step includes calculating the covariance matrix of each feature and then finding the eigenvectors of the covariance matrix. These eigenvectors represent the direction of the maximum variance in the data and are used to optimize the performance of the support vector machine algorithm.
6. A control system for a treatment roller and a drying roller of a spinning machine according to claim 1, characterized in that: The user interface further includes a real-time alert system for sending an alert to an operator when the predicted maintenance requirement reaches a threshold, the real-time alert system being activated by: Monitor maintenance demand indicators output by the long short-term memory network model; When the indicator exceeds the preset threshold, an alarm is automatically triggered and the user is prompted to perform necessary maintenance operations through the graphical user interface.
7. A control system for a treatment roller and a drying roller of a spinning machine according to claim 1, characterized in that: The system further includes a remote monitoring module that allows monitoring and adjustment of operating parameters of the processing roller and the drying roller from a remote location via the Internet, the remote monitoring module comprising: A secure authentication system to ensure that only authorized users can access and modify parameters; Data encryption transmission ensures data security during the transmission of operating parameters.
8. A control system for a treatment roller and a drying roller of a spinning machine according to claim 1, characterized in that: The data acquisition unit further includes a fault detection logic for automatically diagnosing potential hardware faults based on parameter anomalies received from the sensor, the fault detection logic including: Analyze temperature and vibration data for unusual patterns; Predefined anomaly thresholds are used to determine whether a fault condition exists and provide a fault indication on the user interface.
9. A control system for a treatment roller and a drying roller of a spinning machine according to claim 1, characterized in that: The central processing unit is further configured with an adaptive learning module capable of learning and adapting to new operating conditions, which automatically adjusts the parameters of the prediction model based on new data continuously received to improve the accuracy of the prediction and the overall performance of the system.
10. A control system for a treatment roller and a drying roller of a spinning machine according to claim 1, characterized in that: The central processing unit is further configured with a module for dynamic energy-saving optimization, which automatically adjusts the energy use of the equipment according to the current production efficiency and energy consumption data to maximize energy efficiency. The specific steps include: Monitor real-time energy consumption data; Automatically adjusts process and drying roller speed and temperature settings based on preset energy efficiency targets.