Hydraulic machine automatic control method and system based on PLC technology

By deploying multiple sensors on the hydraulic machine and using adaptive fuzzy PID algorithm and edge computing with PLC technology, combined with support vector machine fault diagnosis, the problems of low automation degree and insufficient fault diagnosis capabilities of hydraulic machine control system are solved, and high-precision control is achieved and fault warning improve the intelligence and reliability of the system.

CN119045400AInactive Publication Date: 2024-11-29NANTONG SHIPPING COLLEGE

Patent Information

Application Number
CN202411142769.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-20
Publication Date
2024-11-29
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing hydraulic press control system has low degree of automation, insufficient control accuracy, and insufficient fault diagnosis capabilities, which cannot meet the needs of modern industry for high accuracy, rapid response and strong adaptability.

Method used

Adopting an automated control method of hydraulic press based on PLC technology, by deploying multiple sensors to collect data in real time, using adaptive fuzzy PID algorithm and edge computing technology to perform data analysis and control parameter generation, combining support vector machine fault diagnosis algorithm and deep learning optimization control strategy , realize accurate control and fault warning of hydraulic presses.

Benefits of technology

It improves the automation level and control accuracy of the hydraulic press, enhances the fault prediction and diagnosis capabilities, improves the intelligence level and operation reliability of the system, and ensures the continuity and stability of the production process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119045400A_ABST
    Figure CN119045400A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of industrial automation control, in particular to a hydraulic machine automation control method and system based on the PLC technology, and the method comprises the following steps: S1, collecting data of pressure, displacement, temperature, vibration and sound waves in real time; s2, performing data fusion and preprocessing to generate feature vectors; s3, hydraulic machine control parameters are generated; s4, according to the control parameters of the hydraulic machine, a hydraulic valve set and a servo driving assembly are adjusted in real time through a PLC; s5, identifying a potential fault mode; s6, performing big data analysis and deep learning training, and generating a new control strategy; and S7, the operation state and early warning information of the hydraulic machine are displayed in real time through a human-computer interface. According to the invention, through multi-sensor comprehensive monitoring, PLC adaptive fuzzy PID control, edge calculation fault diagnosis and cloud big data analysis and optimization, efficient, accurate and intelligent control of the hydraulic machine is realized, and the automation degree and operation reliability of the system are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of industrial automation control technology, and in particular to a hydraulic press automation control method and system based on PLC technology. Background Art

[0002] With the development of industrial automation, hydraulic presses have been widely used in metal processing, plastic product manufacturing and other fields. However, the traditional hydraulic press control system mainly relies on relays and manual control methods, which have problems such as low automation, insufficient control accuracy, and high energy consumption. With the improvement of production requirements, the hydraulic press control system requires higher accuracy, faster response speed and stronger adaptability to meet the needs of modern industry. PLC (Programmable Logic Controller) technology has gradually become an important technical means in the field of industrial control due to its high flexibility, reliability and easy programming.

[0003] The existing hydraulic press control system has the following technical difficulties: data collection and processing are not comprehensive enough, and there is a lack of comprehensive monitoring of multiple operating parameters; the control algorithm is simple and cannot achieve precise control of complex working conditions of the hydraulic press; the fault diagnosis capability is insufficient, and it is difficult to timely warn and deal with potential faults. In order to improve the level of automation control of the hydraulic press, it is necessary to design a hydraulic press automation control method and system based on PLC technology. Summary of the invention

[0004] Based on the above objectives, the present invention provides a hydraulic press automation control method and system based on PLC technology.

[0005] A hydraulic press automation control method based on PLC technology comprises the following steps:

[0006] S1: Deploy a variety of sensors at predetermined locations of the hydraulic press to collect data on pressure, displacement, temperature, vibration, and sound waves in real time;

[0007] S2: Transmit the data collected by S1 to the PLC controller through a high-speed data bus, perform data fusion and preprocessing, and generate feature vectors;

[0008] S3: Analyze and calculate the preprocessed feature vector using a preset adaptive fuzzy PID algorithm in the PLC controller to generate hydraulic press control parameters;

[0009] S4: According to the hydraulic press control parameters generated by S3, the hydraulic valve group and servo drive components are adjusted in real time through the PLC controller to achieve precise control of the hydraulic press and ensure the dynamic response of pressure, speed and position;

[0010] S5: Use the PLC controller to perform edge computing and analysis on the large amount of data generated during operation, identify potential failure modes, and issue early warning information when a failure is about to occur;

[0011] S6: Upload the potential failure mode data identified in S5 to the cloud database and perform big data analysis and deep learning training to optimize the control algorithm and generate a new control strategy;

[0012] S7: The operating status and warning information of the hydraulic press are displayed in real time through the human-machine interface, so that the operator can make corresponding adjustments based on the displayed information.

[0013] Optionally, the S1 specifically includes:

[0014] S11: Install a pressure sensor at the main cylinder position of the hydraulic press to collect the pressure data of the hydraulic oil in real time. The pressure sensor adopts a piezoelectric pressure sensor and converts the hydraulic oil pressure into an electrical signal by using the piezoelectric effect;

[0015] S12: Installing a displacement sensor on the movable crossbeam of the hydraulic press to collect position data of the crossbeam in real time, wherein the displacement sensor adopts a linear potentiometer to measure displacement through resistance change;

[0016] S13: installing temperature sensors on the oil tank and hydraulic cylinder of the hydraulic press to monitor the temperature of the hydraulic oil and the cylinder in real time, wherein the temperature sensor adopts a thermocouple sensor and converts temperature changes into electrical signals by using the thermoelectric effect;

[0017] S14: installing a vibration sensor on the base and the supporting structure of the hydraulic press to monitor the vibration of the hydraulic press in real time during operation. The vibration sensor uses an accelerometer to obtain a vibration signal by detecting a change in acceleration.

[0018] S15: Install an acoustic wave sensor on the hydraulic pump and pipeline of the hydraulic press to monitor the acoustic wave signal generated during the operation of the hydraulic system in real time. The acoustic wave sensor adopts a piezoelectric acoustic wave sensor, which converts the response of the piezoelectric material to the acoustic wave into an electrical signal.

[0019] Optionally, the S2 specifically includes:

[0020] S21: transmitting the pressure, displacement, temperature, vibration and sound wave data collected in S1 to the PLC controller via a high-speed data bus, wherein the high-speed data bus is selected from a CAN bus or an EtherCAT bus;

[0021] S22: Inside the PLC controller, data standardization is first performed to convert the data collected by different sensors into a unified format and value range, specifically including linear transformation of the data of each sensor and scaling it to the interval [0,1] to eliminate the dimensional differences between different physical quantities;

[0022] S23: Apply signal processing techniques to filter noise and enhance signals on the standardized data;

[0023] S24: extracting features from the processed data, and selecting the features with the most information value for monitoring and controlling the hydraulic press state, the features including the mean and variance of the pressure data, the rate of change of the displacement data, the slope of the temperature data, the frequency components of the vibration data, and the energy spectrum of the sound wave data;

[0024] S25: Using data fusion algorithm to integrate the extracted multi-source features into a comprehensive feature vector to fully reflect the working state of the hydraulic press;

[0025] S26: Store the generated feature vector in the data cache of the PLC controller.

[0026] Optionally, the S3 specifically includes:

[0027] S31: receiving the feature vector generated by S2 in the PLC controller, wherein the feature vector includes multiple feature parameters of pressure, displacement, temperature, vibration and sound wave;

[0028] S32: fuzzifying the received feature vector, converting the feature parameters into fuzzy variables, and specifically mapping the feature parameters using fuzzy membership functions, mapping the pressure data into three fuzzy levels of low, medium and high;

[0029] S33: Based on the mapped fuzzy variables, reasoning is performed using a preset fuzzy rule base, wherein the fuzzy rule base includes the following rules:

[0030] Rule 1: When the pressure is high and the temperature is high, reduce the hydraulic press working pressure;

[0031] Rule 2: When pressure is low and displacement is fast, increase the hydraulic press operating pressure;

[0032] Rule 3: When the vibration is large and the sound waves are strong, check the stability of the hydraulic system;

[0033] Fuzzy reasoning specifically uses the Mamdani method, and the formula is:

[0034] μ O (C) = max(min(μ H (P),μ H (T)),min(μ L(P),μ F (V)),min(μ G (V),μ S (S))),

[0035] Medium, μ O represents the fuzzy membership of the output variable, C represents the control parameter, μ L Indicates the fuzzy membership of low pressure, μ F Represents the fuzzy membership of fast displacement, μ G represents the fuzzy membership of vibration, μ S represents the fuzzy membership of strong sound waves, T represents the temperature parameter, V represents the displacement parameter, and S represents the sound wave parameter;

[0036] S34: Defuzzify the result of fuzzy reasoning and convert it into control parameters. Specifically, the defuzzification result is calculated using the centroid method. The specific formula is: Among them, C * represents the actual control parameter after defuzzification, μ O (C) is the membership function of the output fuzzy set;

[0037] S35: combining the defuzzified control parameters, applying the adaptive PID algorithm to adjust the parameters, specifically calculating the current error and error change rate according to the real-time feedback data and the preset control model, and adjusting the PID parameters to minimize the error;

[0038] S36: Send the generated hydraulic press control parameters to the hydraulic valve group and the servo drive component.

[0039] Optionally, the formula of the adaptive PID algorithm in S35 is:

[0040] K new =K old +ΔK;

[0041] Among them, K represents the parameters of the PID controller, ΔK represents the change of the PID parameters, ΔE represents the change of the error, α, β, γ are the adjustment coefficients of proportion, integration and differentiation respectively, E represents the error, and t represents time.

[0042] Optionally, the S4 specifically includes:

[0043] S41: receiving the hydraulic press control parameters generated in S3 in real time through the PLC controller;

[0044] S42: According to the received control parameters, the PLC controller generates a corresponding control signal and transmits the control signal to the hydraulic valve group, wherein the hydraulic valve group includes a proportional valve and a servo valve, and adjusts the hydraulic flow and pressure by adjusting the opening of the valve;

[0045] S43: The PLC controller adjusts the output signal of the servo drive component according to the speed control parameter. The servo drive component includes a servo motor and a servo driver. The movement speed of the hydraulic press is controlled by adjusting the speed and torque of the servo motor.

[0046] S44: The PLC controller monitors the current position of the hydraulic press in real time and adjusts the displacement command of the servo motor according to the position control parameters.

[0047] Optionally, the S5 specifically includes:

[0048] S51: receiving and storing real-time data generated during the operation of the hydraulic press in the PLC controller, including parameters of pressure, speed, position, temperature, vibration and sound waves;

[0049] S52: preprocessing the received real-time data to eliminate noise and abnormal values ​​in the data, and the preprocessing technology includes moving average filtering and median filtering;

[0050] S53: Use edge computing technology to perform real-time analysis on the pre-processed data, specifically divide the data into time windows, and perform fast Fourier transform in each time window to extract frequency domain features;

[0051] S54: Based on the extracted frequency domain features, a support vector machine fault diagnosis algorithm is applied to identify potential fault modes, wherein the support vector machine is trained using historical fault data to establish classification boundaries between normal and fault states, and is classified by inputting real-time data to identify potential fault modes;

[0052] S55: Once a potential failure mode is identified, the PLC controller will immediately generate an early warning signal, which includes an audible and visual alarm and a push prompt.

[0053] Optionally, the S54 specifically includes:

[0054] S541: inputting the frequency domain feature data extracted in S53 into a support vector machine model for fault diagnosis, wherein the support vector machine model has been pre-trained with historical fault data and has established a classification boundary between a normal state and a fault state;

[0055] S542: During the training process, use the historical fault data {(x1,y1),(x2,y2),...,(x n ,y n )}, where xi represents the frequency domain feature vector, y i represents the category label, and the training goal is to find an optimal classification hyperplane w·x+b=0 to separate the data points in normal state and fault state;

[0056] S543: Determine the optimal classification hyperplane parameters w and b by solving the following optimization problem:

[0057] Among them, ∥w∥ represents the norm of the weight vector;

[0058] S544: The real-time frequency domain feature data x new Input into the trained support vector machine model for classification and calculate the classification function value f(x new ), the formula is: f(x new )=w·x new +b, according to the classification function value f(x new ) determines the failure mode. new )>0, it is judged as normal state; when f(x new )<0, it is judged as a fault state.

[0059] Optionally, the S6 specifically includes:

[0060] S61: uploading the potential failure mode data identified in S5, including timestamp, frequency domain characteristics, and failure type, to a cloud database via a high-speed network interface;

[0061] S62: Storing the uploaded data in a cloud database;

[0062] S63: Analyze the fault mode data stored in the cloud database using big data analysis technology, including data cleaning, data clustering and data statistical analysis; data cleaning removes noise and outliers; data clustering classifies fault modes by using the K-means clustering algorithm to identify fault types and modes; data statistical analysis calculates the frequency and time distribution of fault occurrence to provide statistical information on faults;

[0063] S64: Based on the results of big data analysis, the fault prediction model is trained using deep learning technology. A multi-layer neural network model is constructed. The input data of the multi-layer neural network model is frequency domain features and historical fault mode data, and the output is the fault prediction result. The model training adopts the back propagation algorithm to optimize the loss function, iy

[0064] S65: Deploy the trained fault prediction model to the cloud database, and receive data from the PLC controller in real time to perform fault prediction and diagnosis and generate a new control strategy. The new control strategy includes adjusting the operating parameters of the hydraulic press.

[0065] A hydraulic press automation control system based on PLC technology, used to implement the above-mentioned hydraulic press automation control method based on PLC technology, includes the following modules:

[0066] Multi-sensor module: installed at the predetermined position of the hydraulic press, used to collect data on pressure, displacement, temperature, vibration and sound waves in real time; and transmit the collected data to the PLC controller through a high-speed data bus;

[0067] Data preprocessing module: integrated in the PLC controller, used to fuse and preprocess the received data and generate feature vectors;

[0068] Control algorithm module: integrated in the PLC controller, using the preset adaptive fuzzy PID algorithm to analyze and calculate the characteristic vector and generate the hydraulic press control parameters;

[0069] Execution module: including hydraulic valve group and servo drive components, receiving the control parameters generated by the PLC controller, adjusting the working state of the hydraulic press in real time to ensure the dynamic response of pressure, speed and position;

[0070] Fault diagnosis module: integrated into the PLC controller, it analyzes the data generated during operation, identifies potential fault modes and issues early warning signals;

[0071] Cloud database module: used to store fault mode data and conduct big data analysis and deep learning training to optimize control algorithms and generate new control strategies;

[0072] Human-machine interface module: connected to the PLC controller, used to display the operating status and warning information of the hydraulic press in real time, and allow the operator to set parameters and switch modes according to the displayed information.

[0073] Beneficial effects of the present invention:

[0074] The present invention realizes comprehensive monitoring of various operating parameters of the hydraulic press by integrating multiple sensors, improves the comprehensiveness and accuracy of data acquisition, and utilizes the preset adaptive fuzzy PID algorithm in the PLC controller to analyze and calculate the pre-processed feature vector to generate accurate control parameters, thereby realizing real-time and accurate control of the hydraulic press and ensuring the dynamic response of pressure, speed and position. This multi-level control strategy significantly improves the automation degree and control accuracy of the hydraulic press and meets the needs of modern industry for efficient and precise control.

[0075] The present invention uses edge computing and support vector machine (SVM) fault diagnosis algorithm to analyze a large amount of data generated during the operation of the hydraulic press in real time, identify potential fault modes and issue early warning signals in advance, thereby improving the system's fault prediction and diagnosis capabilities, uploading the identified fault mode data to the cloud database, and optimizing the control algorithm using big data analysis and deep learning technology to generate new control strategies, further improving the system's intelligence level and operational reliability. The human-machine interface module provides intuitive real-time monitoring and parameter setting functions, enabling operators to quickly respond to and adjust the operating status of the hydraulic press to ensure the continuity and stability of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0077] Figure 1 A schematic diagram of an automatic control method for a hydraulic press according to an embodiment of the present invention;

[0078] Figure 2 Schematic diagram of a hydraulic press automation control system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0079] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0080] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0081] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0082] like Figure 1 As shown, a hydraulic press automation control method based on PLC technology includes the following steps:

[0083] S1: Deploy a variety of sensors at predetermined locations of the hydraulic press to collect data on pressure, displacement, temperature, vibration, and sound waves in real time;

[0084] S2: Transmit the data collected by S1 to the PLC controller through a high-speed data bus, perform data fusion and preprocessing, and generate feature vectors;

[0085] S3: In the PLC controller, the pre-processed feature vector is analyzed and calculated using a preset adaptive fuzzy PID algorithm to generate hydraulic press control parameters. The algorithm adaptively adjusts the PID parameters according to real-time data to optimize control accuracy.

[0086] S4: According to the hydraulic press control parameters generated by S3, the hydraulic valve group and servo drive components are adjusted in real time through the PLC controller to achieve precise control of the hydraulic press and ensure the dynamic response of pressure, speed and position;

[0087] S5: Use the PLC controller to perform edge computing and analysis on the large amount of data generated during operation, identify potential failure modes, and issue early warning information when a failure is about to occur;

[0088] S6: Upload the potential failure mode data identified in S5 to the cloud database and perform big data analysis and deep learning training to optimize the control algorithm and generate a new control strategy;

[0089] S7: The operating status and warning information of the hydraulic press are displayed in real time through the human-machine interface (HMI), so that the operator can make corresponding adjustments based on the displayed information and set parameters and switch modes through the human-machine interface.

[0090] S1 specifically includes:

[0091] S11: A pressure sensor is installed at the main cylinder position of the hydraulic press to collect the pressure data of the hydraulic oil in real time. The pressure sensor adopts a piezoelectric pressure sensor, which converts the hydraulic oil pressure into an electrical signal by using the piezoelectric effect;

[0092] S12: Install a displacement sensor on the movable crossbeam of the hydraulic press to collect the position data of the crossbeam in real time. The displacement sensor adopts a linear potentiometer to measure the displacement through resistance change.

[0093] S13: Temperature sensors are installed on the oil tank and hydraulic cylinder of the hydraulic press to monitor the temperature of the hydraulic oil and the cylinder in real time. The temperature sensor uses a thermocouple sensor and converts temperature changes into electrical signals using the thermoelectric effect.

[0094] S14: Install vibration sensors on the base and supporting structure of the hydraulic press to monitor the vibration of the hydraulic press in real time during operation. The vibration sensor uses an accelerometer to obtain a vibration signal by detecting acceleration changes.

[0095] S15: Install acoustic wave sensors on the hydraulic pump and pipelines of the hydraulic press to monitor the acoustic wave signals generated by the hydraulic system in real time. The acoustic wave sensors use piezoelectric acoustic wave sensors, which convert the response of piezoelectric materials to acoustic waves into electrical signals. By deploying various sensors at predetermined locations on the hydraulic press, the monitoring capability of key performance parameters of the hydraulic press is enhanced, and the operating efficiency and safety of the system are improved. In particular, the application of various high-precision sensors can achieve precise control of the hydraulic press state, significantly improving the automation and intelligence level of the hydraulic press.

[0096] S2 specifically includes:

[0097] S21: The pressure, displacement, temperature, vibration and sound wave data collected in S1 are transmitted to the PLC controller through a high-speed data bus to ensure the real-time and integrity of the data. The high-speed data bus is selected from a CAN bus or an EtherCAT bus to provide high-bandwidth and low-latency data transmission;

[0098] S22: Inside the PLC controller, data standardization is first performed to convert the data collected by different sensors into a unified format and value range, specifically including linear transformation of the data of each sensor and scaling it to the interval [0,1] to eliminate the dimensional differences between different physical quantities;

[0099] S23: Apply signal processing technology to filter noise and enhance signals on the standardized data. Kalman filtering algorithm is used for noise filtering to iteratively eliminate noise through prediction and update steps to improve signal accuracy. Wavelet transform technology is used for signal enhancement to enhance the significance of characteristic signals by decomposing and reconstructing signals.

[0100] S24: extracting features from the processed data, and selecting the features with the most information value for monitoring and controlling the hydraulic press state, the features including the mean and variance of the pressure data, the rate of change of the displacement data, the slope of the temperature data, the frequency components of the vibration data, and the energy spectrum of the sound wave data;

[0101] S25: Use data fusion algorithm to integrate the extracted multi-source features into a comprehensive feature vector to fully reflect the working state of the hydraulic press. The data fusion algorithm includes weighted average method and principal component analysis (PCA) method. The weighted average method is used to integrate the importance of each feature, and the PCA method is used to reduce the dimension and retain the main feature information to reduce redundant data.

[0102] S26: The generated feature vector is stored in the data cache of the PLC controller to ensure the continuity and efficiency of data processing. The data cache adopts a circular buffer structure to ensure that the latest data is always available and the old data is automatically overwritten.

[0103] S3 specifically includes:

[0104] S31: receiving the feature vector generated by S2 in the PLC controller, the feature vector including multiple feature parameters of pressure, displacement, temperature, vibration and sound wave;

[0105] S32: Fuzzify the received feature vector and convert the precise feature parameters into fuzzy variables. Specifically, the fuzzy membership function is used to map the feature parameters. The specific formula is: Among them, μ H represents the fuzzy membership of high pressure, P represents the pressure parameter, P min and P max are the minimum and maximum values ​​of pressure, respectively, mapping the pressure data into three fuzzy levels: low, medium, and high;

[0106] S33: Based on the mapped fuzzy variables, reasoning is performed using a preset fuzzy rule base, where the fuzzy rule base includes the following rules:

[0107] Rule 1: When the pressure is high and the temperature is high, reduce the hydraulic press working pressure;

[0108] Rule 2: When pressure is low and displacement is fast, increase the hydraulic press operating pressure;

[0109] Rule 3: When the vibration is large and the sound waves are strong, check the stability of the hydraulic system;

[0110] Fuzzy reasoning specifically uses the Mamdani method, and the formula is:

[0111] μ O (C) = max(min(μ H(P),μ H (T)),min(μ L (P),μ F (V)),min(μ G (V),μ S (S))),

[0112] Medium, μ O represents the fuzzy membership of the output variable, C represents the control parameter, μ L Indicates the fuzzy membership of low pressure, μ F Represents the fuzzy membership of fast displacement, μ G represents the fuzzy membership of vibration, μ S represents the fuzzy membership of strong sound waves, T represents the temperature parameter, V represents the displacement parameter, and S represents the sound wave parameter;

[0113] S34: Defuzzify the result of fuzzy reasoning and convert it into accurate control parameters. Specifically, the defuzzification result is calculated using the centroid method. The specific formula is: Among them, C * represents the actual control parameter after defuzzification, μ O (C) is the membership function of the output fuzzy set;

[0114] S35: combining the defuzzified control parameters, applying the adaptive PID algorithm to adjust the parameters, specifically calculating the current error and error change rate according to the real-time feedback data and the preset control model, and adjusting the PID parameters to minimize the error;

[0115] S36: The generated hydraulic press control parameters are sent to the hydraulic valve group and servo drive components for real-time adjustment of the working state of the hydraulic press to ensure that the dynamic response of pressure, speed and position meets the expected requirements; by using the preset adaptive fuzzy PID algorithm in the PLC controller to analyze and calculate the preprocessed feature vector, the flexibility and accuracy of the control strategy are significantly improved, ensuring that the hydraulic press can maintain the best working state under various working conditions. This method not only improves the control accuracy, but also enhances the robustness and adaptability of the system.

[0116] The formula for the adaptive PID algorithm in S35 is:

[0117] K new =K old +ΔK;

[0118] Among them, K represents the parameters of the PID controller, ΔK represents the change of the PID parameters, ΔE represents the change of the error, α, β, γ are the adjustment coefficients of proportion, integration and differentiation respectively, E represents the error, and t represents time.

[0119] S4 specifically includes:

[0120] S41: receiving the hydraulic press control parameters (pressure, speed, position) generated in S3 in real time through the PLC controller to ensure the timeliness and accuracy of the control signal;

[0121] S42: According to the received control parameters, the PLC controller generates a corresponding control signal and transmits the control signal to the hydraulic valve group, which includes a proportional valve and a servo valve, and adjusts the hydraulic flow and pressure by adjusting the opening of the valve;

[0122] S43: The PLC controller adjusts the output signal of the servo drive component according to the speed control parameter. The servo drive component includes a servo motor and a servo driver. The movement speed of the hydraulic press is controlled by adjusting the speed and torque of the servo motor.

[0123] S44: The PLC controller monitors the current position of the hydraulic press in real time, and adjusts the displacement command of the servo motor according to the position control parameters. The PLC controller continuously compares the set position and the actual position through the feedback control loop, and corrects the displacement error in real time to ensure the accuracy of the hydraulic press movement. In terms of pressure control, the PLC controller continuously monitors the real-time pressure of the hydraulic system, and dynamically adjusts the opening of the proportional valve and the servo valve according to the preset pressure control parameters to keep the system pressure within the set range and avoid excessively high or low pressure affecting the system performance. In terms of speed control, the PLC controller combines the real-time speed feedback signal and dynamically adjusts the working state of the servo motor according to the speed control parameters to ensure that the operating speed of the hydraulic press meets the set requirements and avoids too fast or too slow movement affecting the processing accuracy. In terms of position control, the PLC controller combines the real-time position signal and dynamically adjusts the working state of the servo motor according to the position control parameters to ensure that the working position of the hydraulic press accurately reaches the set position and avoids deviation affecting the processing quality.

[0124] S5 specifically includes:

[0125] S51: receiving and storing real-time data generated during the operation of the hydraulic press in the PLC controller, including parameters of pressure, speed, position, temperature, vibration and sound waves;

[0126] S52: preprocessing the received real-time data to eliminate noise and outliers in the data. The preprocessing techniques include moving average filtering and median filtering to ensure the smoothness and accuracy of the data.

[0127] S53: Use edge computing technology to perform real-time analysis on the pre-processed data. Edge computing uses local processing to reduce data transmission delays. Specifically, the data is divided into time windows, and a fast Fourier transform (FFT) is performed in each time window to extract frequency domain features.

[0128] S54: Based on the extracted frequency domain features, a support vector machine fault diagnosis algorithm is applied to identify potential fault modes. The support vector machine is trained using historical fault data to establish classification boundaries between normal and fault states. The real-time data is input for classification to identify potential fault modes.

[0129] S55: Once a potential failure mode is identified, the PLC controller will immediately generate a warning signal, which includes sound and light alarms and push prompts, and output to the alarm device through the I / O interface of the PLC controller to remind the operator to take timely measures; the PLC controller performs edge computing and analysis on the large amount of data generated during the operation of the hydraulic press, identifies potential failure modes, and issues warning information in advance when a failure is about to occur. It can monitor and diagnose the working status of the hydraulic press in real time, significantly improving the reliability and safety of the hydraulic press.

[0130] S54 specifically includes:

[0131] S541: inputting the frequency domain feature data extracted in S53 into a support vector machine (SVM) model for fault diagnosis. The support vector machine model has been pre-trained with historical fault data to establish a classification boundary between a normal state and a fault state.

[0132] S542: During the training process, use the historical fault data {(x1,y1),(x2,y2),...,(x n ,y n )}, where x i represents the frequency domain feature vector, y i represents the category label (normal is +1, fault is -1), and the training goal is to find an optimal classification hyperplane w·x+b=0 to separate the data points in normal state and fault state;

[0133] S543: Determine the optimal classification hyperplane parameters w and b by solving the following optimization problem:

[0134] Among them, ∥w∥ represents the norm of the weight vector, and the constraint ensures that all training data points are correctly classified and the classification interval is maximized;

[0135] S544: The real-time frequency domain feature data x new Input into the trained support vector machine model for classification and calculate the classification function value f(x new ), the formula is: f(x new )=w·x new +b, according to the classification function value f(x new ) determines the failure mode. new)>0, it is judged as normal state; when f(x new )<0, it is judged as a fault state; the above-mentioned SVM model obtains the optimal classification hyperplane through historical data training, which can effectively distinguish between normal and fault states, and realizes rapid identification and early warning of hydraulic press faults through real-time classification function calculation. This method improves the accuracy and response speed of fault detection, ensures timely early warning of the hydraulic press before a fault occurs, and reduces the impact of the fault on production.

[0136] S6 specifically includes:

[0137] S61: upload the potential fault mode data identified in S5, including timestamp, frequency domain characteristics, and fault type, to the cloud database through a high-speed network interface to ensure data integrity and real-time performance;

[0138] S62: In the cloud database, the uploaded data is stored and managed, and the distributed database system is used to achieve efficient storage and fast retrieval of data;

[0139] S63: Analyze the fault mode data stored in the cloud database using big data analysis technology, including data cleaning, data clustering and data statistical analysis. Data cleaning ensures data quality by removing noise and outliers. Data clustering classifies fault modes by using the K-means clustering algorithm to identify common fault types and patterns. Data statistical analysis provides fault statistical information by calculating the frequency and time distribution of fault occurrence.

[0140] S64: Based on the results of big data analysis, the fault prediction model is trained using deep learning technology. A multi-layer neural network model is constructed. The input data of the multi-layer neural network model is frequency domain features and historical fault mode data, and the output is the fault prediction result. The model training adopts the back propagation algorithm to optimize the loss function, iy

[0141] S65: Deploy the trained fault prediction model to the cloud database, and receive data from the PLC controller in real time to perform fault prediction and diagnosis and generate new control strategies. The new control strategies include adjusting the operating parameters of the hydraulic press to ensure the safe and efficient operation of the hydraulic press; identify common fault modes and statistical information through big data analysis, use deep learning technology to train the fault prediction model, achieve accurate prediction and diagnosis of hydraulic press faults, generate optimized control strategies, and ensure efficient and safe operation of the hydraulic press. This method improves the intelligence level and fault handling capabilities of the system and ensures the optimal working state of the hydraulic press under various working conditions.

[0142] S7 specifically includes:

[0143] S71: Configure human-machine interface (HMI) software in the PLC controller and design the interface layout, including but not limited to display screens, buttons, indicator lights, and touch screens, so that operators can intuitively monitor the operating status of the hydraulic press and receive warning information;

[0144] S72: Displaying the operating parameters of the hydraulic press in real time through a human-machine interface, including data such as pressure, speed, position and temperature, with the data displayed in the form of numbers and charts updated in real time, for example, using a dashboard to display pressure and speed, a bar chart to display position, and a line chart to track temperature changes;

[0145] S73: Configure a warning information display module on the human-machine interface. When the system detects a fault or performance deviation, it provides visual and audible warnings through pop-up windows and colored warning lights. The warning information includes the fault type, occurrence time and recommended response measures;

[0146] S74: Provides the operator with a parameter setting function on the human-machine interface, allowing the operator to adjust the operating parameters of the hydraulic press according to the real-time display information. The specific operation includes inputting new parameter values, such as setting the upper limit of pressure or adjusting the speed, and completing the adjustment through the touch screen or knob;

[0147] S75: The integrated mode switching function on the human-machine interface enables the operator to switch the hydraulic press's working mode according to production needs or operating conditions, for example, from automatic mode to manual mode, or from high-speed operation mode to low-speed fine adjustment mode;

[0148] S76: Ensure that data communication between the human-machine interface and the PLC controller is fast and reliable, and use industrial Ethernet or wireless communication technology to achieve real-time data synchronization between the two, including the issuance of operating commands and feedback on operating status, ensuring that the operator's input immediately affects the hydraulic press control strategy.

[0149] like Figure 2 As shown, a hydraulic press automation control system based on PLC technology is used to implement the above-mentioned hydraulic press automation control method based on PLC technology, including the following modules:

[0150] Multi-sensor module: installed at the predetermined position of the hydraulic press, used to collect data on pressure, displacement, temperature, vibration and sound waves in real time; and transmit the collected data to the PLC controller through a high-speed data bus;

[0151] Data preprocessing module: integrated in the PLC controller, used to fuse and preprocess the received data and generate feature vectors;

[0152] Control algorithm module: integrated in the PLC controller, using the preset adaptive fuzzy PID algorithm to analyze and calculate the characteristic vector and generate the hydraulic press control parameters;

[0153] Execution module: including hydraulic valve group and servo drive components, receiving the control parameters generated by the PLC controller, adjusting the working state of the hydraulic press in real time to ensure the dynamic response of pressure, speed and position;

[0154] Fault diagnosis module: integrated in the PLC controller, it analyzes the data generated during operation, identifies potential fault modes and issues early warning signals;

[0155] Cloud database module: used to store fault mode data and conduct big data analysis and deep learning training to optimize control algorithms and generate new control strategies;

[0156] Human-machine interface module: connected to the PLC controller, used to display the operating status and warning information of the hydraulic press in real time, and allow the operator to set parameters and switch modes according to the displayed information.

[0157] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0158] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A hydraulic press automation control method based on PLC technology, characterized in that: The following steps are involved: S1: Deploy a variety of sensors at predetermined locations of the hydraulic press to collect data on pressure, displacement, temperature, vibration, and sound waves in real time; S2: Transmit the data collected by S1 to the PLC controller through a high-speed data bus, perform data fusion and preprocessing, and generate feature vectors; S3: Analyze and calculate the preprocessed feature vector using a preset adaptive fuzzy PID algorithm in the PLC controller to generate hydraulic press control parameters; S4: According to the hydraulic press control parameters generated by S3, the hydraulic valve group and servo drive components are adjusted in real time through the PLC controller to achieve precise control of the hydraulic press and ensure the dynamic response of pressure, speed and position; S5: Use the PLC controller to perform edge computing and analysis on the large amount of data generated during operation, identify potential failure modes, and issue early warning information when a failure is about to occur; S6: Upload the potential failure mode data identified in S5 to the cloud database and perform big data analysis and deep learning training to optimize the control algorithm and generate a new control strategy; S7: The operating status and warning information of the hydraulic press are displayed in real time through the human-machine interface, so that the operator can make corresponding adjustments based on the displayed information.

2. The hydraulic press automation control method based on PLC technology according to claim 1 is characterized in that: The S1 specifically includes: S11: Install a pressure sensor at the main cylinder position of the hydraulic press to collect the pressure data of the hydraulic oil in real time. The pressure sensor adopts a piezoelectric pressure sensor and converts the hydraulic oil pressure into an electrical signal by using the piezoelectric effect; S12: Installing a displacement sensor on the movable crossbeam of the hydraulic press to collect position data of the crossbeam in real time, wherein the displacement sensor adopts a linear potentiometer to measure displacement through resistance change; S13: installing temperature sensors on the oil tank and hydraulic cylinder of the hydraulic press to monitor the temperature of the hydraulic oil and the cylinder in real time, wherein the temperature sensor adopts a thermocouple sensor and converts temperature changes into electrical signals by using the thermoelectric effect; S14: installing a vibration sensor on the base and the supporting structure of the hydraulic press to monitor the vibration of the hydraulic press in real time during operation. The vibration sensor uses an accelerometer to obtain a vibration signal by detecting a change in acceleration. S15: Install an acoustic wave sensor on the hydraulic pump and pipeline of the hydraulic press to monitor the acoustic wave signal generated during the operation of the hydraulic system in real time. The acoustic wave sensor adopts a piezoelectric acoustic wave sensor, which converts the response of the piezoelectric material to the acoustic wave into an electrical signal.

3. The hydraulic press automation control method based on PLC technology according to claim 1 is characterized in that: The S2 specifically includes: S21: transmitting the pressure, displacement, temperature, vibration and sound wave data collected in S1 to the PLC controller via a high-speed data bus, wherein the high-speed data bus is selected from a CAN bus or an EtherCAT bus; S22: Inside the PLC controller, data standardization is first performed to convert the data collected by different sensors into a unified format and value range, specifically including linear transformation of the data of each sensor and scaling it to the interval [0,1] to eliminate the dimensional differences between different physical quantities; S23: Apply signal processing techniques to filter noise and enhance signals on the standardized data; S24: extracting features from the processed data, and selecting the features with the most information value for monitoring and controlling the hydraulic press state, the features including the mean and variance of the pressure data, the rate of change of the displacement data, the slope of the temperature data, the frequency components of the vibration data, and the energy spectrum of the sound wave data; S25: Using data fusion algorithm to integrate the extracted multi-source features into a comprehensive feature vector to fully reflect the working state of the hydraulic press; S26: Store the generated feature vector in the data cache of the PLC controller.

4. The hydraulic press automation control method based on PLC technology according to claim 1 is characterized in that: The S3 specifically includes: S31: receiving the feature vector generated by S2 in the PLC controller, wherein the feature vector includes multiple feature parameters of pressure, displacement, temperature, vibration and sound wave; S32: fuzzifying the received feature vector, converting the feature parameters into fuzzy variables, and specifically mapping the feature parameters using fuzzy membership functions, mapping the pressure data into three fuzzy levels of low, medium and high; S33: Based on the mapped fuzzy variables, reasoning is performed using a preset fuzzy rule base, wherein the fuzzy rule base includes the following rules: Rule 1: When the pressure is high and the temperature is high, reduce the hydraulic press working pressure; Rule 2: When pressure is low and displacement is fast, increase the hydraulic press operating pressure; Rule 3: When the vibration is large and the sound waves are strong, check the stability of the hydraulic system; Fuzzy reasoning specifically uses the Mamdani method, and the formula is: μ O (C) = max(min(μ H (P), μ H (T)), min(μ L (P), μ F (V)), min(μ G (V), μ S (S))), where Medium, μ O represents the fuzzy membership of the output variable, C represents the control parameter, μ L Indicates the fuzzy membership of low pressure, μ F Represents the fuzzy membership of fast displacement, μ G represents the fuzzy membership of vibration, μ S represents the fuzzy membership of strong sound waves, T represents the temperature parameter, V represents the displacement parameter, and S represents the sound wave parameter; S34: Defuzzify the result of fuzzy reasoning and convert it into control parameters. Specifically, the defuzzification result is calculated using the centroid method. The specific formula is: Among them, C * represents the actual control parameter after defuzzification, μ O (C) is the membership function of the output fuzzy set; S35: combining the defuzzified control parameters, applying the adaptive PID algorithm to adjust the parameters, specifically calculating the current error and error change rate according to the real-time feedback data and the preset control model, and adjusting the PID parameters to minimize the error; S36: Send the generated hydraulic press control parameters to the hydraulic valve group and the servo drive component.

5. The hydraulic press automation control method based on PLC technology according to claim 4 is characterized in that: The formula of the adaptive PID algorithm in S35 is: K new =K old +ΔK; Among them, K represents the parameters of the PID controller, ΔK represents the change of the PID parameters, ΔE represents the change of the error, α, β, γ are the adjustment coefficients of proportion, integration and differentiation respectively, E represents the error, and t represents time.

6. The hydraulic press automation control method based on PLC technology according to claim 1 is characterized in that: The S4 specifically includes: S41: receiving the hydraulic press control parameters generated in S3 in real time through the PLC controller; S42: According to the received control parameters, the PLC controller generates a corresponding control signal and transmits the control signal to the hydraulic valve group, wherein the hydraulic valve group includes a proportional valve and a servo valve, and adjusts the hydraulic flow and pressure by adjusting the opening of the valve; S43: The PLC controller adjusts the output signal of the servo drive component according to the speed control parameter. The servo drive component includes a servo motor and a servo driver. The movement speed of the hydraulic press is controlled by adjusting the speed and torque of the servo motor. S44: The PLC controller monitors the current position of the hydraulic press in real time and adjusts the displacement command of the servo motor according to the position control parameters.

7. The hydraulic press automation control method based on PLC technology according to claim 1 is characterized in that: The S5 specifically includes: S51: receiving and storing real-time data generated during the operation of the hydraulic press in the PLC controller, including parameters of pressure, speed, position, temperature, vibration and sound waves; S52: preprocessing the received real-time data to eliminate noise and abnormal values ​​in the data, and the preprocessing technology includes moving average filtering and median filtering; S53: Use edge computing technology to perform real-time analysis on the pre-processed data, specifically divide the data into time windows, and perform fast Fourier transform in each time window to extract frequency domain features; S54: Based on the extracted frequency domain features, a support vector machine fault diagnosis algorithm is applied to identify potential fault modes, wherein the support vector machine is trained using historical fault data to establish classification boundaries between normal and fault states, and is classified by inputting real-time data to identify potential fault modes; S55: Once a potential failure mode is identified, the PLC controller will immediately generate an early warning signal, which includes an audible and visual alarm and a push prompt.

8. The hydraulic press automation control method based on PLC technology according to claim 7 is characterized in that: The S54 specifically includes: S541: inputting the frequency domain feature data extracted in S53 into a support vector machine model for fault diagnosis, wherein the support vector machine model has been pre-trained with historical fault data and has established a classification boundary between a normal state and a fault state; S542: During the training process, use the historical fault data {(x1,y1),(x2,y2),...,(x n ,y n )}, where x i represents the frequency domain feature vector, y i represents the category label, and the training goal is to find an optimal classification hyperplane w·x+b=0 to separate the data points in normal state and fault state; S543: Determine the optimal classification hyperplane parameters w and b by solving the following optimization problem: Among them, ∥w∥ represents the norm of the weight vector; S544: The real-time frequency domain feature data x new Input into the trained support vector machine model for classification and calculate the classification function value f(x new ), the formula is: f(x new )=w·x new +b, according to the classification function value f(x new ) determines the failure mode. new )>0, it is judged as normal state; when f(x new )<0, it is judged as a fault state.

9. The hydraulic press automation control method based on PLC technology according to claim 1 is characterized in that: The S6 specifically includes: S61: uploading the potential failure mode data identified in S5, including timestamp, frequency domain characteristics, and failure type, to a cloud database via a high-speed network interface; S62: Storing the uploaded data in a cloud database; S63: Analyze the fault mode data stored in the cloud database using big data analysis technology, including data cleaning, data clustering and data statistical analysis; data cleaning removes noise and outliers; data clustering classifies fault modes by using the K-means clustering algorithm to identify fault types and modes; data statistical analysis calculates the frequency and time distribution of fault occurrence to provide statistical information on faults; S64: Based on the results of big data analysis, the fault prediction model is trained using deep learning technology. A multi-layer neural network model is constructed. The input data of the multi-layer neural network model is frequency domain features and historical fault mode data, and the output is the fault prediction result. The model training adopts the back propagation algorithm to optimize the loss function, iy S65: Deploy the trained fault prediction model to the cloud database, and receive data from the PLC controller in real time to perform fault prediction and diagnosis and generate a new control strategy. The new control strategy includes adjusting the operating parameters of the hydraulic press.

10. A hydraulic press automation control system based on PLC technology, used to implement a hydraulic press automation control method based on PLC technology as claimed in any one of claims 1 to 9, characterized in that: Includes the following modules: Multi-sensor module: installed at the predetermined position of the hydraulic press, used to collect data on pressure, displacement, temperature, vibration and sound waves in real time; and transmit the collected data to the PLC controller through a high-speed data bus; Data preprocessing module: integrated in the PLC controller, used to fuse and preprocess the received data and generate feature vectors; Control algorithm module: integrated in the PLC controller, using the preset adaptive fuzzy PID algorithm to analyze and calculate the characteristic vector and generate the hydraulic press control parameters; Execution module: including hydraulic valve group and servo drive components, receiving the control parameters generated by the PLC controller, adjusting the working state of the hydraulic press in real time to ensure the dynamic response of pressure, speed and position; Fault diagnosis module: integrated into the PLC controller, it analyzes the data generated during operation, identifies potential fault modes and issues early warning signals; Cloud database module: used to store fault mode data and conduct big data analysis and deep learning training to optimize control algorithms and generate new control strategies; Human-machine interface module: connected to the PLC controller, used to display the operating status and warning information of the hydraulic press in real time, and allow the operator to set parameters and switch modes according to the displayed information.

Citation Information

Patent Citations

  • Hydraulic machine energy-saving control system

    CN111070772A

  • Equipment vibration fault diagnosis method based on artificial intelligence

    CN118114186A

  • Temperature and humidity self-adaptive PID control system and method for textile printing and dyeing equipment

    CN118192204A

  • Machine tool based on artificial intelligence and fault detection method thereof

    CN118386024A

Cited By

  • Control system of powder pressing machine

    CN119927209A

  • Powder compaction press control system

    CN119927209B

  • Extruder equipment fault identification method and system based on artificial intelligence

    CN120541617A

  • Self-adaptive control method and system for hydraulically-driven guniting manipulator

    CN120630720A

  • An adaptive control method and system for a hydraulic drive guniting robot

    CN120630720B