Intelligent control system and method for production process of fuel filter of rotary installation machine oil

Abstract

The invention relates to the technical field of production of rotary installation filters, in particular to an intelligent control method for a production process of a rotary installation oil fuel filter, which comprises the following steps of: data acquisition: collecting a large amount of data during operation of an intelligent production line, including sensor readings, actuator states and control signals for establishing a system model and performing subsequent fault diagnosis; the advanced sensing technology and the PID control algorithm technology are introduced, fine management and collaborative optimization of a production line are achieved through a self-adaptive control algorithm, real-time monitoring of key parameters in the production process is achieved, machining parameters are automatically adjusted and corrected through the PID control algorithm, precision control over all key machining procedures is guaranteed, and the production efficiency is improved. The production process is controlled according to the real-time production state and parameter analysis, integrated production is achieved, the purposes of optimizing the production process, improving the product quality and improving the production efficiency are achieved, and meanwhile the functions of equipment fault detection and preventive maintenance are achieved.

Description

Technical Field

[0001] The invention relates to the technical field of spin-on filter production, and in particular to an intelligent control system and method for a spin-on oil and fuel filter production process. Background Art

[0002] A filter is an accessory that filters impurities or gases through filter paper, generally referring to a gasoline filter. It is an engine accessory and is divided into oil filters, fuel filters (gasoline filters, diesel filters, oil-water separators, hydraulic filters), air filters, air conditioning filters, etc. according to different filtering functions. The engine has three filters: air, oil, and fuel, generally referred to as "three filters". Together with the air conditioning filter, it is commonly known as "four filters", which are responsible for filtering the lubrication system, the medium in the combustion system, the engine intake system, and the cabin air circulation system. With the development of science and technology, people's demand for motor vehicles is increasing, and the demand for filters is also increasing.

[0003] For example, the Chinese patent CN110842536A, "Fully automatic assembly production method and production system for spin-on oil and fuel filter assemblies", includes: conveying, testing and assembling the various components of the filter; sealing the assembled filter; thread testing the filter after sealing; silk-screening the filter after thread testing; and air tightness testing the filter after silk-screen printing.

[0004] During the production of existing spin-on oil and fuel filters, the integrated production of filters is usually achieved through various equipment. However, abnormal equipment parameters may occur during the production process, and the existing production process control system is unable to monitor the key parameters of the production process in real time, and is unable to automatically adjust and correct the processing parameters when the parameters are abnormal, thereby failing to ensure the precision control of each key processing step (such as stamping, canning, testing, surface treatment, etc.). At the same time, it is unable to perform preventive protection and fault detection on the equipment in the production process, resulting in an unstable production process of the filter, and failing to ensure the human-machine safety and stable operation of the system during the production process.

[0005] In view of this, the present application proposes an intelligent control system and method for the production process of a spin-on oil and fuel filter. Summary of the invention

[0006] The object of the present invention is to provide an intelligent control system and method for the production process of a spin-on oil and fuel filter to solve the above-mentioned problems.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] An intelligent control method for a production process of a spin-on oil and fuel filter, comprising:

[0009] Ⅰ. Data collection: Collect a large amount of data during the operation of the intelligent production line, including sensor readings, actuator status, and control signals, for building system models and subsequent fault diagnosis;

[0010] II. System Identification: Based on the collected data, use system identification techniques to estimate the dynamic behavior and parameters of the system, including determining the transfer functions, state space representations, and other model parameters of sensors and actuators;

[0011] III. System modeling: Based on the collected data, use the system dynamics or state space modeling method to model the intelligent production line, including defining the various components of the system, sensors, actuators and control logic, and the relationship between them;

[0012] IV. Establish normal state model and anomaly detection: Based on the results of system identification, establish a normal operation model of the system, which is used as a benchmark for subsequent intelligent judgment and control. Monitor real-time data to detect anomalies. By comparing with the normal operation model, situations that are inconsistent with expected behavior can be identified;

[0013] V. Sensor detection: Various status information of the production line is detected through a variety of sensors, key parameters and equipment status of the production process are monitored in real time, parameters involved in the production process are collected in real time, and the detection data is transmitted to the PLC controller;

[0014] Ⅵ. PLC control: The PLC controller receives sensor data, processes control logic and performs parameter analysis and comparison. When the equipment data is abnormal, an alarm is issued, and the processing parameters are automatically adjusted and corrected through the PID control algorithm, and then the control signal is output to various actuators;

[0015] Ⅶ. Execution: According to the control signal of PLC, the corresponding action is performed through the actuator;

[0016] VIII. Human-machine interaction: The interaction between the operator and the PLC is realized through the human-machine interface, which displays the operating status, parameter settings and fault information of the production line.

[0017] Furthermore, in the system modeling stage, the state space model is used to represent the dynamic behavior of the system, which includes the relationship between the state vector x, the input vector u and the output vector y, as shown below:

[0018]

[0019] y=Cx+Du

[0020] Where: represents the derivative of the state vector, A, B, C, D represent the state space matrices of the system, and A, B, C, D can be estimated by the system identification method.

[0021] Furthermore, in the anomaly detection stage, a statistical method is used to calculate the anomaly degree or residual to detect whether there is an abnormality. The anomaly degree calculation formula is as follows:

[0022]

[0023] Where: y 实际 represents the actual observed output, y 预测 Represents the output predicted based on the system model, and the standard deviation is used to determine the threshold of abnormality.

[0024] Furthermore, the processing parameters are automatically adjusted and corrected by a PID control algorithm, and the basic formula of the PID control algorithm is as follows:

[0025]

[0026] Where: u(t) represents the output control quantity of the system at time t, e(t) represents the error of the system at time t, that is, the difference between the expected value and the actual value, K p Represents the proportional coefficient, controls the influence of the proportional part, and is used to adjust the stability and sensitivity of the system. K i Indicates the integral coefficient, controls the influence of the integral part, and is used to eliminate the steady-state error of the system. K d It represents the differential coefficient, controls the influence of the differential part, and is used to suppress the oscillation of the system and improve the response speed of the system. e(Λ)dΛ represents the integral of the error e(t) over time, and is used to process the steady-state error of the system. It represents the derivative of the error e(t) with time and is used to handle instantaneous changes in the system.

[0027] An intelligent control system for the production process of a spin-on oil and fuel filter, comprising a sensor unit, a PLC control unit, a communication unit, an execution unit, a protection unit, an auxiliary unit, an equipment management unit and a human-computer interaction unit;

[0028] The sensor unit detects various status information of the production line through a variety of sensors, monitors key parameters and operating data in the production process in real time, and transmits the detection data to the PLC control unit;

[0029] The PLC control unit receives data from the sensor unit through the PLC controller, processes the control logic and performs parameter analysis and comparison, automatically adjusts and corrects the processing parameters through the PID control algorithm, and then outputs the control signal to the execution unit;

[0030] The communication unit realizes the communication function between the modules of the production line system through industrial Ethernet;

[0031] The execution unit receives the control signal of the PLC control unit and executes the corresponding action through the actuator;

[0032] The protection unit provides safety protection for production line equipment through position detection switches, area protection photoelectric protection devices, and laser scanners;

[0033] The auxiliary unit plays a role of auxiliary safety protection by providing a stop button, an emergency stop button, a reset button, an indicator light and an audible and visual alarm;

[0034] The equipment management unit uploads the equipment status information to the equipment management system through the data management network, supports setting the permission security lock for the human-machine interaction system, and remote viewing and operation functions by setting up video monitoring in the relevant areas of the relevant equipment on the production line;

[0035] The human-machine interaction unit realizes the interaction between the operator and the PLC, displays the operating status, parameter settings and fault information of the production line, and the operator can set parameters at the same time.

[0036] Furthermore, the sensor unit includes an equipment parameter monitoring module, a hydraulic overload protection module, a canning monitoring module and a temperature monitoring module;

[0037] The equipment parameter monitoring module collects key parameters and operating data involved in the production process in real time through sensors, and transmits the parameters and operating data to the PLC control unit;

[0038] The hydraulic overload protection module is used to monitor the pressure points of the multi-station press and transmit the monitoring data to the PLC control unit;

[0039] The can sealing monitoring module performs in-depth monitoring of the can sealing process, calculates the can sealing bite rate through an intelligent algorithm, and transmits the can sealing bite rate signal to the PLC control unit in real time;

[0040] The temperature monitoring module sets temperature detection probes at important positions of multiple processes in the production line and transmits temperature signals to the PLC control unit in real time.

[0041] Furthermore, the PLC control unit includes a data preprocessing module, an adaptive comparison module, an automatic adjustment module, a feature extraction module, a fault prediction module, a fault judgment module, a model correction module and a reporting module:

[0042] The data preprocessing module collects the operation data of the equipment, including sensor data, temperature data, and pressure data, and performs cleaning, denoising, and standardization preprocessing operations on the data to obtain preprocessed data;

[0043] The adaptive comparison module receives data from the sensor unit through the PLC controller, processes the control logic and performs parameter analysis and comparison, and transmits the signal to the automatic adjustment module when the parameter is abnormal;

[0044] The automatic adjustment module automatically adjusts and corrects the processing parameters through the PID control algorithm, and outputs a control signal to the execution unit;

[0045] The feature extraction module uses a deep learning model to automatically learn the hierarchical feature representation of data and extracts features from the preprocessed data;

[0046] The fault prediction module uses a deep learning model to monitor the operating status of the equipment in real time based on the extracted feature representation, and the model discovers abnormal patterns and trends in the operation of the equipment by learning historical data to obtain fault prediction data;

[0047] The fault judgment module is based on the fault prediction data, using the fault diagnosis algorithm to compare with the known fault model, and based on the data-driven method to determine the possible fault type, cause, degree and location;

[0048] The model correction module uses the least square method to correct the system model according to the diagnosis results, and the formula for estimating the parameter θ is as follows:

[0049]

[0050] Where: y 模型 is the model predicted output based on the estimated parameters θ;

[0051] The reporting module generates a fault diagnosis report and maintenance suggestions based on the system fault, and transmits the information to the human-computer interaction unit.

[0052] Furthermore, the protection unit includes a position detection module, a workbench movement protection module, a laser scanning module, a radio frequency identification module and a preventive protection module:

[0053] The position detection module sets a position detection switch at the moving parts of the production line, and detects the open and closed state according to the program setting. When the position detection module sends a safety signal, other parts can move;

[0054] The workbench movement protection module is provided with an area protection photoelectric protection device using invisible infrared light to radiate around the moving area of ​​the workbench in front and behind the host, so as to sense whether a human body enters the danger zone, and will immediately stop the machine once triggered;

[0055] The laser scanning module sets up a laser scanner around the running parts of the equipment, sets up danger and warning areas according to the danger level, and transmits the abnormal alarm signal to the auxiliary unit and the human-machine interaction unit when a person approaches or enters;

[0056] The radio frequency identification module uses radio frequency identification RFID technology to manage the in-place mold information of the production line, read the in-place mold data and determine whether the in-place mold meets the system setting requirements;

[0057] The preventive protection module monitors the equipment status at all times during the production process, responds in time before damage occurs, and takes preventive protection measures.

[0058] Furthermore, the preventive protection module includes an uninterrupted buffer module, a motor operation status monitoring module and an unbalanced load prevention module:

[0059] The uninterruptible buffer module uses DC UPS+ buffer technology to provide short-term DC power supply buffering after the power grid outside the production line is cut off. It can continuously provide DC24 for a maximum of 11 hours and transmit signals to the human-computer interaction unit;

[0060] The motor operation status monitoring module is used to monitor the motor temperature, motor output shaft vibration, and working current of the production line, and transmit the warning signal to the auxiliary unit and the human-machine interaction unit when the warning value is reached;

[0061] The off-center load prevention module uses the permissible eccentric load capacity curve of the multi-station press to predict in advance the off-center load force generated during stamping processing of different molds on the production line.

[0062] Furthermore, the auxiliary unit includes a stop module, an emergency stop module, a reset module, an indicator light module and an alarm module:

[0063] The stop module is interlocked with the host by setting a stop button. When the operator presses the stop button, the stop module issues a stop operation instruction. After completing the current cycle, all mechanisms return to the initial state and the system stops.

[0064] The emergency stop module is provided with multiple emergency stop buttons at multiple workstations and interlocked with the host. When the operator presses the emergency stop button in any dangerous situation, the emergency stop module controls the equipment to stop immediately.

[0065] The reset module is provided with multiple reset buttons at multiple positions and interlocked with the host. When the operator releases the emergency stop button and presses the reset button, all mechanical mechanisms return to the initial state.

[0066] The indicator light module is provided by setting an indicator light next to the production line equipment. When the system is not working, the red light is always on, and when the system is running, the green light is always on;

[0067] The alarm module is used to receive different abnormal alarm signals and early warning signals, and control different sound and light alarms to emit sound and light alarm prompts.

[0068] Beneficial effects of the present invention:

[0069] 1. In the present invention, by introducing advanced sensing technology and PID control algorithm technology, the performance of the system in normal operation is improved through an adaptive control algorithm. By introducing intelligent monitoring, data analysis and multi-objective optimization models, fine management and coordinated optimization of the production line are achieved, and real-time monitoring of key parameters in the production process is achieved. Parameters involved in the production process are collected in real time, system comparison, data abnormality alarms, and automatic adjustment and correction of processing parameters through the PID control algorithm are achieved, thereby ensuring the precision control of each key processing step and the stability of the production process. The production process is controlled according to the real-time production status and parameter analysis, and integrated production is achieved, so as to achieve the purpose of optimizing the production process, improving product quality and improving production efficiency.

[0070] 2. In the present invention, the equipment parameter monitoring module collects key parameters and operation data involved in the production process in real time through sensors, and then preprocesses, extracts features and predicts faults of the equipment operation data. The fault judgment module is based on the fault prediction data and compares the fault diagnosis algorithm with the known fault model, as well as a data-driven method to determine the possible fault type, cause, degree and location, which helps to quickly locate the fault and take corresponding maintenance measures, reduce the time and cost of production interruptions, improve the efficiency, quality and flexibility of the production line, reduce costs and failure rates, provide operators with a safer and more convenient working environment, and achieve a higher level of automated control.

[0071] 3. In the present invention, the protection unit provides safety protection for the production line equipment through position detection switches, area protection photoelectric protection devices, and laser scanners. The functional components are combined with control programs to ensure the safety of the production line equipment. By monitoring the equipment status during the production process, preventive maintenance measures are designed in advance to avoid damage, ensure the reliability and stability of the system, and effectively ensure the goals of human-machine safety, efficient production, and improved automation and intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1This is a system principle diagram of an intelligent control system and method for a production process of a spin-on oil and fuel filter according to the present invention;

[0073] Figure 2 The present invention discloses a PID control algorithm schematic diagram of an intelligent control system and method for a production process of a spin-on oil and fuel filter.

[0074] In the figure: 1. sensor unit; 2. PLC control unit; 3. communication unit; 4. execution unit; 5. protection unit; 6. auxiliary unit; 7. equipment management unit; 8. human-computer interaction unit; 11. equipment parameter monitoring module; 12. hydraulic overload protection module; 13. can sealing monitoring module; 14. temperature monitoring module; 21. data preprocessing module; 22. adaptive comparison module; 23. automatic adjustment module; 24. feature extraction module; 25. fault prediction module; 26. fault judgment module; 27. model correction module; 28. report module; 51. position detection module; 52. workbench movement protection module; 53. laser scanning module; 54. radio frequency identification module; 55. preventive protection module; 551. uninterrupted buffer module; 552. motor operation status monitoring module; 553. overload prevention module; 61. stop module; 62. emergency stop module; 63. reset module; 64. indicator light module; 65. alarm module. DETAILED DESCRIPTION

[0075] 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.

[0076] Example 1: Please refer to Figure 1 and Figure 2 This design proposes an implementation method, an intelligent control method for the production process of a spin-on oil and fuel filter, including:

[0077] Ⅰ. Data collection: Collect a large amount of data during the operation of the intelligent production line, including sensor readings, actuator status, and control signals, for building system models and subsequent fault diagnosis;

[0078] II. System Identification: Based on the collected data, use system identification techniques to estimate the dynamic behavior and parameters of the system, including determining the transfer functions, state space representations, and other model parameters of sensors and actuators;

[0079] III. System modeling: Based on the collected data, use the system dynamics or state space modeling method to model the intelligent production line, including defining the various components of the system, sensors, actuators and control logic, and the relationship between them;

[0080] In the system modeling stage, the state space model is used to represent the dynamic behavior of the system, which includes the relationship between the state vector x, the input vector u and the output vector y, as shown below:

[0081]

[0082] y=Cx+Du

[0083] Where: represents the derivative of the state vector, A, B, C, D represent the state space matrix of the system, A, B, C, D can be estimated by the system identification method;

[0084] IV. Establish normal state model and anomaly detection: Based on the results of system identification, establish a normal operation model of the system, which is used as a benchmark for subsequent intelligent judgment and control. Monitor real-time data to detect anomalies. By comparing with the normal operation model, situations that are inconsistent with expected behavior can be identified;

[0085] In the anomaly detection stage, statistical methods are used to calculate the anomaly degree or residual to detect whether there is an anomaly. The anomaly degree calculation formula is as follows:

[0086]

[0087] Where: y 实际 represents the actual observed output, y 预测 Represents the output predicted based on the system model, and the standard deviation is used to determine the threshold of abnormality;

[0088] V. Sensor detection: Various status information of the production line is detected through a variety of sensors, key parameters and equipment status of the production process are monitored in real time, parameters involved in the production process are collected in real time, and the detection data is transmitted to the PLC controller;

[0089] Ⅵ. PLC control: The PLC controller receives sensor data, processes control logic and performs parameter analysis and comparison. When the equipment data is abnormal, an alarm is issued, and the processing parameters are automatically adjusted and corrected through the PID control algorithm, and then the control signal is output to various actuators;

[0090] The processing parameters are automatically adjusted and corrected through the PID control algorithm. The basic formula of the PID control algorithm is as follows:

[0091]

[0092] Where: u(t) represents the output control quantity of the system at time t, e(t) represents the error of the system at time t, that is, the difference between the expected value and the actual value, K p Represents the proportional coefficient, controls the influence of the proportional part, and is used to adjust the stability and sensitivity of the system. K i Indicates the integral coefficient, controls the influence of the integral part, and is used to eliminate the steady-state error of the system. K d It represents the differential coefficient, controls the influence of the differential part, and is used to suppress the oscillation of the system and improve the response speed of the system. e(Λ)dΛ represents the integral of the error e(t) over time, and is used to process the steady-state error of the system. Represents the derivative of the error e(t) with time, which is used to deal with instantaneous changes in the system;

[0093] Ⅶ. Execution: According to the control signal of PLC, the corresponding action is performed through the actuator;

[0094] VIII. Human-machine interaction: The interaction between the operator and the PLC is realized through the human-machine interface, which displays the operating status, parameter settings and fault information of the production line.

[0095] In this embodiment, by introducing advanced sensing technology and PID control algorithm technology (PID control algorithm, by processing the proportion, integration and differentiation of the error between the system output and the expected value, adjusting the output of the controller to achieve precise control of the system, this feedback-based control mechanism can adjust the control strategy in real time when the production environment changes, thereby ensuring that the system always remains in a stable working state), the performance of the system during normal operation is improved through an adaptive control algorithm, and through the introduction of intelligent monitoring, data analysis and multi-objective optimization models, fine management and collaborative optimization of the production line are achieved, and real-time monitoring of key parameters in the production process is achieved. Parameters involved in the production process are collected in real time, system comparison, data abnormality alarm, and automatic adjustment and correction of processing parameters through the PID control algorithm, thereby ensuring the precision control of each key processing step and the stability of the production process, and controlling the production process according to the real-time production status and parameter analysis to achieve integrated production, so as to achieve the purpose of optimizing the production process, improving product quality and improving production efficiency.

[0096] Example 2: Please refer to Figure 1 and Figure 2 , This design proposes an implementation method, an intelligent control system for the production process of a spin-on oil and fuel filter, including a sensor unit 1, a PLC control unit 2, a communication unit 3, an execution unit 4, a protection unit 5, an auxiliary unit 6, a device management unit 7 and a human-computer interaction unit 8;

[0097] The sensor unit 1 detects various status information of the production line through a variety of sensors, monitors the key parameters and operating data in the production process in real time, and transmits the detection data to the PLC control unit 2; the sensor unit 1 includes an equipment parameter monitoring module 11, a hydraulic overload protection module 12, a canning monitoring module 13 and a temperature monitoring module 14; the equipment parameter monitoring module 11 collects the key parameters and operating data involved in the production process in real time through sensors, and transmits the parameters and operating data to the PLC control unit 2; the hydraulic overload protection module 12 is used to monitor the pressure points of the multi-station press, and transmits the monitoring data to the PLC control unit 2; the canning monitoring module 13 performs in-depth monitoring of the canning process, calculates the canning bite rate through an intelligent algorithm, and transmits the canning bite rate signal to the PLC control unit 2 in real time; the temperature monitoring module 14 sets temperature detection probes at important positions of multiple processes in the production line, and transmits the temperature signal to the PLC control unit 2 in real time;

[0098] The PLC control unit 2 receives the data of the sensor unit 1 through the PLC controller, processes the control logic and performs parameter analysis and comparison, automatically adjusts and corrects the processing parameters through the PID control algorithm, and then outputs the control signal to the execution unit 4; the PLC control unit 2 includes a data preprocessing module 21, an adaptive comparison module 22, an automatic adjustment module 23, a feature extraction module 24, a fault prediction module 25, a fault judgment module 26, a model correction module 27 and a report module 28: the data preprocessing module 21 collects the operation data of the equipment, including sensor data, temperature data, and pressure data, and performs preprocessing operations such as cleaning, denoising and standardization on the data to obtain preprocessed data; the adaptive comparison module 22 receives the data of the sensor unit 1 through the PLC controller, processes the control logic and performs parameter analysis and comparison. When the parameters are abnormal, the signal is transmitted to the automatic The automatic adjustment module 23 automatically adjusts and corrects the processing parameters through the PID control algorithm, and outputs the control signal to the execution unit 4; the feature extraction module 24 uses the deep learning model to automatically learn the hierarchical feature representation of the data, and extracts the features of the pre-processed data; the fault prediction module 25 uses the deep learning model to monitor the operating status of the equipment in real time based on the extracted feature representation, and the model discovers the abnormal patterns and trends in the operation of the equipment through learning historical data, and obtains fault prediction data; the fault judgment module 26 uses the fault diagnosis algorithm to compare with the known fault model based on the fault prediction data, and implements it based on the data-driven method to determine the possible fault type, cause, degree and location; the model correction module 27 uses the least squares method to correct the system model according to the diagnosis result, and estimates the parameter θ formula: Where: y 模型is the model prediction output based on the estimated parameter θ; the reporting module 28 generates a fault diagnosis report and maintenance suggestions based on the system fault, and transmits the information to the human-computer interaction unit 8;

[0099] The communication unit 3 realizes the communication function between the modules of the production line system through industrial Ethernet;

[0100] The execution unit 4 receives the control signal of the PLC control unit 2 and executes the corresponding action through the actuator;

[0101] The protection unit 5 provides safety protection for the production line equipment through position detection switches, area protection photoelectric protection devices, and laser scanners; the protection unit 5 includes a position detection module 51, a workbench movement protection module 52, a laser scanning module 53, a radio frequency identification module 54, and a preventive protection module 55: the position detection module 51 sets a position detection switch at the moving parts of the production line, and detects the open and closed state according to the program setting. When the position detection module 51 sends a safety signal, other parts can move; the workbench movement protection module 52 sets an area protection photoelectric protection device that uses invisible infrared light to emit around the moving area of ​​the workbench in front and behind the main machine, which senses whether the human body enters the danger zone. Once triggered, it will stop immediately to avoid other people accidentally entering the working area of ​​the visual blind spot during the automatic mold changing process of the workbench. The laser scanning module 53 sets a laser scanner around the running parts of the equipment, sets the danger and warning areas according to the danger level, and transmits the abnormal alarm signal to the auxiliary unit 6 and the human-machine interaction unit 8 when a person approaches or enters; the radio frequency identification module 54 uses radio frequency identification RFID technology to manage the in-place mold information of the production line, reads the in-place mold data and determines whether the in-place mold meets the system setting requirements; the preventive protection module 55 monitors the equipment status at all times during the production process, responds in time before damage occurs, and takes preventive protection measures; the preventive protection module 55 includes an uninterrupted buffer module 551, a motor operation status monitoring module 552 and an overload prevention module 553: the uninterrupted buffer module 551 uses DC UPS+ buffer technology provides short-term DC power supply buffering after the power outage of the power grid outside the production line. It can continuously provide DC24 for a maximum duration of 11 hours, and transmit the signal to the human-machine interaction unit 8; the motor operation status monitoring module 552 is used to monitor the motor temperature, motor output shaft vibration, and working current of the production line, and transmit the warning signal to the auxiliary unit 6 and the human-machine interaction unit 8 when the warning value is reached; the eccentric load prevention module 553 uses the permissible eccentric load capacity curve of the multi-station press to predict the eccentric load force generated during the stamping processing of different molds on the production line in advance;

[0102] The auxiliary unit 6 plays an auxiliary safety protection role by setting a stop button, an emergency stop button, a reset button, an indicator light and an audible and visual alarm; the auxiliary unit 6 includes a stop module 61, an emergency stop module 62, a reset module 63, an indicator light module 64 and an alarm module 65; the stop module 61 is provided with a stop button and interlocked with the host. When the operator presses the stop button, the stop module 61 issues a stop operation instruction. After completing the current cycle, all mechanisms return to the initial state and the system shuts down; the emergency stop module 62 is provided with multiple emergency stop buttons at multiple workstations and interlocked with the host. When the operator presses the emergency stop button in any dangerous situation, the emergency stop module 62 controls the equipment to stop immediately; the reset module 63 sets multiple reset buttons at multiple positions and interlocks with the host. When the operator releases the emergency stop button and presses the reset button, all mechanical mechanisms return to the initial state; the indicator light module 64 sets an indicator light next to the production line equipment. When the system is not working, the red light is always on, and when the system is running, the green light is always on; the alarm module 65 is used to receive different abnormal alarm signals and early warning signals, and control different sound and light alarms to send out sound and light alarm prompts;

[0103] The equipment management unit 7 uploads the equipment status information to the equipment management system through the data management network, supports setting the permission security lock for the human-machine interaction system, and remotely views and operates the functions by setting up video monitoring in the relevant areas of the relevant equipment of the production line;

[0104] The human-machine interaction unit 8 realizes the interaction between the operator and the PLC, displays the operating status, parameter settings and fault information of the production line, and the operator can set parameters at the same time.

[0105] In the present invention, the production process control system of the engine oil and fuel filter of the brigade first collects a large amount of data during the operation of the intelligent production line, including sensor readings, actuator states, and control signals, for establishing a system model and subsequent fault diagnosis; based on the collected data, the system identification technology is used to estimate the dynamic behavior and parameters of the system, including determining the transfer function, state space representation and other model parameters of the sensor and actuator; based on the collected data, the system dynamics or state space modeling method is used to perform system modeling of the intelligent production line, including defining the various components of the system, sensors, actuators and control logic, and the relationship between them; normal state model and abnormality detection are established: based on the results of system identification, a normal operation model of the system is established, which is used as a benchmark for subsequent intelligent judgment and control, and real-time data is monitored to detect abnormalities. By comparing with the normal operation model, situations inconsistent with expected behavior can be identified;

[0106] The sensor unit 1 detects various status information of the production line through a variety of sensors, monitors the key parameters and operating data in the production process in real time, and transmits the detection data to the PLC control unit 2; the PLC control unit 2 receives the data of the sensor unit 1 through the PLC controller, processes the control logic and performs parameter analysis and comparison, automatically adjusts and corrects the processing parameters through the PID control algorithm, and then outputs the control signal to the execution unit 4 (the adaptive comparison module 22 receives the data of the sensor unit 1 through the PLC controller, processes the control logic and performs parameter analysis and comparison, and when the parameters are abnormal, transmits the signal to the automatic adjustment module 23; the automatic adjustment module 23 automatically adjusts and corrects the processing parameters through the PID control algorithm, and outputs the control signal to the execution unit 4); the execution unit 4 receives the data of the PLC control The control signal of control unit 2 can be used to execute the corresponding action through the actuator; by introducing advanced sensing technology and PID control algorithm technology, the performance of the system in normal operation is improved through adaptive control algorithm. Through the introduction of intelligent monitoring, data analysis and multi-objective optimization model, the fine management and coordinated optimization of the production line are realized, and the key parameters in the production process are monitored in real time, the parameters involved in the production process are collected in real time, the system is compared, the data is abnormal, and the processing parameters are automatically adjusted and corrected through the PID control algorithm, so as to ensure the precision control of each key processing step and the stability of the production process. The production process is controlled according to the real-time production status and parameter analysis, and integrated production is realized to achieve the purpose of optimizing the production process, improving product quality and improving production efficiency;

[0107] At the same time, the data preprocessing module 21 collects the operation data of the equipment and performs preprocessing operations on the data. The feature extraction module 24 uses the deep learning model to automatically learn the hierarchical feature representation of the data and extracts features from the preprocessed data. The fault prediction module 25 uses the deep learning model to monitor the operation status of the equipment in real time based on the extracted feature representation. The model discovers abnormal patterns and trends in the operation process of the equipment by learning historical data, extracts information useful for equipment status monitoring and fault prediction, and obtains fault prediction data. The fault judgment module 26 uses the fault diagnosis algorithm to compare with the known fault model based on the fault prediction data, and implements it based on the data-driven method to determine the possible fault type, cause, degree and location, which helps to quickly locate the fault and take corresponding maintenance measures. The model correction module 27 uses the least square method to correct the system model according to the diagnosis results; the equipment parameter monitoring module 11 collects the key parameters and operation data involved in the production process in real time through sensors, and then pre-processes, extracts features and predicts faults for the equipment operation data. The fault judgment module 26 then uses the fault diagnosis algorithm to compare with the known fault model based on the fault prediction data, and implements it based on the data-driven method to determine the possible fault type, cause, degree and location, which helps to quickly locate the fault and take corresponding maintenance measures, reduce the time and cost of production interruption, improve the efficiency, quality and flexibility of the production line, reduce costs and failure rates, provide operators with a safer and more convenient working environment, and achieve a higher level of automated control;

[0108] In addition, the protection unit 5 provides safety protection for the production line equipment through position detection switches, area protection photoelectric protection devices, and laser scanners. It uses functional components combined with control programs to ensure the safety of production line equipment. By monitoring the equipment status during the production process, preventive maintenance measures are designed in advance to avoid damage, ensure the reliability and stability of the system, and effectively ensure the goals of human-machine safety, efficient production, and improved automation and intelligence.

[0109] 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. An intelligent control method for the production process of a spin-on oil and fuel filter, characterized in that: include: Ⅰ. Data collection: Collect a large amount of data during the operation of the intelligent production line, including sensor readings, actuator status, and control signals, for building system models and subsequent fault diagnosis; II. System Identification: Based on the collected data, use system identification techniques to estimate the dynamic behavior and parameters of the system, including determining the transfer functions, state space representations, and other model parameters of sensors and actuators; III. System modeling: Based on the collected data, use the system dynamics or state space modeling method to model the intelligent production line, including defining the various components of the system, sensors, actuators and control logic, and the relationship between them; IV. Establish normal state model and anomaly detection: Based on the results of system identification, establish a normal operation model of the system, which is used as a benchmark for subsequent intelligent judgment and control. Monitor real-time data to detect anomalies. By comparing with the normal operation model, situations that are inconsistent with expected behavior can be identified; V. Sensor detection: Various status information of the production line is detected through a variety of sensors, key parameters and equipment status of the production process are monitored in real time, parameters involved in the production process are collected in real time, and the detection data is transmitted to the PLC controller; Ⅵ. PLC control: The PLC controller receives sensor data, processes control logic and performs parameter analysis and comparison. When the equipment data is abnormal, an alarm is issued, and the processing parameters are automatically adjusted and corrected through the PID control algorithm, and then the control signal is output to various actuators; Ⅶ. Execution: According to the control signal of PLC, the corresponding action is performed through the actuator; VIII. Human-machine interaction: The interaction between the operator and the PLC is realized through the human-machine interface, which displays the operating status, parameter settings and fault information of the production line.

2. The intelligent control method for the production process of a spin-on oil and fuel filter according to claim 1, characterized in that: In the system modeling stage, the state space model is used to represent the dynamic behavior of the system, which includes the relationship between the state vector x, the input vector u and the output vector y, as shown below: y=Cx+Du Where: represents the derivative of the state vector, A, B, C, D represent the state space matrices of the system, and A, B, C, D can be estimated by the system identification method.

3. The intelligent control method for the production process of a spin-on oil and fuel filter according to claim 2 is characterized in that: In the anomaly detection stage, statistical methods are used to calculate the anomaly degree or residual to detect whether there is an anomaly. The anomaly degree calculation formula is as follows: Where: y 实际 represents the actual observed output, y 预测 Represents the output predicted based on the system model, and the standard deviation is used to determine the threshold of abnormality.

4. The intelligent control method for the production process of a spin-on oil and fuel filter according to claim 3 is characterized in that: The processing parameters are automatically adjusted and corrected by the PID control algorithm. The basic formula of the PID control algorithm is as follows: Where: u(t) represents the output control quantity of the system at time t, e(t) represents the error of the system at time t, that is, the difference between the expected value and the actual value, K p Represents the proportional coefficient, controls the influence of the proportional part, and is used to adjust the stability and sensitivity of the system. K i Indicates the integral coefficient, controls the influence of the integral part, and is used to eliminate the steady-state error of the system. K d It represents the differential coefficient, controls the influence of the differential part, and is used to suppress the oscillation of the system and improve the response speed of the system. e(Λ)dΛ represents the integral of the error e(t) over time, and is used to process the steady-state error of the system. It represents the derivative of the error e(t) with time and is used to handle instantaneous changes in the system.

5. An intelligent control system for the production process of a spin-on oil and fuel filter, applicable to the intelligent control method for the production process of a spin-on oil and fuel filter according to any one of claims 1 to 4, characterized in that: It comprises a sensor unit (1), a PLC control unit (2), a communication unit (3), an execution unit (4), a protection unit (5), an auxiliary unit (6), a device management unit (7) and a human-machine interaction unit (8); The sensor unit (1) detects various status information of the production line through a variety of sensors, monitors key parameters and operating data in the production process in real time, and transmits the detection data to the PLC control unit (2); The PLC control unit (2) receives data from the sensor unit (1) through the PLC controller, processes the control logic and performs parameter analysis and comparison, automatically adjusts and corrects the processing parameters through the PID control algorithm, and then outputs a control signal to the execution unit (4); The communication unit (3) realizes the communication function between the modules of the production line system through industrial Ethernet; The execution unit (4) receives the control signal from the PLC control unit (2) and executes the corresponding action through the actuator; The protection unit (5) provides safety protection for production line equipment through position detection switches, area protection photoelectric protection devices, and laser scanners; The auxiliary unit (6) plays a role of auxiliary safety protection by providing a stop button, an emergency stop button, a reset button, an indicator light and an audible and visual alarm; The equipment management unit (7) uploads the equipment status information to the equipment management system via the data management network, supports setting a permission security lock for the human-machine interaction system, and remotely views and operates the functions by setting up video monitoring in the relevant areas of the production line related equipment; The human-machine interaction unit (8) realizes the interaction between the operator and the PLC, displays the operating status, parameter settings and fault information of the production line, and the operator can set parameters at the same time.

6. The intelligent control system for the production process of a spin-on oil and fuel filter according to claim 5, characterized in that: The sensor unit (1) comprises an equipment parameter monitoring module (11), a hydraulic overload protection module (12), a canning monitoring module (13) and a temperature monitoring module (14); The equipment parameter monitoring module (11) collects key parameters and operating data involved in the production process in real time through sensors, and transmits the parameters and operating data to the PLC control unit (2); The hydraulic overload protection module (12) is used to monitor the pressure points of the multi-station press and transmit the monitoring data to the PLC control unit (2); The can sealing monitoring module (13) performs in-depth monitoring during the can sealing process, calculates the can sealing bite rate through an intelligent algorithm, and transmits the can sealing bite rate signal to the PLC control unit (2) in real time; The temperature monitoring module (14) is configured by arranging temperature detection probes at important positions of multiple processes in the production line, and transmits temperature signals to the PLC control unit (2) in real time.

7. The intelligent control system for the production process of a spin-on oil and fuel filter according to claim 5, characterized in that: The PLC control unit (2) comprises a data preprocessing module (21), an adaptive comparison module (22), an automatic adjustment module (23), a feature extraction module (24), a fault prediction module (25), a fault judgment module (26), a model correction module (27) and a reporting module (28): The data preprocessing module (21) collects the operation data of the equipment, including sensor data, temperature data, and pressure data, and performs cleaning, denoising, and standardization preprocessing operations on the data to obtain preprocessed data; The adaptive comparison module (22) receives data from the sensor unit (1) through the PLC controller, processes the control logic and performs parameter analysis and comparison, and when a parameter is abnormal, transmits the signal to the automatic adjustment module (23); The automatic adjustment module (23) automatically adjusts and corrects the processing parameters through a PID control algorithm, and outputs a control signal to the execution unit (4); The feature extraction module (24) uses a deep learning model to automatically learn the hierarchical feature representation of data and extracts features from the preprocessed data; The fault prediction module (25) uses a deep learning model to monitor the operating status of the equipment in real time based on the extracted feature representation, and the model discovers abnormal patterns and trends in the operation of the equipment by learning historical data to obtain fault prediction data; The fault judgment module (26) determines the possible fault type, cause, degree and location based on the fault prediction data, by comparing the fault diagnosis algorithm with the known fault model and implementing it based on a data-driven method; The model correction module (27) corrects the system model using the least square method according to the diagnosis result, and the formula for estimating the parameter θ is as follows: Where: y 模型 is the model predicted output based on the estimated parameters θ; The reporting module (28) generates a fault diagnosis report and maintenance suggestions based on the system fault, and transmits the information to the human-computer interaction unit (8).

8. The intelligent control system for the production process of a spin-on oil and fuel filter according to claim 5, characterized in that: The protection unit (5) comprises a position detection module (51), a workbench movement protection module (52), a laser scanning module (53), a radio frequency identification module (54) and a preventive protection module (55): The position detection module (51) is provided with a position detection switch at the moving parts of the production line, and detects the open and closed state according to the program setting. When the position detection module (51) sends a safety signal, other parts can move; The workbench movement protection module (52) is provided with a regional protection photoelectric protection device using invisible infrared light to radiate around the moving area of ​​the workbench in front and behind the main machine, so as to sense whether a human body enters a danger zone, and will immediately stop the machine once triggered; The laser scanning module (53) sets a laser scanner around the operating parts of the equipment, sets danger and warning areas according to the danger level, and transmits the abnormal alarm signal to the auxiliary unit (6) and the human-machine interaction unit (8) when a person approaches or enters; The radio frequency identification module (54) manages the in-place mold information of the production line using radio frequency identification RFID technology, reads the in-place mold data and determines whether the in-place mold meets the system setting requirements; The preventive protection module (55) monitors the equipment status at all times during the production process, responds in time before damage occurs, and takes preventive protection measures.

9. The intelligent control system for the production process of a spin-on oil and fuel filter according to claim 8, characterized in that: The preventive protection module (55) comprises an uninterrupted buffer module (551), a motor operation status monitoring module (552) and an eccentric load prevention module (553): The uninterruptible buffer module (551) provides a short-term DC power supply buffer after the power grid outside the production line is cut off through the DC UPS+ buffer technology, can continuously provide DC24 for a maximum duration of 11 hours, and transmits the signal to the human-machine interaction unit (8); The motor operation status monitoring module (552) is used to monitor the motor temperature, motor output shaft vibration and working current of the production line, and transmit the warning signal to the auxiliary unit (6) and the human-machine interaction unit (8) when the warning value is reached; The off-center load prevention module (553) uses the eccentric load capacity curve dedicated to the multi-station press to predict in advance the off-center load force generated during the stamping process of different molds on the production line.

10. The intelligent control system for the production process of a spin-on oil and fuel filter according to claim 5, characterized in that: The auxiliary unit (6) comprises a stop module (61), an emergency stop module (62), a reset module (63), an indicator light module (64) and an alarm module (65): The stop module (61) is provided with a stop button and interlocked with the host. When the operator presses the stop button, the stop module (61) issues a stop operation instruction. After the current cycle of work is completed, all mechanisms return to the initial state and the system stops. The emergency stop module (62) is provided with multiple emergency stop buttons at multiple workstations and is interlocked with the main machine. When an operator presses the emergency stop button in any dangerous situation, the emergency stop module (62) controls the equipment to stop immediately. The reset module (63) is provided with multiple reset buttons at multiple workstations and interlocked with the host machine. When the operator releases the emergency stop button and presses the reset button, all mechanical mechanisms return to the initial state. The indicator light module (64) is provided next to the production line equipment. When the system is not working, the red light is always on, and when the system is working, the green light is always on. The alarm module (65) is used to receive different abnormal alarm signals and early warning signals, and control different sound and light alarms to emit sound and light alarm prompts.

Images