Anode carbon block forming stamping control system

Abstract

The invention relates to the technical field of carbon block production control, and discloses an anode carbon block forming stamping control system which comprises a stamping process parameter acquisition module, a carbon block quality characteristic analysis module, a stamping dynamic compensation module, a stamping control parameter matching module and a stamping execution module. Process parameters are captured in real time through a multi-source sensing fusion framework, online diagnosis and closed-loop control of the porosity and crack defects of the carbon block are achieved in combination with a microstructure feature dynamic extraction technology, the risk that pores exceed the standard due to fluctuation of raw materials is eliminated, it is guaranteed that the density of the carbon block is stable and meets the superior product standard, and crack initiation and propagation are restrained; the problem of missed judgment of traditional manual sampling inspection is avoided, a static parameter setting mode is broken through, quality fluctuation self-adaptive compensation is achieved, local suboptimal solution traps are avoided through self-adaptive matching of optimal parameter combinations under different formulas and working conditions, a continuous learning standard parameter library is constructed, and digital precipitation of process knowledge is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon block production control, in particular to an anode carbon block forming and stamping control system. Background Art

[0002] Anode carbon block refers to a carbon block produced with petroleum coke and asphalt coke as aggregate and coal tar as binder. It is used as anode material for pre-baked aluminum electrolytic cells. This carbon block has been baked and has a stable geometric shape, so it is also called pre-baked anode carbon block, and is also customarily called carbon anode for aluminum electrolysis. Carbon block stamping is the core process link in the production of anodes for electrolytic aluminum, which directly affects the conductivity, mechanical strength and thermal shock resistance of the anode carbon block.

[0003] The stamping control systems currently used in the industry have the following key flaws: 1. Large quality fluctuations: The qualified rate of carbon block porosity is only low and the crack rate exceeds the standard. The main reason is that the process parameters are statically set and cannot adapt to the fluctuations of raw materials and changes in ambient temperature and humidity.

[0004] 2. High dependence on manual labor: The mainstream solution relies on engineers' experience to adjust parameters, resulting in a long debugging cycle and increased losses due to production line downtime.

[0005] 3. Control response lag: Traditional PID control has strong coupling interference and response delay in multivariable coupling systems, which causes the standard deviation of carbon block density to exceed the standard.

[0006] Therefore, the present invention provides an anode carbon block forming and stamping control system that constructs a closed-loop control architecture of multi-source perception → quality inversion → dynamic compensation → intelligent matching to solve the data layer disconnection, overcome the algorithm convergence defects, and eliminate control lag. Summary of the Invention

[0007] In view of the shortcomings of the prior art, the present invention provides an anode carbon block forming stamping control system, which solves the problems raised in the above background technology.

[0008] To achieve the above objectives, the present invention provides the following technical solutions: an anode carbon block forming stamping control system, the system comprising a stamping process parameter acquisition module, a carbon block quality feature analysis module, a stamping dynamic compensation module, a stamping control parameter matching module and a stamping execution module: The stamping process parameter acquisition module collects the stamping process parameters of the anode carbon block in real time through a multi-source sensor network to generate a stamping process parameter set Q; The carbon block quality feature analysis module extracts the carbon block molding quality features based on Q and combines the carbon block microstructure image processing technology to generate a carbon block quality feature vector V; The punching dynamic compensation module is based on the V and the preset carbon block quality standard vector The deviation value is calculated by using nonlinear compensation algorithm to dynamically correct the stamping process parameters and generate the compensated stamping process parameters. ; The stamping control parameter matching module Input the stamping control parameter matching model built based on the improved particle swarm optimization algorithm, search for the optimal stamping control parameter combination, and generate the target stamping control parameters ; The stamping execution module, according to the Drive the hydraulic servo mechanism to perform the stamping action, and feed back the stamping status data to the stamping process parameter acquisition module in real time to form a closed-loop control.

[0009] Preferably, the stamping process parameter acquisition module includes a pressure sensing unit, a temperature sensing unit, a displacement sensing unit and an image acquisition unit; The pressure sensing unit collects real-time pressure data of each partition of the mold through a distributed pressure sensor array. Where n is the number of mold pressure zones, Real-time pressure value of the i-th partition; The temperature sensing unit collects the carbon blank temperature field distribution data through an infrared thermal imager Among them, m is the number of temperature detection points, Real-time temperature of the jth detection point; The displacement sensing unit collects the punch head stroke data through a laser displacement sensor The image acquisition unit uses a high-speed industrial camera to capture microstructure image sequences during the carbon block forming process. Preferably, the carbon block quality characteristic analysis module performs the following operations: S21, Extract porosity features: Use adaptive threshold segmentation algorithm to identify microstructure pore areas and calculate pore area ratio in is the total pore area, is the total area of ​​the detection area; S22, the Extract crack features: Apply Canny edge detection algorithm to identify crack contours and calculate crack density in is the total crack length; S23. Constructing carbon block quality feature vector in As stated Calculated, is the material characteristic coefficient.

[0010] Preferably, the stamping dynamic compensation module performs the following operations: S31. Calculate the mass deviation vector in is the preset standard value; S32. Establish compensation function: Where is the adaptive gain coefficient, is the weight matrix, Compensation weights corresponding to porosity, crack density, and volume density respectively; S33, when Activate speed-holding time collaborative compensation when: in is the compensation coefficient, is the deviation threshold.

[0011] Preferably, the stamping control parameter matching module includes: Standard parameter library, storing historical optimal stamping control parameter sets in For the Class control parameter combination, is the corresponding carbon block quality characteristic vector; The matching engine, built on an improved particle swarm optimization algorithm, performs the following steps: S51. Initialize the particle swarm position: in is the parameter dimension, The boundary of the parameter value range; S52, Exploration Phase Update Location: in is the global optimal solution, is the exploratory factor; S53, local optimization in the development phase: in is the individual historical optimal solution, is the number of iterations, The particle positions after the development phase update; S54. Output the optimal solution: in To predict the carbon block quality feature vector, To select the parameter combination corresponding to the minimum distance.

[0012] Preferably, the improved particle swarm optimization algorithm introduces dynamic inertia weight: in is the extreme value of weight, is the maximum number of iterations; The position update formula is expanded to: is the position of the new generation of particles, is the inertia component, 、 is the learning factor, is the historical optimal position of particle i, is the global historical optimal position of the population, are independent random numbers in the interval [0,1].

[0013] Preferably, the stamping execution module includes: Hydraulic servo controller, according to Generate PWM control signal; The pressure closed loop unit adjusts the oil pressure through the PID controller to make the actual pressure track The control law is: in ; is the hydraulic control output at time t, is the pressure deviation, 、 、 is the gain coefficient; Speed ​​adaptive unit, according to the carbon billet temperature in is the temperature compensation coefficient, is the average temperature of the carbon blank, is the reference temperature, Control speed for the target.

[0014] Preferably, it also includes: The abnormal fuse module triggers an emergency shutdown when any of the following conditions are detected: Pressure Sudden Change: ; Temperature exceeds limit: ; Crack density exceeds the standard: ;in, is the pressure mutation threshold, is the temperature safety threshold, is the critical value of crack density.

[0015] Preferably, the emergency shutdown implements a three-level response strategy: First level response: When , reduce the punching speed by 50% and activate the holding pressure compensation; Secondary response: When When the current stamping cycle is interrupted and the mold cleaning is started; Level 3 response: 、 When the pressure is released, cut off the hydraulic power source and release the mold pressure.

[0016] Preferably, the method comprises the steps of: S101: Real-time collection of stamping process parameter sets S102: Extracting carbon block quality feature vector S103: Calculate mass deviation And generate compensation parameters S104: Matching optimal control parameters by improving particle swarm optimization algorithm S105: driving the hydraulic system to perform stamping and feeding back status data; S106: When the number of iterations Update the standard parameter library , The historical optimal stamping control parameter set.

[0017] Compared with the prior art, the present invention provides an anode carbon block forming and stamping control system, which has the following beneficial effects: 1. Real-time capture of process parameters through a multi-source sensor fusion architecture, combined with dynamic extraction technology of microstructural features, enables online diagnosis and closed-loop control of carbon block porosity and crack defects, eliminates the risk of excessive porosity due to raw material fluctuations, ensures that the density of carbon blocks is stable and meets the standards of premium products, inhibits crack initiation and expansion, avoids the problem of missed judgments in traditional manual inspections, breaks through the static parameter setting mode, and realizes adaptive compensation for quality fluctuations.

[0018] 2. The particle swarm optimization engine is used to achieve self-optimization of stamping parameters, replacing experience-dependent manual debugging and reducing production line downtime losses. By adaptively matching the optimal parameter combination under different recipes and working conditions, local suboptimal solution traps are avoided, a standard parameter library for continuous learning is built, and the digital accumulation of process knowledge is promoted.

[0019] 3. By innovatively integrating nonlinear dynamic feedforward compensation with a high-precision hydraulic execution architecture, the problem of strongly coupled interference between pressure, speed, and holding time is resolved, achieving millisecond-level response. The erosion of thermal effects on forming accuracy is eliminated through a real-time temperature drift compensation mechanism. The actuator tracking accuracy reaches micron level, ensuring that there is no overshoot or oscillation during the stamping process. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a schematic diagram of the overall system architecture of the present invention. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0022] See also Figure 1 The anode carbon block forming stamping control system includes a stamping process parameter acquisition module, a carbon block quality feature analysis module, a stamping dynamic compensation module, a stamping control parameter matching module and a stamping execution module: The stamping process parameter acquisition module collects the stamping process parameters of the anode carbon block in real time through a multi-source sensor network to generate a stamping process parameter set Q; The carbon block quality feature analysis module extracts the carbon block molding quality features based on Q and combines the carbon block microstructure image processing technology to generate a carbon block quality feature vector V; The punching dynamic compensation module is based on the V and the preset carbon block quality standard vector The deviation value is calculated by using nonlinear compensation algorithm to dynamically correct the stamping process parameters and generate the compensated stamping process parameters. ; The stamping control parameter matching module, the Input the stamping control parameter matching model built based on the improved particle swarm optimization algorithm, search for the optimal stamping control parameter combination, and generate the target stamping control parameters ; The stamping execution module, according to the Drive the hydraulic servo mechanism to perform the stamping action, and feed back the stamping status data to the stamping process parameter acquisition module in real time to form a closed-loop control.

[0023] The stamping process parameter acquisition module includes a pressure sensing unit, a temperature sensing unit, a displacement sensing unit and an image acquisition unit; The pressure sensing unit collects real-time pressure data of each partition of the mold through a distributed pressure sensor array. Where n is the number of mold pressure zones, Real-time pressure value of the i-th partition; The temperature sensing unit collects the carbon blank temperature field distribution data through an infrared thermal imager Among them, m is the number of temperature detection points, Real-time temperature of the jth detection point; The displacement sensing unit collects the punch head stroke data through a laser displacement sensor ; The image acquisition unit uses a high-speed industrial camera to collect microstructure image sequences during the carbon block forming process. .

[0024] The carbon block quality characteristic analysis module performs the following operations: S21, the Extract porosity features: Use adaptive threshold segmentation algorithm to identify microstructure pore areas and calculate pore area ratio in is the total pore area, is the total area of ​​the detection area; S22, the Extract crack features: Apply Canny edge detection algorithm to identify crack contours and calculate crack density in is the total crack length; S23. Constructing carbon block quality feature vector in As stated Calculated, is the material characteristic coefficient.

[0025] The stamping dynamic compensation module performs the following operations: S31. Calculate the mass deviation vector in is the preset standard value; S32. Establish compensation function: in is the adaptive gain coefficient, is the weight matrix, Compensation weights corresponding to porosity, crack density, and volume density respectively; S33, when Activate speed-holding time collaborative compensation when: in is the compensation coefficient, is the deviation threshold.

[0026] The stamping control parameter matching module includes: Standard parameter library, storing historical optimal stamping control parameter sets in For the Class control parameter combination, is the corresponding carbon block quality characteristic vector; The matching engine, built on an improved particle swarm optimization algorithm, performs the following steps: S51. Initialize the particle swarm position: in is the parameter dimension, The boundary of the parameter value range; S52, Exploration Phase Update Location: in is the global optimal solution, is the exploratory factor; S53, local optimization in the development phase: in is the individual historical optimal solution, is the number of iterations, The particle positions after the development phase update; S54. Output the optimal solution: in To predict the carbon block quality feature vector, To select the parameter combination corresponding to the minimum distance.

[0027] Improved particle swarm optimization algorithm introduces dynamic inertia weight: in is the extreme value of weight, is the maximum number of iterations; The position update formula is expanded to: is the position of the new generation of particles, is the inertia component, 、 is the learning factor, is the historical optimal position of particle i, is the global historical optimal position of the population, are independent random numbers in the interval [0,1].

[0028] The stamping execution module includes: Hydraulic servo controller, according to Generate PWM control signal; The pressure closed loop unit adjusts the oil pressure through the PID controller to make the actual pressure track The control law is: in ; is the hydraulic control output at time t, is the pressure deviation, 、 、 is the gain coefficient; Speed ​​adaptive unit, according to the carbon billet temperature in is the temperature compensation coefficient, is the average temperature of the carbon blank, is the reference temperature, Control speed for the target.

[0029] Also includes: The abnormal fuse module triggers an emergency shutdown when any of the following conditions are detected: Pressure Sudden Change: ; Temperature exceeds the limit: ; Crack density exceeds the standard: ; in, is the pressure mutation threshold, is the temperature safety threshold, is the critical value of crack density.

[0030] Emergency shutdown implements a three-level response strategy: First level response: When , reduce the punching speed by 50% and activate the holding pressure compensation; Secondary response: When When the current stamping cycle is interrupted and the mold cleaning is started; Level 3 response: 、 When the pressure is released, cut off the hydraulic power source and release the mold pressure.

[0031] Including steps: S101: Real-time collection of stamping process parameter sets S102: Extracting carbon block quality feature vector S103: Calculate mass deviation And generate compensation parameters S104: Matching optimal control parameters by improving particle swarm optimization algorithm S105: driving the hydraulic system to perform stamping and feeding back status data; S106: When the number of iterations Update the standard parameter library , The historical optimal stamping control parameter set.

[0032] System hardware deployment and initialization Step 1: Multi-source sensor network construction A 16-zone piezoelectric sensor array is evenly arranged on the surface of the stamping machine die, with a sampling frequency of 1kHz and a measurement range of up to 60MPa. An infrared thermal imager is installed above the carbon billet preheating area, and a 5×5 temperature measurement grid is established with a temperature resolution of 0.5°C to monitor the carbon billet temperature field distribution in real time. The punch head hydraulic rod is equipped with a laser displacement sensor to measure the stroke range with an accuracy of 0.01mm; The side wall of the molding cavity is integrated with a high-speed industrial camera, equipped with a ring-shaped LED cold light source, with a shooting resolution of 2048×2048 and a frame rate of 500fps; Step 2: Control system hardware integration The main control unit adopts industrial-grade embedded system; The hydraulic actuator uses a proportional servo valve with a response time of less than 10ms and a pressure control accuracy of 0.2MPa; Deploy real-time Ethernet to achieve millisecond-level communication between sensor and control unit; Step 3: System initialization calibration Perform sensor zero point calibration: collect the reference value of each sensor under no-load condition; Set the initial values ​​of process parameters: pressure 25MPa, speed 30mm / s, holding time 5s; Loading carbon block quality standard vector .

[0033] Dynamic compensation mechanism execution Compensation trigger logic: When the mass deviation vector satisfies: Activate when in, is the deviation between the real-time porosity measurement value and the standard value, is the crack density deviation, is the density deviation; compensation execution process: 1. Basic parameter compensation Construct the compensation matrix: Calculate the compensation amount: in, is the parameter adjustment vector, is the adaptive gain coefficient; is the hyperbolic tangent function; 2. Collaborative compensation strategy when hour: in, is the current punching speed, is the speed after compensation; when hour: in, is the current holding time, It is the holding time after compensation; 3. Temperature drift compensation Real-time monitoring of the average temperature of carbon billets Speed ​​dynamic correction: in, is the average temperature of the carbon billet.

[0034] Hydraulic precision execution control Pressure closed loop control: in, is the pressure deviation at the current moment, is the pressure deviation at the previous moment, is the pressure deviation at the last moment; Parameter setting value: , , Security monitoring mechanism: Calculate the pressure change rate in real time: in, is the pressure value at the current sampling moment, is the pressure value at the last sampling moment, is the system sampling interval; Three-level circuit breaker strategy: Level 1 warning ( >5MPa / ms): Reduce the stamping speed by 50%; Secondary protection (r >8MPa / ms): interrupt the current stamping cycle; Level 3 emergency stop ( >10MPa / ms): Cut off the hydraulic power source.

[0035] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0036] While 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 these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An anode carbon block forming stamping control system, characterized by: The system includes a stamping process parameter acquisition module, a carbon block quality feature analysis module, a stamping dynamic compensation module, a stamping control parameter matching module and a stamping execution module: The stamping process parameter acquisition module collects the stamping process parameters of the anode carbon block in real time through a multi-source sensor network to generate a stamping process parameter set Q; The carbon block quality feature analysis module extracts the carbon block molding quality features based on Q and combines the carbon block microstructure image processing technology to generate a carbon block quality feature vector V; The punching dynamic compensation module is based on the V and the preset carbon block quality standard vector The deviation value is calculated by using nonlinear compensation algorithm to dynamically correct the stamping process parameters and generate the compensated stamping process parameters. ; The stamping control parameter matching module Input the stamping control parameter matching model built based on the improved particle swarm optimization algorithm, search for the optimal stamping control parameter combination, and generate the target stamping control parameters ; The stamping execution module, according to the Drive the hydraulic servo mechanism to perform the stamping action, and feed back the stamping status data to the stamping process parameter acquisition module in real time to form a closed-loop control.

2. The anode carbon block forming stamping control system according to claim 1, characterized in that: The stamping process parameter acquisition module includes a pressure sensing unit, a temperature sensing unit, a displacement sensing unit and an image acquisition unit; The pressure sensing unit collects real-time pressure data of each partition of the mold through a distributed pressure sensor array. ; Where n is the number of mold pressure zones, Real-time pressure value of the i-th partition; The temperature sensing unit collects the carbon blank temperature field distribution data through an infrared thermal imager ; Among them, m is the number of temperature detection points, Real-time temperature of the jth detection point; The displacement sensing unit collects the punch head stroke data through a laser displacement sensor ; The image acquisition unit uses a high-speed industrial camera to collect microstructure image sequences during the carbon block forming process. .

3. The anode carbon block forming stamping control system according to claim 1, characterized in that: The carbon block quality characteristic analysis module performs the following operations: S21, the Extract porosity features: Use adaptive threshold segmentation algorithm to identify microstructure pore areas and calculate pore area ratio ; in is the total pore area, is the total area of ​​the detection area; S22, the Extract crack features: Apply Canny edge detection algorithm to identify crack contours and calculate crack density ; in is the total crack length; S23. Constructing carbon block quality feature vector ; in As stated Calculated, is the material characteristic coefficient.

4. The anode carbon block forming stamping control system according to claim 1, characterized in that: The stamping dynamic compensation module performs the following operations: S31. Calculate the mass deviation vector ; in is the preset standard value; S32. Establish compensation function: ; in is the adaptive gain coefficient, is the weight matrix, Compensation weights corresponding to porosity, crack density, and volume density respectively; S33, when Activate speed-holding time collaborative compensation when: ; in is the compensation coefficient, is the deviation threshold.

5. The anode carbon block forming stamping control system according to claim 1, characterized in that: The stamping control parameter matching module includes: Standard parameter library, storing historical optimal stamping control parameter sets ; in For the Class control parameter combination, is the corresponding carbon block quality characteristic vector; The matching engine, built on an improved particle swarm optimization algorithm, performs the following steps: S51. Initialize the particle swarm position: ; in is the parameter dimension, The boundary of the parameter value range; S52, Exploration Phase Update Location: ; in is the global optimal solution, is the exploratory factor; S53, local optimization in the development phase: ； in is the individual historical optimal solution, is the number of iterations, The particle positions after the development phase update; S54. Output the optimal solution: ； in To predict the carbon block quality feature vector, To select the parameter combination corresponding to the minimum distance.

6. The anode carbon block forming stamping control system according to claim 1, characterized in that: The improved particle swarm optimization algorithm introduces dynamic inertia weight: ； in is the extreme value of weight, is the maximum number of iterations; The position update formula is expanded to: is the position of the new generation of particles, is the inertia component, is the learning factor, is the historical optimal position of particle i, is the global historical optimal position of the population, are independent random numbers in the interval [0,1].

7. The anode carbon block forming stamping control system according to claim 1, characterized in that: The stamping execution module includes: Hydraulic servo controller, according to Generate PWM control signal; The pressure closed loop unit adjusts the oil pressure through the PID controller to make the actual pressure track The control law is: ; in ; is the hydraulic control output at time t, is the pressure deviation, is the gain coefficient; Speed ​​adaptive unit, according to the carbon billet temperature ; in is the temperature compensation coefficient, is the average temperature of the carbon blank, is the reference temperature, Control speed for the target.

8. The anode carbon block forming stamping control system according to claim 1, characterized in that: Also includes: The abnormal fuse module triggers an emergency shutdown when any of the following conditions are detected: Pressure Sudden Change: ; Temperature exceeds the limit: ; Crack density exceeds the standard: ; in, is the pressure mutation threshold, is the temperature safety threshold, is the critical value of crack density.

9. The anode carbon block forming stamping control system according to claim 8, characterized in that: The emergency shutdown implements a three-level response strategy: First level response: When , reduce the punching speed by 50% and activate the holding pressure compensation; Secondary response: When When the current stamping cycle is interrupted and the mold cleaning is started; Level 3 response: 、 When the pressure is released, cut off the hydraulic power source and release the mold pressure.

10. The anode carbon block forming stamping control system according to claim 1, characterized in that: Including steps: S101: Real-time collection of stamping process parameter sets ; S102: Extracting carbon block quality feature vector ; S103: Calculate mass deviation And generate compensation parameters ; S104: Matching optimal control parameters by improving particle swarm optimization algorithm ; S105: driving the hydraulic system to perform stamping and feeding back status data; S106: When the number of iterations Update the standard parameter library , Historical optimal stamping control parameter set.

Images