Dry-method pole piece forming control method based on AI algorithm and pole piece forming and compounding all-in-one machine

Abstract

The invention discloses a dry-method pole piece forming control method based on an AI algorithm and a pole piece forming and combining all-in-one machine. A calendering control system adjusts all roll gaps according to the thickness of a finished product diaphragm, roll gap displacement information, double-outlet-rod position information of a hydraulic cylinder and angle information of a driving motor of a lead screw wedge block assembly; and a control center of the calendaring control system adopts a DRNN neural network algorithm, a linear regression model is established by the obtained lightweight output, expert knowledge base output and historical data fitting output, the obtained control quantity serves as an input vector of a PID controller, and the output quantity is output to a corresponding execution mechanism. According to the calendaring control system, the neural network algorithm is introduced to be combined with the PID controller, and meanwhile, the neural network algorithm is also combined with expert knowledge base output and historical data fitting output to construct a linear regression model, so that the control performance, the stability and the accuracy of the system are improved, and the production efficiency and the product quality of the calendaring machine are also improved.

Description

Technical Field

[0001] The present invention relates to the technical field of pole piece calendering composite equipment, and in particular to a dry pole piece forming control method based on an AI algorithm and a pole piece forming composite all-in-one machine. Background Art

[0002] Calenders are used in calendering, film stretching, rolling and other industries. In the control system of the calender, multiple structural units involve feedback control: roll gap adjustment unit, pole piece correction unit, pole piece tension control unit. The roll gap adjustment structure is used to adjust the gap between the main rollers to complete the adjustment of the rolling force and the thickness of the pole piece; the pole piece correction structure is used to adjust the pole piece deviation to avoid the pole piece deviation causing tower-shaped rolls and other phenomena that affect the quality of the pole piece; the pole piece tension control system is used to maintain the stability of the pole piece tension, ensure the straightness of the rolled pole piece, and avoid the pole piece caused by uneven extension. Waves and other phenomena.

[0003] The control system of the existing calender usually adopts PID control (proportional integral differential control). Traditional PID control usually directly inputs the collected parameters or signals into the PID controller, and forms the control quantity output through linear combination according to proportion, integration and differentiation to control the controlled object. The output of traditional PID control is composed of linear combination. When facing nonlinear, time-varying or multi-variable systems, it is not good at handling complex dynamic performance and multi-variable coupling, and lacks adaptability and robustness, resulting in poor control performance, affecting the control stability and accuracy of the system, and thus affecting the quality of the pole piece. Summary of the invention

[0004] In view of the shortcomings of the above-mentioned existing calender control system, the applicant provides a reasonable dry-process electrode forming control method based on AI algorithm and a electrode forming composite all-in-one machine, introduces a neural network algorithm and combines it with PID control to improve the stability and accuracy of the system.

[0005] The technical solution adopted by the present invention is as follows: A dry electrode forming control method based on AI algorithm, the calendering control system adjusts each roll gap according to the finished film thickness, roll gap displacement information, double rod position information of the hydraulic cylinder and the angle information of the drive motor of the screw wedge assembly; The control center of the calendering control system uses the DRNN neural network algorithm to calculate the signal to obtain the lightweight output. The lightweight output, expert knowledge base output and historical data fitting output are used to establish a linear regression model. The linear regression formula of the three is: , k1, k2, and k3 are the weights of the three outputs: lightweight output O, expert knowledge base P, and historical data fitting Q. b is a constant. The control quantity calculated by the linear regression model is used as the input vector of the PID controller. The output quantity calculated by the PID controller is output to the corresponding actuator to adjust the corresponding components.

[0006] As a further improvement of the above technical solution: The adjustment priority of each roll gap is as follows: along the general traveling direction of the material, the priority of the subsequent roll gap is higher than the priority of the preceding roll gap.

[0007] The weight values ​​of the linear regression formula are k1, 0.4, k2, and k3, 0.3.

[0008] After the roller gaps are adjusted, the following conditions are met: except for the first and last roller gaps, one of the remaining roller gaps is greater than or equal to the previous roller gap.

[0009] The control process of the roll gap includes: the control center converts and calculates the offline detection data of the film produced by the calender unit, and outputs the parameter set {K P1 , T I1 , T D1 , e1(t)}, expert knowledge base and historical data fitting formula output parameter set {K P2 , T I2 , T D2 , e2(t)} and {K P3 , T I3 , T D3 , e3(t)}, the three parameter sets are calculated by the linear regression model and the output parameter set {K P , T I , T D , e(t)}; one or more parameter sets {K P , T I , T D , e(t)} is output to one or more PIDs that control different roll gaps. After the PID is calculated by a discrete algorithm, a displacement vector instruction is issued to the servo motor of the screw wedge assembly and the servo hydraulic valve group of the hydraulic cylinder. The servo motor of the screw wedge assembly and the hydraulic cylinder operate synchronously to adjust the roll gap.

[0010] After the roller gap adjustment is completed, the thickness and surface density of the diaphragm are tested using an offline detection method. If the offline detected thickness is within the range of ±5%, the roller gaps are fixed. If it exceeds the range of ±5%, the calculation is returned and the adjustment steps are repeated until the thickness of the diaphragm is within the range of ±5%.

[0011] The PID controller uses a discrete-time system; the transfer function of the PID is , s is the Laplace variable (s=α+jω), K p is the amplification factor, T I is the integration time, T D is the derivative time; the adjustment function of PID is , the integral of e(t) is approximated by the rectangular sum , e'(t) is approximately a straight line , the control expression of PID is .

[0012] The calendering control system adjusts the speed of the servo motor according to the speed information of each servo motor, adjusts the unwinding tension of the metal foil and the winding tension of the pole piece according to the tension information collected by the tension sensor, and corrects the position of the metal foil and the pole piece according to the displacement information detected by the ultrasonic sensor.

[0013] A pole piece forming composite integrated machine, which is controlled by the dry pole piece forming control method based on the AI ​​algorithm described in claim 1, comprising at least one calendering unit, one unwinding unit and one winding unit, wherein the unwinding unit and the winding unit are arranged on the pole piece composite forming side of the calendering unit; the calendering unit comprises a plurality of calendering rollers arranged in sequence along the main conveying direction X, and a roller gap is provided between two adjacent calendering rollers.

[0014] As a further improvement of the above technical solution: The roll gaps between adjacent calendering rolls gradually decrease from front to back along the main conveying direction X. Except for the first and last roll gaps, one of the remaining roll gaps is equal to the previous one.

[0015] A bearing seat is correspondingly arranged on each calendering roller, and a screw wedge assembly is arranged between the bearing seats corresponding to adjacent calendering rollers. The screw wedge assembly cooperates with the bearing seat through an inclined surface. The screw wedge assembly can adjust the roll gap width between the two calendering rollers by moving along the axial direction of the calendering roller; a roll gap displacement sensor is also arranged between the bearing seats corresponding to adjacent calendering rollers.

[0016] The first calendering roller is provided with a back roller on the side opposite to the main conveying direction X, and the back roller is in close contact with the first calendering roller. The back roller is provided with a hydraulic cylinder on the side opposite to the main conveying direction X, and the last calendering roller is provided with a hydraulic cylinder on the side in the same direction as the main conveying direction X. The hydraulic cylinder controls the extension and retraction of its double rods through a valve group to control the displacement of the back roller or the last calendering roller.

[0017] The roller diameter of the back roller and the roller diameter of the last two calendering rollers are larger than the roller diameters of other calendering rollers; each calendering roller is separately connected to a motor and driven by an independent motor, and the rotation speed of each calendering roller gradually increases from front to back along the main conveying direction X.

[0018] The roller diameters of the first and second calender rollers close to the back roller are smaller than the roller diameters of the other calender rollers and the back roller.

[0019] Each calendering roller can be independently adjusted in a direction perpendicular to the main conveying direction X; the axes of each calendering roller are located in the same plane or the axes of each calendering roller are staggered. When staggered, the extension line of the axis connection line between each pair of adjacent calendering rollers intersects at one point with the extension line of the axis connection line between another pair of adjacent calendering rollers; at least one calendering roller is a heatable roller, and the heating temperature is between 150°C and 200°C.

[0020] The unwinding unit is provided with a metal foil unwinding shaft. Between the metal foil unwinding shaft and the roller gap between the last two calendering rollers of the calendering unit, a tape splicing platform, an unwinding tension sensor, a tension swing roller, an unwinding correction assembly, and an unwinding ultrasonic sensor are arranged in sequence along the unwinding direction of the metal foil, and unwinding guide rollers are respectively arranged between adjacent components.

[0021] The unwinding unit is provided with a film unwinding shaft, and a plurality of unwinding guide rollers are arranged between the film unwinding shaft and the roller gap between the last two calendering rollers of the calendering unit.

[0022] The winding unit is provided with a winding shaft. Between the winding shaft and the roller gap between the last two calendering rollers of the calendering unit, the first winding tension sensor, the first swing roller assembly, the tension isolation assembly, the second winding tension sensor, the second swing roller assembly, the winding correction assembly and the winding ultrasonic sensor are arranged in sequence along the winding direction of the pole piece, and winding guide rollers are respectively arranged between adjacent components.

[0023] The beneficial effects of the present invention are as follows: The calendering control system of the present invention introduces a neural network algorithm in combination with a PID controller. The neural network algorithm also combines the output of an expert knowledge base and the output of historical data fitting to construct a linear regression model. The linear regression output is obtained and then input into the PID controller. The PID controller automatically adjusts the executed control amount in real time according to the linear regression output, and can more accurately control the roll gap, belt speed, tension and deviation correction. When facing nonlinear, time-varying or multi-variable systems, complex dynamic performance and multi-variable coupling can also be accurately processed, with better adaptability and robustness, thereby improving the control performance of the system, improving the stability and accuracy of the system, and also improving the production efficiency and product quality of the calender.

[0024] The PID controller of the present invention uses a discrete time system, which can suppress noise and interference through technologies such as digital filtering. Compared with a continuous time system, the discrete time system is more robust and suitable for real-time control applications, and complex control strategies can be implemented through easy algorithms. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1It is a schematic diagram of the main structure of the first embodiment of the pole piece molding composite integrated machine of the present invention.

[0026] Figure 2 It is a schematic diagram of the top structure of the calendering unit of the present invention.

[0027] Figure 3 Schematic diagram of the roll gap adjustment of the calender unit.

[0028] Figure 4 It is a schematic diagram of the main structure of the second embodiment of the pole piece molding composite integrated machine of the present invention.

[0029] Figure 5 It is a schematic diagram of the main structure of the third embodiment of the pole piece molding composite integrated machine of the present invention.

[0030] Figure 6 It is a schematic diagram of the main structure of the fourth embodiment of the pole piece molding composite integrated machine of the present invention.

[0031] Figure 7 This is the control flow chart of the calendering control system.

[0032] Figure 8 This is the control flow chart of the control center.

[0033] Fig. 9 This is a flow chart from neural network to PID controller and then to actuator.

[0034] In the figure: 100, calendering unit; 11, calendering roller; 12, backing roller; 13, hydraulic cylinder; 14, motor; 15, bearing seat; 16, screw wedge assembly; 17, roll gap displacement sensor; 10, roll gap; 101, roll gap; 102, roll gap; 103, roll gap; 104, roll gap; 105, roll gap; 106, roll gap; 107, roll gap; 200, unwinding unit; 21, metal foil unwinding shaft; 22, film unwinding shaft; 23, unwinding tension sensor; 24, tension swing roller; 25, unwinding deviation correction component; 26, unwinding ultrasonic sensor; 27, tape splicing platform; 28, unwinding guide roller; 300. Winding unit; 31. Winding shaft; 32. First winding tension sensor; 33. First swing roller assembly; 34. Tension barrier assembly; 35. Second winding tension sensor; 36. Second swing roller assembly; 37. Winding deviation correction assembly; 38. Winding ultrasonic sensor; 39. Winding guide roller. DETAILED DESCRIPTION

[0035] The specific implementation of the present invention will be described below in conjunction with the accompanying drawings.

[0036] Example 1 of pole piece forming composite integrated machine: like Figure 1 As shown, this embodiment is a single-sided double-sided electrode sheet forming composite integrated machine, including a calendering unit 100, a unwinding unit 200 and a winding unit 300, and the unwinding unit 200 and the winding unit 300 are arranged on the electrode sheet composite forming side of the calendering unit 100.

[0037] like Figures 1 to 3As shown, the calendering unit 100 includes a plurality of calendering rollers 11 arranged in sequence along the main conveying direction X. In this embodiment, eight calendering rollers 11 are provided, and each calendering roller 11 can be independently adjusted in a direction perpendicular to the main conveying direction X to improve its adaptability. The axes of each calendering roller 11 can be located in the same plane, and the axes of each calendering roller 11 can also be arranged in a staggered manner. When arranged in a staggered manner, the extension line of the axis connection line between each pair of adjacent calendering rollers 11 intersects at one point with the extension line of the axis connection line between another pair of adjacent calendering rollers 11. At least one calendering roller 11 is a heatable roller, and the heating temperature is between 150°C and 200°C. There is a roller gap 10 between two adjacent calendering rollers 11, and the roller gap 10 is arranged along the total direction of material movement. The roll gaps 10 between adjacent calendering rollers 11 gradually decrease from front to back along the main conveying direction X to meet the thickness requirements of multiple calenderings and reduce the thickness of the membrane step by step. At the same time, except for the first and last roll gaps 10, one of the remaining roll gaps 10 is greater than or equal to the previous roll gap 10, such as: roll gap 101> roll gap 102≥ roll gap 104≥ roll gap 103> roll gap 105> roll gap 106> roll gap 107, so as to release the internal stress of the membrane caused by multiple calenderings, thereby improving the compaction density and thickness uniformity of the membrane; the membrane material is input from one side of the roll gap 10 of the first two calendering rollers 11, and is rolled into a membrane after multiple times of rolling by a number of calendering rollers 11. Along the main conveying direction X of the material, the roller diameters of the last two calendering rollers 11 are larger than the roller diameters of the other calendering rollers 11. The roller diameters of the last two calendering rollers 11 are larger, have greater rigidity, can withstand greater rolling force, and are beneficial to improving the uniformity of the formed electrode sheet. The first calendering roller 11 is provided with a back roller 12 on the side opposite to the main conveying direction X. The back roller 12 fits tightly with the first calendering roller 11. The roller diameters of the back roller 12 and the last two calendering rollers 11 are larger than the roller diameters of the other calendering rollers 11. The back roller 12 has a larger roller diameter, which can provide greater rigid support for the calendering roller 11, so that the calendering roller 11 can withstand greater rolling force, increase the shear force of the material to improve the uniformity of the electrode sheet. The back roller 12 is provided with a hydraulic cylinder 13 on the side opposite to the main conveying direction X, and the last calendering roller 11 is provided with a hydraulic cylinder 13 on the side in the same direction as the main conveying direction X. The hydraulic cylinder 13 controls the extension and retraction of its double rods through a valve group to control the displacement of the back roller 12 or the last calendering roller 11, thereby adjusting the roller gap 10 between the calendering rollers 11. Each calendering roller 11 is separately connected to a motor 14, driven by an independent motor 14, and independently controls the rotation speed and torque. The rotation speed of each calendering roller 11 gradually increases from front to back along the main conveying direction X to improve the adhesion of the film on the rear roller and prevent the film from piling up; the speed increments of adjacent calendering rollers 11 can be the same or different, and are set according to actual processing requirements.A bearing seat 15 is provided on each calendering roller 11, and a screw wedge assembly 16 is provided between the bearing seats 15 corresponding to adjacent calendering rollers 11. The screw wedge assembly 16 cooperates with the bearing seat 15 through an inclined surface. The screw wedge assembly 16 moves along the axial direction of the calendering roller 11 to adjust the width of the roll gap 10 between the two calendering rollers 11. A roll gap displacement sensor 17 is also provided between the bearing seats 15 corresponding to adjacent calendering rollers 11, which is used to monitor the distance between the bearing seats 15 to indirectly reflect the width of the roll gap 10, so as to determine the pressure of the hydraulic cylinder 13 and the rotation angle of the motor on the screw wedge assembly 16. Compared with the laser and infrared roll gap sensors for direct measurement, the roll gap displacement sensor 17 has the advantages of low cost, simple structure, and small space occupation. A bearing clearance elimination mechanism is provided on each calendering roller 11 and the backing roller 12.

[0038] like Figure 1 As shown, the unwinding unit 200 is provided with a metal foil unwinding shaft 21 and a film unwinding shaft 22. The metal foil unwinding shaft 21 is used to place the metal foil coil, and the film unwinding shaft 22 is used to place the pre-produced film coil. Between the metal foil unwinding shaft 21 and the roll gap 10 of the last two calendering rollers 11 of the calendering unit 100, a belt connection platform 27, an unwinding tension sensor 23, a tension swing roller 24, an unwinding deviation correction component 25, and an unwinding ultrasonic sensor 26 are arranged in sequence along the unwinding direction of the metal foil, and unwinding guide rollers 28 are respectively arranged between adjacent components; after the metal foil coil is pulled out from the metal foil unwinding shaft 21, it bypasses the belt connection platform 27, the unwinding tension sensor 23, the tension swing roller 24, the unwinding deviation correction component 25, and the unwinding ultrasonic sensor 26 in sequence, and is introduced into the roll gap 10 between the last two calendering rollers 11 of the calendering unit 100. A plurality of unwinding guide rollers 28 are arranged between the film unwinding shaft 22 and the roller gap 10 of the last two calendering rollers 11 of the calendering unit 100; after the pre-produced film coil is pulled out from the film unwinding shaft 22, it is introduced into the roller gap 10 between the last two calendering rollers 11 of the calendering unit 100 after passing through the plurality of unwinding guide rollers 28. The film formed by calendering of the calendering unit 100, the metal foil film guided by the metal foil unwinding shaft 21, and the film guided by the film unwinding shaft 22 are rolled and compounded by the last two calendering rollers 11 to form a pole piece. The metal foil unwinding shaft 21, the film unwinding shaft 22 and the tension swing roller 24 are respectively connected to the drive motor and driven by the drive motor. The unwinding tension sensor 23 is used to monitor the unwinding tension of the metal foil in real time, and the tension swing roller 24 is used to adjust the tension of the metal foil to ensure the accuracy of the unwinding tension; the unwinding ultrasonic sensor 26 is used to monitor the edge position of the metal foil in real time, and the unwinding correction component 25 is used to correct the position of the metal foil to ensure that the position of the metal foil is not deviated.

[0039] like Figure 1As shown, the winding unit 300 is provided with a winding shaft 31, and the winding shaft 31 is used to wind the composite-formed pole piece into a coil. Between the winding shaft 31 and the roller gap 10 of the last two calendering rollers 11 of the calendering unit 100, the first winding tension sensor 32, the first swing roller assembly 33, the tension isolation assembly 34, the second winding tension sensor 35, the second swing roller assembly 36, the winding correction assembly 37 and the winding ultrasonic sensor 38 are arranged in sequence along the winding direction of the pole piece, and the winding guide rollers 39 are respectively arranged between the adjacent components. The first winding tension sensor 32 and the second winding tension sensor 35 are used to monitor the winding tension of the pole piece in real time, and the first swing roller assembly 33 and the second swing roller assembly 36 are used to adjust the tension of the pole piece to ensure the accuracy of the winding tension; the winding ultrasonic sensor 38 is used to monitor the edge position of the pole piece in real time, and the winding correction assembly 37 is used to correct the position of the pole piece to ensure that the position of the pole piece is not deviated. The winding unit 300 is provided with two sets of tension control components (winding tension sensor and swing roller component) to monitor and adjust the winding tension of the winding pole piece, so that the tension adjustment is more accurate and the winding is more stable.

[0040] Example 2 of pole piece forming composite integrated machine: like Figure 4 As shown, this embodiment is a double-sided double-sided electrode sheet forming composite integrated machine, including two groups of symmetrically arranged calendering units 100, a group of unwinding units 200 and a group of winding units 300. The main conveying directions of the two groups of calendering units 100 are opposite, and the last two calendering rollers 11 are shared. One group of calendering units 100 is introduced into the roller gap 10 of the last two calendering rollers 11 after multiple calendering from left to right along the main conveying direction X1, and the other group of calendering units 100 is introduced into the roller gap 10 of the last two calendering rollers 11 after multiple calendering from right to left along the main conveying direction X2 in the opposite direction. The membranes calendered by the two groups of calendering units 100 and the metal foil membranes guided by the unwinding unit 200 are rolled and composited into electrode sheets by the last two calendering rollers 11. The diaphragms on both sides of the double-sided double-sided pole piece forming and compounding integrated machine are directly compounded after online continuous forming, which saves the diaphragm unwinding device of the unwinding unit 200 and also saves the time of diaphragm pre-production, and the pole piece production efficiency is higher.

[0041] like Figure 4As shown, the unwinding unit 200 and the winding unit 300 of this embodiment are respectively arranged on the upper side and the lower side of the two calendering units 100. The unwinding unit 200 is provided with a metal foil unwinding shaft 21, and between the metal foil unwinding shaft 21 and the roller gap 10 between the last two calendering rollers 11 of the calendering unit 100, a tape connection platform 27, an unwinding tension sensor 23, a tension swing roller 24, an unwinding correction component 25, and an unwinding ultrasonic sensor 26 are sequentially arranged along the unwinding direction of the metal foil, and unwinding guide rollers 28 are respectively arranged between adjacent components. Between the winding shaft 31 of the winding unit 300 and the roller gap 10 of the last two calendering rollers 11 of the calendering unit 100, the first swing roller assembly 33, the first winding tension sensor 32, the tension isolation assembly 34, the second winding tension sensor 35, the second swing roller assembly 36, the winding correction assembly 37 and the winding ultrasonic sensor 38 are arranged in sequence along the winding direction of the pole piece, and winding guide rollers 39 are respectively provided between adjacent components.

[0042] Example 3 of pole piece forming composite integrated machine: like Figure 5 As shown, this embodiment is a single-sided double-sided pole piece forming composite integrated machine. This embodiment is different from the first embodiment in that the calendering unit 100 of this embodiment is provided with six calendering rollers, and the roller diameters of the first and second calendering rollers 11 close to the back roller 12 are smaller than the roller diameters of the other calendering rollers 11 and the back roller 12. The size of each roller gap 10 also satisfies: at the same time, except for the first and last roller gaps 10, one of the remaining roller gaps 10 is greater than or equal to the previous roller gap 10, such as: roller gap 101> roller gap 102≥ roller gap 104≥ roller gap 103> roller gap 105.

[0043] Example 4 of the pole piece forming composite integrated machine: like Figure 6 As shown, this embodiment is a double-sided double-sided pole piece forming composite integrated machine. The difference between this embodiment and the second embodiment is that each calendering unit 100 of this embodiment is provided with six calendering rollers, and the roller diameters of the first and second calendering rollers 11 close to the back roller 12 are smaller than the roller diameters of the other calendering rollers 11 and the back roller 12. The size of each roller gap 10 also satisfies: at the same time, except for the first and last roller gaps 10, one of the remaining roller gaps 10 is greater than or equal to the previous roller gap 10, such as: roller gap 101> roller gap 102≥ roller gap 104≥ roller gap 103> roller gap 105.

[0044] The pole piece forming composite integrated machine of the present invention performs real-time monitoring and real-time parameter adjustment by a calendering control system, thereby ensuring the stability and accuracy of calendering and composite forming.

[0045] like Figure 7 As shown, the control method of the calendering control system mainly includes the following steps: 1) The calendering unit 100, the unwinding unit 200 and the winding unit 300 transmit the detection signals required for roll gap control, the detection signals required for belt speed control, the detection signals required for tension control, and the detection signals required for deviation correction control to the control center: the detection signals required for roll gap control include the displacement information of the roll gap 10 collected by the roll gap displacement sensor 17, the double rod position information of the hydraulic cylinder 13, the angle information of the drive motor of the screw wedge assembly 16, and the finished film thickness information; the detection signals required for belt speed control include the rotation speed information of each calendering roller 11, the metal foil unwinding shaft 21, the film unwinding shaft 22, and the winding shaft 31. These rollers or shafts are based on the rotation speed of one of the calendering rollers 11. In this embodiment, the rotation speed of the second to last calendering roller 11 is used as the reference. The speed is used as a reference, and the connected motors of the other rollers or shafts feed back their own speeds to the control center; the detection signal required for tension control includes the tension information detected by the tension sensor, the tension information of the unwinding unit 200 is the tension information collected by the unwinding tension sensor 23, and the tension information of the winding unit 300 is the tension information collected by the first winding tension sensor 32 and / or the second winding tension sensor 35; the detection signal required for deviation correction control includes the displacement information detected by the ultrasonic sensor, the displacement information of the unwinding unit 200 is the position difference information between the edge of the metal foil detected by the unwinding ultrasonic sensor 26 and its preset value, and the displacement information of the winding unit 300 is the position difference information between the edge of the pole piece detected by the winding ultrasonic sensor 38 and its preset value; 2) The control center performs fitting calculations on the received signals based on the neural network algorithm: for roll gap control, the roll gap 10 displacement information collected by the roll gap displacement sensor 17, the double rod position information of the hydraulic cylinder 13, and the angle information of the drive motor of the screw wedge assembly 16 are fitted and calculated; for belt speed control, the rotation speed of each roller or shaft is calculated; for tension control, the tension information of the tension sensor is calculated; for deviation correction control, the displacement information of the ultrasonic sensor is calculated; 3) The execution instructions calculated by the control center are sent to the corresponding execution components: the roll gap control execution instruction is sent to the driving motor of the hydraulic cylinder 13 and / or the screw wedge assembly 16 of the calender unit 100; the belt speed control execution instruction is sent to the motor driver of each roller or shaft of each unit; the tension control execution instruction of the unwinding unit 200 is sent to the tension swing roller 24, and the tension control execution instruction of the winding unit 300 is sent to the first swing roller assembly 33 and / or the second swing roller assembly 36; the deviation correction control execution instruction of the unwinding unit 200 is sent to the unwinding deviation correction assembly 25, and the deviation correction control execution instruction of the winding unit 300 is sent to the winding deviation correction assembly 37; 4) Each execution component is adjusted according to the received execution instruction: the hydraulic cylinder 13 and / or the screw wedge assembly 16 of the calender unit 100 adjusts the roll gap 10 according to the execution instruction. The hydraulic cylinder 13 can reduce the roll gap 10, and the screw wedge assembly 16 can enlarge the roll gap 10 to ensure the stability of the roll gap 10, thereby ensuring the compaction density and thickness uniformity of the diaphragm; the motor driver of each roller or shaft of each unit adjusts the speed of each motor in real time according to the execution instruction to ensure the speed between each motor Matching; the tension swing roller 24 of the unwinding unit 200, the first swing roller assembly 33 and / or the second swing roller assembly 36 of the winding unit 300 adjust the torque of their swing roller motors according to the execution instruction, thereby adjusting the unwinding tension of the metal foil and the winding tension of the pole piece; the unwinding correction assembly 25 of the unwinding unit 200 and the winding correction assembly 37 of the winding unit 300 adjust the torsion angle of their rollers according to the execution instruction, thereby correcting the position of the metal foil and the pole piece to ensure that the position of the metal foil and the pole piece is not deviated.

[0046] The control center of the calendering control system uses the DRNN (lightweight deep recurrent neural network) neural network algorithm to fit or analyze the signal to obtain lightweight output. At the same time, the expert knowledge base and historical data fitting are introduced to establish a linear regression model of lightweight output, expert knowledge base output and historical data fitting output. The linear regression formula of the three is: , k1, k2, k3 are the weights of the three outputs of lightweight output O(x), expert knowledge base P(x), and historical data fitting Q(x), respectively. b is a constant. In this embodiment, k1 is 0.4, k2 is 0.3, and k3 is 0.3. The calendering control system is mainly based on a deep recurrent neural network. At the same time, an expert knowledge base and historical data fitting are introduced, and a relatively large proportion of weights are given to them (40%, 30%, and 30% respectively) to ensure the stable operation of the equipment, improve the accuracy of control, and reduce the control deviation caused by insufficient total database data. Based on this, a more accurate and reasonable control amount is obtained. The neural network structure includes an input layer, a hidden layer, and an output layer, and the neural network has an activation function.

[0047] Figure 8 The control flow chart of the control center of the calendering control system is shown. The control center adopts a neural network algorithm combined with a linear regression model and a PID controller. The control quantity obtained by the neural network algorithm is used as the input vector of the PID controller. The output quantity calculated by the PID controller is output to the corresponding actuator to adjust the corresponding components.

[0048] Before the neural network model is embedded in the control system, it needs to be trained to learn the mapping function X→Y, where X is the input vector and Y is the output vector. The neural network model uses historical data for expert training, and the historical data includes the roller gap information, motor speed, diaphragm and pole piece tension information, swing roller angle, position and other key parameter data required by the control system. The collected information is preprocessed before being input into the neural network model. The preprocessing includes noise removal, data normalization and other operations, which is conducive to improving the training effect of the neural network model. The neural network model can also be updated and adjusted regularly, and retrained when the working conditions change to adapt to changes in the working environment and the evolution of the system. The neural network model can also store and self-learn multiple processes to obtain flexible self-regulation functions. During the training process of the neural network model, optimization algorithms such as gradient descent, Adam and other algorithms can be used to continuously adjust the weights and biases of the neural network to minimize the error value between the predicted output and the actual output, and improve the accuracy and stability of the predicted output.

[0049] After the neural network model is embedded in the control system, the specific control method of the control center is as follows: 1) The neural network model starts running; 2) Initialization of each actuator: the hydraulic cylinder 13 and the screw wedge assembly 16 are initialized to the initial position; each motor driver is initialized to a constant speed; the swing roller motor of each swing roller assembly is initialized to a constant torque; the unwinding correction assembly 25 and the winding correction assembly 37 are initialized to the initial position; the initial position of each actuator is preset during installation; 3) The neural network model predicts the initial control amount of the actuator according to the difference between the initialization actual parameter value and the set parameter value of each actuator; 4) The actual parameter values ​​detected by each detection component in real time are input into the neural network model as lightweight input vectors; For roll gap control, the input vector is the actual displacement vector of each roll gap displacement sensor 17 and the offline detected film thickness. After the roll gap parameters of each roll gap displacement sensor 17 are input, priority screening is required. The screening logic is: along the main conveying direction of the film from front to back, the priority gradually increases, that is, the closer the roll gap 10 to the end of calendering, the more priority it should be adjusted, which can reduce the impact of the adjustment of a certain roll gap 10 on other roll gaps 10, making the adjustment more accurate and efficient; For belt speed control, the input vector is the speed of each motor; For tension control, the input vectors are the swing roller angle of the swing roller assembly (actual angle and set angle), the speed and acceleration of the swing roller motor); For the deviation correction control, the input vector is the displacement of the metal foil and the pole piece; 5) The neural network model calculates the lightweight output vector; For roll gap control, the output vector is the extension and retraction amount of the double output rods of the hydraulic cylinder 13; For belt speed control, the output vector is the speed of the motor of the reference roller; For tension control, the output vector is the speed and acceleration of the swing roller motor of the swing roller assembly; For the deflection control, the output vector is the twisting angle of the roller of the deflection correction component; 6) The lightweight output vector, the expert knowledge base output, and the historical data fitting output are used to establish a linear regression model. The three are combined to obtain the linear regression output. The parameters of the linear regression output are the same as those of the lightweight output vector. 7) The linear regression output is input into the PID controller, which adjusts the output in real time according to the output vector (predicted control quantity) of the neural network model; The adjustment function of the PID controller is: u'(t) = u(t) + f(Y) (where u(t) is usually a function based on the error e(t), including proportional, integral and differential terms. The error e(t) refers to the difference between the actual parameter value and the set parameter value; f(Y) is an empirical adjustment function).

[0050] 8) Determine whether the signal is in a stable state based on the values ​​detected by each detection component: if it is stable, execute and complete the control; if it is unstable, return to the starting point and restart the operation until the signal is stable.

[0051] The calendering control system of the present invention introduces a neural network algorithm in combination with a PID controller. At the same time, the neural network algorithm also combines the output of the expert knowledge base and the historical data fitting output to construct a linear regression model, and the linear regression output is obtained and then input into the PID controller. The PID controller automatically adjusts the executed control amount in real time according to the linear regression output, and can more accurately control the roller gap 10, belt speed, tension and correction. When facing nonlinear, time-varying or multi-variable systems, complex dynamic performance and multi-variable coupling can also be accurately processed, with better adaptability and robustness, thereby improving the control performance of the system, improving the stability and accuracy of the system, and also improving the production efficiency and product quality of the calender.

[0052] like Fig. 9 As shown, in the present invention, a discrete time system is used in the PID controller. The discrete time system can suppress noise and interference through digital filtering and other technologies. Compared with the continuous time system, it is more robust and suitable for real-time control applications. Complex control strategies can be implemented through easy algorithms. In the present invention, PID uses the Euler transform discretization control algorithm: where P is the proportional band. The smaller P is, the larger the error signal (e(t)) is.P The larger the value, the greater the set value. I represents the integral part of the control algorithm. This part is to eliminate the "residual error". Without this part, the set value and the process value may be different even in the stable state. Finally, D represents the differential part of the algorithm. This part has two goals. It makes the system more flexible to sudden changes or disturbances in the set value, but most importantly, it helps to stabilize the system.

[0053] The transfer function of PID is:

[0054] Where s is the Laplace variable (s=α+jω), K p is the amplification factor, T I is the integration time, T D is the derivative time, {K p , T I , T D} is the parameter set of PID, which depends on the physical properties of the process.

[0055] The adjustment function of PID is:

[0056] The integral of e(t) can be approximated as a rectangular sum, that is

[0057] Among them, e'(t) can be approximated as a straight line, that is,

[0058] Therefore, when using the Euler transform discrete control algorithm, the PID gets the following expression:

[0059] Taking the roller gap control of the single-sided double-sided electrode sheet forming composite integrated machine of the first embodiment as an example, the detailed control process is as follows: When the calendering unit 100 is installed, the calendering rollers 11 are tangent to each other, the calendering rollers 11 and the backing rollers 12 are tangent to each other, and the roller gaps 101-107 are debugged according to the initialization position; the thickness of the film produced by the calendering unit 100 is detected offline, that is, each time the calendering unit 100 starts to run stably, part of the film will be intercepted for weighing and thickness measurement, and its thickness and surface density will be tested. After the test, the thickness data will be input into the control center. At the same time, the control center will convert the thickness information into x(t) and input it into DRNN. After deep cycle calculation, DRNN outputs the parameter set {K P1 ,T I1 ,T D1 ,e1(t)}, and the expert knowledge base and historical data fitting formula will also output the parameter set {K P2,T I2 ,T D2 ,e2(t)} and {K P3 ,T I3 ,T D3 ,e3(t)}, the three parameter sets are calculated by the linear regression model and the output parameter set {K P ,T I ,T D ,e(t)}.

[0060] Parameter set {K P ,T I ,T D ,e(t)} after output, it is necessary to compare the sizes of the adjusted roll gaps 101-107 to satisfy the relationship of roll gap 101>roll gap 102≥roll gap 104≥roll gap 103>roll gap 105>roll gap 106>roll gap 107. Through the optimal control theory, priority control is performed against the total direction of material travel (i.e. from roll gap 101 to roll gap 107, the priority level increases successively, and the priority level of the subsequent roll gap 10 is higher than the priority level of the previous roll gap). If the conditions are not met, return to DRNN for recalculation. If this size order relationship is met, proceed to the next step.

[0061] The next step is to satisfy the size relationship of one or more parameter sets {K P ,T I ,T D ,e(t)} is output to one or more PIDs that control different roll gaps. After the PID is calculated through a discrete algorithm, a displacement vector instruction is issued to the servo motor of the screw wedge assembly 16 and the servo hydraulic valve group of the hydraulic cylinder 13. The servo motor of the screw wedge assembly 16 and the hydraulic cylinder 13 operate synchronously to quickly and accurately adjust the roll gap 10. After the execution of the movement is completed, the roll gap displacement sensor 17 feeds back the displacement of each roll gap to the PID and DRNN to ensure the accurate completion of the execution process. If it is accurately completed, the servo motor of the screw wedge assembly 16 and the hydraulic cylinder 13 stop moving and maintain the current state.

[0062] After the adjustment is completed, the offline detection method is continued to be used to detect the thickness and surface density of the produced diaphragm. If the offline detected thickness information meets the fluctuation range (within plus or minus 5%), the roller gaps are fixed. If it does not meet the fluctuation range (exceeding plus or minus 5%), it is continued to be input into DRNN for calculation. The above steps are repeated until the thickness of the produced diaphragm is within the fluctuation range (±5%). At this time, the single roller gap control process is completed and each execution component maintains the status quo.

[0063] The above description is an explanation of the present invention, not a limitation of the present invention. The present invention may be modified in any form without violating the spirit of the present invention.

Claims

1. A dry electrode forming control method based on AI algorithm, characterized in that: The calendering control system adjusts each roll gap (10) according to the thickness of the finished film, the displacement information of the roll gap (10), the position information of the double rods of the hydraulic cylinder (13), and the angle information of the drive motor of the screw wedge assembly (16); The control center of the calendering control system uses the DRNN neural network algorithm to calculate the signal to obtain the lightweight output. The lightweight output, expert knowledge base output and historical data fitting output are used to establish a linear regression model. The linear regression formula of the three is: , k1, k2, and k3 are the weights of the three outputs: lightweight output O, expert knowledge base P, and historical data fitting Q. b is a constant. The control quantity calculated by the linear regression model is used as the input vector of the PID controller. The output quantity calculated by the PID controller is output to the corresponding actuator to adjust the corresponding components.

2. The dry-process electrode forming control method based on AI algorithm according to claim 1 is characterized in that: The adjustment priority of each roller gap (10) is as follows: along the general traveling direction of the material, the priority of the subsequent roller gap (10) is higher than the priority of the preceding roller gap.

3. The dry electrode forming control method based on AI algorithm according to claim 1 is characterized in that: The weight values ​​of the linear regression formula are k1, 0.4, k2, and k3, 0.

3.

4. The dry electrode forming control method based on AI algorithm according to claim 1 is characterized in that: After the roller gaps (10) are adjusted, the following conditions are met: except for the first and last roller gaps (10), one of the remaining roller gaps (10) is greater than or equal to the previous roller gap (10).

5. The dry electrode forming control method based on AI algorithm according to claim 1 is characterized in that: The control process of the roll gap includes: the control center converts and calculates the offline detection data of the film produced by the calender unit (100), and outputs a parameter set {K P1 ,T I1 ,T D1 ,e1(t)}, expert knowledge base and historical data fitting formula output parameter set {K P2 ,T I2 ,T D2 ,e2(t)} and {K P3 ,T I3 ,T D3 ,e3(t)}, the three parameter sets are calculated by the linear regression model and the output parameter set {K P ,T I ,T D ,e(t)}; one or more parameter sets {K P ,T I ,T D ,e(t)} is output to one or more PIDs that control different roll gaps. After the PID is calculated by a discrete algorithm, a displacement vector instruction is issued to the servo motor of the screw wedge assembly (16) and the servo hydraulic valve group of the hydraulic cylinder (13). The servo motor of the screw wedge assembly (16) and the hydraulic cylinder (13) operate synchronously to adjust the roll gap (10).

6. The dry-process electrode forming control method based on AI algorithm according to claim 5 is characterized in that: After the roller gap (10) is adjusted, the thickness and surface density of the diaphragm are tested using an offline testing method. If the offline tested thickness is within the range of ±5%, the roller gaps (10) are fixed. If it exceeds the range of ±5%, the calculation is returned and the adjustment steps are repeated until the thickness of the diaphragm is within the range of ±5%.

7. The dry electrode forming control method based on AI algorithm according to claim 1 is characterized in that: The PID controller uses a discrete-time system; the transfer function of the PID is , s is the Laplace variable (s=α+jω), K p is the amplification factor, T I is the integration time, T D is the derivative time; The adjustment function of PID is , the integral of e(t) is approximated by the rectangular sum , e'(t) is approximately a straight line , the control expression of PID is .

8. The dry-process pole piece forming control method based on AI algorithm according to claim 1 is characterized in that: The calendering control system adjusts the speed of the servo motor according to the speed information of each servo motor, adjusts the unwinding tension of the metal foil and the winding tension of the pole piece according to the tension information collected by the tension sensor, and corrects the position of the metal foil and the pole piece according to the displacement information detected by the ultrasonic sensor.

9. A pole piece forming composite integrated machine, characterized in that: The control method for dry electrode forming based on the AI ​​algorithm as described in claim 1 is adopted for control, comprising at least one calendering unit (100), one unwinding unit (200) and one winding unit (300), wherein the unwinding unit (200) and the winding unit (300) are arranged on the electrode composite forming side of the calendering unit (100); the calendering unit (100) comprises a plurality of calendering rollers (11) arranged in sequence along the main conveying direction X, and a roller gap (10) is provided between two adjacent calendering rollers (11).

10. The pole piece forming composite integrated machine according to claim 9, characterized in that: The roller gaps (10) between adjacent calendering rollers (11) gradually decrease from front to back along the main conveying direction X, and except for the first and last roller gaps (10), one of the remaining roller gaps (10) is equal to the previous roller gap (10).

11. The pole piece forming composite integrated machine according to claim 9, characterized in that: A bearing seat (15) is correspondingly arranged on each calendering roller (11), and a screw wedge assembly (16) is arranged between the bearing seats (15) corresponding to adjacent calendering rollers (11). The screw wedge assembly (16) cooperates with the bearing seat (15) via an inclined surface. The screw wedge assembly (16) moves axially along the calendering roller (11) to adjust the width of the roller gap (10) between the two calendering rollers (11); a roller gap displacement sensor (17) is also arranged between the bearing seats (15) corresponding to adjacent calendering rollers (11).

12. The pole piece forming composite integrated machine according to claim 9, characterized in that: The first calendering roller (11) is provided with a back roller (12) on the side opposite to the main conveying direction X, and the back roller (12) is closely fitted with the first calendering roller (11). The back roller (12) is provided with a hydraulic cylinder (13) on the side opposite to the main conveying direction X, and the last calendering roller (11) is provided with a hydraulic cylinder (13) on the side opposite to the main conveying direction X, and the last calendering roller (11) is provided with a hydraulic cylinder (13) on the side in the same direction as the main conveying direction X. The hydraulic cylinder (13) controls the extension and retraction of its double rods through a valve group to control the displacement of the back roller (12) or the last calendering roller (11).

13. The pole piece forming composite integrated machine according to claim 9, characterized in that: The roller diameter of the back roller (12) and the roller diameter of the last two calender rollers (11) are both larger than the roller diameters of the other calender rollers (11); each calender roller (11) is individually connected to a motor (14) and driven by an independent motor (14); the rotation speed of each calender roller (11) gradually increases from front to back along the main conveying direction X.

14. The pole piece forming composite integrated machine according to claim 9, characterized in that: The roller diameters of the first and second calender rollers (11) close to the back roller (12) are smaller than the roller diameters of the other calender rollers (11) and the back roller (12).

15. The pole piece forming composite integrated machine according to claim 9, characterized in that: Each calendering roller (11) can be independently adjusted in a direction perpendicular to the main conveying direction X; the axes of each calendering roller (11) are located in the same plane or the axes of each calendering roller (11) are arranged in a staggered manner. When arranged in a staggered manner, an extension line of a line connecting the axes of each pair of adjacent calendering rollers (11) intersects at a point with an extension line of a line connecting the axes of another pair of adjacent calendering rollers (11); at least one calendering roller (11) is a heatable roller, and the heating temperature is between 150°C and 200°C.

16. The pole piece forming composite integrated machine according to claim 9, characterized in that: The unwinding unit (200) is provided with a metal foil unwinding shaft (21), and between the metal foil unwinding shaft (21) and the roller gap (10) between the last two calendering rollers (11) of the calendering unit (100), a tape connection platform (27), an unwinding tension sensor (23), a tension swing roller (24), an unwinding deviation correction component (25), and an unwinding ultrasonic sensor (26) are arranged in sequence along the unwinding direction of the metal foil, and unwinding guide rollers (28) are respectively arranged between adjacent components.

17. The pole piece forming composite integrated machine according to claim 9, characterized in that: The unwinding unit (200) is provided with a film unwinding shaft (22), and a plurality of unwinding guide rollers (28) are arranged between the film unwinding shaft (22) and the roller gap (10) between the last two calendering rollers (11) of the calendering unit (100).

18. The pole piece forming composite integrated machine according to claim 9, characterized in that: The winding unit (300) is provided with a winding shaft (31), and between the winding shaft (31) and the roller gap (10) between the last two calender rollers (11) of the calender unit (100), a first winding tension sensor (32), a first swing roller assembly (33), a tension isolation assembly (34), a second winding tension sensor (35), a second swing roller assembly (36), a winding deviation correction assembly (37) and a winding ultrasonic sensor (38) are arranged in sequence along the winding direction of the pole piece, and winding guide rollers (39) are respectively arranged between adjacent components.

Images