Filter-based model-free adaptive iterative learning injection speed control method

Abstract

The application provides a filter-based model-free adaptive iterative learning injection speed control method, which comprises the following steps: modeling an injection process as an actual output model containing a measured disturbance; constructing a control law with a filter, calculating a control input, sending the control input to an injection system, and collecting a measured output after operation; if a sampling time is less than a maximum sampling time, updating the measured output and recalculating the control input; otherwise, performing an end judgment; if a measurement error is greater than an error threshold, entering a next iteration to recalculate the control input; otherwise, taking the current control input as a control input of completed learning. The application takes the measured disturbance into the model, so that the model can more truly reflect the injection system; in addition, the application filters high-frequency disturbances in the measurement error through the filter, so that the high-frequency disturbances are more close to the real deviation of the injection speed, and the tracking precision of the injection speed is significantly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of injection molding, in particular to a filter-based model-free adaptive iterative learning injection speed control method, system, device and storage medium. BACKGROUND

[0002] Injection molding, as an important plastic processing and molding process, melts solid plastic into a molten flow state, then injects it into a mold, and cools to form a plastic product with a specific shape and meet specific performance requirements. As a typical intermittent production process, the injection molding process consists of multiple stages, each of which is completed within a limited time and produces plastic products in batches periodically. During the entire injection molding process, precise control of multiple parameters is involved, such as barrel temperature, injection speed, nozzle pressure, and hydraulic pressure, among which the injection speed is particularly critical as it directly affects the quality and production efficiency of plastic products. Therefore, precise control of the injection speed is crucial to improving product quality and production efficiency.

[0003] In actual injection molding production, the traditional PID (Proportional-Integral-Derivative) control, due to its simple structure and easy engineering implementation, has been widely used in the control of injection speed. However, this traditional PID method has weak anti-interference ability when facing high-frequency disturbances in the injection molding process: for example, high-frequency disturbances such as electronic thermal noise of sensors, pressure pulsation caused by high-frequency reciprocation of hydraulic pump plungers, and high-frequency valve core tremor of flow valves; since the parameters of the traditional PID control are mostly based on static working condition setting, the response to such millisecond-level high-frequency disturbances is lagging, and it is difficult to correct their impact in real time, resulting in frequent deviation of the system output from the desired injection speed trajectory, and further affecting the consistency and qualification rate of injection molded products.

[0004] Therefore, how to design a filter-based model-free adaptive iterative learning injection speed control method, system, device and storage medium that can effectively resist high-frequency disturbances in the injection molding process is a technical problem that has not been solved in the prior art. SUMMARY

[0005] Therefore, the technical problem to be solved by the present application is to overcome the technical defect that the traditional PID control has weak anti-interference ability when facing high-frequency disturbances in the injection molding process, and to provide a filter-based model-free adaptive iterative learning injection speed control method, system, device and storage medium that can effectively resist high-frequency disturbances in the injection molding process.

[0006] The present application mainly includes the following aspects:

[0007] In a first aspect, the present application provides a filter-based model-free adaptive iterative learning injection speed control method, which comprises:

[0008] Step 1: obtaining the maximum sampling time of a single iteration , pseudo partial derivative initial value , initial control input of system operation and initial system output data ;

[0009] wherein, is the control input, representing the flow of the hydraulic system during the injection process at the th iteration, time; is the system output, representing the injection speed during the injection process at the th iteration, time; is the sampling time, ; is the iteration number, ;

[0010] Step 2: modeling the injection process as a nonlinear system model with iteration characteristics based on the input and output data;

[0011] Step 3: linearizing the nonlinear system model with iteration characteristics in step 2 on the iteration axis by introducing a pseudo partial derivative , to obtain a compact format dynamic linearization model;

[0012] Step 4: deriving the nonlinear system model with iteration characteristics in step 2 into a compact format dynamic linearization output model based on the compact format dynamic linearization model in step 3;

[0013] Step 5: extending the compact format dynamic linearization output model in step 4 into an actual output model with measurement disturbance by introducing a measurement disturbance :

[0014] ;

[0015] wherein, is the measurement output with measurement disturbance at the th iteration, time; the measurement disturbance is a random signal, and the statistical characteristics are , wherein is a mathematical expectation factor, is a variance factor, and the measurement disturbance is related to the sampling time , the iteration number , the measurement output , and the system output the control input and the pseudo partial derivative are all irrelevant, the initial disturbance value of the measurement disturbance is 0;

[0016] Step 6: based on the expected output and the measurement output , the measurement error is calculated;

[0017] Step 7: a low-pass filter is constructed, and the measurement error is processed into an error signal by the low-pass filter:

[0018] ;

[0019] wherein, the measurement error of step 6; is the low-pass filter transfer function, used to filter out high-frequency disturbances in the measurement error ;

[0020] wherein, the low-pass filter transfer function is:

[0021] ;

[0022] wherein, is a lead factor; is a filter parameter; is a filter order; filter for satisfies ;

[0023] Step 8: a pseudo partial derivative estimation algorithm is constructed, and a pseudo partial derivative estimation value is calculated;

[0024] Step 9: based on the error signal of step 7 and the pseudo partial derivative estimation value of step 8, a control law with filter is constructed, the control input is calculated, the control input is sent to the injection molding system, and the measurement output after running is collected;

[0025] wherein, the control law with filter is:

[0026] ;

[0027] wherein, is a step factor, for making the control law with filter more general; is a weight factor;

[0028] Step 10: comparing the sampling time with the maximum sampling time of the single iteration , if , returning to step 6 and updating the measurement output of step 6 to the post-run measurement output collected in step 9; otherwise, executing step 11;

[0029] Step 11: collecting the measurement errors of all times within the current iteration, comparing the absolute value of the maximum measurement error with an error threshold , if , returning to step 6, otherwise sending the final control input to the injection molding system and ending the iterative learning process.

[0030] According to an embodiment of the present application, the nonlinear system model with iterative characteristics modeled in step 2 comprises:

[0031] ;

[0032] wherein, is the order of the output variable, is the order of the input variable.

[0033] According to an embodiment of the present application, the tight format dynamic linearization model established in step 3 comprises:

[0034] ;

[0035] ;

[0036] ;

[0037] wherein, and respectively represent the control input change amount and the system output change amount under the running of the adjacent batch of the system; for the arbitrary sampling time and the iteration number , both satisfy , wherein, is a constant; all pseudo partial derivatives have the same sign, i.e. , wherein, is a constant.

[0038] According to one embodiment of the present application, the tight-format dynamic linearization output model derived in step 4 comprises:

[0039] .

[0040] According to one embodiment of the present application, the method for calculating the measurement error in step 6 comprises:

[0041] ;

[0042] wherein, is the expected output, representing the known optimal injection speed; is the measurement output at the kth iteration, .

[0043] According to one embodiment of the present application, the step of constructing the pseudo partial derivative estimation algorithm and calculating the pseudo partial derivative estimation value in step 8 comprises:

[0044] establishing a pseudo partial derivative estimation function to determine a quantitative index of estimation error; the pseudo partial derivative estimation function comprises:

[0045] ; wherein, is the objective function; is the weight coefficient; is the estimation value of the pseudo partial derivative; is the measurement output change, and the calculation formula is: ; is the control input change, and the calculation formula is: ;

[0046] based on the pseudo partial derivative estimation function and the optimal condition , the pseudo partial derivative estimation algorithm is obtained, and the pseudo partial derivative estimation value is calculated; the pseudo partial derivative estimation algorithm comprises:

[0047] ; wherein, is a step factor, for facilitating adjustment of the pseudo partial derivative and enhancing flexibility of the algorithm; is the weight coefficient;

[0048] a reset algorithm is established to ensure that the pseudo partial derivative estimation algorithm has good tracking performance; the reset algorithm comprises:

[0049] ;​

[0050] If or or ;

[0051] wherein, is the pseudo partial derivative initial value obtained in step 1 ; is a reset threshold value; is a sign function.

[0052] According to one embodiment of the present application, the step 9 of constructing a control law with a filter based on the error signal of step 7 and the pseudo partial derivative estimate of step 8 comprises:

[0053] establishing a control input target function:

[0054] ;

[0055] wherein, is a target function; is a weight factor;

[0056] based on the control input target function and an optimal condition , a control law is obtained: ;

[0057] wherein, is a step size factor, for making the control law more general; is a weight factor;

[0058] based on the control law, the error signal of step 7 and the pseudo partial derivative estimate of step 8 , the control law with a filter is established for calculating the control input .

[0059] In a second aspect, the embodiments of the present application also provide a filter-based model-free adaptive iterative learning injection speed control system, which comprises:

[0060] an acquisition module for acquiring the maximum sampling time , the pseudo partial derivative initial value , the initial control input , the initial system output data , the expected output and the measured output ;

[0061] a storage module for storing relevant data;

[0062] a computing module for calculating measurement error , pseudo partial derivative estimate , control input ; the computing module comprises a filtering processing unit for processing measurement error into error signal by a low-pass filter;

[0063] a comparison module for comparing sampling time with maximum sampling time of single iteration, and comparing absolute value of measurement error maximum value with error threshold value ;

[0064] an output module for sending final control input to the injection molding system.

[0065] In a third aspect, the embodiments of the present application further provide a computer device, which comprises at least one processor, and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the steps of the method.

[0066] In a fourth aspect, the embodiments of the present application further provide a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the method.

[0067] The technical scheme provided by the present application has the following advantages:

[0068] 1. The present application takes measurement disturbance into the model, so that the model can more truly reflect the injection molding system, and ensure that the control law designed based on the model can respond to the disturbance influence in a targeted manner, thereby guaranteeing the effectiveness of the control strategy in actual working conditions and avoiding the problem of error expansion or system instability caused by not considering the disturbance.

[0069] 2. The present application processes the measurement error into an error signal by a low-pass filter, filters out the high-frequency disturbance in the measurement error, so that the error signal is closer to the real deviation of the injection speed, and the control law constructed based on this can more accurately adjust the flow of the hydraulic system to correct the speed deviation, thereby significantly improving the tracking accuracy of the injection speed.

[0070] ​3. The filtered error signal of the application reduces the control input fluctuations caused by high-frequency interference, making the actions of the hydraulic system, injection screw, and other actuators more stable, enhancing the stability of the system during the key stages of the injection molding process, thus adapting to the nonlinear and repetitive characteristics of the injection molding process and ensuring the consistency of the quality of plastic products.

[0071] 4. The filter of the application can not only filter out high-frequency measurement disturbances caused by external environmental factors or the sensor itself, but also eliminate high-frequency signals caused by changes in system structure and parameters, effectively suppressing the adverse effects of high-frequency disturbances and achieving better tracking control effects.

[0072] 5. The model-free adaptive iterative learning control strategy used in the embodiments of the application does not rely on the accurate mathematical model of the injection molding process, but only relies on real-time system input and output data and an iterative learning mechanism to dynamically optimize the control strategy and adapt to the complex nonlinear characteristics of the injection molding process, thereby accurately controlling the injection speed.

[0073] 6. The model-free adaptive iterative learning control strategy used in the application does not rely on the accurate mathematical model of a specific system, so it is not only suitable for injection speed control in the injection molding process, but also can be extended to other dynamic systems with nonlinear and repetitive characteristics, and has good versatility.

[0074] In order to make the above-mentioned purposes, features and advantages of the application more obvious and easy to understand, the following preferred embodiments are described in detail below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0075] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the application, and therefore should not be considered as limiting the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0076] Figure 1 is the overall flowchart of the model-free adaptive iterative learning injection speed control method of the application based on the filter.

[0077] Figure 2 is the iterative running framework diagram of the application.

[0078] Figure 3 is the system architecture diagram of the application.

[0079] Figure 4 is a schematic diagram of the basic structure of the existing hydraulic screw injection molding machine.

[0080] Figure 5is a schematic diagram of the existing optimal injection speed curve.

[0081] Figure 6 is a schematic diagram of the comparison of the maximum tracking error curve in the iteration domain of the present application and the general model-free adaptive iterative learning control scheme.

[0082] Figure 7 is a schematic diagram of the comparison of the maximum tracking error curve in the iteration domain of the present application under different measurement noise variance conditions.

[0083] Figure 8 is a schematic diagram of the injection speed tracking curve under different control schemes.

[0084] Figure 9 is a schematic diagram of the injection speed tracking error situation of the present application and the PID control scheme. DETAILED DESCRIPTION

[0085] In order to make the objects, technical schemes and advantages of the embodiments of the present application clearer, the technical schemes in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of illustration and description, and are not used to limit the protection scope of the present application. In addition, it should be understood that the schematic drawings are not drawn according to the actual proportions. The flowchart shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can not be implemented in sequence, and the steps without logical context relationship can be reversed in sequence or implemented simultaneously. In addition, one or more other operations can be added to the flowchart or one or more operations can be removed from the flowchart under the guidance of the content of the present application.

[0086] In addition, the described embodiments are only some of the embodiments of the present application, not all the embodiments. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0087] The present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0088] EMBODIMENT

[0089] As shown in Figure 1 and Figure 2 The present embodiment provides a filter-based model-free adaptive iterative learning injection speed control method, which comprises the following steps:

[0090] Step 1: obtaining the maximum sampling time of a single iteration , pseudo partial derivative initial value , initial control input of system operation and initial system output data ;

[0091] wherein, is the control input, representing the flow of the hydraulic system during the injection process at the th iteration, time; is the system output, representing the injection speed during the injection process at the th iteration, time; is the sampling time, ; is the iteration number, ;

[0092] Step 2: modeling the injection process as a nonlinear system model with iteration characteristics based on the input and output data;

[0093] Step 3: linearizing the nonlinear system model with iteration characteristics in step 2 on the iteration axis by introducing a pseudo partial derivative to obtain a compact format dynamic linearization model;

[0094] Step 4: deriving the nonlinear system model with iteration characteristics in step 2 into a compact format dynamic linearization output model based on the compact format dynamic linearization model in step 3;

[0095] Step 5: extending the compact format dynamic linearization output model in step 4 into an actual output model with measurement disturbance by introducing a measurement disturbance :

[0096] ;

[0097] wherein, is the measurement output with measurement disturbance at the th iteration, time; the measurement disturbance is a random signal, and the statistical characteristics are , wherein is a mathematical expectation factor, is a variance factor, and the measurement disturbance is related to the sampling time , the iteration number , the measurement output , and the system output the control input and the pseudo partial derivative are all irrelevant, the initial disturbance value of the measurement disturbance is 0;

[0098] Step 6: based on the expected output and the measurement output , the measurement error is calculated;

[0099] Step 7: a low-pass filter is constructed, and the measurement error is processed into an error signal by the low-pass filter:

[0100] ;

[0101] wherein, the measurement error of the step 6; is the low-pass filter transfer function, used to filter out high-frequency disturbances in the measurement error ;

[0102] wherein, the low-pass filter transfer function is:

[0103] ;

[0104] wherein, is a lead factor; is a filter parameter; is a filter order; the filter satisfies ;

[0105] Step 8: a pseudo partial derivative estimation algorithm is constructed, and a pseudo partial derivative estimation value is calculated;

[0106] Step 9: based on the error signal of step 7 and the pseudo partial derivative estimation value of step 8, a control law with filter is constructed, the control input is calculated, the control input is sent to the injection molding system, and the measurement output after running is collected;

[0107] wherein, the control law with filter is:

[0108] ;

[0109] wherein,​ Step size factor This is used to make the control law with the filter more general; As a weighting factor;

[0110] Step 10: For the sampling time With the maximum sampling time of the single iteration If a comparison is made, Then return to step 6 and output the measurement from step 6. Updated to the measurement output acquired in step 9 after the run. Otherwise, proceed to step 11.

[0111] Step 11: Collect the measurement error at all times within this iteration, and calculate the absolute value of the maximum measurement error. With error threshold If a comparison is made, If so, return to step 6; otherwise, return to the final control input. The data is sent to the injection molding system, ending the iterative learning process.

[0112] The following details each step of the filter-based model-free adaptive iterative learning injection molding speed control method:

[0113] Step 1: Obtain the maximum sampling time in a single iteration initial value of pseudo-partial derivative Initial control inputs for system operation and initial system output data ;

[0114] in, To control the input, indicating the first Next iteration, The flow rate of the hydraulic system during the injection process; For system output, indicating the first... Next iteration, The injection speed during the injection process; Sampling time, ; For the number of iterations, ;

[0115] Here, the maximum sampling time in a single iteration The initial value of the pseudo-partial derivative depends on the specific system conditions. The initial control input is 10 during the first iteration. The initial system output data is 0. It is 0.

[0116] It should be noted that, asFigure 4 As shown in the figure, the basic structure of the hydraulic screw injection molding machine includes a clamping unit, an injection unit, a power unit and a control unit; the injection unit includes a plasticizing device, a screw driving device, an injection device, a measuring device, an injection seat, a frame and a barrel feeding device; the injection device includes a cylinder, a screw and a nozzle; during injection, hydraulic oil is injected into the cylinder to generate pressure to push the screw to press the melt in the front part of the barrel, so that the melt enters the mold cavity through the nozzle.

[0117] Based on the structure of the hydraulic screw injection molding machine, the control input of the embodiment of the present application is the flow of the hydraulic system during the injection process, specifically the flow of the hydraulic oil injected into the cylinder; correspondingly, the system output of the embodiment of the present application is the injection speed during the injection process, specifically the speed of the melt when it is injected into the mold cavity through the nozzle, which can be measured by a speed sensor.

[0118] Step 2: based on the input and output data, modeling the injection process as a nonlinear system model with iterative characteristics;

[0119] In one possible implementation, the nonlinear system model with iterative characteristics modeled in step 2 includes:

[0120] ;

[0121] wherein, is the order of the output variable, is the order of the input variable.

[0122] It should be noted that at the beginning of the injection molding production process, the mold is first closed, the movable mold of the mold is closed with the fixed mold, and the injection seat table is moved forward, so that the nozzle at the front end of the barrel contacts the main sprue of the mold; after the mold is closed and the nozzle is pressed against the main sprue, the injection program starts: the hydraulic system provides hydraulic oil to the injection cylinder to push the screw to move forward, and the high polymer melt at the head of the screw is pushed by the screw to pass through the nozzle, the injection channel, the flow channel, the gate, and finally enters the mold cavity; after the injection program ends, the pressure maintaining stage begins: in order to prevent the melt in the mold cavity from flowing back due to the action of the reverse pressure gradient, and to compensate for the shrinkage of the plastic material due to cooling and solidification, the injection nozzle must maintain a certain pressure to push the melt into the mold cavity; when the melt in the mold cavity cools to the point where it cannot flow back, the cooling stage begins, and the plastic product is further cooled and shaped in the mold cavity; at the same time as the cooling stage is carried out, the system enters the plasticizing stage: the hydraulic motor drives the screw to rotate, and the material is transported forward along the screw groove under the action of friction, and at the same time the material begins to plasticize and melt under the action of the barrel heating ring, and changes into a viscous fluid stored in the storage chamber in front of the screw, preparing for the next injection; after the plasticizing stage and the cooling stage end, the mold is opened, the ejection device is connected to make the product fall off, and the injection molding process ends.

[0123] Wherein, the injection phase can be represented by the model constructed by the following equation group:

[0124] ;

[0125] ;

[0126] ;

[0127] ;

[0128] Wherein, is the cross-sectional area of the injection cylinder, is the cross-sectional area of the barrel, is the volume of the injection rod, is the volume of the material in the barrel, is the injection speed, is the flow of the hydraulic system, is the bulk modulus of the hydraulic fluid, is the bulk modulus of the nozzle material, is the injection cylinder pressure, is the nozzle pressure, is the nozzle radius, is the screw mass, is the injection position, is the power law index of material melting, is the initial length of the screw, is the radius ratio of the screw to the nozzle, is the shear rate the corresponding melt viscosity, is the average flow rate of the material.

[0129] Due to different working environments and measurement conditions, modeling in actual environment will be more complex, and it will be more difficult to construct a mathematical model that accurately reflects the real situation, therefore, the following nonlinear system model is constructed to represent the above injection phase model:

[0130] ;

[0131] Wherein, is the order of the output variable, is the order of the input variable; is a nonlinear function.

[0132] Since the injection molding process is repetitive, an iteration index can be introduced to represent the number of iterations of the system, so that the above nonlinear system model can be further modeled as a nonlinear system model with iteration characteristics:

[0133] .

[0134] The model-free adaptive iterative learning control strategy adopted by the embodiment of the application does not need to rely on an accurate mathematical model of the injection molding process, but only relies on real-time system input and output data and an iterative learning mechanism, so as to dynamically optimize a control strategy, adapt to complex nonlinear characteristics in the injection molding process, and thus precisely control the injection speed.

[0135] Similarly, since the embodiment of the application does not rely on an accurate mathematical model of a specific system, it is not only applicable to injection speed control of the injection molding process, but also can be extended to other dynamic systems with nonlinear and repetitive characteristics, and has good universality.

[0136] Step 3: introducing pseudo partial derivatives linearizing the nonlinear system model with the iterative characteristics in step 2 on an iteration axis to obtain a compact format dynamic linearization model;

[0137] In a possible implementation, the compact format dynamic linearization model established in step 3 includes:

[0138] ;

[0139] ;

[0140] ;

[0141] wherein, and respectively represent a control input change amount and a system output change amount under running of adjacent batches of the system; for the arbitrary sampling time and the iteration number , both satisfy , wherein, is a constant; all pseudo partial derivatives symbols are consistent, that is, , wherein, is a constant.

[0142] Here, the derivation logic of the compact format dynamic linearization model established in step 3 is as follows:

[0143] The nonlinear system model with the iterative characteristics satisfies the assumptions of the compact format dynamic linearization method:

[0144] Assumption 1: the partial derivative of the control input is continuous, that is, , is a positive number.

[0145] Assumption 2: The nonlinear system model with iterative characteristics satisfies the generalized Lipschitz condition on the iteration axis, i.e., for , and have:

[0146] ;

[0147] wherein , and is a constant; ; .

[0148] When the nonlinear system model with iterative characteristics satisfies the assumption 1 and the assumption 2, if , there is a pseudo partial derivative (PPD) to make the injection process system represented as a compact format dynamic linearization model:

[0149] ;

[0150] Step 4: Based on the compact format dynamic linearization model of step 3, the nonlinear system model with iterative characteristics of step 2 is derived into a compact format dynamic linearization output model;

[0151] In one possible implementation, based on the compact format dynamic linearization model of step 3, the nonlinear system model with iterative characteristics of step 2 can be converted into a compact format dynamic linearization output model: .

[0152] Specifically: taking into , the following can be obtained:

[0153] .

[0154] Step 5: By introducing a measurement disturbance , the compact format dynamic linearization output model of step 4 is extended into an actual output model containing measurement disturbance:

[0155] ;

[0156] wherein is the measurement output containing measurement disturbance at the th iteration, moment; the measurement disturbance is a random signal, and the statistical characteristics are , , wherein is a mathematical expectation factor, is a variance factor, and the measurement disturbance With the sampling time The number of iterations The measurement output The system output The control input and the pseudo-partial derivatives All are uncorrelated, measurement disturbance initial disturbance value =0;

[0157] Here, the measurement disturbances are various high-frequency disturbances, which may be caused by external environmental factors or the sensor itself, or by high-frequency signals caused by changes in system structure or parameters. These disturbances are not simulated but real and can affect the sensor measurement results. The embodiments of this application take into account the impact of these measurement disturbances on the measurement results, and therefore incorporate measurement disturbances into the compact form dynamic linearization output model. Thus, the actual output model containing measurement perturbations was obtained:

[0158] .

[0159] This application incorporates measured disturbances into the model, enabling the model to more realistically reflect the injection molding system. This ensures that the control law designed based on the model can specifically address the impact of disturbances, guaranteeing the effectiveness of the control strategy in actual working conditions and avoiding error expansion or system instability caused by not considering disturbances.

[0160] Step 6: Based on the expected output and the measurement output Calculate the measurement error ;

[0161] In one possible implementation, the measurement error is calculated in step 6. The methods include:

[0162] ;

[0163] in, The desired output represents the known optimal injection speed; For the first Next iteration, The measured output at time [time].

[0164] It should be noted that the desired output of this embodiment is the optimal injection rate curve that dynamically changes over time (e.g., Figure 5The control target of the present embodiment is thus the precise "tracking" of the optimal injection speed profile, with the focus on dynamically following the preset speed trajectory, rather than simply adjusting the injection speed to a fixed value.

[0165] Here, the optimal injection speed profile is further described:

[0166] From the general industry cognition and practical experience, when the molten material can be injected into the mold cavity at a stable and uniform rate at a certain specific injection speed, the benefits achieved are multi-dimensional and significant. On the one hand, it can ensure that the injection molded products fully meet the stringent standards set by the injection molding production in terms of specification accuracy, color consistency, and appearance integrity, greatly reducing the proportion of defective products; on the other hand, it can effectively promote the overall production efficiency of the injection molding process, maximizing resource utilization and production capacity release. The injection speed corresponding to this time is defined as the optimal injection speed in the industry, which is equivalent to the expected injection speed.

[0167] In the injection molding process, the screw continuously pushes the melt into the mold cavity by rotating and advancing, which can be divided into four stages. The first stage is the high-speed pushing stage, in which the screw pushes the melt at a faster speed to reduce heat loss, maintain good flowability of the melt, reduce heat loss during transportation, and ensure that the melt maintains appropriate temperature and rheological properties to smoothly enter the mold cavity. The second stage is the mold cavity mouth deceleration stage, when the melt front reaches the mold cavity mouth, the screw pushing speed needs to be reduced in time to avoid splashing when the melt hits the mold cavity mouth at high speed, prevent material waste and uneven pressure inside the mold cavity, and ensure smooth injection molding process. The third stage is the acceleration filling stage, in which the screw needs to speed up the pushing speed to achieve rapid and full filling of the mold cavity, prevent the melt from cooling and affecting the flowability, overcome the problem of poor flowability caused by melt cooling, and ensure that the melt fills all corners of the mold cavity in a short time, ensuring the integrity of the product formation. The fourth stage is the second deceleration stage, in which the screw needs to reduce the pushing speed again, because if the injection speed is too fast, the melt injection amount will exceed the expected value, which may cause the product to be unqualified, such as generating flash affecting size accuracy and appearance quality, and may also cause internal structural defects to reduce mechanical properties, reducing the speed can accurately control the melt injection amount, and ensure that the product quality meets the standard.

[0168] Step 7: Construct a low-pass filter and pass the measurement error through the low-pass filter to process the measurement error as an error signal :

[0169] ;

[0170] wherein, the measurement error of step 6; is the low-pass filter transfer function for filtering out the measurement error High-frequency disturbances in the middle;

[0171] Wherein, the low-pass filter transfer function for:

[0172] ;

[0173] in, It is a forward shift factor; These are filter parameters; The filter order; the filter for satisfy ;

[0174] This application embodiment processes the measurement error into an error signal through a low-pass filter, filtering out high-frequency disturbances in the measurement error and making the error signal closer to the true deviation of the injection speed. Based on this, the control law can more accurately adjust the flow of the hydraulic system to correct the speed deviation, significantly improving the tracking accuracy of the injection speed.

[0175] The filtered error signal in this embodiment reduces control input fluctuations caused by high-frequency interference, making the operation of actuators such as hydraulic systems and injection screws smoother and enhancing the stability of the system in critical stages of the injection molding process. This adapts to the nonlinear and repeatable characteristics of the injection molding process and ensures the consistency of plastic product quality.

[0176] The filter in this application embodiment can not only filter out high-frequency measurement disturbances caused by external environmental factors or the sensor itself, but also eliminate high-frequency signals caused by changes in system structure and parameters, thereby effectively suppressing the adverse effects of high-frequency disturbances and achieving better tracking control performance.

[0177] Step 8: Construct a pseudo-partial derivative estimation algorithm and calculate the pseudo-partial derivative estimates. ;

[0178] In one possible implementation, step 8 involves constructing a pseudo-partial derivative estimation algorithm and calculating the pseudo-partial derivative estimates. The steps include the following:

[0179] S801: Establish a pseudo-partial derivative estimation function and determine the quantification index of the estimation error; the pseudo-partial derivative estimation function includes:

[0180] ;in, The objective function is... These are the weighting coefficients; This is an estimate of the pseudo-partial derivative; To measure the change in output, the calculation formula is: ; For controlling the input variation, the calculation formula is: ;

[0181] S802: Based on the pseudo partial derivative estimation function and the optimal condition , the pseudo partial derivative estimation algorithm is obtained, and the pseudo partial derivative estimation value is calculated ; the pseudo partial derivative estimation algorithm comprises:

[0182] ; wherein, is a step factor, , which is used for conveniently adjusting the pseudo partial derivative and enhancing the flexibility of the algorithm; is a weight coefficient;

[0183] S803: A reset algorithm is established, which is used for ensuring that the pseudo partial derivative estimation algorithm has good tracking performance; the reset algorithm comprises:

[0184] ;

[0185] If or or ;

[0186] wherein, is the pseudo partial derivative initial value obtained in step 1 ; is a reset threshold, specifically ; is a sign function.

[0187] Step 9: Based on the error signal of step 7 and the pseudo partial derivative estimation value of step 8, a control law with a filter is constructed, and the control input is calculated , the control input is sent to the injection molding system, and the measured output after running is collected

[0188] ;

[0189] ;

[0190] wherein, is a step factor, , which is used for making the control law with the filter more general; is a weight factor;

[0191] In one possible implementation, in the step 9, the control law with the filter is based on the error signal and the pseudo partial derivative estimate value of step 8 The step of constructing the control law with filter comprises:

[0192] S901: Establish a control input target function:

[0193] ;

[0194] wherein, is the target function; is a weight factor;

[0195] S902: Based on the control input target function and the optimal condition , obtain a control law: ;

[0196] wherein, is a step factor, for making the control law more general; is a weight factor;

[0197] S903: Based on the control law, the error signal of step 7 and the pseudo partial derivative estimate value of step 8 , establish the control law with filter for calculating the control input .

[0198] Step 10: Compare the sampling time with the maximum sampling time of the single iteration , if , return to step 6 and update the measurement output of step 6 to the measurement output after operation collected in step 9 ; otherwise, execute step 11;

[0199] Step 11: Collect the measurement errors at all times in the current iteration, compare the absolute value of the maximum measurement error with an error threshold , if , return to step 6, otherwise send the final control input to the injection molding system and end the iterative learning process.

[0200] The absolute value of the maximum measurement error can reflect the worst control accuracy in the current iteration; if the value is less than or equal to the error threshold , it means that the deviation at all times in the current iteration is within an acceptable range, avoiding product defects caused by the average error being qualified but the deviation at local times being out of limits; here, the error threshold Specifically .

[0201] As Figure 3 shown, based on the same application concept, the application embodiment further provides a filter-based model-free adaptive iterative learning injection speed control system, characterized in that it comprises an acquisition module, a storage module, a calculation module, a comparison module and an output module; the acquisition module is used to acquire the maximum sampling time , the pseudo partial derivative initial value , the initial control input , the initial system output data , the expected output and the measured output of a single iteration; the storage module is used to store relevant data; the calculation module is used to calculate the measurement error , the pseudo partial derivative estimation value and the control input ; the calculation module comprises a filter processing unit, which is used to process the measurement error into an error signal through a low-pass filter; the comparison module is used to compare the sampling time with the maximum sampling time of a single iteration, and compare the absolute value of the maximum measurement error with the error threshold ; the output module is used to send the final control input to the injection system.

[0202] Based on the same application concept, the application embodiment further provides a computer device, comprising at least one processor; and a memory communicatively connected with the at least one processor; wherein the memory stores instructions executable by the processor, and the instructions are executed by the at least one processor to enable the at least one processor to implement the above method when executing the instructions.

[0203] Based on the same application concept, the application embodiment further provides a computer-readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the above method.

[0204] The convergence is analyzed as follows:

[0205] 1. Prove that the error must converge:

[0206] The calculation formula of the tracking error is as follows: ; the formula (1) can be obtained by substituting the tight format dynamic linearization output model into the control law with the filter:

[0207] ;

[0208] By The formula (2) can be obtained:

[0209] ;

[0210] Wherein, is a constant.

[0211] Taking absolute value on both sides of the formula (1) and combining the formula (2), the formula (3) can be obtained:

[0212] ;

[0213] Wherein, In the limited time interval Converges to 0, when Approaches infinity, Is bounded, which means that when the injection molding system output contains a measurement disturbance Converges and is bounded; therefore, the embodiment of the application has strong robustness, and the injection molding process obtains good tracking output performance.

[0214] The above proof process proves from the algebraic convergence level that the embodiment of the application can make the tracking error of the injection molding process containing the measurement disturbance converge to zero along the iteration axis point by point, that is, it proves that the error must converge;

[0215] 2, prove that the convergence is not destroyed by random disturbance:

[0216] Taking On both sides of the formula (1), the formula (4) can be obtained:

[0217] ;

[0218] Therefore, the formula (5) can be obtained:

[0219] ;

[0220] Taking expectation on both ends of the formula (5), the formula (6) is obtained:

[0221] ;

[0222] Taking square on both sides of the formula (1), the formula (7) can be obtained:

[0223] ;

[0224] By As a low-pass filter, From the formula (2), it can be obtained that Therefore, for all There exists a positive constant Satisfy formula (8):

[0225] ;

[0226] From formula (7) and formula (8), formula (9) is obtained:

[0227] ;

[0228] Taking expectation on both ends of formula (9), formula (10) is obtained:

[0229] ;

[0230] Since ;

[0231] And Formula (11) is obtained:

[0232] ;

[0233] According to formula (10) and formula (11), formula (12) is obtained:

[0234] ;

[0235] From the above derivation And It can be obtained: even if there is a measurement disturbance, the mathematical expectation and variance of the error of the embodiments of the application can still converge to zero, which guarantees the statistical optimality and anti-disturbance robustness, that is, it is proved that "the convergence is not damaged by random disturbance".

[0236] It should be noted that for a low-pass filter, when This is only an idealized case; in actual application process, due to the influence of various factors, there will inevitably be a certain degree of filter error, although the error is relatively small; in view of this, the variance of the output error will not be equal to zero in a strict sense, but will tend to an extremely small positive number; but even if there is the above-mentioned actual situation, compared with the general model-free adaptive iterative learning control algorithm, the embodiments of the application still show significant advantages in comprehensive performance such as trajectory tracking accuracy and disturbance suppression ability.

[0237] So far, the convergence analysis is finished, and the simulation verification is carried out below:

[0238] It should be noted that in order to simplify the model of the injection stage, the following state variables are introduced: , , , , The model of the injection stage is simplified as the following state equation:

[0239] ;

[0240] Since the injection phase belongs to a nonlinear system, the model of the injection phase given by the embodiment of the present application is only used to generate input and output data. The remaining parameters in the model are known system parameters, and the parameter size and physical meaning represented by the parameters are shown in Table 1 below:

[0241]

[0242] Table 1

[0243] The following simulation experiment is carried out by means of the MATLAB platform, aiming to verify the effectiveness of the embodiment of the present application in the aspect of injection speed trajectory tracking. According to the state equation, the injection speed system of the injection molding machine belongs to a single-input single-output system; based on this, a mathematical model of the injection speed is constructed in Simulink; in addition, in order to simulate the measurement disturbance existing in the actual environment, white noise with a frequency range of 500-600 Hz is introduced into the system, so as to verify the robustness of the embodiment of the present application.

[0244] In the MATLAB simulation process, the controller parameters involved are set as follows:

[0245] 、 、 、 、 、 , initial control input , initial system output data , maximum sampling time of a single iteration , sampling time is , and the filter is set as:

[0246] ;

[0247] Among them, the filter satisfies under the condition of .

[0248] The results of the simulation verification are as follows:

[0249] Figure 6 The comparison of the maximum tracking error (maximum learning error) curve in the iterative domain between the embodiment of the present application (MFAILC scheme with filter) and the general model-free adaptive iterative learning control scheme (MFAILC scheme) is shown; from Figure 6As can be seen, after the 40th iteration of learning, the tracking error of the embodiment of this application is significantly reduced, and the convergence speed is faster than that of the general model-free adaptive iterative learning control scheme; therefore, the convergence performance of the embodiment of this application is better than that of the general model-free adaptive iterative learning control scheme.

[0250] Figure 7 This paper presents a comparison of the maximum tracking error curves in the iterative domain under different measurement noise variance conditions, based on embodiments of this application; Figure 7 It is understood that the smaller the measurement noise variance, the more significant the improvement in convergence performance of the embodiments of this application, and even if the measurement noise variance is large, the tracking error can still be ensured to converge on the iteration axis.

[0251] Figure 8 The injection speed tracking curves under different control schemes are shown. In injection molding systems, PID control is a common control method, and the PID controller structure is as follows: ,in , , ;Depend on Figure 8 It can be seen that after 50 iterations of learning, the embodiments of this application have significant advantages over general MFAILC schemes and PID control schemes in terms of injection speed tracking accuracy.

[0252] Figure 9 This paper demonstrates the injection speed tracking error of embodiments of this application and a PID control scheme; by Figure 9 As can be calculated, at the 50th iteration of learning, the average tracking error value of this application embodiment is The average error value of the tracking trajectory error of the injection molding system under PID control is Therefore, it can be seen that after 50 learning cycles, the average tracking error of the embodiment of this application is significantly smaller than the average tracking error under PID control, which fully demonstrates that the embodiment of this application has excellent tracking performance.

[0253] The above experimental results clearly demonstrate that the embodiments of this application can effectively suppress the adverse effects of measurement disturbances on injection speed, effectively reduce tracking deviation, and enable the injection speed to closely and stably follow the preset trajectory. This ensures that the injection molding process can maintain a high-precision operating state under complex interference, providing a strong guarantee for the high quality and stability of injection molding production.

[0254] In this embodiment, the computer program, when run by the processor, can also execute other machine-readable instructions to perform other methods as described in the embodiments. For details on the specific execution steps and principles, please refer to the description of the embodiments, which will not be repeated here.

[0255] In the embodiments of the present application, it should be understood that the disclosed apparatus and method can be implemented in other manners. The embodiments described above are merely exemplary, for example, the division of the units is only a logical function division, and there can be another division manner in actual implementation; for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, and electrical, mechanical or other forms.

[0256] The units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments.

[0257] In addition, each functional unit in the embodiments provided by the present application can be integrated into one processing unit, or each unit can exist physically, or two or more units can be integrated into one unit.

[0258] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, and various media that can store program codes.

[0259] It should be noted that: similar reference numerals and letters in the following drawings represent similar items, and therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. In addition, the terms "first", "second", "third" and the like are only used to distinguish descriptions, and cannot be understood as indicating or implying relative importance.

[0260] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present application, and are used to illustrate the technical solutions of the present application, but not to limit the same. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that any person skilled in the art can make modifications or easily think of changes to the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some of the technical features within the technical scope disclosed by the present application. The modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. All should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A filter-based model-free adaptive iterative learning injection molding speed control method, characterized in that, include: Step 1: Obtain the maximum sampling time in a single iteration initial value of pseudo-partial derivative Initial control inputs for system operation and initial system output data ; in, To control the input, indicating the first Next iteration, The flow rate of the hydraulic system during the injection process; For system output, indicating the first... Next iteration, The injection speed during the injection process; Sampling time, ; For the number of iterations, ; Step 2: Based on the input and output data, model the injection process as a nonlinear system model with iterative characteristics; Step 3: Introduce pseudo-partial derivatives The nonlinear system model with iterative characteristics described in step 2 is linearized on the iteration axis to obtain a compact dynamic linearized model. Step 4: Based on the compact dynamic linearization model described in Step 3, derive the nonlinear system model with iterative characteristics described in Step 2 into a compact dynamic linearization output model; Step 5: Introduce measurement disturbance The compact-form dynamic linearized output model described in step 4 is then extended to an actual output model that includes measurement perturbations: ； in, For the first Next iteration, At any given time, the measurement output includes the measurement disturbance; the measurement disturbance It is a random signal with the following statistical properties: , ,in For mathematical expectation factor, The variance factor is the measurement disturbance. With the sampling time The number of iterations The measurement output The system output The control input and the pseudo-partial derivatives All are uncorrelated, measurement disturbance initial disturbance value =0; Step 6: Based on the expected output and the measurement output Calculate the measurement error ; Step 7: Construct a low-pass filter and pass the measurement error through the low-pass filter. Processed into error signal : ； in, This refers to the measurement error in step 6; The transfer function of the low-pass filter is used to filter out the measurement error. High-frequency disturbances in the middle; Wherein, the low-pass filter transfer function for: ； in, It is a forward shift factor; These are filter parameters; The filter order; the filter for satisfy ; Step 8: Construct a pseudo-partial derivative estimation algorithm and calculate the pseudo-partial derivative estimates. ; Step 9: Based on the error signal described in Step 7 and the pseudo-partial derivative estimate in step 8 Construct a control law with a filter and calculate the control input. The control input The measured output is sent to the injection molding system and collected after the operation. ; The control law with the filter is as follows: ； in, Step size factor This is used to make the control law with the filter more general; As a weighting factor; Step 10: For the sampling time With the maximum sampling time of the single iteration If a comparison is made, Then return to step 6 and output the measurement from step 6. Updated to the measurement output acquired in step 9 after the run. Otherwise, proceed to step 11. Step 11: Collect the measurement error at all times within this iteration, and calculate the absolute value of the maximum measurement error. With error threshold If a comparison is made, If so, return to step 6; otherwise, return to the final control input. The data is sent to the injection molding system, ending the iterative learning process.

2. The filter-based model-free adaptive iterative learning injection molding speed control method according to claim 1, characterized in that, The nonlinear system models with iterative characteristics modeled in step 2 include: ； in, To output the order of the variable, The order of the input variable.

3. The filter-based model-free adaptive iterative learning injection molding speed control method according to claim 1, characterized in that, The compact-format dynamic linearization model established in step 3 includes: ； ； ； in, and These represent the changes in control input and system output respectively during adjacent batches of system operation; for any given sampling time... and the number of iterations All satisfy ,in, It is a constant; all pseudo-partial derivatives All symbols remain consistent, that is ,in, It is a constant.

4. The filter-based model-free adaptive iterative learning injection molding speed control method according to claim 3, characterized in that, The compact-format dynamic linearized output model derived in step 4 includes: 。 5. The filter-based model-free adaptive iterative learning injection molding speed control method according to claim 1, characterized in that, Step 6 involves calculating the measurement error. The methods include: ； in, The desired output represents the known optimal injection speed; For the first Next iteration, The measured output at time [time].

6. The filter-based model-free adaptive iterative learning injection molding speed control method according to claim 1, characterized in that, In step 8, a pseudo-partial derivative estimation algorithm is constructed, and the pseudo-partial derivative estimates are calculated. The steps include: A pseudo-partial derivative estimation function is established, and a quantitative index for the estimation error is determined; the pseudo-partial derivative estimation function includes: ;in, The objective function is... These are the weighting coefficients; This is an estimate of the pseudo-partial derivative; To measure the change in output, the calculation formula is: ; To control the amount of input variation, the calculation formula is as follows: ; Based on the pseudo-partial derivative estimation function and optimal conditions The pseudo-partial derivative estimation algorithm is obtained, and the pseudo-partial derivative estimates are calculated. The pseudo-partial derivative estimation algorithm includes: ;in, Step size factor This is used to easily adjust the pseudo-partial derivatives and enhance the flexibility of the algorithm; These are the weighting coefficients; A reset algorithm is established to ensure that the pseudo-partial derivative estimation algorithm has good tracking performance; the reset algorithm includes: ； like or or ; in, The initial value of the pseudo-partial derivative obtained in step 1 ; To reset the threshold; It is a symbolic function.

7. The filter-based model-free adaptive iterative learning injection molding speed control method according to claim 1, characterized in that, In step 9, the error signal from step 7 is used as a basis. and the pseudo-partial derivative estimate in step 8 The steps for constructing a control law with a filter include: Establish the objective function for controlling the input: ； in, The objective function is... As a weighting factor; Based on the control input objective function and optimal conditions Thus, the control law is obtained: ; in, Step size factor This is used to make the control law more general; As a weighting factor; Based on the control law and the error signal from step 7 and the pseudo-partial derivative estimate in step 8 Establish the control law with the filter, and use it to calculate the control input. .

8. A computer device, characterized in that, include: At least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to cause the at least one processor to perform the steps of the method according to any one of claims 1 to 7 when executing the instructions.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images