Two-axis drive and control integrated injection molding robot control system

Abstract

The present application discloses a two-axis drive-control integrated injection molding robot control system, which collects the timing data of the actual motor speed, and calculates the difference between the actual motor speed timing data and the theoretical speed to obtain the speed deviation of these timing data, and then introduces a data processing and analysis algorithm based on artificial intelligence and deep learning at the back end to analyze the motor speed deviation timing data, so as to learn and characterize the time-series significant aggregation semantic representation of the motor speed deviation, so as to automatically generate control instructions, thereby obtaining the recommended duty ratio of the PWN control signal. In this way, the time-series change semantics and aggregation representation information of the speed deviation can be automatically learned, and the duty cycle of the PWN control signal can be automatically adjusted adaptively. In this way, the defects brought by the traditional PID control can be avoided, so as to ensure the reliability and stability of the injection molding robot control on the basis of improving the control intelligence level.

Description

Technical Field

[0001] The present application relates to the field of intelligent control, and more specifically, to a two-axis drive-control integrated injection molding robot control system. Background Art

[0002] The injection molding machine manipulator is a machine specially equipped for injection molding production automation. It can reduce heavy physical labor, improve working conditions and ensure safe production. The drive system of a traditional injection molding machine manipulator usually includes multiple drivers, each of which is responsible for providing power for one of the manipulator's motion axes. This method causes the entire drive system to be heavy and occupy a large space. In order to reduce the weight of the manipulator and improve space utilization, Chinese patent CN105984077A proposes a method for controlling an injection molding machine manipulator and an injection molding machine manipulator and its driver, which include a rectifier module, a current calculation module, a control module, and multiple IGBT modules (the number is determined by the number of motion axes). The rectifier module is responsible for converting AC power into DC power to supply the IGBT module, and the IGBT module controls the speed of the motor according to the instructions issued by the control module. The control module can simultaneously receive the actual speed feedback from the encoder and compare it with the theoretical speed provided by the current calculation module. The motor speed is adjusted through PID closed-loop operation to achieve the expected target speed, ensuring that the manipulator moves accurately along the preset path.

[0003] However, the PID control algorithm mainly adjusts the control effect through three parameters: proportional, integral and differential. However, in dynamic environments or when the load changes frequently, the PID parameters are difficult to adapt to the changing working conditions and speed control tasks, resulting in a decrease in control accuracy. In addition, the PID control method has weak anti-interference ability and is very sensitive to system delays and noise, which may cause overshoot, oscillation and other problems in the actual speed control process, thereby affecting the stability and efficiency of the robot.

[0004] Therefore, an optimized injection molding robot control system is desired. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a two-axis drive-control integrated injection molding robot control system, which collects the timing data of the actual speed of the motor, and calculates the difference between these actual speed timing data of the motor and the theoretical speed respectively to obtain the speed deviation of these timing data, and then introduces a data processing and analysis algorithm based on artificial intelligence and deep learning at the back end to analyze the speed deviation timing data of the motor, so as to learn and characterize the time-series significant aggregation semantic representation of the motor speed deviation, so as to automatically generate control instructions, thereby obtaining the recommended duty ratio of the PWN control signal. In this way, artificial intelligence and deep learning technology can be used to automatically learn the time-series change semantics and aggregation representation information of the speed deviation, and thereby automatically adjust the duty cycle of the PWN control signal. In this way, the defects brought by traditional PID control can be avoided, so as to ensure the reliability and stability of the injection molding robot control on the basis of improving the level of intelligent control.

[0006] According to one aspect of the present application, a two-axis drive-controlled integrated injection molding robot control system is provided, which is used to control an injection molding machine robot, and the injection molding machine robot includes N motion axes, a motor, an encoder, a logic controller and a driver; each of the motion axes is provided with a motor and an encoder for collecting the actual speed of the motor; the logic controller is communicatively connected with a control module of the driver, and the two-axis drive-controlled integrated injection molding robot control system is deployed on the driver, and is characterized in that the two-axis drive-controlled integrated injection molding robot control system includes: a data acquisition module, which is used to collect a time queue of the actual speed of the motor; a current calculation module, which is used to obtain the theoretical speed of the motor; a control module, which is used to jointly analyze the time queue of the actual speed and the theoretical speed to generate a control instruction; an insulated gate bipolar transistor IGBT module, Used to control the speed of the motor based on the control instruction; wherein the control module includes: a speed timing deviation calculation unit, used to calculate the difference between the actual speed and the theoretical speed at each predetermined time point in the time queue of the actual speed to obtain a time queue of the speed deviation value; a speed deviation timing feature aggregation representation unit, used to perform timing dynamic aggregation analysis on the time queue of the speed deviation value to obtain a speed deviation timing significant aggregation representation; a control instruction generation unit, used to determine the control instruction based on the speed deviation timing significant aggregation representation, the control instruction including a recommended duty ratio of the PWN control signal sent to the insulated gate bipolar transistor IGBT module.

[0007] Compared with the prior art, the present application provides a two-axis drive-control integrated injection molding robot control system, which collects the timing data of the actual motor speed, and calculates the difference between these actual motor speed timing data and the theoretical speed to obtain the speed deviation of these timing data, and then introduces a data processing and analysis algorithm based on artificial intelligence and deep learning at the back end to analyze the motor speed deviation timing data, so as to learn and characterize the time-series significant aggregation semantic representation of the motor speed deviation, so as to automatically generate control instructions, thereby obtaining the recommended duty ratio of the PWN control signal. In this way, artificial intelligence and deep learning technology can be used to automatically learn the time-series change semantics and aggregation representation information of the speed deviation, and automatically adjust the duty cycle of the PWN control signal. In this way, the defects brought by traditional PID control can be avoided, so as to ensure the reliability and stability of the injection molding robot control on the basis of improving the control intelligence level. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0009] Figure 1 It is a block diagram of a two-axis drive-controlled integrated injection molding robot control system according to an embodiment of the present application.

[0010] Figure 2 Schematic diagram of data flow of a two-axis drive-controlled integrated injection molding robot control system according to an embodiment of the present application.

[0011] Figure 3 It is a block diagram of a control module in a two-axis drive-controlled integrated injection molding robot control system according to an embodiment of the present application.

[0012] Figure 4 It is a block diagram of a speed deviation timing feature aggregation representation unit in a two-axis drive-controlled integrated injection molding robot control system according to an embodiment of the present application. DETAILED DESCRIPTION

[0013] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0014] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0015] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0016] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0017] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0018] In the technical solution of the present application, a two-axis drive-integrated injection molding robot control system is proposed. The control system is used to control an injection molding machine robot, and the injection molding machine robot includes N motion axes, a motor, an encoder, a logic controller, and a driver; each of the motion axes is provided with a motor and an encoder for collecting the actual speed of the motor; the logic controller is communicatively connected with the control module of the driver, and the two-axis drive-integrated injection molding robot control system is deployed on the driver. In particular, the N motion axes include an X-axis, a Y-axis, and a Z-axis; the driver is arranged inside the box of the X-axis; and the logic controller is arranged inside the box of the Z-axis.

[0019] Figure 1 It is a block diagram of a two-axis drive-controlled integrated injection molding robot control system according to an embodiment of the present application. Figure 2 Schematic diagram of data flow of a two-axis drive-control integrated injection molding robot control system according to an embodiment of the present application. Figure 1 and Figure 2As shown, according to the embodiment of the present application, the two-axis drive-controlled integrated injection molding robot control system 300 includes: a data acquisition module 310, which is used to collect the time queue of the actual speed of the motor; a current calculation module 320, which is used to obtain the theoretical speed of the motor; a control module 330, which is used to jointly analyze the time queue of the actual speed and the theoretical speed to generate a control instruction; an insulated gate bipolar transistor IGBT module 340, which is used to control the speed of the motor based on the control instruction.

[0020] In particular, the data acquisition module 310 is used to collect the time queue of the actual speed of the motor. In the control system of the injection molding machine manipulator, the data acquisition module mainly uses an encoder to collect the actual speed of the motor and feeds this data back to the control module so that the control system can accurately grasp the current state of the motor.

[0021] In particular, the current calculation module 320 is used to obtain the theoretical speed of the motor. In the control system of the injection molding machine robot, the theoretical speed of the motor is obtained by the current calculation module and fed back to the control module to determine whether there is a deviation by comparing the actual speed with the theoretical speed, and to adjust through the PID closed-loop operation to ensure that the speed of the motor remains within a predetermined range.

[0022] In particular, the control module 330 is used to jointly analyze the time queue of the actual speed and the theoretical speed to generate a control instruction. The first input terminal of the control module is connected to the output terminal of the current calculation module; the second input terminal of the control module is connected to the output terminal of the encoder of each moving axis of the injection molding machine robot, and the output terminal of the control module is connected to the input terminal of each insulated gate bipolar transistor IGBT module. In a specific example of the present application, Figure 3 As shown, the control module 330 includes: a speed timing deviation calculation unit 331, which is used to calculate the difference between the actual speed and the theoretical speed at each predetermined time point in the time queue of the actual speed to obtain a time queue of the speed deviation value; a speed deviation timing feature aggregation representation unit 332, which is used to perform timing dynamic aggregation analysis on the time queue of the speed deviation value to obtain a speed deviation timing significant aggregation representation; a control instruction generation unit 333, which is used to determine the control instruction based on the speed deviation timing significant aggregation representation, and the control instruction includes a recommended duty ratio of the PWN control signal sent to the insulated gate bipolar transistor IGBT module.

[0023] Specifically, the speed timing deviation calculation unit 331 is used to calculate the difference between the actual speed and the theoretical speed at each predetermined time point in the time queue of the actual speed to obtain a time queue of speed deviation values. That is, by calculating the difference between the actual speed and the theoretical speed, it is possible to accurately understand whether there is a speed deviation during the operation of the motor. The time queue of speed deviation values ​​can reflect the performance of the system in different time periods, which is very important for evaluating the stability and response speed of the system. In the technical solution of the present application, it is expected to analyze the speed deviation timing data of the motor to learn and characterize the time-series significant aggregation semantic representation of the motor speed deviation, so as to automatically generate control instructions, thereby obtaining the recommended duty ratio of the PWN control signal.

[0024] Specifically, the speed deviation time series feature aggregation representation unit 332 is used to perform time series dynamic aggregation analysis on the time queue of the speed deviation value to obtain a speed deviation time series significant aggregation representation. In a specific example of the present application, Figure 4 As shown, the speed deviation time series feature aggregation representation unit 332 includes: an empirical mode decomposition subunit 3321, used to perform empirical mode decomposition on the time queue of the speed deviation value to obtain a series of speed deviation intrinsic mode functions; an intrinsic mode waveform semantic feature extraction subunit 3322, used to perform intrinsic mode waveform semantic feature extraction on the series of speed deviation intrinsic mode functions to obtain a series of speed deviation intrinsic mode waveform semantic coding vectors; a feature distribution field dynamic aggregation subunit 3323, used to perform feature distribution field dynamic aggregation on the series of speed deviation intrinsic mode waveform semantic coding vectors to obtain the speed deviation time series significant aggregation representation.

[0025] More specifically, the empirical mode decomposition subunit 3321 is used to perform empirical mode decomposition on the time queue of the speed deviation value to obtain a series of speed deviation intrinsic mode functions. It should be understood that the time queue of the speed deviation value can be constructed as a time-varying signal about the speed deviation in the time domain, and there is often a large noise component in this signal, which will affect the subsequent speed control task. Therefore, in order to extract the intrinsic mode or characteristics in the speed deviation time-varying signal, in the technical solution of the present application, the time queue of the speed deviation value is further subjected to empirical mode decomposition to obtain a series of speed deviation intrinsic mode functions. It is worth mentioning that empirical mode decomposition can decompose a complex signal into several intrinsic mode functions, each of which represents a different frequency component of the signal. This means that the speed timing fluctuations of multiple different frequencies originally mixed together are separated, and the characteristics of each speed deviation fluctuation can be analyzed separately. In addition, the noise component in the original speed deviation time domain signal can be removed by empirical mode decomposition. In the decomposed series of speed deviation intrinsic mode functions, the high-frequency component is often related to the noise, while the low-frequency component reflects the main trend of the signal. By properly selecting the speed deviation inherent mode function, the noise reduction effect can be achieved.

[0026] More specifically, the intrinsic modal waveform semantic feature extraction subunit 3322 is used to extract intrinsic modal waveform semantic features from the series of speed deviation intrinsic modal functions to obtain a series of speed deviation intrinsic modal waveform semantic coding vectors. In a specific example of the present application, each speed deviation intrinsic modal function in the series of speed deviation intrinsic modal functions is respectively input into the intrinsic modal waveform semantic feature extractor based on the 1D-CNN model to obtain the series of speed deviation intrinsic modal waveform semantic coding vectors. Here, through the processing of the intrinsic modal waveform semantic feature extractor based on the 1D-CNN model, the semantic feature information in each speed deviation intrinsic modal function can be captured respectively, which includes the waveform semantic essential features of the signal and the periodicity, trend and other important features of the waveform in the signal. In the control of the injection molding machine robot, these speed deviation timing waveform semantic features can be used to generate control signals for real-time optimization control of the motor speed.

[0027] More specifically, the feature distribution field dynamic aggregation subunit 3323 is used to perform feature distribution field dynamic aggregation on the series of speed deviation intrinsic modal waveform semantic coding vectors to obtain the speed deviation time series significant aggregation representation. It should be understood that each speed deviation intrinsic modal waveform semantic coding vector in the series of speed deviation intrinsic modal waveform semantic coding vectors respectively contains waveform semantic features of different frequency components extracted from the original speed deviation time domain original signal, and the waveform semantic features of each component are used as a semantic particle. When participating in the subsequent speed deviation time series feature aggregation process to obtain a more sufficient and accurate speed deviation time series significant aggregation representation, these different speed deviation intrinsic modal waveform semantic particles will have different importance and contribution to the subsequent control task. Based on this, in the technical solution of the present application, the series of speed deviation intrinsic modal waveform semantic coding vectors are further subjected to feature distribution field dynamic aggregation to obtain the speed deviation time series significant aggregation representation. In particular, here, the process of feature distribution field dynamic aggregation is modeled based on the interaction between each speed deviation intrinsic modal waveform semantic particle through a concept similar to a force field. This force field not only considers the direct spatial relationship between the semantics of each speed deviation intrinsic modal waveform (such as Euclidean distance), but also combines the properties of each speed deviation intrinsic modal waveform semantics itself (such as static energy factor) and the overall semantic structure of the entire speed deviation intrinsic modal waveform semantic set. In this way, the importance of each speed deviation intrinsic modal waveform semantic feature in the speed deviation time series semantic aggregation process can be dynamically adjusted, and the information can be integrated into a more compact and representative speed deviation time series significant aggregation representation form, namely, the speed deviation time series significant aggregation representation vector, according to specific aggregation strategies and control tasks.

[0028] Specifically, the specific process of dynamically aggregating the feature distribution field of the series of speed deviation intrinsic modal waveform semantic coding vectors includes: first, calculating the static energy factor of each speed deviation intrinsic modal waveform semantic coding vector in the series of speed deviation intrinsic modal waveform semantic coding vectors to obtain a set of speed deviation intrinsic modal waveform semantic static energy factors; that is, for each vector in the input series of speed deviation intrinsic modal waveform semantic coding vectors, based on a predefined metric function, evaluate its stability or importance in the feature space, and assign a numerical representation, namely, the speed deviation intrinsic modal waveform semantic static energy factor. In this way, the status and importance of each speed deviation intrinsic modal waveform semantic feature in its data distribution and the overall speed deviation intrinsic modal waveform semantics can be quantified, providing a basis for the subsequent selection of the initial clustering center. At the same time, by identifying those relatively isolated or highly localized speed deviation time series waveform semantic feature points, it is helpful to discover potential data cluster cores. In this way, the uniqueness and influence of each speed deviation waveform semantic in the feature space can be quantified, providing a basis for the subsequent aggregation process. Next, based on the set of semantic static energy factors of the rotational speed deviation intrinsic modal waveform, the series of rotational speed deviation intrinsic modal waveform semantic encoding vectors are subjected to feature significant aggregation based on the imitation field to obtain the rotational speed deviation time series significant aggregation representation.

[0029] Specifically, the process of performing feature-significant aggregation based on the imitation field on the series of speed deviation intrinsic modal waveform semantic coding vectors includes: first selecting the speed deviation intrinsic modal waveform semantic coding vector corresponding to the largest speed deviation intrinsic modal waveform semantic static energy factor in the set of speed deviation intrinsic modal waveform semantic static energy factors as the initial center vector of speed deviation intrinsic modal waveform semantic clustering. That is, determine a reliable starting point for iterative clustering operations. This point should represent the most representative part of the speed deviation intrinsic modal waveform semantic set, which can serve as the basis for subsequent clustering to ensure the rationality of the clustering results, thereby enhancing the adaptability of the clustering process to real scenarios and speed control tasks, and reducing the adverse effects caused by random initialization. Next, based on the spatial span between each speed deviation inherent modal waveform semantic coding vector in the series of speed deviation inherent modal waveform semantic coding vectors and the initial center vector of the speed deviation inherent modal waveform semantic clustering, as well as the static energy factor of each speed deviation inherent modal waveform semantic coding vector and the static energy factor of the initial center vector of the speed deviation inherent modal waveform semantic clustering, the dynamic aggregation energy factor of each speed deviation inherent modal waveform semantic coding vector in the set of speed deviation inherent modal waveform semantic coding vectors is calculated to obtain a set of speed deviation inherent modal waveform semantic dynamic aggregation energy factors. That is, based on the spatial span between each speed deviation inherent modal waveform semantic coding vector and the initial center vector of the speed deviation inherent modal waveform semantic clustering, as well as the static energy factor of each speed deviation inherent modal waveform semantic coding vector and the static energy factor of the initial center vector of the speed deviation inherent modal waveform semantic clustering, the dynamic aggregation energy factor of each speed deviation inherent modal waveform semantic coding vector is further derived. In particular, the dynamic aggregation energy factor not only takes into account the semantic proximity of the speed deviation intrinsic modal waveform at the position, but also includes the importance difference of the intrinsic attributes of the speed deviation intrinsic modal waveform semantics presented at each point, aiming to more accurately capture the semantic interaction between the speed deviation intrinsic modal waveforms, so as to measure the semantic importance and contribution of each speed deviation intrinsic modal waveform semantics in the overall collection and subsequent feature aggregation process. Then, the set of speed deviation intrinsic modal waveform semantic dynamic aggregation energy factors is input into the gated mask unit to obtain the set of speed deviation intrinsic modal waveform semantic dynamic aggregation weight factors. In particular, the gated mask unit automatically adjusts the weight of each speed deviation intrinsic modal waveform semantic dynamic aggregation energy factor according to the learned knowledge. In this way, by nonlinearly transforming and screening the original energy factors, the model's attention to the key speed deviation intrinsic modal waveform text semantic information is enhanced, while suppressing the irrelevant parts, so that the key answer semantics related to the subsequent task is given a higher weight in the aggregation process.Finally, the set of speed deviation intrinsic modal waveform semantic dynamic aggregation weight factors is used as weighted weights to calculate the weighted sum of the series of speed deviation intrinsic modal waveform semantic encoding vectors to obtain the speed deviation time series significant aggregation representation vector as the speed deviation time series significant aggregation representation. That is, the set of speed deviation intrinsic modal waveform semantic dynamic aggregation weight factors is used as weighting coefficients to calculate the weighted sum of the series of speed deviation intrinsic modal waveform semantic encoding vectors, so as to combine all the speed deviation intrinsic modal waveform semantic feature information, and at the same time, appropriately emphasize or weaken the feature expression according to the importance of the respective waveform semantics, so as to generate a more concise and representative speed deviation time series significant aggregation representation vector, which contains the main semantic information of the original speed deviation waveform and removes redundant or irrelevant parts, so as to improve the accuracy and efficiency of subsequent control instruction generation and speed control tasks.

[0030] Among them, calculating the static energy factor of each speed deviation inherent modal waveform semantic coding vector in the series of speed deviation inherent modal waveform semantic coding vectors to obtain a set of speed deviation inherent modal waveform semantic static energy factors includes: calculating the mean and variance of the speed deviation inherent modal waveform semantic coding vector to obtain the speed deviation inherent modal waveform semantic mean and the speed deviation inherent modal waveform semantic variance; subtracting the speed deviation inherent modal waveform semantic coding vector from the speed deviation inherent modal waveform semantic mean by position, and calculating the fourth power of each position of the subtracted eigenvector to obtain the speed deviation inherent modal waveform semantic difference modulation vector; calculating the expected value of the speed deviation inherent modal waveform semantic difference modulation vector to obtain the speed deviation inherent modal waveform semantic expected value; dividing the speed deviation inherent modal waveform semantic expected value by the square of the speed deviation inherent modal waveform semantic variance, and inputting the divided value into the sigmoid function to obtain the speed deviation inherent modal waveform semantic static energy factor.

[0031] More specifically, based on the spatial span between each speed deviation inherent modal waveform semantic coding vector in the series of speed deviation inherent modal waveform semantic coding vectors and the initial center vector of the speed deviation inherent modal waveform semantic clustering, as well as the static energy factor of each speed deviation inherent modal waveform semantic coding vector and the static energy factor of the initial center vector of the speed deviation inherent modal waveform semantic clustering, the dynamic aggregation energy factor of each speed deviation inherent modal waveform semantic coding vector in the set of the speed deviation inherent modal waveform semantic coding vector is calculated to obtain a set of speed deviation inherent modal waveform semantic dynamic aggregation energy factors, including: converting the speed deviation inherent modal waveform semantic coding vector into The static energy factor of the speed deviation inherent modal waveform semantics quantity and the static energy factor of the initial center vector of the speed deviation inherent modal waveform semantics clustering are multiplied with the first weighting parameter to obtain the first speed deviation inherent modal waveform semantics dynamic aggregation energy factor; the square of the spatial span between the speed deviation inherent modal waveform semantics encoding vector and the initial center vector of the speed deviation inherent modal waveform semantics clustering are multiplied with the second weighting parameter to obtain the second speed deviation inherent modal waveform semantics dynamic aggregation energy factor; the first speed deviation inherent modal waveform semantics dynamic aggregation energy factor is divided by the second speed deviation inherent modal waveform semantics dynamic aggregation energy factor to obtain the speed deviation inherent modal waveform semantics dynamic aggregation energy factor.

[0032] More specifically, the set of speed deviation inherent modal waveform semantic dynamic aggregation energy factors is input into a gated mask unit to obtain a set of speed deviation inherent modal waveform semantic dynamic aggregation weight factors, including: normalizing the set of speed deviation inherent modal waveform semantic dynamic aggregation energy factors to obtain a set of normalized speed deviation inherent modal waveform semantic dynamic aggregation energy factors; masking the set of normalized speed deviation inherent modal waveform semantic dynamic aggregation energy factors to obtain a set of speed deviation inherent modal waveform semantic dynamic aggregation weight factors. Among them, the process of normalizing the set of speed deviation inherent modal waveform semantic dynamic aggregation energy factors includes: calculating the exponential function value with the natural constant e as the base and the negative number of each speed deviation inherent modal waveform semantic dynamic aggregation energy factor in the set of speed deviation inherent modal waveform semantic dynamic aggregation energy factors as the exponent to obtain the set of speed deviation inherent modal waveform semantic dynamic aggregation energy index factors; adding the set of speed deviation inherent modal waveform semantic dynamic aggregation energy index factors to the constant one by position, and calculating the value of each speed deviation inherent modal waveform semantic dynamic aggregation energy index modulation factor in the set of speed deviation inherent modal waveform semantic dynamic aggregation energy index modulation factors. The inverse of the state aggregation energy index modulation factor is obtained to obtain the set of normalized speed deviation inherent modal waveform semantic dynamic aggregation energy factors; and the process of masking the set of normalized speed deviation inherent modal waveform semantic dynamic aggregation energy factors includes: in response to each normalized speed deviation inherent modal waveform semantic dynamic aggregation energy factor in the set of normalized speed deviation inherent modal waveform semantic dynamic aggregation energy factors being greater than a predetermined threshold, the normalized speed deviation inherent modal waveform semantic dynamic aggregation energy factors greater than the predetermined threshold are set to the original value, and the rest are set to zero to obtain the set of speed deviation inherent modal waveform semantic dynamic aggregation weight factors.

[0033] In summary, in the above embodiment, the series of speed deviation intrinsic modal waveform semantic coding vectors are dynamically aggregated in the feature distribution field to obtain the speed deviation time series significant aggregation representation, including: the series of speed deviation intrinsic modal waveform semantic coding vectors are dynamically aggregated in the feature distribution field using the following feature distribution dynamic aggregation formula to obtain the speed deviation time series significant aggregation representation; wherein the feature distribution dynamic aggregation formula is: ;in, is the semantic encoding vector of the series of speed deviation intrinsic modal waveforms, are the first, second, ..., and third vectors of the semantic encoding vector of the speed deviation intrinsic modal waveform. ,..., The semantic encoding vector of the speed deviation intrinsic mode waveform, It is The eigenvalues ​​of each position in the semantic encoding vector of the speed deviation intrinsic modal waveform, To calculate the expected value, and They are The mean and variance of yes function, yes The corresponding speed deviation intrinsic modal waveform semantic static energy factor, To select the maximum value corresponding to value, is the maximum matching value, is the initial center vector of semantic clustering of the speed deviation intrinsic modal waveform, yes The corresponding speed deviation intrinsic modal waveform semantic static energy factor, express and The space span between and is the weighting parameter, for The corresponding speed deviation intrinsic modal waveform semantic dynamic aggregation energy factor, yes The corresponding normalized speed deviation intrinsic modal waveform semantic dynamic aggregation energy factor, For masking, is a predetermined threshold, yes The corresponding speed deviation intrinsic modal waveform semantic dynamic aggregation weight factor, is the number of vectors in the series of semantic encoding vectors of the speed deviation intrinsic modal waveform, is a vector representing significant aggregation of the rotation speed deviation time series.

[0034] Specifically, the control instruction generating unit 333 is used to determine the control instruction based on the significant aggregation representation of the speed deviation timing, and the control instruction includes the recommended duty ratio of the PWN control signal sent to the insulated gate bipolar transistor IGBT module. In a specific example of the present application, the speed deviation timing significant aggregation representation vector is input into a decoder-based control module to obtain the control instruction, and the control instruction includes the recommended duty ratio of the PWN control signal sent to the insulated gate bipolar transistor IGBT module. That is, the time-series significant aggregation feature representation of the speed deviation is used to perform decoding regression to automatically generate control instructions, thereby obtaining the recommended duty ratio of the PWN control signal. In this way, artificial intelligence and deep learning technology can be used to automatically learn the time-series change semantics and aggregation representation information of the speed deviation, and the duty ratio of the PWN control signal can be automatically adjusted adaptively. Through this intelligent control method, the defects brought by traditional PID control can be avoided, so as to ensure the reliability and stability of the injection molding robot control on the basis of improving the control intelligence level.

[0035] Preferably, based on the source time series distribution differences of a series of speed deviation intrinsic modal functions obtained by performing empirical mode decomposition on the time queue of the speed deviation value, after being extracted by an intrinsic modal waveform semantic feature extractor based on the 1D-CNN model, the series of speed deviation intrinsic modal waveform semantic coding vectors will also have coding feature distribution differences, resulting in that when the feature distribution field is dynamically aggregated based on the force field, the force field feature distribution under the coding feature distribution difference will have different field dynamic aggregation modes, causing the speed deviation time series significant aggregation representation vector to have a complex aggregation space structure. Therefore, when the speed deviation time series significant aggregation representation vector is input into a decoder-based control module to obtain a control instruction, it is expected to improve the decoding regression convergence and generalization effect of the speed deviation time series significant aggregation representation vector under the complex aggregation space structure.

[0036] Therefore, the applicant of the present application considers optimizing the speed deviation time series significant aggregation representation vector when inputting the speed deviation time series significant aggregation representation vector into the decoder-based control module. The optimization process includes: calculating the absolute value sum of each eigenvalue of the speed deviation time series significant aggregation representation vector to obtain a first speed deviation time series significant aggregation spatial structure value, and calculating the square root of the sum of squares of each eigenvalue of the speed deviation time series significant aggregation representation vector to obtain a second speed deviation time series significant aggregation spatial structure value: ;in , are the eigenvalues ​​of the significant aggregation representation vector of the speed deviation time series, is the significant aggregated spatial structure value of the first speed deviation time series, is the significant aggregated spatial structure value of the second speed deviation time series.

[0037] Each eigenvalue of the speed deviation time series significant aggregation representation vector is multiplied by the first speed deviation time series significant aggregation spatial structure value and the second speed deviation time series significant aggregation spatial structure value to obtain a first speed deviation time series significant aggregation structure reference value and a second speed deviation time series significant aggregation structure reference value corresponding to each eigenvalue; each eigenvalue of the speed deviation time series significant aggregation representation vector is multiplied by the length of the speed deviation time series significant aggregation representation vector and the square root of the length to obtain a first speed deviation time series significant aggregation scale transformation value and a second speed deviation time series significant aggregation scale transformation value corresponding to each eigenvalue; the first speed deviation time series significant aggregation representation vector is multiplied by the length of the speed deviation time series significant aggregation representation vector and the square root of the length to obtain a first speed deviation time series significant aggregation scale transformation value and a second speed deviation time series significant aggregation scale transformation value corresponding to each eigenvalue; The combined structure reference value is divided by the difference between the first speed deviation timing significant aggregation spatial structure value and the first speed deviation timing significant aggregation scale transformation value to obtain the first speed deviation timing significant aggregation transformation adjustment value; the second speed deviation timing significant aggregation structure reference value is divided by the difference between the second speed deviation timing significant aggregation spatial structure value and the second speed deviation timing significant aggregation scale transformation value to obtain the second speed deviation timing significant aggregation transformation adjustment value; and the weighted sum of the first speed deviation timing significant aggregation transformation adjustment value and the second speed deviation timing significant aggregation transformation adjustment value is calculated to obtain each eigenvalue of the optimized speed deviation timing significant aggregation representation vector.

[0038] Here, the rotation speed deviation time series significant aggregation representation vector is recorded as The optimization expression is: ;exist ,and In the case of: ;in, is the first speed deviation timing significant aggregate transformation adjustment value, is the second speed deviation timing significant aggregate transformation adjustment value, is the length of the speed deviation time series significant aggregation representation vector, is a first speed deviation time series significant aggregation transformation adjustment feature vector composed of the first speed deviation time series significant aggregation transformation adjustment values, is a second speed deviation time series significant aggregation transformation adjustment feature vector composed of the second speed deviation time series significant aggregation transformation adjustment values, is added by position, It is the point multiplication by position. is a weighted hyperparameter, is the optimized rotation speed deviation timing significant aggregation representation vector.

[0039] That is, for the spatial structure information of the feature set of the speed deviation time series significant aggregation representation vector in the high-dimensional space, the scale-based frame transformation of each characteristic value of the speed deviation time series significant aggregation representation vector is performed by taking the class norm space structured representation of the speed deviation time series significant aggregation representation vector as the reference window, and the spatial structure-based frame attention weight adjustment of each characteristic value of the speed deviation time series significant aggregation representation vector is realized to ensure the spatial transformation invariance of the speed deviation time series significant aggregation representation vector under the interaction of feature space, thereby improving the convergence and generalization effect of the decoding regression of the feature set of the speed deviation time series significant aggregation representation vector under the complex spatial structure representation, and improving the accuracy of the control instruction obtained by inputting it into the control module based on the decoder. In this way, artificial intelligence and deep learning technology can be used to automatically learn the time series change semantics and aggregation representation information of the speed deviation, and the duty cycle of the PWN control signal can be automatically adjusted adaptively. Through this intelligent control method, the defects brought by the traditional PID control can be avoided, so as to ensure the reliability and stability of the injection molding robot control on the basis of improving the control intelligence level.

[0040] In particular, the insulated gate bipolar transistor IGBT module 340 is used to control the speed of the motor based on the control instruction. That is, after the control module receives the instruction from the logic controller, it sends the instruction to the corresponding IGBT module according to the information contained in the instruction. In a specific example, if the instruction requires the manipulator of the X-axis to take action, the control module sends the instruction to the IGBT module corresponding to the X-axis.

[0041] As described above, the two-axis drive-integrated injection molding robot control system 300 according to the embodiment of the present application can be implemented in various wireless terminals, such as a server with a two-axis drive-integrated injection molding robot control algorithm. In a possible implementation, the two-axis drive-integrated injection molding robot control system 300 according to the embodiment of the present application can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the two-axis drive-integrated injection molding robot control system 300 can be a software module in the operating system of the wireless terminal, or it can be an application developed for the wireless terminal; of course, the two-axis drive-integrated injection molding robot control system 300 can also be one of the many hardware modules of the wireless terminal.

[0042] Alternatively, in another example, the two-axis driven integrated injection molding robot control system 300 and the wireless terminal may also be separate devices, and the two-axis driven integrated injection molding robot control system 300 may be connected to the wireless terminal via a wired and / or wireless network, and transmit interactive information in accordance with an agreed data format.

[0043] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A two-axis drive-control integrated injection molding manipulator control system, used to control an injection molding machine manipulator, the injection molding machine manipulator comprises N motion axes, a motor, an encoder, a logic controller and a driver; each of the motion axes is provided with a motor and an encoder for collecting the actual speed of the motor; the logic controller is communicatively connected with a control module of the driver, the two-axis drive-control integrated injection molding manipulator control system is deployed on the driver, characterized in that: The two-axis drive-control integrated injection molding robot control system includes: a data acquisition module for collecting the time queue of the actual speed of the motor; a current calculation module for obtaining the theoretical speed of the motor; a control module for jointly analyzing the time queue of the actual speed and the theoretical speed to generate a control instruction; an insulated gate bipolar transistor IGBT module for controlling the speed of the motor based on the control instruction; wherein the control module includes: a speed timing deviation calculation unit for calculating the difference between the actual speed and the theoretical speed at each predetermined time point in the time queue of the actual speed to obtain a time queue of speed deviation values; a speed deviation timing feature aggregation representation unit for performing timing dynamic aggregation analysis on the time queue of the speed deviation values ​​to obtain a speed deviation timing significant aggregation representation; a control instruction generation unit for determining the control instruction based on the speed deviation timing significant aggregation representation, the control instruction including a recommended duty ratio of the PWN control signal sent to the insulated gate bipolar transistor IGBT module.

2. The two-axis drive-control integrated injection molding robot control system according to claim 1 is characterized in that: The speed deviation time series feature aggregation representation unit includes: an empirical mode decomposition subunit, which is used to perform empirical mode decomposition on the time queue of the speed deviation value to obtain a series of speed deviation intrinsic mode functions; an intrinsic mode waveform semantic feature extraction subunit, which is used to perform intrinsic mode waveform semantic feature extraction on the series of speed deviation intrinsic mode functions to obtain a series of speed deviation intrinsic mode waveform semantic coding vectors; a feature distribution field dynamic aggregation subunit, which is used to perform feature distribution field dynamic aggregation on the series of speed deviation intrinsic mode waveform semantic coding vectors to obtain the speed deviation time series significant aggregation representation, including: a speed deviation intrinsic mode waveform semantic static energy factor calculation secondary subunit, which is used to calculate the static energy factor of each speed deviation intrinsic mode waveform semantic coding vector in the series of speed deviation intrinsic mode waveform semantic coding vectors to obtain a set of speed deviation intrinsic mode waveform semantic static energy factors; a feature significant aggregation secondary subunit, which is used to perform feature significant aggregation based on the imitation force field on the series of speed deviation intrinsic mode waveform semantic coding vectors based on the set of speed deviation intrinsic mode waveform semantic static energy factors to obtain the speed deviation time series significant aggregation representation.

3. The two-axis drive-control integrated injection molding robot control system according to claim 2 is characterized in that: The intrinsic modal waveform semantic feature extraction subunit is used to: input each speed deviation intrinsic modal function in the series of speed deviation intrinsic modal functions into the intrinsic modal waveform semantic feature extractor based on the 1D-CNN model to obtain the series of speed deviation intrinsic modal waveform semantic encoding vectors.

4. The two-axis drive-control integrated injection molding robot control system according to claim 3 is characterized in that: The speed deviation inherent modal waveform semantic static energy factor calculation secondary subunit is used to: calculate the mean and variance of the speed deviation inherent modal waveform semantic coding vector to obtain the speed deviation inherent modal waveform semantic mean and the speed deviation inherent modal waveform semantic variance; subtract the speed deviation inherent modal waveform semantic coding vector from the speed deviation inherent modal waveform semantic mean by position, and calculate the fourth power of each position of the subtracted feature vector to obtain the speed deviation inherent modal waveform semantic difference modulation vector; calculate the expected value of the speed deviation inherent modal waveform semantic difference modulation vector to obtain the speed deviation inherent modal waveform semantic expected value; divide the speed deviation inherent modal waveform semantic expected value by the square of the speed deviation inherent modal waveform semantic variance, and input the divided value into the sigmoid function to obtain the speed deviation inherent modal waveform semantic static energy factor.

5. The two-axis drive-control integrated injection molding robot control system according to claim 4, characterized in that: The feature significant aggregation secondary sub-unit includes: a speed deviation inherent modal waveform semantic clustering tertiary sub-unit, which is used to select the speed deviation inherent modal waveform semantic coding vector corresponding to the largest speed deviation inherent modal waveform semantic static energy factor in the set of speed deviation inherent modal waveform semantic static energy factors as the speed deviation inherent modal waveform semantic clustering initial center vector; a speed deviation inherent modal waveform semantic dynamic aggregation energy factor calculation tertiary sub-unit, which is used to calculate the speed deviation inherent modal waveform semantic coding vector based on the spatial span between each speed deviation inherent modal waveform semantic coding vector in the series of speed deviation inherent modal waveform semantic coding vectors and the initial center vector of the speed deviation inherent modal waveform semantic clustering, as well as the static energy factor of each speed deviation inherent modal waveform semantic coding vector and the initial center vector of the speed deviation inherent modal waveform semantic clustering. The static energy factor of the initial center vector is used to calculate the dynamic aggregation energy factor of each speed deviation inherent modal waveform semantic coding vector in the set of the speed deviation inherent modal waveform semantic coding vector to obtain a set of speed deviation inherent modal waveform semantic dynamic aggregation energy factors; the mask three-level sub-unit is used to input the set of speed deviation inherent modal waveform semantic dynamic aggregation energy factors into the gated mask unit to obtain a set of speed deviation inherent modal waveform semantic dynamic aggregation weight factors; the speed deviation time series significant aggregation representation three-level sub-unit is used to use the set of speed deviation inherent modal waveform semantic dynamic aggregation weight factors as the weighted weight, calculate the weighted sum of the series of speed deviation inherent modal waveform semantic coding vectors to obtain the speed deviation time series significant aggregation representation vector as the speed deviation time series significant aggregation representation.

6. The two-axis drive-control integrated injection molding robot control system according to claim 5, characterized in that: The three-level sub-unit for calculating the dynamic aggregation energy factor of the speed deviation inherent modal waveform semantics is used to: multiply the static energy factor of the speed deviation inherent modal waveform semantic coding vector and the static energy factor of the initial center vector of the speed deviation inherent modal waveform semantics clustering with a first weighting parameter to obtain a first speed deviation inherent modal waveform semantics dynamic aggregation energy factor; multiply the square of the spatial span between the speed deviation inherent modal waveform semantics coding vector and the initial center vector of the speed deviation inherent modal waveform semantics clustering with a second weighting parameter to obtain a second speed deviation inherent modal waveform semantics dynamic aggregation energy factor; divide the first speed deviation inherent modal waveform semantics dynamic aggregation energy factor by the second speed deviation inherent modal waveform semantics dynamic aggregation energy factor to obtain the speed deviation inherent modal waveform semantics dynamic aggregation energy factor.

7. The two-axis drive-control integrated injection molding robot control system according to claim 6, characterized in that: The masked third-level sub-unit includes: a normalized speed deviation inherent modal waveform semantic dynamic aggregation fourth-level sub-unit, which is used to normalize the set of speed deviation inherent modal waveform semantic dynamic aggregation energy factors to obtain a set of normalized speed deviation inherent modal waveform semantic dynamic aggregation energy factors; a masked fourth-level sub-unit, which is used to mask the set of normalized speed deviation inherent modal waveform semantic dynamic aggregation energy factors to obtain a set of speed deviation inherent modal waveform semantic dynamic aggregation weight factors.

8. The two-axis drive-control integrated injection molding robot control system according to claim 7, characterized in that: The normalized speed deviation inherent modal waveform semantic dynamic aggregation fourth-level sub-unit is used to: calculate the exponential function value with the natural constant e as the base and the negative number of each speed deviation inherent modal waveform semantic dynamic aggregation energy factor in the set of speed deviation inherent modal waveform semantic dynamic aggregation energy factors as the exponent to obtain a set of speed deviation inherent modal waveform semantic dynamic aggregation energy index factors; add the set of speed deviation inherent modal waveform semantic dynamic aggregation energy index factors and constant one by position, and then calculate the inverse of each speed deviation inherent modal waveform semantic dynamic aggregation energy index modulation factor in the set of speed deviation inherent modal waveform semantic dynamic aggregation energy index modulation factors to obtain the set of normalized speed deviation inherent modal waveform semantic dynamic aggregation energy factors.

9. The two-axis drive-control integrated injection molding robot control system according to claim 8, characterized in that: The masked four-level sub-unit is used to: in response to each normalized speed deviation inherent modal waveform semantic dynamic aggregation energy factor in the set of normalized speed deviation inherent modal waveform semantic dynamic aggregation energy factors being greater than a predetermined threshold, set the normalized speed deviation inherent modal waveform semantic dynamic aggregation energy factors greater than the predetermined threshold to the original value, and set the rest to zero, so as to obtain a set of speed deviation inherent modal waveform semantic dynamic aggregation weight factors.

10. The two-axis drive-control integrated injection molding robot control system according to claim 9, characterized in that: The control instruction generating unit is used to: input the rotation speed deviation timing significant aggregation representation vector into a decoder-based control module to obtain the control instruction, and the control instruction includes a recommended duty ratio of the PWN control signal sent to the insulated gate bipolar transistor IGBT module.

Images