Adaptive control method and system for shaft groove gauge detection control system

Abstract

An embodiment of the present invention provides an adaptive control method and system for an axis groove gauge detection control system. First, the sample control feature path data sequence of the system is determined, and then a candidate neural network learns this data to generate a candidate adaptive control strategy. Next, by comparing the actual adaptive control strategy with the candidate strategy, the parameters of the neural network are optimized. Finally, a target adaptive control decision network is trained, which can predict and generate an adaptive control strategy corresponding to the input control feature path data. This method improves the adaptability, accuracy, and efficiency of the axis groove gauge detection control system through automated learning and optimization of the control strategy, reduces the need for manual intervention and operation complexity, and provides an efficient and accurate adaptive control solution for the axis groove gauge detection control system.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and more particularly, to an adaptive control method and system based on a shaft groove gauge detection control system. Background Art

[0002] In existing shaft groove gauge detection control systems, the formulation of control strategies usually relies on the experience of engineers and manual adjustment. This method is not only inefficient but also difficult to ensure the stability and accuracy of the system. Especially when facing complex and changeable working environments and task requirements, traditional control methods often cannot make timely and effective adjustments.

[0003] On the one hand, the traditional manual adjustment method cannot achieve real-time and precise control of the shaft groove gauge detection control system. Due to the interference of human factors, the response speed of the control system may be slow, the control accuracy may be low, and even the instability of the system may be caused.

[0004] On the other hand, existing control systems often lack adaptability. When facing different working environments and task requirements, the system cannot automatically adjust the control strategy and requires manual intervention. This not only increases the operation complexity and labor cost but also may affect the performance and stability of the system due to untimely or inaccurate adjustment.

[0005] Therefore, how to design a shaft groove gauge detection control system that can automatically learn and optimize control strategies and has good adaptability has become an important issue in the current technical field. Summary of the Invention

[0006] In view of this, an object of an embodiment of the present invention is to provide an adaptive control method and system based on a shaft groove gauge detection control system.

[0007] According to one aspect of the embodiments of the present invention, an adaptive control method based on a shaft groove gauge detection control system is provided, and the method includes:

[0008] Determine a sample control feature path data sequence of the shaft groove gauge detection control system; wherein, the sample control feature path data sequence includes multiple sample control task tags, and multiple sample control feature paths are included under different sample control task tags. The sample control feature path includes control behavior data to be learned corresponding to a target adaptive control node and an actual adaptive control strategy;

[0009] For each sample control feature path, use the current sample control feature path as the learning data of the candidate neural network to generate at least one candidate adaptive control strategy corresponding to the current sample control feature path;

[0010] For each sample control feature path, based on at least one actual adaptive control strategy and the corresponding at least one candidate adaptive control strategy in the current sample control feature path, optimize the network parameters of the candidate neural network;

[0011] Minimize the training error parameter in the candidate neural network as the learning direction to generate a target adaptive control decision network; wherein, the target adaptive control decision network is used to predict the input control feature path data and generate an adaptive control strategy corresponding to the control feature path data.

[0012] In a possible implementation manner of the first aspect, the determining the sample control feature path data sequence includes:

[0013] Obtain control feature path data including a target adaptive control node;

[0014] Determine at least one control feature vector direction corresponding to each control feature path data, and generate multiple control feature path data corresponding to each control feature vector direction;

[0015] Determine the actual adaptive control strategy corresponding to each control feature path data;

[0016] According to the control feature path data corresponding to each control feature vector direction and the corresponding actual adaptive control strategy, determine each sample control task label in the sample control feature path data sequence.

[0017] In a possible implementation manner of the first aspect, the determining at least one control feature vector direction corresponding to each control feature path data and generating multiple control feature path data corresponding to each control feature vector direction includes:

[0018] Encode each control feature path data to determine a control feature path vector;

[0019] Based on a set derivation strategy, derive the control feature path vector to generate target control feature path data;

[0020] Determine at least one control feature vector direction corresponding to each target control feature path data.

[0021] In a possible implementation manner of the first aspect, the at least one control feature vector direction is determined according to the basic operation information of the shaft groove gauge detection control system, the control execution device corresponding to the control behavior data to be learned, and the control direction of the control execution device relative to the target adaptive control node.

[0022] In a possible implementation manner of the first aspect, it further includes:

[0023] Obtain a verification data sequence; wherein, the verification data sequence includes a plurality of network verification tags, and under different network verification tags, there are a plurality of verification control feature path data, and the network verification tags match the sample control task tags;

[0024] Load each verification control feature path data into the trained target adaptive control decision network respectively to generate an actual adaptive control strategy corresponding to each verification data;

[0025] Based on the actual adaptive control strategies of each verification control feature path data and the corresponding actual adaptive control strategies, determine the verification performance parameters under the same network verification tag;

[0026] If there is a target network verification tag whose verification performance parameter is less than the preset verification performance parameter, obtain the sample control feature path corresponding to the target network verification tag, and continue to optimize the network parameters of the target adaptive control decision network until the verification performance parameters of each network verification tag are greater than the preset verification performance parameter.

[0027] In a possible implementation manner of the first aspect, the obtaining the sample control feature path corresponding to the target network verification tag and continuing to optimize the network parameters of the target adaptive control decision network until the verification performance parameters of each network verification tag are greater than the preset verification performance parameter includes:

[0028] Obtain a candidate sample control feature path corresponding to the target network verification tag, and re-train the target adaptive control decision network according to the candidate sample control feature path and the sample control feature path in the sample control feature path data sequence until it is determined according to the verification data sequence that the verification performance parameters of each network verification tag are greater than the preset verification performance parameter.

[0029] In a possible implementation manner of the first aspect, it further includes:

[0030] Obtain target control feature path data; wherein, the target control feature path data includes target adaptive control nodes;

[0031] Load the target control feature path data into the target adaptive control decision network to generate at least one adaptive control strategy corresponding to the target control feature path data;

[0032] According to the at least one adaptive control strategy, determine the adaptive control parameters of the target adaptive control nodes in the target control feature path data.

[0033] According to another aspect of the embodiments of the present invention, an adaptive control system based on a shaft groove gauge detection control system is provided, including: a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus; the memory is used to store a computer program; when the processor executes the computer program, it realizes the steps of the adaptive control method of the shaft groove gauge detection control system described in any one of the above.

[0034] According to another aspect of the embodiments of the present invention, a readable storage medium is provided. A computer program is stored on the readable storage medium, and when the computer program is run by a processor, it can execute the steps of the above-mentioned adaptive control method of the shaft groove gauge detection control system.

[0035] To make the above objects, features, and advantages of the embodiments of the present invention more obvious and understandable, the following will be described in detail in conjunction with the embodiments and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0037] Figure 1 The schematic diagram of the components of the adaptive control system of the shaft groove gauge detection control system provided by the embodiments of the present invention is shown;

[0038] Figure 2 The schematic flow diagram of the adaptive control method of the shaft groove gauge detection control system provided by the embodiments of the present invention is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. According to the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0040] In the description, claims, and above-mentioned drawings of the present invention, the terms "first", "second", "third", etc. (if any) are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that comprises a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0041] Figure 1 FIG. shows an exemplary component diagram of an adaptive control system 100 of an axis-based groove gauge detection control system. The adaptive control system 100 of the axis-based groove gauge detection control system may include one or more processors 104, such as one or more central processing units (CPUs), and each processing unit may implement one or more hardware threads. The adaptive control system 100 of the axis-based groove gauge detection control system may also include any storage medium 106 for storing any type of information such as code, settings, data, etc. By way of non-limiting example, the storage medium 106 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory devices, hard disks, optical discs, etc. More generally, any storage medium may use any technology to store information. Further, any storage medium may provide volatile or non-volatile retention of information. Further, any storage medium may represent a fixed or removable component of the adaptive control system 100 of the axis-based groove gauge detection control system. In one case, when the processor 104 executes the associated instructions stored in any storage medium or combination of storage media, the adaptive control system 100 of the axis-based groove gauge detection control system may perform any operation of the associated instructions. The adaptive control system 100 of the axis-based groove gauge detection control system also includes one or more drive units 108 for interacting with any storage medium, such as a hard disk drive unit, an optical disc drive unit, etc.

[0042] The adaptive control system 100 of the shaft groove gauge detection control system further includes an input / output 110 (I / O), which is used to receive various inputs (via the input unit 112) and to provide various outputs (via the output unit 114). A specific output mechanism may include a presentation device 116 and an associated graphical user interface (GUI) 118. The adaptive control system 100 of the shaft groove gauge detection control system may also include one or more network interfaces 120, which are used to exchange data with other devices via one or more communication units 122. One or more communication buses 124 couple the components described above together.

[0043] The communication unit 122 can be implemented in any way, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication unit 122 can include any combination of hardwired links, wireless links, routers, gateway functions, name-based shaft groove gauge detection control system adaptive control system 100, etc., governed by any protocol or combination of protocols.

[0044] Figure 2 The flowchart of the adaptive control method and system of the shaft groove gauge detection control system provided by the embodiment of the present invention is shown. The adaptive control method and system of the shaft groove gauge detection control system can be Figure 1 executed by the adaptive control system 100 of the shaft groove gauge detection control system shown in the following. The detailed steps of the adaptive control method of the shaft groove gauge detection control system are introduced as follows.

[0045] Step S110, determine the sample control feature path data sequence of the shaft groove gauge detection control system. Among them, the sample control feature path data sequence includes a plurality of sample control task tags. Under different sample control task tags, there are a plurality of sample control feature paths. The sample control feature path includes the to-be-learned control behavior data and the actual adaptive control strategy corresponding to the target adaptive control node.

[0046] In this embodiment, the server first determines the sample control feature path data sequence of the shaft groove gauge detection control system. Specifically, the server selects representative samples from past control tasks. These samples include different control tasks, such as adjusting the position of the groove gauge and changing the angle of the detection head. Each sample control task is labeled, such as "position adjustment task", "angle adjustment task", etc. Under each task label, the server collects multiple successful control feature paths, which detail how to achieve the predetermined goal through operations on the shaft groove gauge detection control system. These path data include the control behavior data to be learned corresponding to the target adaptive control nodes (such as a certain key sensor or actuator), that is, how the system should respond when performing the task, and the actual adaptive control strategy adopted, that is, how to adjust the control parameters according to the system state in actual operation.

[0047] Step S120: For each sample control feature path, use the current sample control feature path as the learning data of the candidate neural network to generate at least one candidate adaptive control strategy corresponding to the current sample control feature path.

[0048] Next, the server will operate on each sample control feature path. It takes the current sample control feature path, such as a specific position adjustment path, as the learning data input of the candidate neural network. The neural network tries to generate a candidate adaptive control strategy corresponding to this specific path by learning these data. This process is like teaching the neural network how to simulate human control behavior based on historical successful cases.

[0049] Step S130: For each sample control feature path, optimize the network parameters of the candidate neural network based on at least one actual adaptive control strategy and the corresponding at least one candidate adaptive control strategy in the current sample control feature path.

[0050] After the neural network generates the candidate adaptive control strategies, the server will compare these strategies with the strategies adopted in the actual successful cases. For example, in the position adjustment task, the neural network may propose a candidate strategy of first quickly moving to 80% of the target position and then slowly adjusting to the final position. The server will compare this strategy with the strategy adopted in the actual operation (such as first moving to 60% and then gradually approaching the target position). Based on this comparison, the server optimizes the parameters of the neural network to make the generated strategy closer to the successful strategy in actual operation.

[0051] Step S140, minimize the training error parameter in the candidate neural network as the learning direction to generate a target adaptive control decision network. The target adaptive control decision network is used to predict the input control feature path data and generate an adaptive control strategy corresponding to the control feature path data.

[0052] After multiple parameter optimizations, the server minimizes the training error parameter in the neural network, which means that the difference between the strategy generated by the neural network and the actual strategy becomes smaller and smaller. Finally, the server will obtain a target adaptive control decision network, which can predict and generate corresponding adaptive control strategies based on the input control feature path data, such as the current position and target position of the groove gauge. In this way, in future control tasks, the server can use this trained neural network to automatically decide how to adjust the parameters of the shaft groove gauge detection control system to achieve more efficient and accurate control.

[0053] Based on the above steps, by determining the sample control feature path data sequence and using the candidate neural network for learning and optimization, a target adaptive control decision network is finally generated. This network can predict and generate corresponding adaptive control strategies for the input control feature path data, thereby achieving precise control of the shaft groove gauge detection control system and improving the control accuracy. The target adaptive control decision network is generated by learning multiple sample control feature paths, which contain various possible control situations and corresponding adaptive control strategies. Therefore, the network can automatically select and adjust control strategies according to different control requirements and environmental changes, making the system more adaptable. Finally, an adaptive control strategy corresponding to the input control feature path data is automatically generated, avoiding the cumbersome process of manually adjusting control parameters in traditional methods. This not only improves the control efficiency but also reduces the operation difficulty and labor cost. That is, by optimizing the network parameters of the candidate neural network and minimizing the training error parameter, the stability and reliability of the target adaptive control decision network are improved. This means that in practical applications, the system can operate more stably, reducing the risk of system failures or performance degradation caused by inappropriate control strategies.

[0054] In a possible implementation manner, the determining the sample control feature path data sequence includes:

[0055] Obtain control feature path data including target adaptive control nodes.

[0056] Determine at least one control feature vector direction corresponding to each control feature path data, and generate multiple control feature path data corresponding to each control feature vector direction.

[0057] Determine the actual adaptive control strategies corresponding to each control feature path data.

[0058] Based on the control feature path data corresponding to each control feature vector direction and the corresponding actual adaptive control strategies, determine each sample control task label in the sample control feature path data sequence.

[0059] In a possible implementation manner, the determining at least one control feature vector direction corresponding to each control feature path data and generating multiple control feature path data corresponding to each control feature vector direction includes:

[0060] Encode each control feature path data to determine the control feature path vector.

[0061] Based on the set derivation strategy, derive the control feature path vector to generate the target control feature path data.

[0062] Determine at least one control feature vector direction corresponding to each target control feature path data.

[0063] In a possible implementation manner, the at least one control feature vector direction is determined according to the basic operation information of the shaft groove gauge detection control system, the control execution device corresponding to the control behavior data to be learned, and the control direction of the control execution device corresponding to the target adaptive control node.

[0064] In a possible implementation manner, it further includes:

[0065] Obtain the verification data sequence. Wherein, the verification data sequence includes multiple network verification labels, and multiple verification control feature path data are included under different network verification labels, and the network verification labels match the sample control task labels.

[0066] Load each verification control feature path data into the trained target adaptive control decision network respectively to generate the actual adaptive control strategies corresponding to each verification data.

[0067] Based on the actual adaptive control strategies of each verification control feature path data and the corresponding actual adaptive control strategies, determine the verification performance parameters under the same network verification label.

[0068] If there is a target network verification label with a verification performance parameter less than the preset verification performance parameter, obtain the sample control feature path corresponding to the target network verification label, and continue to optimize the network parameters of the target adaptive control decision network until the verification performance parameters of each network verification label are greater than the preset verification performance parameter.

[0069] In a possible implementation manner, obtaining the sample control feature path corresponding to the target network verification label, and continuing to optimize the network parameters of the target adaptive control decision network until the verification performance parameters of each network verification label are greater than the preset verification performance parameters, includes:

[0070] Obtaining the candidate sample control feature path corresponding to the target network verification label, and retraining the target adaptive control decision network based on the candidate sample control feature path and the sample control feature paths in the sample control feature path data sequence until it is determined according to the verification data sequence that the verification performance parameters of each network verification label are greater than the preset verification performance parameters.

[0071] In a possible implementation manner, it further includes:

[0072] Obtaining target control feature path data. Wherein, the target control feature path data includes target adaptive control nodes.

[0073] Loading the target control feature path data into the target adaptive control decision network to generate at least one adaptive control strategy corresponding to the target control feature path data.

[0074] Determining the adaptive control parameters of the target adaptive control nodes in the target control feature path data according to the at least one adaptive control strategy.

[0075] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0076] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and when not departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to embrace all changes within the meaning and scope of the equivalent elements of the claims in the present invention.

Claims

1. An adaptive control method for an axis groove gauge detection control system, characterized in that, The method includes: Determining a sample control feature path data sequence of a shaft groove gauge detection control system; wherein, the sample control feature path data sequence includes multiple sample control task tags, and multiple sample control feature paths are included under different sample control task tags. The sample control feature path includes to-be-learned control behavior data corresponding to a target adaptive control node and an actual adaptive control strategy; For each sample control feature path, using the current sample control feature path as learning data of a candidate neural network to generate at least one candidate adaptive control strategy corresponding to the current sample control feature path; For each sample control feature path, optimizing network parameters of the candidate neural network based on at least one actual adaptive control strategy and corresponding at least one candidate adaptive control strategy in the current sample control feature path; Taking minimizing a training error parameter in the candidate neural network as a learning direction to generate a target adaptive control decision network; wherein, the target adaptive control decision network is used to predict input control feature path data and generate an adaptive control strategy corresponding to the control feature path data; Wherein, determining the sample control feature path data sequence of the shaft groove gauge detection control system includes: Obtaining control feature path data including a target adaptive control node; Determining at least one control feature vector direction corresponding to each control feature path data to generate multiple control feature path data corresponding to each control feature vector direction; Determining an actual adaptive control strategy corresponding to each control feature path data; Determining each sample control task tag in the sample control feature path data sequence according to the control feature path data corresponding to each control feature vector direction and the corresponding actual adaptive control strategy; Wherein, the method further includes: Obtaining target control feature path data; wherein, the target control feature path data includes a target adaptive control node; Loading the target control feature path data into the target adaptive control decision network to generate at least one adaptive control strategy corresponding to the target control feature path data; Determining an adaptive control parameter of the target adaptive control node in the target control feature path data according to the at least one adaptive control strategy; 2. The self-adaptive control method of the shaft groove gauge detection control system according to claim 1, wherein The determining at least one control feature vector direction corresponding to each control feature path data to generate multiple control feature path data corresponding to each control feature vector direction includes: Encoding each control feature path data to determine a control feature path vector; Deriving the control feature path vector based on a set derivation strategy to generate target control feature path data; Determining at least one control feature vector direction corresponding to each target control feature path data; 3. The self-adaptive control method of the shaft groove gauge detection control system according to claim 2, wherein The at least one control feature vector direction is determined according to basic operation information of the shaft groove gauge detection control system, a control execution device corresponding to the to-be-learned control behavior data, and a control direction of the control execution device relative to the target adaptive control node; 4. The self - adaptive control method of the shaft - based groove gauge detection control system according to claim 1, characterized in that, It further includes: Obtain a verification data sequence; wherein, the verification data sequence includes a plurality of network verification tags, and under different network verification tags, there are a plurality of verification control feature path data, and the network verification tags match the sample control task tags; Load each verification control feature path data into the trained target adaptive control decision network respectively to generate an actual adaptive control strategy corresponding to each verification data; Based on the actual adaptive control strategies of each verification control feature path data and the corresponding actual adaptive control strategies, determine the verification performance parameters under the same network verification tag; If there is a target network verification tag whose verification performance parameter is less than the preset verification performance parameter, obtain the sample control feature path corresponding to the target network verification tag, and continue to optimize the network parameters of the target adaptive control decision network until the verification performance parameters of each network verification tag are greater than the preset verification performance parameter.

5. The self-adaptive control method of the shaft groove gauge detection control system according to claim 4, characterized in that The obtaining the sample control feature path corresponding to the target network verification tag and continuing to optimize the network parameters of the target adaptive control decision network until the verification performance parameters of each network verification tag are greater than the preset verification performance parameter includes: Obtain the candidate sample control feature path corresponding to the target network verification tag, and re-train the target adaptive control decision network according to the candidate sample control feature path and the sample control feature path in the sample control feature path data sequence until it is determined according to the verification data sequence that the verification performance parameters of each network verification tag are greater than the preset verification performance parameter.

6. An adaptive control system based on a shaft groove gauge detection control system, characterized in that, Include: A processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory complete communication with each other through the communication bus; The memory is used to store a computer program; the processor is used to implement the steps of the adaptive control method of the shaft groove gauge detection control system according to any one of claims 1-5 when executing the computer program.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the adaptive control method of the shaft groove gauge detection control system according to any one of claims 1-5.

Images