A modular design method and system for a fully automated inspection robot

Abstract

This invention discloses a modular design method and system for a fully automated inspection robot, relating to the field of automated inspection technology. The method includes: dividing the robot system into multiple functionally independent modules; acquiring the state parameters and operating parameters of each module; and generating module output data based on these parameters. During task execution, the robot optimizes its output at each task stage by dynamically adjusting the combination and weights of the modules. Module selection is based on a comprehensive evaluation of error minimization and inter-module synergy. The optimal module is selected according to real-time task and environmental changes, and the module configuration is adjusted in real-time. This invention addresses the problem that existing robot systems typically employ fixed structural designs, lacking flexibility and adjustability between modules, and unable to quickly switch and adjust between different tasks, thus affecting the overall efficiency and stability of the robot system.

Description

Technical Field

[0001] This invention relates to the field of automated inspection technology, specifically to a modular design method and system for a fully automated inspection robot. Background Technology

[0002] As industrial production and service sectors increasingly demand higher precision and efficiency in automated inspection, existing inspection robot systems have revealed shortcomings in handling complex and ever-changing task requirements. Traditional automated inspection robot systems are typically based on fixed structural designs, lacking sufficient flexibility and adjustability between their functional modules. This structural design often results in the system's inability to quickly adapt to new inspection tasks in different environments, making it difficult to meet personalized and diverse work needs. Therefore, improving the adaptability, flexibility, and efficiency of robot systems has become an urgent need for technological development.

[0003] Meanwhile, with the continuous development of intelligent technologies, higher demands are being placed on robot systems. Modern inspection tasks often involve multiple complex environmental factors (such as power, gravity, temperature, humidity, and light intensity), and the task objectives may dynamically change at different stages. Therefore, robot systems not only need powerful data processing and inspection capabilities, but also the ability to adjust their working status and parameters in a timely manner according to changes in the external environment to ensure that each task is completed under optimal conditions. Furthermore, with the gradual development of robot technology, collaborative work among multiple modules has become an important direction for improving robot performance. To effectively solve these problems, robot systems are required to not only have highly integrated hardware capabilities, but also sufficient intelligence in software and control systems, enabling them to self-adjust and optimize according to real-time task requirements.

[0004] The existing technology has at least the following technical problems: Existing robot systems typically employ fixed structural designs, lacking flexibility and adjustability between modules, making it impossible to quickly switch and adjust between different tasks, thus affecting the overall efficiency and stability of the robot system; existing modules are difficult to effectively adjust according to the real-time working environment or task objectives, leading to low efficiency when handling multiple tasks, or even failure to complete tasks; existing modules have poor collaboration and lack intelligent collaborative scheduling mechanisms, resulting in poor information transmission or uneven allocation of computing resources between different modules, thereby affecting overall performance. Summary of the Invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the present invention provides a modular design method and system for a fully automated inspection robot, which can solve the problems mentioned in the background art.

[0007] To solve the above technical problems, the present invention provides the following technical solution: a modular design method for a fully automated inspection robot, comprising: dividing the robot system into multiple functionally independent modules, obtaining the state parameters and working parameters of the modules, and generating module output data based on the state parameters and the working parameters;

[0008] During task execution, the robot optimizes the output of each task stage by dynamically adjusting the combination and weight of modules. Module selection is based on a comprehensive evaluation of error minimization and inter-module synergy. The optimal module is selected according to real-time task and environmental changes, and the module configuration is adjusted in real time.

[0009] As a preferred embodiment of the modular design method for the fully automated inspection robot described in this invention, the steps of constructing the modular system include:

[0010] Obtain environmental factor parameters and module efficiency coefficients;

[0011] Calculate the initial module output data, which satisfies the following:

[0012] D i (0)=η i ·(S i (0)·P i (0))+ξ i ·E i ;

[0013] Where, η i ξ is the efficiency coefficient of the i-th module, reflecting the module's efficiency in completing the task under the initial state, and is obtained through experimental measurement; i It is the influence coefficient of external environmental factors.

[0014] As a preferred embodiment of the modular design method for the fully automated inspection robot described in this invention, the steps of constructing the modular system include:

[0015] The data output by the acquisition module at the previous moment;

[0016] Obtain the target output data and module collaboration coefficients;

[0017] Calculate the update amount of the state parameters, and update the state parameters, wherein:

[0018] The update of the state parameters satisfies:

[0019] S i (t)=S i (t-1)+ΔS i (t);

[0020] The update amount of the state parameter satisfies:

[0021]

[0022] Among them, S i (t) represents the state of the i-th module at time t, based on the state S at the previous time. i (t-1) and the current state change ΔS i (t) is updated; state change ΔS i (t) consists of two parts: one is an adjustment term α based on the output error. i ·(D i (t-1)-D target (t-1)), the other is an adjustment item based on inter-module collaboration. Among them, D i (t-1) and D target (t-1) represent the previous time-to-time output and the target output of the module, respectively; α i It is the sensitivity coefficient of the i-th module to its own error, which determines the output error D. i (t-1)-D target (t-1) represents the degree of influence on state updates; w ik (t) is the coordination coefficient between the i-th module and the k-th module at the current time; β i This represents the sensitivity of the i-th module to collaborative information feedback; n is the number of modules; D k (t-1) is the output of the k-th module at the previous time step.

[0023] As a preferred embodiment of the modular design method for the fully automated inspection robot described in this invention, the step of optimizing the execution module includes:

[0024] Obtain the activation sensitivity coefficient and the co-regulation factor;

[0025] Calculate the module weight value;

[0026] The system output is generated based on the module weight values, and the system output satisfies the following:

[0027]

[0028] Among them, O j The output of the j-th task stage is obtained by weighted summation of the outputs of all modules; the output of the i-th module in the j-th task stage is determined by weight w. i The output of the activation function determines the outcome. It is a co-regulatory factor; C ik(t) is the collaboration metric between the i-th module and the k-th module at time t.

[0029] As a preferred embodiment of the modular design method for the fully automated inspection robot described in this invention, the step of optimizing the execution module includes:

[0030] Obtain the error threshold parameter;

[0031] The module error value of the calculation function module satisfies:

[0032] E i (t)=|D i (t)-D target (t)|≤∈ i ;

[0033] Among them, E i (t) is the output error of the module at time t, ∈ i It is the error threshold, representing the maximum allowable error of the system; when the error E i (t) is less than or equal to the set threshold ∈ j When the error is close to the target value, it indicates that the module output is performing well; conversely, modules with errors greater than the set threshold will be suppressed during the optimal selection process.

[0034] As a preferred embodiment of the modular design method for the fully automated inspection robot described in this invention, the step of optimizing the execution module includes:

[0035] Obtain the output data of the functional modules;

[0036] The average output of the calculation function module;

[0037] The coordination parameters between the calculation function modules satisfy the following:

[0038]

[0039] Among them, C ik (t) represents the collaboration metric between the i-th module and the k-th module at time t; and These are the average output values ​​of the i-th module and the k-th module, respectively.

[0040] As a preferred embodiment of the modular design method for the fully automated inspection robot described in this invention, the step of optimizing the execution module includes:

[0041] Obtain the error threshold parameter and the collaborative threshold parameter;

[0042] Calculate the module error value and coordination parameters of the functional modules;

[0043] Determine the relationship between the module error value and the error threshold parameter;

[0044] Determine the relationship between the collaborative parameter and the collaborative threshold parameter;

[0045] Adjust the module weight value based on the judgment result.

[0046] To further solve the above-mentioned technical problems, the present invention provides the following technical solution: a modular design system for a fully automated inspection robot, comprising: a parameter configuration module, used to divide the robot system into multiple functionally independent modules, and to obtain the status parameters and working parameters of the functionally independent modules;

[0047] The data generation module is used to generate data based on the state parameters and the operating parameters.

[0048] An optimization control module is used to calculate the module error value and coordination parameters based on the module output data, determine the module weight value based on the module error value and the coordination parameters, and generate the system output result.

[0049] A computer device includes a memory and a processor, the memory storing a computer program, characterized in that the processor executes the computer program to implement the steps of the modular design method for a fully automated inspection robot as described above.

[0050] A computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of the modular design method for a fully automated inspection robot as described above.

[0051] The beneficial effects of this invention are as follows: 1. By dividing the robot system into multiple functionally independent modules, each module focuses on a specific task, enabling the system to be flexibly combined and configured according to actual needs. This modular structure greatly enhances the system's scalability, allowing for rapid adjustment and adaptation of module combinations according to different detection tasks, thereby achieving optimal detection results. The independence between modules allows the system to be easily adjusted when encountering new tasks or changing requirements without requiring significant modifications to the overall structure, reducing the coupling between hardware and software, and enhancing the system's maintainability and upgradeability.

[0052] 2. This invention allows each module to dynamically adjust its initial state and operating parameters according to current environmental changes and task requirements. The operating state and output of a module not only depend on its inherent characteristics but are also closely related to environmental factors (such as power, voltage, gravity, temperature, humidity, etc.) and task objectives. By precisely configuring the initial conditions, state, and operating parameters of the modules and monitoring the performance and feedback information of the modules in real time, this invention ensures that the system can adapt to different working environments, thereby maximizing the accuracy and efficiency of the detection task.

[0053] 3. In this invention, the modules can not only work independently, but also work collaboratively according to task requirements; by establishing a collaborative metric between modules, the modules can dynamically adjust themselves based on each other's output information when performing tasks; this collaborative mechanism not only enhances the accuracy of task completion, but also optimizes the task execution results based on the interaction between modules; when multiple modules work collaboratively, task resources can be better allocated, system errors can be reduced, and overall performance can ultimately be improved.

[0054] 4. During task execution, this invention optimizes the configuration and combination of modules to ensure that the most suitable module is selected at each task stage. By minimizing errors and measuring inter-module collaboration, it ensures that the optimal combination of modules is used at each stage, thereby minimizing task execution errors. The contribution of each module is evaluated through weighted fusion and combined with its synergistic effect with other modules to finally select the optimal module for task execution. This dynamic adjustment and optimization of module selection enables the robot to maintain high efficiency and accuracy in ever-changing task environments. Attached Figure Description

[0055] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 This is a schematic diagram of the overall process of a modular design method for a fully automated inspection robot proposed in this invention;

[0057] Figure 2 This is a diagram of the computer equipment used in the modular design method of a fully automated inspection robot proposed in this invention. Detailed Implementation

[0058] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0059] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0060] Example 1, referring to Figure 1 As an embodiment of the present invention, a modular design method for a fully automated inspection robot is provided.

[0061] S1. Divide the robot system into functionally independent modules. Each module is dynamically adjusted according to specific initial conditions, state and working parameters to adapt to different task requirements and environmental conditions. By adjusting the cooperation and feedback between modules, the status and output of the modules are dynamically updated during the task.

[0062] The robot system is divided into functionally independent modules, each responsible for a specific task, such as data acquisition, signal processing, detection algorithms, and decision-making systems. These modules can be recombined and configured according to actual needs without significantly altering the overall robot structure. This modular design not only enhances the system's scalability and flexibility but also allows for rapid adaptation of different functional module combinations to achieve optimal detection results for various detection tasks.

[0063] To ensure that the modules can collaborate effectively in a changing working environment, each module needs to be precisely configured according to specific initial conditions, status, and working parameters. Each module is not static at startup, but is dynamically adjusted according to the overall needs of the system and the actual situation of the current environment.

[0064] The initial conditions, status, and operating parameters of each module are defined based on its functional requirements, environmental characteristics, and preset task objectives. Specifically, initial conditions refer to external environmental factors and system-set task objectives at module startup, such as variables like power, gravity, voltage, temperature, humidity, light intensity, and network latency, which directly affect the module's performance. Status refers to the module's operating condition at each moment, including its working state (e.g., on / off, normal / faulty), feedback information during execution, and the results of the previous operation. Operating parameters include all adjustable variables that determine the module's behavior, such as processing speed, data acquisition frequency, signal amplitude, and drive current, which are dynamically adjusted through external control signals to ensure stable operation of the module under constantly changing environments and task requirements.

[0065] When the task starts, each module sets its state S according to specific initial conditions. i (0) and operating parameter P i (0), and calculate the initial output D. i (0); The initial output is affected not only by the inherent characteristics of the module but also by environmental factors; by analyzing the initial state, initial parameters, and external environment of the module, the preliminary task output can be obtained. The initial output is calculated using the following formula:

[0066] D i (0)=η i ·(S i (0)·P i (0))+ξ i ·E i ;

[0067] Where, η i ξ is the efficiency coefficient of the i-th module, reflecting the module's efficiency in completing the task under the initial state, and is obtained through experimental measurement; i This is the influence coefficient of external environmental factors, reflecting the degree of influence of the external environment on the module performance, obtained through experiments; the external environmental factor E of the i-th module. i Variables such as power, gravity, voltage, temperature, and humidity directly affect the module's operating status. In the initial stage, the initial output results are used to predict the performance of each module at the beginning of the task, thereby providing basic data for subsequent adjustments and optimizations.

[0068] As the task progresses, the state and output of each module will change. Therefore, the state of each module must be continuously adjusted to adapt to the current working environment and task requirements. Based on the error between the output of the previous moment and the target output, and combined with feedback from the collaborative modules, the state of the modules is dynamically adjusted. The formula for updating the state of a module at each moment is:

[0069] S i (t)=S i (t-1)+ΔS i (t);

[0070]

[0071] Among them, S i (t) represents the state of the i-th module at time t, based on the state S at the previous time. i (t-1) and the current state change ΔS i (t) is updated; state change ΔS i (t) consists of two parts: one is an adjustment term α based on the output error. i ·(D i (t-1)-D target (t-1)), the other is an adjustment item based on inter-module collaboration. Among them, D i (t-1) and D target (t-1) represent the previous time-to-time output and the target output of the module, respectively; α i It is the sensitivity coefficient of the i-th module to its own error, which determines the output error D. i (t-1)-D target The extent of the impact of (t-1) on state updates is determined by the engineer's experience; w ik (t) is the coordination coefficient between the i-th module and the k-th module at the current time, which determines the degree of mutual influence between the modules and is obtained through experimental adjustment; β i The sensitivity of the i-th module to collaborative information feedback is represented by , obtained through experimentation or design optimization; n is the number of modules; D k (t-1) is the output of the k-th module at the previous time step. The module state update ensures that the module state can be adjusted in a timely manner based on the current error and the output of other modules.

[0072] S2. During task execution, the robot optimizes the output of each task stage by dynamically adjusting the combination and weight of modules. Module selection is based on a comprehensive evaluation of error minimization and inter-module synergy. The optimal module is selected according to real-time task and environmental changes, and the module configuration is adjusted in real time.

[0073] In each task phase, the configuration and combination of modules are dynamically adjusted to select the optimal modules based on specific task requirements and the current task phase objectives. The optimization goal of task partitioning and module configuration is to minimize task execution errors. Therefore, the combination and weight of modules are optimized using the following formula:

[0074]

[0075] Among them, O j The output of the j-th task stage is obtained by weighted summation of the outputs of all modules; the output of the i-th module in the j-th task stage is determined by weight w. i The activation function is determined by the output of the activation function; the activation function used is the Sigmoid function, which is determined by γ. i Adjust the sensitivity to module output error and activate the sensitivity coefficient γ. i Adjust through actual testing; It is a synergistic modulator, controlling the degree of influence of synergistic effects on the final output, and is obtained through experiments; C ik (t) is the collaboration metric between the i-th module and the k-th module at time t. The output error of each module is mapped to a range of [0,1]. The smaller the error, the closer the output is to 1, indicating a greater contribution of the module to task completion. Therefore, the optimal module is selected in the following two ways:

[0076] 1. Minimize Error Output: To measure the performance of each module in the task phase, an error metric formula is used to quantify the difference between the module's output and the target output, thereby selecting the module that contributes the most. The error formula is defined as follows:

[0077] E i (t)=|D i (t)-D target (t)|≤∈ i ;

[0078] Among them, E i (t) is the output error of the module at time t, ∈ i This is the error threshold, representing the maximum allowable error of the system. When the error E... i (t) is less than or equal to the set threshold ∈ j When the error is close to the target value, it indicates that the module output is performing well; conversely, modules with errors greater than the set threshold will be suppressed during the optimal selection process. The error minimization process is achieved through an activation function, which adjusts the contribution of each module so that modules with errors less than or equal to the set threshold have higher weights in the final weighted sum.

[0079] 2. Module Collaboration: Introduce a collaboration metric to describe the collaborative effect of a module with other modules in the task phase, which ultimately affects module selection.

[0080]

[0081] Among them, C ik (t) represents the collaboration metric between the i-th module and the k-th module at time t; and These are the average outputs of the i-th and k-th modules, respectively. The collaboration metric evaluates the collaborative effect between modules by calculating the output correlation. Modules with strong collaboration mean they can jointly optimize task completion, thereby improving overall system performance. A larger collaboration metric value indicates a stronger collaborative effect between modules, and the corresponding module will receive a higher weight in the final output.

[0082] The selection process for the optimal module is based on a comprehensive evaluation of module output error and inter-module synergy. Modules with small errors and strong synergy are assigned the highest weight and selected as the optimal module. Finally, the optimal task output O is formed through weighted fusion. j .

[0083] The selected optimal module will connect with other modules via a network. Each module will exchange data through a standardized communication interface, ensuring the stability and efficiency of data transmission. The selection of the optimal module depends not only on the output and synergy of the current task phase but also on the dynamic changes in the task. For example, environmental changes may lead to a decrease in the efficiency of some modules, or new task requirements may necessitate the introduction of different types of modules. Therefore, during task execution, the progress of the task and changes in the environment will be continuously monitored, and the module configuration will be adjusted in real time to ensure that the most suitable combination of modules can be used at each stage.

[0084] In summary, the beneficial effects of this invention are as follows: 1. By dividing the robot system into multiple functionally independent modules, each module focuses on a specific task, enabling the system to be flexibly combined and configured according to actual needs. This modular structure greatly enhances the system's scalability, allowing for rapid adjustment and adaptation of module combinations according to different detection tasks, thereby achieving optimal detection results. The independence between modules allows the system to be easily adjusted when encountering new tasks or changing requirements without requiring significant modifications to the overall structure, reducing the coupling between hardware and software, and enhancing the system's maintainability and upgradeability.

[0085] 2. This invention allows each module to dynamically adjust its initial state and operating parameters according to current environmental changes and task requirements. The operating state and output of a module not only depend on its inherent characteristics but are also closely related to environmental factors (such as power, voltage, gravity, temperature, humidity, etc.) and task objectives. By precisely configuring the initial conditions, state, and operating parameters of the modules and monitoring the performance and feedback information of the modules in real time, this invention ensures that the system can adapt to different working environments, thereby maximizing the accuracy and efficiency of the detection task.

[0086] 3. In this invention, the modules can not only work independently, but also work collaboratively according to task requirements; by establishing a collaborative metric between modules, the modules can dynamically adjust themselves based on each other's output information when performing tasks; this collaborative mechanism not only enhances the accuracy of task completion, but also optimizes the task execution results based on the interaction between modules; when multiple modules work collaboratively, task resources can be better allocated, system errors can be reduced, and overall performance can ultimately be improved.

[0087] 4. During task execution, this invention optimizes the configuration and combination of modules to ensure that the most suitable module is selected at each task stage. By minimizing errors and measuring inter-module collaboration, it ensures that the optimal combination of modules is used at each stage, thereby minimizing task execution errors. The contribution of each module is evaluated through weighted fusion and combined with its synergistic effect with other modules to finally select the optimal module for task execution. This dynamic adjustment and optimization of module selection enables the robot to maintain high efficiency and accuracy in ever-changing task environments.

[0088] Example 2, an embodiment of the present invention, provides a modular design system for a fully automated inspection robot, comprising:

[0089] The parameter configuration module is used to divide the robot system into multiple functionally independent modules and obtain the status parameters and working parameters of each functionally independent module.

[0090] The data generation module is used to generate output data based on status parameters and operating parameters.

[0091] The optimization control module is used to calculate the module error value and coordination parameters based on the module output data, determine the module weight value based on the module error value and coordination parameters, and generate the system output results.

[0092] Example 3, referring to Figure 2This is one embodiment of the present invention, which differs from the previous embodiment in that: if the function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0093] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0094] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0095] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0096] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A modular design method for a fully automated inspection robot, characterized in that, include: The robot system is divided into multiple functionally independent modules, the state parameters and working parameters of the modules are obtained, and the module output data is generated based on the state parameters and working parameters. During task execution, the robot optimizes the output of each task stage by dynamically adjusting the combination and weight of modules. Module selection is based on a comprehensive evaluation of error minimization and inter-module synergy. The optimal module is selected according to real-time task and environmental changes, and the module configuration is adjusted in real time. The steps to build a modular system include: Obtain environmental factor parameters and module efficiency coefficients; Calculate the initial module output data, which satisfies the following: D i (0) = η i · (S i (0) · P i (0)) + ξ i · E i ; Where, η i ξ is the efficiency coefficient of the i-th module, reflecting the module's efficiency in completing the task under the initial state, and is obtained through experimental measurement; i It is the influence coefficient of external environmental factors; The steps involved in building a modular system also include: The data output by the acquisition module at the previous moment; Obtain the target output data and module collaboration coefficients; Calculate the update amount of the state parameters, and update the state parameters, wherein: The update of the state parameters satisfies: S i (t)=S i (t-1)+ΔS i (t); The update amount of the state parameter satisfies: Among them, S i (t) represents the state of the i-th module at time t, based on the state S at the previous time. i (t-1) and the current state change ΔS i (t) is updated; state change ΔS i (t) consists of two parts: one is an adjustment term α based on the output error. i ·(D i (t-1)-D target (t-1)), the other is an adjustment item based on inter-module collaboration. Among them, D i (t-1) and D target (t-1) represent the previous time-to-time output and the target output of the module, respectively; α i It is the sensitivity coefficient of the i-th module to its own error, which determines the output error D. i (t-1)-D target (t-1) represents the degree of influence on state updates; w ik (t) is the coordination coefficient between the i-th module and the k-th module at the current time; β i This represents the sensitivity of the i-th module to collaborative information feedback; n is the number of modules; D k (t-1) is the output of the k-th module at the previous time step.

2. The modular design method for the fully automated inspection robot as described in claim 1, characterized in that: The steps for optimizing the execution module include: Obtain the activation sensitivity coefficient and the co-regulation factor; Calculate the module weight value; The system output is generated based on the module weight values, and the system output satisfies the following: Among them, O j The output of the j-th task stage is obtained by weighted summation of the outputs of all modules; the output of the i-th module in the j-th task stage is determined by weight w. i The output of the activation function determines the outcome. It is a co-regulatory factor; C ik (t) is the collaboration metric between the i-th module and the k-th module at time t.

3. The modular design method for a fully automated inspection robot as described in claim 2, characterized in that: The steps for performing module optimization also include: Obtain the error threshold parameter; The module error value of the calculation function module satisfies: E i (t)=|D i (t)-D target (t)|≤∈ i ; Among them, E i (t) is the output error of the module at time t, ∈ i It is the error threshold, representing the maximum allowable error of the system; when the error E i (t) is less than or equal to the set threshold ∈ j When the error is close to the target value, it indicates that the module output is performing well; conversely, modules with errors greater than the set threshold will be suppressed during the optimal selection process.

4. The modular design method for the fully automated inspection robot as described in claim 3, characterized in that: The steps for performing module optimization also include: Obtain the output data of the functional modules; The average output of the calculation function module; The coordination parameters between the calculation function modules satisfy the following: Among them, C ik (t) represents the collaboration metric between the i-th module and the k-th module at time t; and These are the average output values ​​of the i-th module and the k-th module, respectively.

5. The modular design method for a fully automated inspection robot as described in claim 4, characterized in that: The steps for performing module optimization also include: Obtain the error threshold parameter and the collaborative threshold parameter; Calculate the module error value and coordination parameters of the functional modules; Determine the relationship between the module error value and the error threshold parameter; Determine the relationship between the collaborative parameter and the collaborative threshold parameter; Adjust the module weight value based on the judgment result.

6. A modular design system for a fully automated inspection robot, based on the modular design method for a fully automated inspection robot according to any one of claims 1 to 5, characterized in that: include, The parameter configuration module is used to divide the robot system into multiple functionally independent modules and obtain the status parameters and working parameters of the functionally independent modules. The data generation module is used to generate data based on the state parameters and the operating parameters. An optimization control module is used to calculate the module error value and coordination parameters based on the module output data, determine the module weight value based on the module error value and the coordination parameters, and generate the system output result.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the modular design method for the fully automated inspection robot according to any one of claims 1 to 5.

8. 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 modular design method for the fully automated inspection robot according to any one of claims 1 to 5.

Images