Nano ceramic material preparation method and system for multi-robot intelligent cooperative scheduling

Abstract

The invention provides a nano ceramic material preparation method and system for multi-robot intelligent cooperative scheduling. The method comprises the steps that S1, initialization self-inspection is conducted on multiple robots participating in preparation; s2, receiving a production order containing formula information, and extracting key parameters from the generated order; generating a task chain composed of a plurality of associated tasks based on a nano ceramic preparation process sequence; s3, storing the task chain into a priority queue; the exclusive mechanical arm executes operation according to the task parameters; s4, uploading the task ID, the process parameters and the sensor data to an IMS (IP Multimedia Subsystem) in real time; dynamically optimizing the parameters of the next process by adopting a machine learning algorithm based on the real-time data of the current process to form a data closed loop; s5, updating the prediction model based on historical data; dynamically adjusting a task priority rule; and S6, triggering the next task until all tasks are completed. And through multi-robot cooperation and intelligent scheduling, the idle time of equipment is shortened, and the overall production efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of intelligent manufacturing technology, and more specifically, to a method and system for preparing nano-ceramic materials using intelligent collaborative scheduling of multiple robots. Background Technology

[0002] Nanoceramic materials, due to their excellent mechanical, electrical, and thermal properties, have broad application prospects in electronics, energy, aerospace, and other fields. However, the preparation process of nanoceramics involves multiple complex steps, including batching, dispersion, degassing, sintering, modification, and testing, requiring extremely high precision in process parameter control. Traditional manual operation or simple automated control methods suffer from low production efficiency, poor process stability, and difficulty in ensuring quality consistency, failing to meet the demands for large-scale, high-quality production of nanoceramics.

[0003] Currently, although there are some studies on multi-robot collaborative ceramic preparation, no reports have been published on intelligent scheduling schemes for multi-robots throughout the entire process of nano-ceramic preparation or dynamic priority allocation strategies based on data closed-loop. Existing multi-robot collaborative ceramic preparation technologies mainly suffer from the following shortcomings:

[0004] 1. Lack of targeted optimization for the specific process requirements of nanoceramic preparation; 2. The multi-robot collaborative scheduling strategy is not flexible enough and cannot cope with real-time changes in process parameters; 3. The data closed-loop mechanism was not fully utilized to achieve dynamic optimization of process parameters and adaptive adjustment of task priorities. Summary of the Invention

[0005] In view of this, this application provides a method and system for preparing nano-ceramic materials using intelligent collaborative scheduling of multiple robots, which can achieve dynamic optimization of process parameters and intelligent allocation of task priorities through a data closed-loop mechanism, thereby improving the production efficiency, product quality and consistency of nano-ceramic material preparation.

[0006] To achieve the above objectives, the technical solution adopted in this application is as follows: A method for preparing nano-ceramic materials using intelligent collaborative scheduling of multiple robots includes: S1: System Initialization and Resource Configuration: Perform initialization self-checks on the multiple robots involved in the preparation to confirm the motion accuracy, sensor status, and actuator performance of each robot; connect each robot to the Information Management System (IMS) to ensure real-time data transmission and storage; the robots include dedicated robotic arms and hot-end robotic arms; initialize the artificial intelligence (AI) optimization module; preset the threshold values ​​of key parameters for each process of nano-ceramic materials according to the requirements of the nano-ceramic preparation process; S2: Production Order Parsing and Task Chain Generation: Receive production orders containing formula information, extract key parameters from the generated orders, including raw material composition, proportioning accuracy, sintering atmosphere, and yield requirements; generate a task chain consisting of multiple related tasks based on the nano-ceramic preparation process sequence, with each task corresponding to a dedicated robotic arm; S3: Dynamic scheduling and execution of multiple robots: The task chain is stored in a priority queue, and the priority is dynamically adjusted based on the process sequence, order urgency, or task delay cost; the dedicated robotic arm performs operations according to the task parameters and collects sensor data in real time; The sensor is mounted on the robot.

[0007] S4: Data closed loop and AI real-time optimization: The task ID, process parameters and sensor data are uploaded to the IMS system in real time to form a traceable production data chain; the task ID is used to mark different tasks; for key processes, the AI ​​optimization module uses machine learning algorithms to dynamically optimize the parameters of the next process based on the real-time data of the current process, forming a data closed loop, automatically updating the optimized parameters to the parameter set of the next task, and recording the parameter change history; S5: AI Offline Optimization and Scheduling Strategy Update: The AI ​​optimization module periodically extracts historical data from IMS and updates the prediction model based on the historical data; it feeds back the optimization suggestions output by the model to the scheduling system to dynamically adjust the task priority rules; S6: Detect and record the current task completion status, trigger the next task, and continue until all tasks are completed.

[0008] Furthermore, in S1, the nano-ceramic material processing steps are, in sequence, batching, dispersion, degassing, sintering, modification, detection, and storage; in S2, based on the nano-ceramic preparation process sequence, a task chain consisting of multiple related tasks is generated, with each task corresponding to a dedicated robotic arm. Specifically, based on the nano-ceramic preparation process sequence, a task chain consisting of 7 related tasks is generated, with each task corresponding to 1 process and 1 dedicated robotic arm; there are 7 dedicated robotic arms, namely R1-R7; among them, robotic arm R4 and the hot-end robotic arm form a composite execution unit, specifically for handling the high-temperature sintering process.

[0009] Furthermore, based on the sequence of nano-ceramic preparation processes, a task chain consisting of seven related tasks is generated, with each task corresponding to one process and one dedicated robotic arm; there are seven dedicated robotic arms, designated R1-R7; among them, robotic arm R4 and the hot-end robotic arm form a composite execution unit, specifically handling the high-temperature sintering process, including: Generate a batching task T1 and assign task T1 to robotic arm R1. The parameters of task T1 include raw material composition, weighing accuracy and mixing ratio. Generate a dispersion task T2: Assign task T2 to the R2 robotic arm. The parameters of task T2 include the multiphysics dispersion method, the AI-predicted dispersion time and intensity; the multiphysics dispersion method includes ultrasound, ball milling and shearing. Generate debubbling task T3: Assign task T3 to the R3 robotic arm. The parameters of task T3 include vacuum level, bubble threshold, and debubbling time. Generate sintering task T4: Task T4 is executed collaboratively by the R4 robotic arm and the hot end robotic arm. The parameters of task T4 include the sintering temperature curve, the pressure value of the gas environment in the sintering furnace, and the second-level time control accuracy. Generate modified task T5: Assign task T5 to the R5 robotic arm. The parameters of task T5 include coupling agent type and coating thickness. Generate inspection task T6: Assign task T6 to the R6 robotic arm. The parameters of task T6 include material particle size, viscosity, dielectric properties test items and inspection accuracy. Generate storage task T7: Assign task T7 to the R7 robotic arm. The parameters of task T7 include storage location code and sample tracking ID. Task association settings: Establish task dependencies through "next task ID" to form a one-way closed-loop task chain; T1-T7 are task IDs.

[0010] Furthermore, in step S3, before the dedicated robotic arm executes operations according to the task parameters and collects sensor data in real time, it also includes: detecting whether the robotic arm corresponding to the current task is in a busy state. If so, the task delay cost is calculated, the task priority is adjusted according to the task delay cost, and the robotic arm is re-entered into the queue; otherwise, the dedicated robotic arm executes operations according to the task parameters and collects sensor data in real time.

[0011] Furthermore, in S3, the dynamic adjustment formula for task priority is: new priority = original priority + (delay cost / priority adjustment coefficient), where the delay cost is calculated based on the task type, formula value, and delivery date; the priority adjustment coefficient adopts a dynamic feedback method and is set in layers according to task type.

[0012] A multi-robot intelligent collaborative scheduling system for the preparation of nano-ceramic materials includes: The initialization module is used for system initialization and resource configuration: it performs an initialization self-check on the multiple robots involved in the preparation to confirm the motion accuracy, sensor status, and actuator performance of each robot; it connects each robot to the Information Management System (IMS) to ensure real-time data transmission and storage; the robots include dedicated robotic arms and hot-end robotic arms; it initializes the Artificial Intelligence (AI) optimization module; and it presets the threshold values ​​of key parameters for each process of nano-ceramic material preparation according to the requirements of the nano-ceramic preparation process. The task chain generation module is used for production order parsing and task chain generation: it receives production orders containing formula information, extracts key parameters from the generated orders, including raw material composition, proportioning accuracy, sintering atmosphere and yield requirements; and generates a task chain composed of multiple related tasks based on the nano-ceramic preparation process sequence, with each task corresponding to a dedicated robotic arm. The scheduling and execution module is used for dynamic scheduling and execution of multiple robots: it stores task chains in a priority queue, and the priority is dynamically adjusted based on process sequence, order urgency, or task delay cost; the dedicated robotic arm executes operations according to task parameters and collects sensor data in real time; The sensor is mounted on the robot.

[0013] The AI ​​closed-loop optimization module is used for data closure and real-time AI optimization: it uploads task IDs, process parameters, and sensor data to the IMS system in real time to form a traceable production data chain; the task ID is used to mark different tasks; for key processes, the AI ​​optimization module uses machine learning algorithms to dynamically optimize the parameters of the next process based on the real-time data of the current process, forming a data closed loop, automatically updating the optimized parameters to the parameter set of the next task, and recording the parameter change history; The AI ​​offline optimization and priority update module is used for AI offline optimization and scheduling strategy updates: the AI ​​optimization module periodically extracts historical data from IMS and updates the prediction model based on the historical data; the optimization suggestions output by the model are fed back to the scheduling system to dynamically adjust the task priority rules.

[0014] The detection and triggering module is used to detect and record the current task completion status, trigger the next task, and so on until all tasks are completed.

[0015] Furthermore, the processes for producing the nano-ceramic material are, in sequence, batching, dispersion, degassing, sintering, modification, testing, and storage. The process of generating a task chain based on the nano-ceramic preparation process sequence, with each task corresponding to a dedicated robotic arm, specifically involves generating a task chain of 7 related tasks, each task corresponding to one process and one dedicated robotic arm. There are 7 dedicated robotic arms, designated R1-R7. Among them, robotic arm R4, together with the hot-end robotic arm, forms a composite execution unit specifically for handling the high-temperature sintering process.

[0016] Furthermore, based on the sequence of nano-ceramic preparation processes, a task chain consisting of seven related tasks is generated, with each task corresponding to one process and one dedicated robotic arm; there are seven dedicated robotic arms, designated R1-R7; among them, robotic arm R4 and the hot-end robotic arm form a composite execution unit, specifically handling the high-temperature sintering process, including: Generate a batching task T1 and assign task T1 to robotic arm R1. The parameters of task T1 include raw material composition, weighing accuracy and mixing ratio. Generate a dispersion task T2: Assign task T2 to the R2 robotic arm. The parameters of task T2 include the multiphysics dispersion method, the AI-predicted dispersion time and intensity; the multiphysics dispersion method includes ultrasound, ball milling and shearing. Generate debubbling task T3: Assign task T3 to the R3 robotic arm. The parameters of task T3 include vacuum level, bubble threshold, and debubbling time. Generate sintering task T4: Task T4 is executed collaboratively by the R4 robotic arm and the hot end robotic arm. The parameters of task T4 include the sintering temperature curve, the pressure value of the gas environment in the sintering furnace, and the second-level time control accuracy. Generate modified task T5: Assign task T5 to the R5 robotic arm. The parameters of task T5 include coupling agent type and coating thickness. Generate inspection task T6: Assign task T6 to the R6 robotic arm. The parameters of task T6 include material particle size, viscosity, dielectric properties test items and inspection accuracy. Generate storage task T7: Assign task T7 to the R7 robotic arm. The parameters of task T7 include storage location code and sample tracking ID. Task association settings: Establish task dependencies through "next task ID" to form a one-way closed-loop task chain; T1-T7 are task IDs.

[0017] Furthermore, before the dedicated robotic arm executes operations according to task parameters and collects sensor data in real time, the process includes: detecting whether the robotic arm corresponding to the current task is in a busy state; if so, calculating the task delay cost, adjusting the task priority based on the task delay cost, and re-entering the queue; otherwise, the dedicated robotic arm executes operations according to task parameters and collects sensor data in real time.

[0018] Furthermore, the dynamic adjustment formula for task priority is: New priority = Original priority + (Delay cost / Priority adjustment coefficient), where the delay cost is calculated based on the task type, formula value, and delivery date; the priority adjustment coefficient adopts a dynamic feedback method and is set in layers according to task type.

[0019] Compared with the prior art, the beneficial effects of this application are: 1. Improve production efficiency: Reduce equipment downtime and improve overall production efficiency through multi-robot collaboration and intelligent scheduling.

[0020] 2. Optimize process parameters: Based on a data closed-loop mechanism, dynamically optimize process parameters to improve product quality and consistency.

[0021] 3. Adaptive scheduling capability: It can dynamically adjust task priorities based on real-time production status and resource conflicts to ensure that critical tasks are executed first.

[0022] 4. Reduce human intervention: Achieve full automation of the nano-ceramic preparation process, reduce human intervention, and minimize the impact of human factors on product quality.

[0023] 5. Data-driven decision-making: Utilize historical data and AI models to achieve continuous optimization of the production process and decision support. Attached Figure Description

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0025] Figure 1 This is a flowchart of the method for preparing nano-ceramic materials using intelligent collaborative scheduling of multiple robots, as described in this application.

[0026] Figure 2 This is a schematic diagram illustrating the principle of the method for preparing nano-ceramic materials using intelligent collaborative scheduling of multiple robots, as described in this application.

[0027] Figure 3 This is a structural block diagram of the multi-robot intelligent collaborative scheduling system for the preparation of nano-ceramic materials according to this application. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of this application, but not all embodiments.

[0029] like Figure 1 and Figure 2 As shown, the method for preparing nano-ceramic materials using intelligent collaborative scheduling of multiple robots includes: S1: System Initialization and Resource Configuration: Perform initialization self-checks on the multiple robots involved in the preparation to confirm the motion accuracy, sensor status, and actuator performance of each robot; connect each robot to the Information Management System (IMS) to ensure real-time data transmission and storage; the robots include dedicated robotic arms and hot-end robotic arms; initialize the artificial intelligence (AI) optimization module; preset the threshold values ​​of key parameters for each process of nano-ceramic materials according to the requirements of the nano-ceramic preparation process; The multiple robots refer to various types of robots responsible for different process steps, including batching robots, dispersing robots, degassing robots, sintering robots, modification robots, inspection robots, and storage robots. In this application, the robots are visualized as robotic arms.

[0030] Specifically, the artificial intelligence (AI) optimization module is used to optimize dispersion time and sintering process curve.

[0031] The Information Management System (IMS) is responsible for storing and managing all data in the production process, including process parameters, sensor data, task status, and optimization records.

[0032] Specifically, the key parameter thresholds for each process of the nano-ceramic material are preset as follows: the vacuum degree of the vacuum degassing zone is preset to be ≥0.1Pa and the dielectric test frequency of the detection zone is set to 10GHz.

[0033] S2: Production Order Parsing and Task Chain Generation: Receive production orders containing formula information, extract key parameters from the generated orders, including raw material composition, proportioning accuracy, sintering atmosphere, and yield requirements; generate a task chain consisting of multiple related tasks based on the nano-ceramic preparation process sequence, with each task corresponding to a dedicated robotic arm; Specifically, the raw material components include, for example... The sintering atmosphere is argon (Ar).

[0034] S3: Dynamic scheduling and execution of multiple robots: The task chain is stored in a priority queue, and the priority is dynamically adjusted based on the process sequence, order urgency, or task delay cost; the dedicated robotic arm performs operations according to the task parameters and collects sensor data in real time; For example, the R1 robotic arm completes the feeding of multiple components according to the formula ratio. The sensors are mounted on the robot.

[0035] S4: Data Closed Loop and AI Real-Time Optimization: Task ID, process parameters, and sensor data are uploaded to the IMS system in real time to form a traceable production data chain; the task ID is used to mark different tasks; for key processes, the AI ​​optimization module uses machine learning algorithms to dynamically optimize the parameters of the next process based on the real-time data of the current process, forming a data closed loop, automatically updating the optimized parameters to the parameter set of the next task (such as feeding back the optimized parameters of T4 to T5), and recording the parameter change history; The sensor data includes: viscosity values ​​during dispersion and sintering temperature curves during sintering.

[0036] For core processes such as dispersion, sintering, and modification, the AI ​​optimization module optimizes subsequent parameters based on real-time data. For example, in the dispersion process, the AI ​​adjusts the vacuum parameters of the next process (degassing) based on real-time viscosity data; in the sintering process, the AI ​​corrects the subsequent holding time based on temperature curve deviations.

[0037] Since the process parameters of key process steps (including dispersion, sintering and modification) have a significant impact on the quality of nano-ceramic products, they need to be optimized in real time.

[0038] S5: AI Offline Optimization and Scheduling Strategy Update: The AI ​​optimization module periodically extracts historical data from IMS and updates the prediction model based on the historical data; it feeds back the optimization suggestions output by the model to the scheduling system and dynamically adjusts the task priority rules.

[0039] For example, the AI ​​optimization module extracts historical data from the IMS every hour (such as the correlation data between dispersion time and product performance of different formulations), and updates the prediction model based on the historical data (such as optimizing the mapping relationship between dispersion time and particle size distribution).

[0040] The optimization suggestions output by the model (such as "for high-viscosity formulations, it is recommended to extend the dispersion time") are fed back to the scheduling system to dynamically adjust the task priority rules.

[0041] Therefore, this application periodically retrieves historical data from the database to train and update the AI ​​model; and generates process optimization suggestions to update the multi-robot scheduling strategy.

[0042] S6: Detect and record the current task completion status, trigger the next task, and continue until all tasks are completed.

[0043] Furthermore, in S1, the nano-ceramic material processing steps are, in sequence, batching, dispersion, degassing, sintering, modification, detection, and storage; in S2, based on the nano-ceramic preparation process sequence, a task chain consisting of multiple related tasks is generated, with each task corresponding to a dedicated robotic arm. Specifically, based on the nano-ceramic preparation process sequence, a task chain consisting of 7 related tasks is generated, with each task corresponding to 1 process and 1 dedicated robotic arm; there are 7 dedicated robotic arms, namely R1-R7; among them, robotic arm R4 and the hot-end robotic arm form a composite execution unit, specifically for handling the high-temperature sintering process.

[0044] Furthermore, based on the sequence of nano-ceramic preparation processes, a task chain consisting of seven related tasks is generated, with each task corresponding to one process and one dedicated robotic arm; there are seven dedicated robotic arms, designated R1-R7; among them, robotic arm R4 and the hot-end robotic arm form a composite execution unit, specifically handling the high-temperature sintering process, including: Generate a batching task T1 and assign task T1 to robotic arm R1. The parameters of task T1 include raw material composition, weighing accuracy and mixing ratio. Specifically, the weighing accuracy is at the 0.1 mg level.

[0045] Generate a dispersion task T2: Assign task T2 to the R2 robotic arm. The parameters of task T2 include the multiphysics dispersion method, the AI-predicted dispersion time and intensity; the multiphysics dispersion method includes ultrasound, ball milling and shearing. Generate debubbling task T3: Assign task T3 to the R3 robotic arm. The parameters of task T3 include vacuum level, bubble threshold, and debubbling time. Specifically, the vacuum degree is ≥0.1Pa, and the bubble threshold is ≤1ppm.

[0046] Generate sintering task T4: Task T4 is executed collaboratively by the R4 robotic arm and the hot end robotic arm. The parameters of task T4 include the sintering temperature curve, the pressure value of the gas environment in the sintering furnace, and the second-level time control accuracy. Generate modified task T5: Assign task T5 to the R5 robotic arm. The parameters of task T5 include coupling agent type and coating thickness. Specifically, the coating thickness error is ±0.01mm.

[0047] Generate inspection task T6: Assign task T6 to the R6 robotic arm. The parameters of task T6 include material particle size, viscosity, dielectric properties test items and inspection accuracy. Specifically, the detection accuracy is 0.5%.

[0048] Generate storage task T7: Assign task T7 to the R7 robotic arm. The parameters of task T7 include storage location code and sample tracking ID. Task association settings: Establish task dependencies through the next task ID to form a one-way closed-loop task chain; Specifically, by marking the next task of T1 as T2, a task dependency relationship is established, forming a unidirectional closed-loop task chain.

[0049] T1-T7 are task IDs.

[0050] Furthermore, in step S3, before the dedicated robotic arm executes operations according to the task parameters and collects sensor data in real time, it also includes: detecting whether the robotic arm corresponding to the current task is in a busy state. If so, the task delay cost is calculated, the task priority is adjusted according to the task delay cost, and the robotic arm is re-entered into the queue; otherwise, the dedicated robotic arm executes operations according to the task parameters and collects sensor data in real time.

[0051] The resource conflict detection in this application includes checking whether the robot is busy, whether the device is available, etc. When a conflict is detected (for example, R2 is performing a distributed task), a priority adjustment strategy based on latency cost is used to resolve the conflict.

[0052] This application adopts a dynamic task priority allocation strategy: the task delay cost is calculated based on factors such as formula value, task type, and delivery time. When resource conflicts occur, the task priority is adjusted based on the task delay cost. Specifically, tasks with high delay costs are given higher priority and executed first.

[0053] The formula for dynamically adjusting task priorities is: New priority = Original priority + (Delay cost / Priority adjustment coefficient).

[0054] To ensure timely responses to high-value or urgent tasks while avoiding frequent system oscillations, priority adjustment coefficients are set using a dynamic feedback method, combined with a hierarchical setting based on task type. For example, tasks are categorized into high-value tasks, routine tasks, and pre-processing tasks, with their priority adjustment coefficients decreasing sequentially. Online optimization is achieved through continuous monitoring of actual production indicators (latency rate, equipment changeover losses).

[0055] like Figure 3 As shown, a multi-robot intelligent collaborative scheduling system for the preparation of nano-ceramic materials includes: Initialization module 310 is used for system initialization and resource configuration: it performs initialization self-check on the multiple robots involved in the preparation, confirms the motion accuracy, sensor status and actuator performance of each robot; it connects each robot to the information management system (IMS) to ensure real-time data transmission and storage; the robots include dedicated robotic arms and hot-end robotic arms; it initializes the artificial intelligence (AI) optimization module; and it presets the threshold values ​​of key parameters for each process of nano-ceramic materials according to the requirements of the nano-ceramic preparation process. The task chain generation module 320 is used for production order parsing and task chain generation: it receives production orders containing formula information, extracts key parameters from the generated orders, including raw material composition, proportioning accuracy, sintering atmosphere and yield requirements; and generates a task chain composed of multiple related tasks based on the nano-ceramic preparation process sequence, with each task corresponding to a dedicated robotic arm. The scheduling and execution module 330 is used for dynamic scheduling and execution of multiple robots: it stores the task chain into a priority queue, and the priority is dynamically adjusted based on the process sequence, order urgency or task delay cost; the dedicated robotic arm performs operations according to the task parameters and collects sensor data in real time; The AI ​​closed-loop optimization module 340 is used for data closed-loop and AI real-time optimization: it uploads task ID, process parameters and sensor data to the IMS system in real time to form a traceable production data chain; the task ID is used to mark different tasks; for key processes, the AI ​​optimization module uses machine learning algorithms to dynamically optimize the parameters of the next process based on the real-time data of the current process, forming a data closed loop, automatically updating the optimized parameters to the parameter set of the next task, and recording the parameter change history; The AI ​​offline optimization and priority update module 350 is used for AI offline optimization and scheduling strategy updates: the AI ​​optimization module periodically extracts historical data from IMS and updates the prediction model based on the historical data; it feeds back the optimization suggestions output by the model to the scheduling system to dynamically adjust the task priority rules.

[0056] The detection trigger module 360 ​​is used to detect and record the current task completion status, trigger the next task, and continue until all tasks are completed.

[0057] Furthermore, the processes for producing the nano-ceramic material are, in sequence, batching, dispersion, degassing, sintering, modification, testing, and storage. The process of generating a task chain based on the nano-ceramic preparation process sequence, with each task corresponding to a dedicated robotic arm, specifically involves generating a task chain of 7 related tasks, each task corresponding to one process and one dedicated robotic arm. There are 7 dedicated robotic arms, designated R1-R7. Among them, robotic arm R4, together with the hot-end robotic arm, forms a composite execution unit specifically for handling the high-temperature sintering process.

[0058] Furthermore, based on the sequence of nano-ceramic preparation processes, a task chain consisting of seven related tasks is generated, with each task corresponding to one process and one dedicated robotic arm; there are seven dedicated robotic arms, designated R1-R7; among them, robotic arm R4 and the hot-end robotic arm form a composite execution unit, specifically handling the high-temperature sintering process, including: Generate a batching task T1 and assign task T1 to robotic arm R1. The parameters of task T1 include raw material composition, weighing accuracy and mixing ratio. Generate a dispersion task T2: Assign task T2 to the R2 robotic arm. The parameters of task T2 include the multiphysics dispersion method, the AI-predicted dispersion time and intensity; the multiphysics dispersion method includes ultrasound, ball milling and shearing. Generate debubbling task T3: Assign task T3 to the R3 robotic arm. The parameters of task T3 include vacuum level, bubble threshold (1ppm), and debubbling time. Generate sintering task T4: Task T4 is executed collaboratively by the R4 robotic arm and the hot end robotic arm. The parameters of task T4 include the sintering temperature curve, the pressure value of the gas environment in the sintering furnace, and the second-level time control accuracy. Generate modified task T5: Assign task T5 to the R5 robotic arm. The parameters of task T5 include coupling agent type and coating thickness. Generate inspection task T6: Assign task T6 to the R6 robotic arm. The parameters of task T6 include material particle size, viscosity, dielectric properties test items and inspection accuracy. Generate storage task T7: Assign task T7 to the R7 robotic arm. The parameters of task T7 include storage location code and sample tracking ID. Task association settings: Establish task dependencies through "next task ID" to form a one-way closed-loop task chain; T1-T7 are task IDs.

[0059] Furthermore, before the dedicated robotic arm executes operations according to task parameters and collects sensor data in real time, the process includes: detecting whether the robotic arm corresponding to the current task is in a busy state; if so, calculating the task delay cost, adjusting the task priority based on the task delay cost, and re-entering the queue; otherwise, the dedicated robotic arm executes operations according to task parameters and collects sensor data in real time.

[0060] Furthermore, the dynamic adjustment formula for task priority is: New priority = Original priority + (Delay cost / Priority adjustment coefficient), where the delay cost is calculated based on the task type, formula value, and delivery date; the priority adjustment coefficient adopts a dynamic feedback method and is set in layers according to task type.

[0061] For the apparatus embodiments, since they basically correspond to the method embodiments, the description is relatively simple; relevant details can be found in the description of the method embodiments. The apparatus embodiments described above are merely illustrative; the units described as separate components may or may not be physically separate, and are shown as units.

[0062] The components may or may not be physical units; that is, they may be located in one place or distributed across multiple network units, such as servers and clients. Some or all of the modules can be selected to achieve the purpose of this embodiment, depending on actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0063] The method and system for preparing nano-ceramic materials using multi-robot intelligent collaborative scheduling provided in this application achieve dynamic optimization of process parameters and intelligent allocation of task priorities through a data closed-loop mechanism, thereby improving the production efficiency, product quality, and consistency of nano-ceramic preparation.

[0064] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for preparing nano-ceramic materials using intelligent collaborative scheduling of multiple robots, characterized in that, include: S1: System Initialization and Resource Configuration: Perform initialization self-checks on the multiple robots involved in the preparation to confirm the motion accuracy, sensor status, and actuator performance of each robot; connect each robot to the Information Management System (IMS) to ensure real-time data transmission and storage; the robots include dedicated robotic arms and hot-end robotic arms; initialize the artificial intelligence (AI) optimization module; preset the threshold values ​​of key parameters for each process of nano-ceramic materials according to the requirements of the nano-ceramic preparation process; S2: Production Order Parsing and Task Chain Generation: Receive production orders containing formula information, extract key parameters from the generated orders, including raw material composition, proportioning accuracy, sintering atmosphere, and yield requirements; generate a task chain consisting of multiple related tasks based on the nano-ceramic preparation process sequence, with each task corresponding to a dedicated robotic arm; S3: Dynamic scheduling and execution of multiple robots: The task chain is stored in a priority queue, and the priority is dynamically adjusted based on the process sequence, order urgency, or task delay cost; the dedicated robotic arm performs operations according to the task parameters and collects sensor data in real time; S4: Data closed loop and AI real-time optimization: The task ID, process parameters and sensor data are uploaded to the IMS system in real time to form a traceable production data chain; the task ID is used to mark different tasks; for key processes, the AI ​​optimization module uses machine learning algorithms to dynamically optimize the parameters of the next process based on the real-time data of the current process, forming a data closed loop, automatically updating the optimized parameters to the parameter set of the next task, and recording the parameter change history; S5: AI Offline Optimization and Scheduling Strategy Update: The AI ​​optimization module periodically extracts historical data from IMS and updates the prediction model based on the historical data; it feeds back the optimization suggestions output by the model to the scheduling system to dynamically adjust the task priority rules; S6: Detect and record the current task completion status, trigger the next task, and continue until all tasks are completed.

2. The method for preparing nano-ceramic materials with intelligent collaborative scheduling of multiple robots as described in claim 1, characterized in that, In S1, the nano-ceramic material processing steps are, in sequence, batching, dispersion, degassing, sintering, modification, detection, and storage. In S2, based on the nano-ceramic preparation process sequence, a task chain consisting of multiple related tasks is generated, with each task corresponding to a dedicated robotic arm. Specifically, based on the nano-ceramic preparation process sequence, a task chain consisting of 7 related tasks is generated, with each task corresponding to 1 process and 1 dedicated robotic arm. There are 7 dedicated robotic arms, namely R1-R7. Among them, robotic arm R4 and hot-end robotic arm form a composite execution unit, which is specifically used to handle the high-temperature sintering process.

3. The method for preparing nano-ceramic materials with intelligent collaborative scheduling of multiple robots as described in claim 2, characterized in that, Based on the sequence of nano-ceramic preparation processes, a task chain consisting of 7 related tasks is generated, with each task corresponding to one process and one dedicated robotic arm; there are 7 dedicated robotic arms, designated R1-R7; among them, robotic arm R4 and the hot-end robotic arm form a composite execution unit, specifically handling the high-temperature sintering process, including: Generate a batching task T1 and assign task T1 to robotic arm R1. The parameters of task T1 include raw material composition, weighing accuracy and mixing ratio. Generate a distributed task T2: Assign task T2 to the R2 robotic arm. The parameters of task T2 include the multiphysics dispersion method, the AI-predicted dispersion time and intensity; the multiphysics dispersion method includes ultrasound, ball milling and shearing. Generate debubbling task T3: Assign task T3 to the R3 robotic arm. The parameters of task T3 include vacuum level, bubble threshold, and debubbling time. Generate sintering task T4: Task T4 is executed collaboratively by the R4 robotic arm and the hot end robotic arm. The parameters of task T4 include the sintering temperature curve, the pressure value of the gas environment in the sintering furnace, and the second-level time control accuracy. Generate modified task T5: Assign task T5 to the R5 robotic arm. The parameters of task T5 include coupling agent type and coating thickness. Generate inspection task T6: Assign task T6 to the R6 robotic arm. The parameters of task T6 include material particle size, viscosity, dielectric properties test items and inspection accuracy. Generate storage task T7: Assign task T7 to the R7 robotic arm. The parameters of task T7 include storage location code and sample tracking ID. Task association settings: Establish task dependencies through "next task ID" to form a one-way closed-loop task chain; T1-T7 are task IDs.

4. The method for preparing nano-ceramic materials with intelligent collaborative scheduling of multiple robots as described in any one of claims 1-3, characterized in that, In step S3, before the dedicated robotic arm executes operations according to the task parameters and collects sensor data in real time, the following steps are also included: detecting whether the robotic arm corresponding to the current task is in a busy state. If so, the task delay cost is calculated, the task priority is adjusted according to the task delay cost, and the task is re-entered into the queue; otherwise, the dedicated robotic arm executes operations according to the task parameters and collects sensor data in real time.

5. The method for preparing nano-ceramic materials with intelligent collaborative scheduling of multiple robots as described in claim 4, characterized in that, In S3, the dynamic adjustment formula for task priority is: new priority = original priority + (delay cost / priority adjustment coefficient), where the delay cost is calculated based on the task type, formula value and delivery date; the priority adjustment coefficient adopts a dynamic feedback method and is set in layers according to task type.

6. A multi-robot intelligent collaborative scheduling system for the preparation of nano-ceramic materials, characterized in that, include: The initialization module is used for system initialization and resource configuration: it performs an initialization self-check on the multiple robots involved in the preparation to confirm the motion accuracy, sensor status, and actuator performance of each robot; it connects each robot to the Information Management System (IMS) to ensure real-time data transmission and storage; the robots include dedicated robotic arms and hot-end robotic arms; it initializes the Artificial Intelligence (AI) optimization module; and it presets the threshold values ​​of key parameters for each process of nano-ceramic material preparation according to the requirements of the nano-ceramic preparation process. The task chain generation module is used for production order parsing and task chain generation: it receives production orders containing formula information, extracts key parameters from the generated orders, including raw material composition, proportioning accuracy, sintering atmosphere and yield requirements; and generates a task chain composed of multiple related tasks based on the nano-ceramic preparation process sequence, with each task corresponding to a dedicated robotic arm. The scheduling and execution module is used for dynamic scheduling and execution of multiple robots: it stores task chains in a priority queue, and the priority is dynamically adjusted based on process sequence, order urgency, or task delay cost; the dedicated robotic arm executes operations according to task parameters and collects sensor data in real time; The AI ​​closed-loop optimization module is used for data closure and real-time AI optimization: it uploads task IDs, process parameters, and sensor data to the IMS system in real time to form a traceable production data chain; the task ID is used to mark different tasks; for key processes, the AI ​​optimization module uses machine learning algorithms to dynamically optimize the parameters of the next process based on the real-time data of the current process, forming a data closed loop, automatically updating the optimized parameters to the parameter set of the next task, and recording the parameter change history; The AI ​​offline optimization and priority update module is used for AI offline optimization and scheduling strategy updates: the AI ​​optimization module periodically extracts historical data from IMS and updates the prediction model based on the historical data; it feeds back the optimization suggestions output by the model to the scheduling system to dynamically adjust the task priority rules; The detection and triggering module is used to detect and record the current task completion status, trigger the next task, and so on until all tasks are completed.

7. The multi-robot intelligent collaborative scheduling nano-ceramic material preparation system as described in claim 6, characterized in that, The nano-ceramic material preparation process, in sequence, includes batching, dispersion, degassing, sintering, modification, testing, and storage. Based on the nano-ceramic preparation process sequence, a task chain consisting of multiple related tasks is generated, with each task corresponding to a dedicated robotic arm. Specifically, a task chain consisting of 7 related tasks is generated based on the nano-ceramic preparation process sequence, with each task corresponding to one process and one dedicated robotic arm. There are 7 dedicated robotic arms, designated R1-R7. Among them, robotic arm R4 and the hot-end robotic arm form a composite execution unit, specifically for handling the high-temperature sintering process.

8. The multi-robot intelligent collaborative scheduling nano-ceramic material preparation system as described in claim 7, characterized in that, Based on the sequence of nano-ceramic preparation processes, a task chain consisting of 7 related tasks is generated, with each task corresponding to one process and one dedicated robotic arm; there are 7 dedicated robotic arms, designated R1-R7; among them, robotic arm R4 and the hot-end robotic arm form a composite execution unit, specifically handling the high-temperature sintering process, including: Generate a batching task T1 and assign task T1 to robotic arm R1. The parameters of task T1 include raw material composition, weighing accuracy and mixing ratio. Generate a distributed task T2: Assign task T2 to the R2 robotic arm. The parameters of task T2 include the multiphysics dispersion method, the AI-predicted dispersion time and intensity; the multiphysics dispersion method includes ultrasound, ball milling and shearing. Generate debubbling task T3: Assign task T3 to the R3 robotic arm. The parameters of task T3 include vacuum level, bubble threshold, and debubbling time. Generate sintering task T4: Task T4 is executed collaboratively by the R4 robotic arm and the hot end robotic arm. The parameters of task T4 include the sintering temperature curve, the pressure value of the gas environment in the sintering furnace, and the second-level time control accuracy. Generate modified task T5: Assign task T5 to the R5 robotic arm. The parameters of task T5 include coupling agent type and coating thickness. Generate inspection task T6: Assign task T6 to the R6 robotic arm. The parameters of task T6 include material particle size, viscosity, dielectric properties test items and inspection accuracy. Generate storage task T7: Assign task T7 to the R7 robotic arm. The parameters of task T7 include storage location code and sample tracking ID. Task association settings: Establish task dependencies through "next task ID" to form a one-way closed-loop task chain; T1-T7 are task IDs.

9. The multi-robot intelligent collaborative scheduling nano-ceramic material preparation system according to any one of claims 6-8, characterized in that, Before the dedicated robotic arm executes operations according to the task parameters and collects sensor data in real time, the process also includes: detecting whether the robotic arm corresponding to the current task is in a busy state; if so, calculating the task delay cost, adjusting the task priority according to the task delay cost, and re-entering the queue; otherwise, the dedicated robotic arm executes operations according to the task parameters and collects sensor data in real time.

10. The multi-robot intelligent collaborative scheduling nano-ceramic material preparation system as described in claim 9, characterized in that, The formula for dynamically adjusting task priority is: New priority = Original priority + (Delay cost / Priority adjustment coefficient), where the delay cost is calculated based on the task type, formula value, and delivery date; the priority adjustment coefficient adopts a dynamic feedback method and is set in layers according to task type.

Images