A production control adjustment method based on multi-control mode switching of industrial robots

Abstract

The present invention relates to the technical field of industrial robots, and in particular to a production control and adjustment method based on multi-control mode switching of industrial robots, comprising the following steps: S1, demand analysis and environmental monitoring: analyzing the demand of the production line, and monitoring the production situation data in real time through sensors; S2, mode switching based on situational awareness: applying situational awareness algorithms to analyze the current production status; S3, dynamic task scheduling optimization: automatically adjusting task allocation according to real-time data and task priority, and optimizing robot resource allocation; S4, feedback mechanism and effect evaluation: establishing a real-time feedback mechanism, monitoring the effects of mode switching and task allocation, and evaluating the effectiveness of mode switching by analyzing robot operation data. The present invention ensures the maximization of production efficiency and the rational use of resources, reduces the risk of overload and production delays, and improves the overall flexibility and responsiveness of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial robots, and in particular to a production control and adjustment method based on multi-control mode switching of industrial robots. Background Art

[0002] With the continuous development of industrial automation, industrial robots are being used more and more widely in production. In order to cope with the complexity and diversity of production tasks, industrial robots need to operate efficiently in different production modes and be able to make intelligent adjustments based on the real-time production environment. Traditional industrial control systems usually use a single control mode, which is difficult to adapt to the dynamically changing production environment, and the scheduling of production tasks often relies on manual settings, resulting in low production efficiency, insufficient resource utilization and other problems.

[0003] However, existing production control systems have obvious shortcomings when dealing with complex and dynamic industrial environments. First, traditional control modes are too fixed and lack the ability to adapt to real-time production needs and environmental changes, resulting in the inability to achieve efficient optimization in resource allocation and task allocation. Second, the task scheduling method is relatively single and cannot be intelligently adjusted according to key factors such as task urgency and resource availability, which can easily lead to some robots being overloaded while other robot resources are idle. In addition, the existing system lacks an effective feedback mechanism, making it difficult to timely optimize the control mode and production strategy according to changes in production results.

[0004] The purpose of the present invention is to provide a production control and adjustment method based on multi-control mode switching of industrial robots, so as to ensure that the system has higher flexibility and adaptability in complex production environments, reduce human intervention, and improve the overall stability and efficiency of the production line. Summary of the invention

[0005] The invention provides a production control and adjustment method based on multi-control mode switching of an industrial robot.

[0006] A production control and adjustment method based on multi-control mode switching of an industrial robot comprises the following steps:

[0007] S1, demand analysis and environmental monitoring: Analyze the needs of the production line and monitor the production situation data in real time through sensors, including temperature, humidity, noise and equipment status;

[0008] S2, mode switching based on context awareness: Based on the acquired context data, the context awareness algorithm is applied to analyze the current production status and intelligently select the control mode to cope with the real-time changing production needs and environmental conditions, including:

[0009] S21, situational status analysis: Use situational awareness algorithms to analyze collected situational data and identify current production status and potential change trends;

[0010] S22, mode adaptability assessment: assess the adaptability of the current control mode and analyze its performance in the current situation;

[0011] S23, control mode selection: intelligently select the control mode of the current production status based on the results of situational status analysis and mode adaptability evaluation;

[0012] S3, dynamic task scheduling optimization: After determining the control mode, the dynamic task scheduling optimization algorithm is used to automatically adjust task allocation according to real-time data and task priority to optimize robot resource configuration;

[0013] S4, Feedback mechanism and effect evaluation: Establish a real-time feedback mechanism to monitor the effects of mode switching and task allocation, and evaluate the effectiveness of mode switching by analyzing robot operation data.

[0014] Optionally, the demand analysis and environment monitoring in S1 include:

[0015] S11, production demand identification: by collecting historical production data, market demand information and production line operation plans, the actual demand of the production line is analyzed by linear regression method to determine the required production volume, production cycle and resource allocation;

[0016] S12, Sensor placement: Various sensors are placed at key locations of the production line to monitor environmental parameters in real time, including temperature sensors, humidity sensors, noise sensors and equipment status monitors, to obtain comprehensive production situation data.

[0017] Optionally, the situation status analysis in S21 includes:

[0018] S211, context data preprocessing: cleaning and normalizing the collected context data;

[0019] S212, application of situational awareness algorithm: using weighted average method to calculate the comprehensive score S of the current production status;

[0020] S213, status identification and trend prediction: Identify the current production status based on the comprehensive score S, and use the ARIMA model to predict the changing trend of the production status.

[0021] Optionally, the mode adaptability evaluation in S22 includes:

[0022] S221, current mode performance parameter collection: collecting performance parameters from the current control mode, including production efficiency, resource utilization, response time and failure rate, as performance indicators of the current mode;

[0023] S222, target situation and mode adaptability calculation: quantitatively evaluate the adaptability of the current control mode in the current situation and calculate the mode adaptability score A;

[0024] S223, performance analysis: compare the adaptability score A with a preset benchmark threshold. If A is higher than the benchmark threshold, it indicates that the current mode is adapted to the current situation. If A is lower than the benchmark threshold, consider switching the control mode or adjusting the current mode parameters.

[0025] Optionally, the control mode selection in S23 includes:

[0026] S231, intelligent mode selection: based on the comprehensive results of the situation status score S and the adaptability score A, a preset weighted comprehensive scoring algorithm is applied to determine the control mode with the highest score as the control mode of the current production state;

[0027] S232, control mode switching execution: automatically switching to the optimal control mode according to the result of the intelligent selection algorithm.

[0028] Optionally, the dynamic task scheduling optimization in S3 includes:

[0029] S31, task priority calculation: assigning a priority to each task using a task priority calculation algorithm according to task deadline, task urgency and resource availability;

[0030] S32, real-time resource monitoring and scheduling: real-time monitoring of the robot's resource usage, including available processing power, energy consumption, and operating status, and dynamically adjusting task allocation based on priority and current resource usage status;

[0031] S33, Task load balancing and optimization: Use load balancing algorithm to distribute tasks among robots and dynamically optimize task scheduling.

[0032] Optionally, the task priority calculation in S31 includes:

[0033] S311, task parameter collection: real-time acquisition of parameter information of each task in the production process, including the task deadline T i 、Urgent i and the availability of the required resources R i ;

[0034] S312, task priority calculation: Based on the collected task parameters, the task priority Q is calculated by a weighted comprehensive algorithm. i ;

[0035] S313, priority sorting: according to the calculated task priority Q i, sort all tasks and execute the highest priority tasks first.

[0036] Optionally, the real-time resource monitoring and scheduling in S32 includes:

[0037] S321, resource usage monitoring: real-time monitoring of robot resource usage through sensors and monitoring devices, including processing capacity (such as CPU or computing capacity occupancy), energy consumption (such as power or power consumption), and operating status (such as the robot's current task execution progress, fault status, etc.);

[0038] S322, Task priority and resource matching: Combine real-time monitoring data with task priority Q i , evaluate the matching of the current task with the available resources of the robot, and dynamically evaluate the task's adaptability K based on the task's resource requirements i ;

[0039] S323, dynamic task allocation: according to the task's adaptability K i and real-time resource usage to dynamically adjust robot task allocation.

[0040] Optionally, the task load balancing and optimization in S33 includes:

[0041] S331, load monitoring and evaluation: collect the current load of each robot in real time, including processing capacity utilization, number of tasks and energy consumption, and use the load evaluation algorithm to calculate the current load L of each robot i ;

[0042] S332, Load balancing algorithm application: Using the minimum load priority allocation strategy, according to the load rate L of each robot i , dynamically adjust task allocation;

[0043] S333, task scheduling optimization: based on load balancing and task priority, continuously optimize task scheduling and redistribute robot tasks with unbalanced loads.

[0044] Optionally, the feedback mechanism and effect evaluation in S4 include:

[0045] S41, real-time feedback data collection: real-time collection of robot operation data, including task completion rate, task execution time, and resource consumption (such as energy consumption and processing capacity utilization);

[0046] S42, effect evaluation: based on task completion time, resource usage and task success rate, the effect score E of mode switching is calculated by a weighted comprehensive algorithm;

[0047] S43, mode switching effectiveness evaluation: According to the effect score E, the effectiveness of the current mode switching is evaluated. When the effect score E reaches or exceeds the set effective threshold, the mode switching is considered effective. If it is lower than the effective threshold, the mode or task allocation is readjusted.

[0048] Beneficial effects of the present invention:

[0049] The present invention realizes real-time adaptation and adjustment of the production environment through a multi-control mode switching method combined with a context-aware algorithm, dynamic task scheduling optimization, feedback mechanism and effect evaluation. The system can dynamically select the optimal control mode and perform task allocation according to the actual needs of the production line and environmental changes, thereby ensuring maximum production efficiency and rational use of resources, reducing the risk of overload and production delays, and improving the overall flexibility and responsiveness of the system.

[0050] The present invention can continuously optimize the production process through real-time monitoring and data feedback. Based on task priority and resource availability, the system can effectively balance task loads and allocate resources to ensure that all robots operate evenly in different task scenarios, avoiding waste of resources and inefficient task execution. The feedback mechanism also helps the system to make timely adjustments according to different production scenarios through quantitative evaluation of the mode switching effect, thereby improving production accuracy and response speed.

[0051] The present invention, through intelligent mode selection and dynamic feedback mechanism, can intelligently select and optimize the current control mode according to the comprehensive evaluation of historical data and real-time operating status. Based on the weighted comprehensive scoring algorithm, the system can automatically determine the optimal control mode and automatically switch according to the evaluation results to ensure that the production system is always in the best operating state. In addition, based on real-time feedback data analysis and dynamic tuning, the system has self-learning and self-adaptive capabilities, can continuously improve the production process, reduce human intervention, thereby improving operating efficiency, reducing failure rates and resource waste in complex production environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 A schematic diagram of a flow chart of an adjustment method according to an embodiment of the present invention;

[0054] Figure 2 Schematic diagram of mode switching based on context awareness according to an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0056] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0057] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0058] like Figure 1-Figure 2 As shown, a production control and adjustment method based on multi-control mode switching of an industrial robot includes the following steps:

[0059] S1, demand analysis and environmental monitoring: Analyze the needs of the production line and monitor the production situation data in real time through sensors, including temperature, humidity, noise and equipment status;

[0060] S2, mode switching based on context awareness: Based on the acquired context data, the context awareness algorithm is applied to analyze the current production status and intelligently select the control mode to cope with the real-time changing production needs and environmental conditions, including:

[0061] S21, situational status analysis: Use situational awareness algorithms to analyze collected situational data and identify current production status and potential change trends;

[0062] S22, mode adaptability assessment: assess the adaptability of the current control mode and analyze its performance in the current situation;

[0063] S23, control mode selection: intelligently select the control mode of the current production status based on the results of situational status analysis and mode adaptability evaluation;

[0064] S3, dynamic task scheduling optimization: After determining the control mode, the dynamic task scheduling optimization algorithm is used to automatically adjust task allocation according to real-time data and task priority to optimize robot resource configuration;

[0065] S4, feedback mechanism and effect evaluation: establish a real-time feedback mechanism to monitor the effects of mode switching and task allocation, and evaluate the effectiveness of mode switching by analyzing robot operation data;

[0066] Through the above content, it is possible to adapt to changes in the production environment in real time, optimize resource allocation, and improve production efficiency and safety. In addition, the real-time feedback mechanism ensures continuous improvement, enabling the system to show higher flexibility and responsiveness in complex and dynamic industrial environments, thereby significantly enhancing the overall operation of the production line.

[0067] Demand analysis and environmental monitoring in S1 include:

[0068] S11, production demand identification: by collecting historical production data, market demand information and production line operation plan, the actual demand of the production line is analyzed by linear regression method to determine the required production volume, production cycle and resource allocation, which is expressed as:

[0069] D = a + bX;

[0070] Among them, D is demand, a is the intercept, b is the slope, and X is the variable that affects demand;

[0071] S12, sensor placement: Various sensors are placed at key locations of the production line to monitor environmental parameters in real time, including temperature sensors, humidity sensors, noise sensors and equipment status monitors, to obtain comprehensive production situation data;

[0072] Through the above content, comprehensive and accurate production demand identification can be provided, which not only optimizes production planning and resource allocation and improves production efficiency, but also can respond to market changes and environmental fluctuations in a timely manner and reduce production risks. In addition, the data collected by real-time monitoring provides a reliable basis for continuous improvement and decision-making support, thereby enhancing the competitiveness and flexibility of the enterprise.

[0073] Situational state analysis in S21 includes:

[0074] S211, context data preprocessing: cleaning and normalizing the collected context data to ensure the accuracy and consistency of the data;

[0075] S212, application of situational awareness algorithm: use the weighted average method to calculate the comprehensive score S of the current production status, expressed as:

[0076] S=w1T score +w2H score +w3N score +w4D score ;

[0077] Among them, S is the comprehensive score, T score , H score 、N score , D score They represent the temperature, humidity, noise and equipment status scores respectively, and w1, w2, w3 and w4 are the weight coefficients of each score;

[0078]

[0079] Where T is the current actual temperature, is the lowest value of the ideal temperature range, T max is the highest value of the ideal temperature range;

[0080]

[0081] Among them, H score is the humidity score, between 0 and 1, H is the current actual humidity, H min is the lowest value of the ideal humidity range, H max This is the highest value of the ideal humidity range;

[0082]

[0083] Among them, N score is the noise score, between 0 and 1, N is the current actual noise value, in decibels (dB), N max This is the ideal maximum value of noise. Exceeding this value will affect the production environment.

[0084]

[0085] Among them, D score Score the device status, where the status is the current operating state of the device (normal, warning, or fault);

[0086] The weight coefficients w1, w2, w3, and w4 of the score should be set based on the production process, environment, historical data, and expert experience. Usually, their sum should be equal to 1, and each weight fluctuates between 0 and 1 to reflect the relative importance of different parameters to the comprehensive score.

[0087] S213, state identification and trend prediction: Identify the current production state based on the comprehensive score S, and use the ARIMA model to predict the changing trend of the production state, so as to adjust the production strategy in time to cope with potential changes, expressed as:

[0088] Y t =c+φ1Y t-1 +φ2Y t-2 +…+φ p Y t-p +θ1ε t-1 +θ2ε t-2 +…+

[0089] θ q ε t-q +ε t ;

[0090] Among them, Y t is the observed value at time t, c is a constant term, φ i is the coefficient of the autoregressive (AR) term, θ i is the coefficient of the moving average (MA) term, ε t is the white noise error term;

[0091] Through the above content, the production status can be identified in real time and potential change trends can be predicted. Combined with weighted scoring and trend analysis, it can provide more accurate and comprehensive production environment monitoring and effectively optimize production decisions. In addition, this analysis method can dynamically adjust weights according to different production needs to ensure that the system has higher adaptability and responsiveness in complex environments, thereby improving production efficiency and safety.

[0092] The mode suitability assessment in S22 includes:

[0093] S221, current mode performance parameter collection: collecting performance parameters from the current control mode, including production efficiency, resource utilization, response time and failure rate, as performance indicators of the current mode;

[0094] S222, target situation and mode adaptability calculation: quantitatively evaluate the adaptability of the current control mode in the current situation, and calculate the mode adaptability score A, which is expressed as:

[0095]

[0096] Among them, A is the model adaptability score, P i is the performance value of the ith performance parameter, w i is the importance weight of the performance parameter, and n is the number of performance parameters;

[0097] S223, performance analysis: comparing the adaptability score A with a preset benchmark threshold. If A is higher than the benchmark threshold, it indicates that the current mode is adapted to the current situation. If A is lower than the benchmark threshold, consider switching the control mode or adjusting the current mode parameters.

[0098] Benchmark thresholds are set based on historical data and include:

[0099] Data collection: Collect key performance parameters in different scenarios (such as temperature, humidity, equipment status, etc.) during historical production processes, including production efficiency, resource utilization, system response time, and failure rate;

[0100] Performance value calculation: For each set of historical data, the key performance parameter P i Calculate and generate the mode adaptability score A, expressed as:

[0101]

[0102] Among them, A j is the adaptability score of the j-th historical data, P i,j is the performance value of the i-th performance parameter in the j-th historical data, w i is the weight of the i-th performance parameter, n is the number of performance parameters;

[0103] Benchmark threshold calculation: After collecting enough historical data, based on the historical adaptability score A j , the benchmark threshold is set as the average of the best and second-best performance scores in the historical data, expressed as:

[0104]

[0105] Among them, A threshold is the benchmark threshold for adaptability assessment, A j is the adaptability score of the j-th historical data, and m is the number of historical samples used to calculate the threshold;

[0106] Dynamic adjustment: The baseline threshold can be dynamically adjusted based on the addition of new data, ensuring that the threshold is continuously optimized as the production environment and conditions change;

[0107] Through the above content, combined with the comprehensive analysis of historical data and real-time parameters, it is possible to quickly identify whether the mode is suitable for current production needs, so as to adjust the control mode or optimize parameters in time, improve the system's responsiveness and overall production efficiency, and reduce downtime and resource waste.

[0108] The control mode selection in S23 includes:

[0109] S231, intelligent mode selection: Based on the comprehensive results of the situation status score S and the adaptability score A, a preset weighted comprehensive scoring algorithm is applied to determine the control mode with the highest score as the control mode of the current production state, expressed as:

[0110] S(M i )=α×S context (M i )+β×S performance (M i )+γ×S adaptability

[0111] (M i );

[0112] Among them, S(M i ) is mode M i Total score, S context (M i ) is mode M i The adaptability score in the current situation, S performance (M i ) is mode M i The historical performance scores (such as efficiency, resource utilization, etc.) shown in the past production process, S adaptability (M i ) is mode M i The responsiveness or adaptability score in the current situation (e.g., the score obtained by the mode adaptability assessment), α, β, γ are the weight coefficients of each score, which are used to adjust the impact of different factors on the total score, usually satisfying α+β+γ=1;

[0113]

[0114] Among them, M optimal is the optimal control mode, which means the mode with the highest score in the current production environment;

[0115] S232, control mode switching execution: automatically switching to the optimal control mode according to the result of the intelligent selection algorithm to ensure that the production system operates efficiently in the new mode;

[0116] Through the above content, the production mode can be adjusted intelligently according to the real-time environment and historical data to ensure that the system is always in the best working state. This not only improves production efficiency, but also reduces the need for human intervention and improves the system's adaptability, ensuring efficient, safe and stable operation in a dynamically changing production environment.

[0117] Dynamic task scheduling optimizations in S3 include:

[0118] S31, task priority calculation: assigning a priority to each task using a task priority calculation algorithm according to task deadline, task urgency and resource availability;

[0119] S32, real-time resource monitoring and scheduling: real-time monitoring of the robot's resource usage, including available processing power, energy consumption, and operating status, dynamically adjusting task allocation based on priority and current resource usage status to ensure that each robot works efficiently within its load range and avoid resource overload or idleness;

[0120] S33, Task load balancing and optimization: Use load balancing algorithms to distribute tasks among robots, ensure that workloads are evenly distributed among different robots, prevent some robots from being overloaded or operating inefficiently, and dynamically optimize task scheduling to improve overall resource utilization and production efficiency, and reduce task execution time and delays;

[0121] Through the above content, it is ensured that robot resources are optimally configured, and tasks can be intelligently allocated according to changes in production needs and resource availability to avoid overload and waste of resources, ensuring the efficient operation of the production process. Task load balancing and optimization further enhance the flexibility and response speed of the overall system, reduce production delays, and improve resource utilization, thereby significantly improving production efficiency and system stability.

[0122] The task priority calculation in S31 includes:

[0123] S311, task parameter collection: real-time acquisition of parameter information of each task in the production process, including the task deadline T i 、Urgent i and the availability of the required resources R i ;

[0124] S312, task priority calculation: Based on the collected task parameters, the task priority Q is calculated by a weighted comprehensive algorithm. i , expressed as:

[0125]

[0126] Among them, Q i Score the priority of task i, T i is the deadline of task i. The smaller the value, the more urgent the task. i is the urgency of task i, a predefined task attribute. The higher the value, the more urgent the task. i is the resource availability of task i, indicating the resources currently available for the task. The higher the value, the better the resource availability. w4, w5, and w6 are the weight coefficients of deadline, urgency, and resource availability, respectively.

[0127]

[0128] Among them, Remaining Time i The remaining completion time of task i, usually the task deadline minus the current time;

[0129]

[0130] Among them, U i Score the urgency of task i, where a higher value indicates a more urgent task;

[0131]

[0132] Among them, Available Resources i Required Resources is the amount of resources currently available to task i (such as CPU, memory, machines, workers, etc.). i The amount of resources required to complete task i;

[0133] The weight coefficients w4, w5, and w6 are set based on the specific needs of the production environment and the importance of each factor to the task completion. For time-sensitive tasks, the weight of the deadline should be higher; for tasks with high business importance or urgency, the weight of the urgency needs to be increased; and in the case of resource constraints, the weight of resource availability should be greater. The value of each weight is usually between 0 and 1, satisfying w4+w5+w6=1;

[0134] S313, priority sorting: according to the calculated task priority Q i , sort all tasks, prioritize the highest priority tasks, and ensure that critical tasks can be completed in a timely manner;

[0135] Through the above content, the task sequence can be intelligently adjusted according to real-time production needs to avoid resource waste and production delays. Through weighted calculation, it can flexibly respond to changes in different production scenarios, ensure efficient use of resources, optimize production processes, and improve overall production efficiency and system responsiveness.

[0136] Real-time resource monitoring and scheduling in S32 include:

[0137] S321, resource usage monitoring: real-time monitoring of robot resource usage through sensors and monitoring devices, including processing capacity (such as CPU or computing capacity occupancy), energy consumption (such as power or power consumption), and operating status (such as the robot's current task execution progress, fault status, etc.);

[0138] S322, Task priority and resource matching: Combine real-time monitoring data with task priority Q i , evaluate the matching of the current task with the available resources of the robot, and dynamically evaluate the task's adaptability K based on the task's resource requirements i , expressed as:

[0139]

[0140] Among them, K i is the suitability of task i, Available Resources i Required Resources is the amount of resources available to the current robot. i is the amount of resources required for task i, Q i Rate the priority of tasks;

[0141] S323, dynamic task allocation: according to the task's adaptability K i and real-time resource usage, dynamically adjusting robot task allocation to ensure maximum resource utilization and avoid overload or idle resources;

[0142] Through the above content, it is possible to optimize resource utilization, avoid resource overload or idleness, ensure that robots perform tasks with maximum efficiency, and improve the flexibility and response speed of the system by dynamically adjusting the task load, thereby improving production efficiency, reducing resource waste, and ensuring the continuity and stability of the production process.

[0143] Task load balancing and optimization in S33 include:

[0144] S331, load monitoring and evaluation: collect the current load of each robot in real time, including processing capacity utilization, number of tasks and energy consumption, and use the load evaluation algorithm to calculate the current load L of each robot i , expressed as:

[0145]

[0146] Among them, L i is the current load rate of robot i, Current Task Load i is the total amount of tasks currently assigned to robot i, Max Capacity i is the maximum processing capacity of robot i;

[0147] S332, Load balancing algorithm application: Using the minimum load priority allocation strategy, according to the load rate L of each robot i , dynamically adjust the task allocation to ensure that the tasks are evenly distributed among different robots, expressed as:

[0148] i min =argmin i L i ;

[0149] Among them, i min Indicates the robot number with the smallest load, L i represents the current load rate of robot i;

[0150] S333, Task Scheduling Optimization: Based on the load balancing situation and task priority, continuously optimize task scheduling, reallocate robot tasks with unbalanced loads, ensure the optimal configuration of overall system resources, and improve overall operating efficiency;

[0151] Through the above content, the workload is ensured to be evenly distributed among all robots to avoid overload or inefficient operation. Through the minimum load priority algorithm, new tasks are preferentially assigned to the robot with the smallest load to ensure the flexibility of task execution and the stability of the system. By continuously optimizing task scheduling, the overall resource utilization is improved, production delays are reduced, and the overall operating efficiency and response speed of the system are improved.

[0152] The feedback mechanism and effect evaluation in S4 include:

[0153] S41, real-time feedback data collection: real-time collection of robot operation data, including task completion rate, task execution time, and resource consumption (such as energy consumption and processing capacity utilization);

[0154] S42, effect evaluation: Based on the task completion time, resource usage and task success rate, the effect score E of the mode switching is calculated by a weighted comprehensive algorithm, which is expressed as:

[0155]

[0156] Among them, T target Schedule the completion time for the task, T actual is the actual completion time of the task, R available is the available resources (processing power, energy consumption, etc.), R used For actual use of resources, C success is the task completion success rate, indicating whether the task is successfully completed under given conditions, w7, w8, and w9 are the weight coefficients of various parameters respectively;

[0157] The basis for setting weight coefficients w7, w8, and w9 mainly depends on the importance of different indicators in the production process. The weight of task completion time w7 should be set according to the strictness of production on delivery time, the weight of resource utilization rate w8 should be adjusted according to resource tension and cost control requirements, and the weight of task success rate w9 is suitable for tasks that require high precision and high completion rate, and the weight satisfies w7+w8+w9=1;

[0158] S43, mode switching effectiveness evaluation: according to the effect score E, the effectiveness of the current mode switching is evaluated. When the effect score E reaches or exceeds the set effective threshold, the mode switching is considered effective. If it is lower than the effective threshold, the mode or task allocation is readjusted.

[0159] The effective threshold is based on historical data to determine the optimal performance of the system in different production environments. It is set by scoring E based on the effectiveness of past task executions. Specifically, it includes:

[0160] Data collection: Collect historical operation data of the system in different modes, including task completion time, resource utilization rate, and task success rate, and calculate the effect score of each mode switch based on historical data And record the actual effect score of each task;

[0161] Effective threshold setting: based on historical performance scores The statistical data is used to determine the threshold, which is expressed as:

[0162]

[0163] Among them, E threshold is the effective threshold of mode switching effectiveness, is the effect score of the i-th historical mode switching, and N is the number of historical samples used to calculate the threshold;

[0164] Through the above content, it is possible to automatically determine whether the mode switching is effective and optimize the production process in a timely manner, ensuring that the production system maintains efficient operation in a dynamic environment, reducing resource waste, improving the accuracy of task completion and the overall stability of the production line, and improving production efficiency.

[0165] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0166] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A production control and adjustment method based on multi-control mode switching of an industrial robot, characterized in that: The following steps are involved: S1, demand analysis and environmental monitoring: Analyze the needs of the production line and monitor the production situation data in real time through sensors, including temperature, humidity, noise and equipment status; S2, mode switching based on context awareness: Based on the acquired context data, the context awareness algorithm is applied to analyze the current production status and intelligently select the control mode to cope with the real-time changing production needs and environmental conditions, including: S21, situational status analysis: Use situational awareness algorithms to analyze collected situational data and identify current production status and potential change trends. Situational status analysis includes: S211, context data preprocessing: cleaning and normalizing the collected context data; S212, application of situational awareness algorithm: using weighted average method to calculate the comprehensive score S of the current production status; S213, status identification and trend prediction: Identify the current production status based on the comprehensive score S, and use the ARIMA model to predict the changing trend of the production status; S22, mode adaptability assessment: assess the adaptability of the current control mode and analyze its performance in the current situation; S23, control mode selection: intelligently select the control mode of the current production status based on the results of situational status analysis and mode adaptability evaluation; S3, dynamic task scheduling optimization: After determining the control mode, the dynamic task scheduling optimization algorithm is used to automatically adjust task allocation according to real-time data and task priority to optimize robot resource configuration; S4, Feedback mechanism and effect evaluation: Establish a real-time feedback mechanism to monitor the effects of mode switching and task allocation, and evaluate the effectiveness of mode switching by analyzing robot operation data.

2. A production control and adjustment method based on multi-control mode switching of an industrial robot according to claim 1, characterized in that: The demand analysis and environment monitoring in S1 include: S11, production demand identification: by collecting historical production data, market demand information and production line operation plans, the actual demand of the production line is analyzed by linear regression method to determine the required production volume, production cycle and resource allocation; S12, Sensor placement: Various sensors are placed at key locations of the production line to monitor environmental parameters in real time, including temperature sensors, humidity sensors, noise sensors and equipment status monitors, to obtain comprehensive production situation data.

3. The production control and adjustment method based on multi-control mode switching of an industrial robot according to claim 1 is characterized in that: The mode adaptability evaluation in S22 includes: S221, current mode performance parameter collection: collecting performance parameters from the current control mode, including production efficiency, resource utilization, response time and failure rate, as performance indicators of the current mode; S222, target situation and mode adaptability calculation: quantitatively evaluate the adaptability of the current control mode in the current situation and calculate the mode adaptability score A; S223, performance analysis: compare the adaptability score A with a preset benchmark threshold. If A is higher than the benchmark threshold, it indicates that the current mode is adapted to the current situation. If A is lower than the benchmark threshold, consider switching the control mode or adjusting the current mode parameters.

4. A production control and adjustment method based on multi-control mode switching of an industrial robot according to claim 3, characterized in that: The control mode selection in S23 includes: S231, intelligent mode selection: based on the comprehensive results of the situation status score S and the adaptability score A, a preset weighted comprehensive scoring algorithm is applied to determine the control mode with the highest score as the control mode of the current production state; S232, control mode switching execution: automatically switching to the optimal control mode according to the result of the intelligent selection algorithm.

5. The production control and adjustment method based on multi-control mode switching of an industrial robot according to claim 1 is characterized in that: The dynamic task scheduling optimization in S3 includes: S31, task priority calculation: assigning a priority to each task using a task priority calculation algorithm according to task deadline, task urgency and resource availability; S32, real-time resource monitoring and scheduling: real-time monitoring of the robot's resource usage, including available processing power, energy consumption, and operating status, and dynamically adjusting task allocation based on priority and current resource usage status; S33, Task load balancing and optimization: Use load balancing algorithm to distribute tasks among robots and dynamically optimize task scheduling.

6. A production control and adjustment method based on multi-control mode switching of an industrial robot according to claim 5, characterized in that: The task priority calculation in S31 includes: S311, task parameter collection: real-time acquisition of parameter information of each task in the production process, including the task deadline T i 、Urgent i and the availability of the required resources R i ; S312, task priority calculation: Based on the collected task parameters, the task priority Q is calculated by a weighted comprehensive algorithm. i ; S313, priority sorting: according to the calculated task priority Q i , sort all tasks and execute the highest priority tasks first.

7. A production control and adjustment method based on multi-control mode switching of an industrial robot according to claim 6, characterized in that: The real-time resource monitoring and scheduling in S32 includes: S321, resource usage monitoring: real-time monitoring of robot resource usage, including processing power, energy consumption, and operating status, through sensors and monitoring devices; S322, Task priority and resource matching: Combine real-time monitoring data with task priority Q i , evaluate the matching of the current task with the available resources of the robot, and dynamically evaluate the task's adaptability K based on the task's resource requirements i ; S323, dynamic task allocation: according to the task's adaptability K i and real-time resource usage to dynamically adjust robot task allocation.

8. The production control and adjustment method based on multi-control mode switching of an industrial robot according to claim 7 is characterized in that: The task load balancing and optimization in S33 includes: S331, load monitoring and evaluation: collect the current load of each robot in real time, including processing capacity utilization, number of tasks and energy consumption, and use the load evaluation algorithm to calculate the current load L of each robot i ; S332, Load balancing algorithm application: Using the minimum load priority allocation strategy, according to the load rate L of each robot i , dynamically adjust task allocation; S333, task scheduling optimization: According to the load balancing situation and task priority, continuously optimize task scheduling and redistribute robot tasks with unbalanced loads.

9. The production control and adjustment method based on multi-control mode switching of an industrial robot according to claim 1, characterized in that: The feedback mechanism and effect evaluation in S4 include: S41, real-time feedback data collection: real-time collection of robot operation data, including task completion rate, task execution time, and resource consumption; S42, effect evaluation: based on task completion time, resource usage and task success rate, the effect score E of mode switching is calculated by a weighted comprehensive algorithm; S43, mode switching effectiveness evaluation: According to the effect score E, the effectiveness of the current mode switching is evaluated. When the effect score E reaches or exceeds the set effective threshold, the mode switching is considered effective. If it is lower than the effective threshold, the mode or task allocation is readjusted.

Images