Robot intelligent manufacturing workshop energy consumption optimization method based on Internet of Things

Abstract

The invention discloses a robot intelligent manufacturing workshop energy consumption optimization method based on the Internet of Things, and belongs to the field of energy consumption optimization, and the method comprises the steps: optimizing a path based on a genetic algorithm, and generating a candidate path set containing diversified paths; aiming at a time sequence scheme, predicting energy consumption uncertainty caused by task change and equipment aging by adopting a Monte Carlo simulation algorithm, and generating prediction distribution containing an energy consumption fluctuation range; if the predicted distributed energy consumption fluctuation range exceeds 10% of a preset threshold value, a path set and a time sequence scheme are adjusted through a reinforcement learning algorithm, and an optimized path and time sequence combination is generated; otherwise, the current path and the time sequence scheme are reserved, and a stable energy consumption distribution scheme is obtained; and extracting a task execution sequence and equipment operation parameters from the final adaptive energy consumption optimization scheme, and transmitting the task execution sequence and the equipment operation parameters to a workshop control system to complete real-time deployment of energy consumption optimization.

Description

Technical Field

[0001] The present invention belongs to the field of energy consumption optimization, and in particular relates to an energy consumption optimization method for a robot intelligent manufacturing workshop based on the Internet of Things. Background Art

[0002] In the field of intelligent manufacturing, optimizing energy consumption in robotic smart manufacturing workshops is a key area for promoting sustainable industrial development. Energy efficiency directly impacts production costs and environmental impact, making energy optimization a core research topic. With the widespread adoption of IoT technology, workshops can collect production data in real time, opening up new possibilities for energy optimization. However, existing methods often rely on static energy consumption models or single optimization objectives, making them difficult to adapt to the complex and changing environments and task requirements of the production process, resulting in inefficient energy utilization.

[0003] While current research has made some progress in energy optimization, limitations are common. Many solutions are designed only for specific equipment or a single production process, lacking consideration for multi-task coordination across the entire shop floor. This makes it difficult to achieve optimal global energy allocation when faced with changes in production tasks or fluctuations in equipment status. Furthermore, existing methods often ignore energy consumption uncertainties, such as the impact of production task adjustments or changing environmental factors, resulting in a disconnect between optimization results and actual needs. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides an energy consumption optimization method for a robot intelligent manufacturing workshop based on the Internet of Things, comprising:

[0005] Use IoT technology to obtain production task data, robot location data, and equipment operating status data from workshop sensors to generate real-time data sets;

[0006] Classifying the real-time data set, and dividing the production tasks into a high-priority task group and a low-priority task group according to task priorities and energy consumption parameters;

[0007] According to the task classification results, a path planning algorithm is selected to plan the robot path and generate a path set;

[0008] Extract path data from the path set, combine it with the device operating status data, calculate the device power on / off timing, and generate a timing plan;

[0009] For the timing plan, predict the energy consumption uncertainty caused by task changes and equipment aging, and generate a predicted distribution of energy consumption fluctuation range;

[0010] Adjusting the path set and timing plan according to the predicted distribution to generate an optimized path and timing combination;

[0011] Extracting global energy consumption data from the optimized path and timing combination, iteratively adjusting task allocation and equipment operating parameters, and generating a task scheduling solution with optimal global energy consumption;

[0012] Verify the task scheduling solution with the best global energy consumption, update the energy consumption parameters based on the latest data, and generate the final adaptive energy consumption optimization solution;

[0013] The task execution sequence and equipment operating parameters in the final adaptive energy consumption optimization solution are transmitted to the workshop control system to complete the real-time deployment of energy consumption optimization.

[0014] Preferably, the process of generating a real-time data set includes:

[0015] If the production task data contains a task identifier and a deadline, the task priority is calculated based on the deadline to obtain a task priority sequence;

[0016] Calculate the optimal path from the current position to the task target point according to the task priority sequence and the robot position data, and generate path planning data;

[0017] Analyze device status data, calculate the energy consumption parameters of each device in path planning, and obtain the energy consumption parameter set;

[0018] If the task priority and path planning or energy consumption parameters in the real-time data set exceed the preset threshold, the sensor data is re-acquired through the Internet of Things technology to update the real-time data set.

[0019] Preferably, the process of dividing the production tasks into a high-priority task group and a low-priority task group according to the task priority and the energy consumption parameter includes:

[0020] Obtain real-time production task data sets, extract task priorities and energy consumption parameters, standardize the data format, and obtain preprocessed data sets;

[0021] Using a K-means clustering algorithm to classify the preprocessed data set, determine a high-priority task group and a low-priority task group, and obtain an initial classification result;

[0022] If there is a mismatch between the task priority and the energy consumption parameter in the initial classification result, the classification is readjusted according to the preset priority threshold and energy consumption threshold to obtain an optimized classification result.

[0023] Preferably, the process of generating a path set includes:

[0024] If the task classification result shows that the proportion of high-priority task groups exceeds the preset threshold, the high-priority task list is obtained from the task classification module to determine the triggering path planning conditions;

[0025] According to the high-priority task list, task location data and workshop layout information are obtained to generate a set of spatial coordinates of the task locations;

[0026] The A* search algorithm is used to process the spatial coordinate set of the task location and obtain the shortest path set in combination with the spatial constraints of the workshop layout;

[0027] If there is a path conflict in the shortest path set, the path set is analyzed by a conflict detection module to determine the conflicting path pairs, and the conflicting paths are replanned using the Dijkstra algorithm to obtain an optimized path set;

[0028] If the task classification result shows that the proportion of high-priority task groups does not exceed the preset threshold, the population is initialized through the genetic algorithm to obtain an initial path set containing multiple paths;

[0029] Encoding the path individuals in the initial path set and expressing them using a path node sequence;

[0030] If the path individual satisfies the preset fitness function, the path individual is retained, otherwise a new path individual is generated through crossover and mutation operations;

[0031] Based on the new path individuals generated by the crossover operation and the mutation operation, a selection strategy is used to determine a set of retained path individuals;

[0032] If the retained path individual set meets the convergence condition, the optimized candidate path set is output; otherwise, the crossover operation and mutation operation are returned to generate a new path individual.

[0033] Preferably, the process of generating a timing plan includes:

[0034] Acquire path data from the path set, and obtain a path data set by parsing path nodes and connection relationships;

[0035] Combining the path data set with the equipment operating status data to generate a fused data set;

[0036] If the fused data set meets the preset integrity threshold, the device power on / off timing is optimized using a linear programming algorithm to obtain an optimized timing result;

[0037] Based on the optimized timing results, extract the device startup time and shutdown time to generate a timing data table;

[0038] According to the time series data table, a time series analysis method is used to detect abnormal points in the time series data to obtain corrected time series data;

[0039] A timing plan including a start-up time and a shut-down time is generated using the corrected timing data.

[0040] Preferably, the process of generating the predicted distribution of energy consumption fluctuation range includes:

[0041] Using Monte Carlo simulation, we obtain multiple sets of random sampling scenarios from sequential task changes and equipment aging data to generate an initial energy consumption uncertainty distribution.

[0042] If the variance of the initial energy consumption uncertainty distribution exceeds a preset threshold, adjusting the sampling parameters through iterative Monte Carlo simulation to obtain a converged energy consumption uncertainty distribution;

[0043] According to the converged energy consumption uncertainty distribution, a probability density function of the energy consumption fluctuation range is generated using kernel density estimation to determine the energy consumption fluctuation range;

[0044] By integrating the probability density function, the upper and lower limits of the energy consumption fluctuation range are obtained to generate a predicted distribution.

[0045] Preferably, the process of generating the optimized path and timing combination includes:

[0046] If the predicted energy consumption fluctuation range exceeds a preset threshold, the data acquisition module obtains distribution characteristics from historical energy consumption data to obtain energy consumption fluctuation trends;

[0047] According to the energy consumption fluctuation trend, a reinforcement learning algorithm is used to iteratively adjust the path set to generate a candidate path combination;

[0048] The timing scheme is optimized by the reinforcement learning algorithm to obtain a timing combination that matches the candidate path combination, and to determine the optimized path and timing combination.

[0049] Preferably, the process of generating a task scheduling solution with optimal global energy consumption includes:

[0050] Obtaining global energy consumption data from the task assignments and equipment operating parameters, and generating an initial energy consumption dataset using a data extraction process;

[0051] Analyzing the global energy consumption data using a particle swarm optimization algorithm, performing an iterative adjustment process on the task allocation plan and equipment operating parameters, and determining an optimized task allocation plan and operating parameter adjustment combination;

[0052] If the optimized task allocation scheme meets the preset energy consumption threshold, the task execution path is adjusted using the path optimization combination to obtain the path optimization combination;

[0053] If the energy consumption data of the path optimization combination is lower than the initial energy consumption data set, the task execution timing is adjusted through the timing optimization combination to determine the timing optimization combination;

[0054] The particle swarm optimization algorithm is used to jointly iterate the path optimization combination and the timing optimization combination, and the operating parameter combination with the optimal energy consumption is generated for the operating parameter adjustment to obtain the operating parameter adjustment;

[0055] The task scheduling scheme integrates the path optimization combination, the timing optimization combination and the operation parameter adjustment to generate a task scheduling scheme, thereby obtaining a task scheduling scheme with optimal energy consumption.

[0056] On the other hand, the present invention further provides an electronic device, comprising a memory, a processor, and a computing program stored in the memory and executable on the processor, wherein the method is implemented when the processor executes the computing program.

[0057] On the other hand, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the method when executed by a processor.

[0058] Compared with the prior art, the present invention has the following advantages and technical effects:

[0059] The present invention discloses a method for optimizing industrial production energy consumption based on the Internet of Things and artificial intelligence. This method uses Internet of Things technology to collect real-time workshop data, classifies tasks using a K-means clustering algorithm, performs path planning based on priority using an A* algorithm or a genetic algorithm, and generates equipment timing plans using a linear programming algorithm. Furthermore, the present invention uses Monte Carlo simulation to predict energy consumption uncertainty and, when necessary, adjusts the plan through reinforcement learning. Finally, a particle swarm optimization algorithm is used to iteratively optimize global energy consumption, and an adaptive optimization plan is generated based on the latest data. This invention achieves intelligent and adaptive task scheduling and energy consumption optimization in industrial production processes, effectively improving production efficiency and reducing energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings:

[0061] Figure 1 Schematic diagram of a method flow in an embodiment of the present invention. DETAILED DESCRIPTION

[0062] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0063] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0064] Example 1

[0065] like Figure 1 As shown, this embodiment provides an energy consumption optimization method for a robot intelligent manufacturing workshop based on the Internet of Things, including:

[0066] Through the Internet of Things technology, production task data, robot location data and equipment operation status data are obtained from workshop sensors to generate a real-time data set containing task priorities, path requirements and energy consumption parameters.

[0067] Using IoT technology, production tasks, robot positions, and equipment status data are acquired from shop floor sensors to generate a real-time dataset containing task priorities, path planning, and energy consumption parameters. If the production task data includes a task identifier and deadline, the task priority is calculated based on the deadline to generate a task priority sequence. Based on the task priority sequence and robot position data, the A algorithm is used to calculate the optimal path from the current position to the task destination, generating path planning data. The operating power and load are analyzed using equipment status data to calculate the energy consumption parameters of each device in the path planning process and generate a set of energy consumption parameters. If the task priority, path planning, or energy consumption parameters in the real-time dataset exceed preset thresholds, sensor data is retrieved using IoT technology to update the real-time dataset. Based on the updated real-time dataset, the K-means algorithm is used to cluster task priorities and energy consumption parameters to determine the task execution order and equipment allocation plan. Based on the path planning data and equipment allocation plan, control instructions are generated and issued to the robots and equipment to obtain the task execution results.

[0068] The K-means clustering algorithm is used to classify the real-time data set. The production tasks are divided into high-priority task groups and low-priority task groups according to task priority and energy consumption parameters, and the task classification results are obtained.

[0069] A real-time production task dataset is acquired, task priorities and energy consumption parameters are extracted, and the data format is standardized to obtain a preprocessed dataset. A K-means clustering algorithm is used to classify the preprocessed dataset. Based on task priorities and energy consumption parameters, high-priority and low-priority task groups are determined to obtain an initial classification result. If the initial classification result shows a mismatch between task priorities and energy consumption parameters, the classification is readjusted based on preset priority and energy consumption thresholds to obtain an optimized classification result. By analyzing the optimized classification results, the average priority and average energy consumption of each task group are calculated to obtain task group characteristic parameters. Based on the task group characteristic parameters, if the average energy consumption of the high-priority task group exceeds the preset threshold, the tasks in this group are sorted to determine the priority ranking result. A scheduling algorithm is used to assign tasks based on the priority ranking results, and the task execution sequence is obtained based on the real-time system resource status. By monitoring the running status of the task execution sequence, dynamic changes in priority and energy consumption are recorded, and the real-time dataset is updated to obtain an updated classification basis.

[0070] Specifically, in a real-time production task classification scenario, task feature data must first be collected, such as priority scores (ranging from 1 to 10, e.g., Task A has a priority of 8.5) and energy consumption parameters (e.g., Task B has an energy consumption of 3.2 kW·h). Through data normalization, the Z-score method is used to convert the original data (with a mean priority of 6.3 and a standard deviation of 2.1) into a standard normal distribution. K-means clustering is initialized with k = 2, and the k-means++ algorithm is used to select the initial center points. For example, in the first iteration, the center of the high-priority group is [0.8, -0.5], and the center of the low-priority group is [-0.6, 0.3]. During the iteration, the Euclidean distance is calculated. When the eigenvector of Task C is [0.7, -0.4], its distance to the high-priority center (1.2) is less than its distance to the low-priority center (2.8), so it is placed in the high-priority group. After five iterations, the algorithm was terminated when the center point moved less than a threshold of 0.01. The final classification results were: the high-priority group contained 12 tasks, with a mean priority of 8.1±0.9 and an energy consumption of 4.5±1.2 kW·h; the low-priority group contained 18 tasks, with a mean priority of 4.3±1.5 and an energy consumption of 2.1±0.8 kW·h. The good clustering results were verified by the silhouette coefficient (overall value 0.62).

[0071] If the task classification results show that the proportion of high-priority task groups exceeds the preset threshold of 0.6, the robot path is planned based on the A algorithm, and the shortest path set is generated based on the workshop layout and task location.

[0072] If the task classification results show that the proportion of high-priority task groups exceeds a preset threshold, a list of high-priority tasks is obtained from the task classification module to determine the triggering conditions for path planning. Based on the high-priority task list, the task location data and workshop layout information are obtained to generate a set of spatial coordinates for the task locations. The A algorithm is used to process the set of spatial coordinates of the task locations, and combined with the spatial constraints of the workshop layout, a set of shortest paths is obtained. If there are path conflicts in the shortest path set, the path set is analyzed through the conflict detection module to determine conflicting path pairs. Based on the conflicting path pairs, the Dijkstra algorithm is used to replan the conflicting paths to obtain an optimized path set. By optimizing the path set, a robot path allocation plan is generated to determine the execution path for each robot. Based on the robot path allocation plan, path execution time data is obtained to determine the execution efficiency of the path set.

[0073] Specifically, in the task classification results, if the proportion of high-priority task groups exceeds the preset threshold of 0.6, the system will automatically trigger the A algorithm to perform robot path planning. Assume that the current workshop layout is a 10-meter-by-10-meter rectangular area, and the task locations are located at coordinates (2,3), (5,7), and (8,2), respectively. The A algorithm first takes the current position of the robot (0,0) as the starting point and calculates the Manhattan distance to each task point, which is 5, 12, and 10, respectively. Through the heuristic search of the A algorithm, the system generates the shortest path from (0,0) to (2,3) as [(0,0)→(1,0)→(2,0)→(2,1)→(2,2)→(2,3)], with a path length of 5. Next, the system continues to plan the path from (2,3) to (5,7), generating [(2,3)→(3,3)→(4,3)→(5,3)→(5,4)→(5,5)→(5,6)→(5,7)], with a path length of 7. Finally, the system plans the path from (5,7) to (8,2), generating [(5,7)→(6,7)→(7,7)→(8,7)→(8,6)→(8,5)→(8,4)→(8,3)→(8,2)], with a path length of 9. Through iterative optimization of algorithm A, the system finally generates the shortest path set.

[0074] Otherwise, the paths are optimized based on the genetic algorithm to generate a candidate path set containing diversified paths.

[0075] A population is initialized using a genetic algorithm to obtain an initial path set containing multiple paths. Individual encoding is represented by a sequence of path nodes, and the encoded path individuals are obtained from the initial path set. If a path individual satisfies the preset fitness function, it is retained; otherwise, a new path individual is generated through crossover and mutation operations. Based on the new path individuals generated by the crossover and mutation operations, a selection strategy is used to determine the set of retained path individuals. If the retained path individual set meets the convergence criteria, the optimized candidate path set is output; otherwise, the crossover and mutation operations are returned to generate new path individuals. From the optimized candidate path set, paths that meet the diversified path criteria are obtained to generate the final path set. For this final path set, a path optimization algorithm is used to fine-tune the paths to obtain the final optimized diversified path set.

[0076] Specifically, when optimizing paths using a genetic algorithm, the population must first be initialized. For example, 50 paths are randomly generated, each containing 10 nodes, with node coordinates ranging from 0 to 100 in a two-dimensional space. The fitness function is designed to be the sum of path length and an obstacle collision penalty. Path length is calculated using the Euclidean distance, and the collision penalty is set to increase the cost by 100 units per collision. A roulette wheel selection strategy is used, retaining the top 30% of individuals in fitness to advance to the next generation. The crossover operation uses a two-point crossover method, randomly swapping the middle four nodes of two parent paths with a crossover probability of 0.8. The mutation operation randomly replaces the coordinates of one node in a path with a probability of 0.05, within a range of ±5 units. After 100 iterations, the 10 best paths are selected to form the candidate set. The shortest path length is 245.7 units, the longest path length is 278.3 units, and the average difference between paths is 15.2 units. The cosine similarity between paths is calculated to ensure that the similarity within the set is below 0.3, meeting the diversity requirement. Path smoothing uses cubic B-spline interpolation, with control point spacing set to 8 units. The resulting executable path has a maximum curvature of no more than 0.15. An energy consumption model shows that the optimized path saves an average of 12.3% more energy than the initial path.

[0077] Path data is extracted from the shortest path set or candidate path set, combined with the equipment operating status data, and the equipment power on and off timing is calculated through a linear programming algorithm to generate a timing plan including startup time and shutdown time.

[0078] Path data is obtained from the candidate path set, and the path data set is obtained by parsing the path nodes and connection relationships. Data fusion processing is used to combine the path data set with the equipment operating status data to generate a fused data set. If the fused data set meets the preset integrity threshold, the equipment power-on and power-off timing is optimized using a linear programming algorithm to obtain the optimized timing result; if not, the process returns to the path data extraction step and retrieves it again. Based on the optimized timing result, the equipment startup time and shutdown time are extracted to generate a timing data table. Based on the timing data table, a time series analysis method is used to detect anomalies in the timing data and obtain corrected timing data. Based on the corrected timing data, a timing plan containing the startup time and shutdown time is generated. Key time nodes are extracted from the timing plan and stored in the database to generate the final timing plan file.

[0079] Specifically, when extracting path data from the shortest path set, assume that the candidate path set contains three paths with lengths of 120 meters, 150 meters, and 180 meters, respectively. The Dijkstra algorithm calculates the shortest path to be 120 meters, passing through nodes A, B, and C, corresponding to the device numbers DEV001, DEV002, and DEV003. Device operating status data includes DEV001's startup power of 5.2 kW and a shutdown delay of 30 seconds; DEV002's startup power of 3.8 kW and a shutdown delay of 45 seconds; and DEV003's startup power of 4.5 kW and a shutdown delay of 60 seconds. This data is input into a linear programming model, with the objective function set to minimize total energy consumption. Constraints include a maximum parallel power limit of 10 kW for each device and a task completion time of no more than 300 seconds. Using the simplex method, we found that DEV001's startup time is 0 seconds and its shutdown time is 120 seconds; DEV002's startup time is 30 seconds and its shutdown time is 165 seconds; and DEV003's startup time is 75 seconds and its shutdown time is 225 seconds. Verification of the timing scheme shows that the total energy consumption is (5.2 × 120 + 3.8 × 135 + 4.5 × 150) / 3600 = 0.52 kWh, satisfying all constraints.

[0080] For the timing scheme, the Monte Carlo simulation algorithm is used to predict the energy consumption uncertainty caused by task changes and equipment aging, and generate a prediction distribution that includes the energy consumption fluctuation range.

[0081] Monte Carlo simulation is used to obtain multiple sets of randomly sampled scenarios from time-series task changes and equipment aging data to generate an initial energy consumption uncertainty distribution. If the variance of the initial energy consumption uncertainty distribution exceeds a preset threshold, the sampling parameters are adjusted through iterative Monte Carlo simulation to obtain a converged energy consumption uncertainty distribution. Based on the converged energy consumption uncertainty distribution, kernel density estimation is used to generate a probability density function for the energy consumption fluctuation range and determine the energy consumption fluctuation range. By integrating the probability density function, the upper and lower limits of the energy consumption fluctuation range are obtained to generate a predicted distribution. If the confidence interval width of the predicted distribution exceeds a preset threshold, performance degradation characteristics are extracted from the equipment aging data, and the input parameters of the Monte Carlo simulation are updated to obtain an optimized predicted distribution. Based on the optimized predicted distribution, quantile analysis is used to extract the key quantiles of the energy consumption fluctuation range and determine the final energy consumption prediction range. By visualizing the boundary values ​​of the final energy consumption prediction range, a distribution map of the energy consumption fluctuation range is generated and quantitative results are output.

[0082] Specifically, in the time series energy consumption prediction, it is necessary to first build an equipment aging model. For example, the Weibull distribution is used to describe the equipment failure rate, and the shape parameter β is set to 2.5 and the scale parameter η is set to 10,000 hours to simulate the equipment performance degradation curve. By collecting historical operating data (for example, the monthly average temperature of a fan bearing gradually increases from 40°C to 65°C), a linear regression model of temperature and energy consumption is established: y = 0.8x + 120, where x is temperature, y is energy consumption (kWh), and R 2 =0.92. Then, a Monte Carlo simulation framework was designed, with 10,000 iterations set. Each iteration randomly sampled the remaining life of the equipment (based on the Weibull distribution) and the task load fluctuation (normal distribution N (μ = 150kW, σ 2 =25). In each simulation, the sampled device state parameters were fed into an LSTM neural network (hidden layer with 128 units and dropout = 0.2), which output a 24-hour energy consumption series. The task load perturbation term ΔP~N(0, 3.2) was also superimposed. Finally, all simulation results were aggregated to generate a prediction band with an 80% confidence interval. For example, the baseline prediction for a data center cooling system at t+12h was 215 kWh, with a fluctuation range of [208, 223] kWh. To quantify the sources of uncertainty, a Sobol sensitivity analysis was performed, finding that task load variation contributed 62%, device aging 31%, and model error 7%.

[0083] If the energy consumption fluctuation range of the predicted distribution exceeds the preset threshold of 10%, the path set and timing plan are adjusted through the reinforcement learning algorithm to generate an optimized path and timing combination.

[0084] If the predicted energy consumption fluctuation range exceeds the preset threshold, the data acquisition module extracts distribution characteristics from historical energy consumption data to determine the energy consumption fluctuation trend. Based on the energy consumption fluctuation trend, the reinforcement learning algorithm is used to iteratively adjust the path set to generate candidate path combinations. The reinforcement learning algorithm is used to optimize the timing scheme to obtain a timing combination that matches the candidate path combination, and the optimized path and timing combination are determined. If the energy consumption fluctuation range of the optimized path and timing combination still exceeds the preset threshold, the path set and timing scheme are secondary optimized using a genetic algorithm to obtain an updated path and timing combination. Based on the updated path and timing combination, the simulation module is used to predict energy consumption fluctuations and obtain a predicted energy consumption distribution. If the fluctuation range of the predicted energy consumption distribution does not exceed the preset threshold, the output module generates the final path and timing combination to determine the optimization result. The storage module associates the optimization result with the historical energy consumption data, updates the distribution characteristics of the data acquisition module, and obtains a new energy consumption fluctuation trend.

[0085] Otherwise, the current path and timing plan are retained to obtain a stable energy consumption allocation plan.

[0086] The initial energy consumption allocation data is obtained through the preset path plan and timing plan, and the energy consumption allocation plan is determined. If the initial energy consumption allocation data exceeds the preset energy consumption balance threshold, the linear regression algorithm is used to optimize the path plan to obtain the optimized path plan. According to the optimized path plan, the timing plan is adjusted, new timing data is obtained, and the updated timing plan is determined. Through the updated timing plan and the optimized path plan, resource scheduling is performed, the energy consumption allocation data after scheduling is obtained, and the energy consumption balance status is determined. If the energy consumption allocation data after scheduling meets the preset stability analysis threshold, the energy consumption monitoring module is used to obtain real-time energy consumption data to determine the stability of the energy consumption allocation. According to the real-time energy consumption data, the K-means clustering algorithm is used to classify the energy consumption allocation plan to obtain the classified energy consumption allocation plan. Based on the classified energy consumption allocation plan, the plan evaluation is performed to obtain the final stable energy consumption allocation plan and determine the stable plan.

[0087] Specifically, by introducing an energy optimization algorithm while retaining the current path and timing plan, a stable energy allocation solution can be obtained. First, an energy allocation algorithm based on dynamic programming is used to limit the total system energy consumption to within 1000W while ensuring that the energy consumption requirements of each subsystem are met.

[0088] The global energy consumption data is extracted from the optimized path and timing combination, and the particle swarm optimization algorithm is used to iteratively adjust the task allocation and equipment operation parameters to generate a task scheduling solution with the best global energy consumption.

[0089] Global energy consumption data is obtained from task assignments and equipment operating parameters. An initial energy consumption dataset is generated through a data extraction process, resulting in global energy consumption data. The global energy consumption data is analyzed using a particle swarm optimization algorithm. An iterative adjustment process is performed on the task assignment plan and equipment operating parameters to determine the optimized task assignment plan and operating parameter adjustment combination. If the optimized task assignment plan meets the preset energy consumption threshold, the task execution path is adjusted using a path optimization combination to obtain a path optimization combination. If the energy consumption data of the path optimization combination is lower than the energy consumption data of the initial energy consumption dataset, the task execution timing is adjusted using a timing optimization combination to determine a timing optimization combination. The path optimization combination and the timing optimization combination are jointly iterated using a particle swarm optimization algorithm to generate an energy-optimized operating parameter combination for the operating parameter adjustment, resulting in an operating parameter adjustment. A task scheduling solution is generated by integrating the path optimization combination, the timing optimization combination, and the operating parameter adjustment to obtain the energy-optimized task scheduling solution. If the global energy consumption data of the task scheduling solution does not meet the preset energy consumption threshold, the particle swarm optimization algorithm is returned to the algorithm and the iterative adjustment process is repeated to determine the final energy-optimized task scheduling solution.

[0090] Specifically, when extracting global energy consumption data from the optimization path and time series combination, the equipment operating parameters are first collected through sensors. For example, the motor power on a certain production line is 5.2 kilowatts, the speed is 1500 rpm, and the ambient temperature recorded by the temperature sensor is 25 degrees Celsius. These data are uploaded to the energy consumption analysis system in real time through the Internet of Things platform. The system uses a sliding window algorithm to smooth the time series data with a window size of 10 seconds and a step size of 1 second. After eliminating noise interference, a stable energy consumption curve is obtained. Then, the dynamic time warping algorithm (DTW) is used to align the energy consumption time series data of different devices, calculate the similarity matrix, and identify energy consumption anomalies. For example, the instantaneous energy consumption of a certain device suddenly increased to 7.8 kilowatts at 2 pm, deviating from the baseline value by 35%. Based on these data, multiple linear regression is used to construct the energy consumption model. The equipment power, operating time and ambient temperature are used as independent variables to fit the energy consumption function E = 2.3P + 0.8T + 0.5θ, where P is power, T is operating time, θ is the temperature coefficient, and the model determination coefficient R is 1. 2The particle swarm optimization (PSO) algorithm achieved a performance of 0.92. During the particle swarm optimization phase, 50 particles were initialized, each representing a task allocation plan. For example, a particle position vector of [0.6, 0.3, 0.1] indicates that 60% of tasks are allocated to device A, 30% to device B, and 10% to device C. The fitness function is defined as total energy consumption E = Σ(E_i × t_i), where E_i is the energy consumption per unit time of the i-th device and t_i is the running time. During the iteration process, the global optimal solution is updated by comparing the particle's historical optimal solution with the swarm's optimal solution. For example, at the 20th iteration, the optimal solution reduced total energy consumption to 42.7 kWh, an 18.6% reduction compared to the initial solution. The resulting scheduling plan prioritized high-load tasks to device C with the highest energy efficiency (3.2 kWh / ton) and adjusted its operating parameters to 85% of its rated speed. This resulted in a global minimum system energy consumption of 39.4 kWh, while also meeting the production cycle constraints.

[0091] The task scheduling scheme with the best global energy consumption is verified through the real-time data processing module, and the energy consumption parameters are updated based on the latest data collected by the Internet of Things to generate the final adaptive energy consumption optimization scheme.

[0092] Real-time data streams are acquired from IoT devices, and stream processing techniques are used to parse the data to obtain energy-related parameters. If the parsed energy consumption parameters do not match the preset thresholds, the parameters are adjusted based on the deviation to determine the updated energy consumption parameters. The updated energy consumption parameters are loaded into the task scheduling module, and task allocation is optimized using a genetic algorithm to obtain a preliminary task scheduling solution. Based on the preliminary task scheduling solution, global energy consumption data is obtained, and simulation techniques are used to verify the energy consumption effect and determine the degree of optimization. If the degree of optimization is lower than the preset threshold, the task allocation strategy is adjusted, and a scheduling solution is regenerated using a genetic algorithm to obtain an improved task scheduling solution. Based on the improved task scheduling solution, a dynamic programming algorithm is used to generate an adaptive energy consumption optimization solution and determine the final solution. The operating status of the optimization solution is continuously monitored through the real-time data stream, feedback data is obtained, and the energy consumption parameters are updated to obtain the cyclically optimized energy consumption parameters.

[0093] The task execution sequence and equipment operating parameters are extracted from the final adaptive energy consumption optimization plan and transmitted to the workshop control system to complete the real-time deployment of energy consumption optimization.

[0094] The task execution sequence and equipment operating parameters are obtained from the energy consumption optimization plan. A preset optimization algorithm is used to generate an optimized task sequence and parameter configuration, resulting in the task execution sequence and equipment operating parameters. These are then transmitted to the shop floor control system via a data transmission interface. Data connection is completed using a system integration protocol, confirming the data transfer is complete. Once the shop floor control system receives the task execution sequence and equipment operating parameters, it determines whether the parameters meet current production scheduling requirements based on the equipment status data and generates parameter adjustment instructions. The equipment operating parameters are updated based on the parameter adjustment instructions. The energy consumption monitoring module collects equipment status data in real time to generate energy consumption monitoring data. If the energy consumption monitoring data indicates that energy consumption exceeds a preset threshold, the optimization algorithm is used to regenerate the task execution sequence and equipment operating parameters, determining a new optimization plan. The new optimization plan is then transmitted to the shop floor control system via the system integration interface, and the updated task execution sequence and equipment operating parameters are deployed in real time to obtain the real-time deployment status. Based on the real-time deployment status, the shop floor control system's operation log is collected, and data analysis tools are used to extract abnormal information and determine system operational stability.

[0095] Specifically, in the adaptive energy consumption optimization scheme, a genetic algorithm was first used to optimize the shop floor task execution sequence, setting the population size to 100, the number of iterations to 50, the crossover probability to 0.8, and the mutation probability to 0.1. The optimal task sequence was ultimately determined to be [Task A, Task B, Task C, Task D]. Next, a particle swarm optimization algorithm was used to adjust the equipment operating parameters, setting the number of particles to 30, the number of iterations to 40, the inertia weight to 0.7, and the learning factors c1 and c2 to 1.5. After optimization, the operating speed of equipment A was set to 1200 rpm, the temperature of equipment B to 85°C, and the power of equipment C to 2.5 kW. An energy consumption model was then used to compare and analyze the energy consumption before and after optimization. The total energy consumption before and after optimization was 1500 kWh, while after optimization it was 1200 kWh, a 20% reduction. Finally, the optimized task execution sequence and equipment operating parameters were transmitted to the shop floor control system via the OPC UA protocol, enabling real-time deployment of energy consumption optimization.

[0096] On the other hand, this embodiment further provides an electronic device, comprising a memory, a processor, and a computing program stored in the memory and executable on the processor, wherein the method is implemented when the processor executes the computing program.

[0097] On the other hand, this embodiment further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the method when executed by a processor.

[0098] The above are merely preferred embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for optimizing energy consumption in a robot intelligent manufacturing workshop based on the Internet of Things, characterized in that: include: Use IoT technology to obtain production task data, robot location data, and equipment operating status data from workshop sensors to generate real-time data sets; Classifying the real-time data set, and dividing the production tasks into a high-priority task group and a low-priority task group according to task priorities and energy consumption parameters; According to the task classification results, a path planning algorithm is selected to plan the robot path and generate a path set; Extract path data from the path set, combine it with the device operating status data, calculate the device power on / off timing, and generate a timing plan; For the timing plan, predict the energy consumption uncertainty caused by task changes and equipment aging, and generate a predicted distribution of energy consumption fluctuation range; Adjusting the path set and timing plan according to the predicted distribution to generate an optimized path and timing combination; Extracting global energy consumption data from the optimized path and timing combination, iteratively adjusting task allocation and equipment operating parameters, and generating a task scheduling solution with optimal global energy consumption; Verify the task scheduling solution with the best global energy consumption, update the energy consumption parameters based on the latest data, and generate the final adaptive energy consumption optimization solution; The task execution sequence and equipment operating parameters in the final adaptive energy consumption optimization solution are transmitted to the workshop control system to complete the real-time deployment of energy consumption optimization.

2. The method according to claim 1, characterized in that The process of generating a real-time data set includes: If the production task data contains a task identifier and a deadline, the task priority is calculated based on the deadline to obtain a task priority sequence; Calculate the optimal path from the current position to the task target point according to the task priority sequence and the robot position data, and generate path planning data; Analyze device status data, calculate the energy consumption parameters of each device in path planning, and obtain the energy consumption parameter set; If the task priority and path planning or energy consumption parameters in the real-time data set exceed the preset threshold, the sensor data is re-acquired through the Internet of Things technology to update the real-time data set.

3. The method according to claim 1, characterized in that The process of dividing the production tasks into a high-priority task group and a low-priority task group according to the task priority and the energy consumption parameter includes: Obtain real-time production task data sets, extract task priorities and energy consumption parameters, standardize the data format, and obtain preprocessed data sets; Using a K-means clustering algorithm to classify the preprocessed data set, determine a high-priority task group and a low-priority task group, and obtain an initial classification result; If there is a mismatch between the task priority and the energy consumption parameter in the initial classification result, the classification is readjusted according to the preset priority threshold and energy consumption threshold to obtain an optimized classification result.

4. The method according to claim 1, wherein The process of generating a path set includes: If the task classification result shows that the proportion of high-priority task groups exceeds the preset threshold, the high-priority task list is obtained from the task classification module to determine the triggering path planning conditions; According to the high-priority task list, task location data and workshop layout information are obtained to generate a set of spatial coordinates of the task locations; The A* search algorithm is used to process the spatial coordinate set of the task location and obtain the shortest path set in combination with the spatial constraints of the workshop layout; If there is a path conflict in the shortest path set, the path set is analyzed by a conflict detection module to determine the conflicting path pairs, and the conflicting paths are replanned using the Dijkstra algorithm to obtain an optimized path set; If the task classification result shows that the proportion of high-priority task groups does not exceed the preset threshold, the population is initialized through the genetic algorithm to obtain an initial path set containing multiple paths; Encoding the path individuals in the initial path set and expressing them using a path node sequence; If the path individual satisfies the preset fitness function, the path individual is retained, otherwise a new path individual is generated through crossover and mutation operations; Based on the new path individuals generated by the crossover operation and the mutation operation, a selection strategy is used to determine a set of retained path individuals; If the retained path individual set meets the convergence condition, the optimized candidate path set is output; otherwise, the crossover operation and mutation operation are returned to generate a new path individual.

5. The method according to claim 4, characterized in that The process of generating a timing plan includes: Acquire path data from the path set, and obtain a path data set by parsing path nodes and connection relationships; Combining the path data set with the equipment operating status data to generate a fused data set; If the fused data set meets the preset integrity threshold, the device power on / off timing is optimized using a linear programming algorithm to obtain an optimized timing result; Based on the optimized timing results, extract the device startup time and shutdown time to generate a timing data table; According to the time series data table, a time series analysis method is used to detect abnormal points in the time series data to obtain corrected time series data; A timing plan including a start-up time and a shut-down time is generated using the corrected timing data.

6. The method according to claim 1, characterized in that The process of generating a predicted distribution of energy consumption fluctuation range includes: Using Monte Carlo simulation, we obtain multiple sets of random sampling scenarios from sequential task changes and equipment aging data to generate an initial energy consumption uncertainty distribution. If the variance of the initial energy consumption uncertainty distribution exceeds a preset threshold, adjusting the sampling parameters through iterative Monte Carlo simulation to obtain a converged energy consumption uncertainty distribution; According to the converged energy consumption uncertainty distribution, a probability density function of the energy consumption fluctuation range is generated using kernel density estimation to determine the energy consumption fluctuation range; By integrating the probability density function, the upper and lower limits of the energy consumption fluctuation range are obtained to generate a predicted distribution.

7. The method according to claim 1, characterized in that The process of generating the optimized path and timing combination includes: If the predicted energy consumption fluctuation range exceeds a preset threshold, the data acquisition module obtains distribution characteristics from historical energy consumption data to obtain energy consumption fluctuation trends; According to the energy consumption fluctuation trend, a reinforcement learning algorithm is used to iteratively adjust the path set to generate a candidate path combination; The timing scheme is optimized by the reinforcement learning algorithm to obtain a timing combination that matches the candidate path combination, and to determine the optimized path and timing combination.

8. The method according to claim 1, characterized in that The process of generating a task scheduling solution with the best global energy consumption includes: Obtaining global energy consumption data from the task assignments and equipment operating parameters, and generating an initial energy consumption dataset using a data extraction process; Analyzing the global energy consumption data using a particle swarm optimization algorithm, performing an iterative adjustment process on the task allocation plan and equipment operating parameters, and determining an optimized task allocation plan and operating parameter adjustment combination; If the optimized task allocation scheme meets the preset energy consumption threshold, the task execution path is adjusted using the path optimization combination to obtain the path optimization combination; If the energy consumption data of the path optimization combination is lower than the initial energy consumption data set, the task execution timing is adjusted through the timing optimization combination to determine the timing optimization combination; The particle swarm optimization algorithm is used to jointly iterate the path optimization combination and the timing optimization combination, and the operating parameter combination with the optimal energy consumption is generated for the operating parameter adjustment to obtain the operating parameter adjustment; The task scheduling scheme integrates the path optimization combination, the timing optimization combination and the operation parameter adjustment to generate a task scheduling scheme, thereby obtaining a task scheduling scheme with optimal energy consumption.

9. An electronic device comprising a memory, a processor, and a computing program stored in the memory and executable on the processor, wherein: When the processor executes the computing program, the method according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images