Power-on and power-off method and device, equipment and storage medium

Abstract

The invention discloses a power-on and power-off method, device and equipment and a storage medium, and relates to the power-on and power-off method, device and equipment and the storage medium, and the method comprises the steps: obtaining a production task sequence diagram of production equipment and a current equipment state under the condition of receiving task change data; according to the production task sequence diagram, the task change data and the current equipment state, carrying out probability prediction on the production task demand of the production equipment to obtain probability distribution of a preset time period; under a preset optimization constraint condition, power-on and power-off time points of the production equipment in the production task process are optimized through probability distribution, a power-on and power-off strategy is obtained, and the preset optimization constraint condition is constructed based on equipment energy consumption, production delay and / or start-stop loss; based on the power-on and power-off strategy, power-on and power-off of the production equipment in the production task process are controlled. Compared with an existing equipment power-on and power-off control mode based on a simple rule, the method can adapt to a complex and changeable production environment, and therefore the production efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of equipment control technology, and in particular to a power-on / off method, apparatus, device, and storage medium. Background Technology

[0002] Currently, in energy control and management scenarios for production equipment (such as manufacturing production lines and machining centers), in order to efficiently manage the energy consumption of production equipment and improve production efficiency, a simple rule-based power-on / off control method is generally adopted, such as timed switching of equipment or setting fixed energy consumption thresholds for alarms.

[0003] However, due to the complexity and variability of the production environment, this simple method of controlling the power on and off of equipment is difficult to adapt to the dynamically changing production process. For example, in the event of a sudden equipment failure, simple timed switching rules are insufficient to adjust the start and stop of the equipment in a timely manner, which may lead to the stagnation of the production line; or when faced with urgent orders, frequent manual start and stop of equipment will also increase production time, resulting in low production efficiency. Summary of the Invention

[0004] The main purpose of this application is to provide a power-on / off method, apparatus, device, and storage medium, which aims to solve the technical problem that traditional power-on / off control methods based on simple rules are difficult to adapt to complex and ever-changing production environments, resulting in low production efficiency.

[0005] To achieve the above objectives, this application proposes a power-on / off method, the method comprising:

[0006] Upon receiving task change data, obtain the production task sequence diagram and current equipment status of the production equipment; Based on the production task timeline, the task change data, and the current equipment status, the production task demand of the production equipment is probabilistically predicted to obtain the probability distribution for a preset time period. Under preset optimization constraints, the power-on and power-off time points of the production equipment during the production task are optimized through the probability distribution to obtain the power-on and power-off strategy. The preset optimization constraints are constructed based on equipment energy consumption, production delay and / or start-up and shutdown losses. Based on the aforementioned power-on / off strategy, the power supply to the production equipment is controlled during the production process.

[0007] In one embodiment, the step of probabilistically predicting the production task demand of the production equipment based on the production task timeline, the task change data, and the current equipment status to obtain a probability distribution over a preset time period includes: The production task timing diagram, the task change data, and the current equipment status are respectively structured and encoded to obtain corresponding timing vectors, event vectors, and status vectors; The timing vector, the event vector, and the state vector are concatenated to obtain a composite vector. Based on the comprehensive vector, the production task demand of the production equipment is predicted in multiple steps to obtain the probability value of the production task demand in each time step. Based on the probability value at each time step, the probability distribution of the production task demand within a preset time period is determined.

[0008] In one embodiment, the step of optimizing the power-on and power-off timing of the production equipment during the production task process using the probability distribution under preset optimization constraints to obtain a power-on / power-off strategy includes: The power-on and power-off times of the production equipment are used as decision variables; Pre-defined optimization constraints are constructed based on equipment energy consumption, production delays, and / or start-up and shutdown losses, and uncertainty constraints are constructed based on the probability distribution. Under the preset optimization constraints and the uncertainty constraints, the decision variables are optimized by a mixed integer programming optimization algorithm to obtain the power-on and power-off command set of the production equipment during the production task, and the power-on and power-off command set is used as the power-on and power-off strategy.

[0009] In one embodiment, before the step of obtaining the production task sequence diagram and current equipment status of the production equipment upon receiving task change data, the method further includes: Extract sample equipment status from the historical production data of the production equipment, and extract the sample production task time sequence diagram and corresponding sample task change data corresponding to the sample equipment status; Statistically analyze the probability distribution of the sample task change data across various production task requirements. A prediction model is obtained by training the model based on the sample equipment status, the sample production task time sequence diagram, the sample task change data, and the sample probability distribution. The step of probabilistically predicting the production task demand of the production equipment based on the production task timeline, the task change data, and the current equipment status to obtain the probability distribution over a preset time period includes: The production task timeline, the task change data, and the current equipment status are input into the prediction model to obtain the probability distribution of the production task demand over a preset time period.

[0010] In one embodiment, after the step of training the model based on the sample device status, the sample production task time sequence diagram, the sample task change data, and the sample probability distribution to obtain the prediction model, the method further includes: The historical production data is labeled to obtain the sample power-on / off strategy corresponding to the sample equipment status; A preset optimization constraint is constructed with the equipment energy consumption, production delay and / or start-up and shutdown loss of the production equipment as the optimization objective. Under the preset optimization constraint, the prediction model is trained according to the sample power on and off strategy to obtain the strategy generation model. The step of optimizing the power-on and power-off timing of the production equipment during the production task to obtain the power-on and power-off strategy includes: The power on / off timing of the production equipment during the production task is optimized using the strategy generation model to obtain the power on / off strategy.

[0011] In one embodiment, after the step of controlling the power supply to the production equipment during the production task based on the power supply strategy, the method further includes: The power-on / off execution results of the production equipment after the production task is completed are obtained, and the power-on / off execution results are compared with the power-on / off strategy to obtain execution deviation data; The strategy generation model is optimized based on the execution deviation data to obtain an optimized strategy generation model; Based on the optimized strategy generation model, the process returns to the step of obtaining the production task sequence diagram and current equipment status of the production equipment upon receiving task change data.

[0012] In one embodiment, the step of obtaining the production task timing diagram of the production equipment includes: Obtain production planning and scheduling data for the production equipment and determine the equipment type of the production equipment; Based on the production plan scheduling data and the equipment type, the system queries a preset equipment knowledge base to obtain the equipment preparation time, production energy consumption curve, and sleep time corresponding to the production plan scheduling data. The equipment knowledge base includes the mapping relationship between various types of production equipment and various types of production tasks. Based on the equipment preparation time, the production energy consumption curve, and the sleep time, a production task sequence diagram corresponding to the production equipment is constructed.

[0013] Furthermore, to achieve the above objectives, this application also proposes a power-on / off device, the device comprising: The status module is used to obtain the production task sequence diagram and current equipment status of the production equipment when task change data is received. The prediction module is used to perform probability prediction of the production task demand of the production equipment based on the production task time sequence diagram, the task change data and the current equipment status, and obtain the probability distribution of a preset time period. The optimization module is used to optimize the power-on and power-off time points of the production equipment during the production task process through the probability distribution under preset optimization constraints to obtain a power-on and power-off strategy. The preset optimization constraints are constructed based on equipment energy consumption, production delay and / or start-up and shutdown losses. The control module is used to control the power supply to the production equipment during the production task based on the power supply strategy.

[0014] In addition, to achieve the above objectives, this application also proposes a power-on / off device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the power-on / off method as described above.

[0015] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the power-on / off method described above.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: The power-on / off method of this application includes: upon receiving task change data, acquiring a production task time sequence diagram and the current equipment status of the production equipment; performing probability prediction on the production task demand of the production equipment based on the production task time sequence diagram, the task change data, and the current equipment status to obtain a probability distribution for a preset time period; under preset optimization constraints, optimizing the power-on / off time points of the production equipment during the production task process through the probability distribution to obtain a power-on / off strategy, wherein the preset optimization constraints are constructed based on equipment energy consumption, production delay, and / or start-up / shutdown losses; and controlling the power-on / off of the production equipment during the production task process based on the power-on / off strategy.

[0017] This application, upon receiving task change data, first acquires the production task sequence diagram and current equipment status of the production equipment. Then, based on this information, it performs probabilistic prediction of the production task requirements of the production equipment to obtain a probability distribution for a preset time period. Under preset optimization constraints, it optimizes the power-on and power-off times of the production equipment during the production task process using the probability distribution to obtain a power-on / off strategy. Finally, it controls the equipment's power-on and power-off based on this strategy. Compared to existing equipment power-on / off control methods based on simple rules, this application, by combining task change data and current equipment status to formulate a power-on / off strategy, can adapt to complex and ever-changing production environments, thereby improving production efficiency. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating an embodiment of the power-on / off method of this application. Figure 2 This is an overall flowchart of the power-on / off control provided in Embodiment 1 of this application; Figure 3 This is a flowchart illustrating Embodiment 2 of the power-on / off method of this application; Figure 4 This is a flowchart illustrating Embodiment 3 of the power-on / off method of this application; Figure 5 This is a block diagram of the module structure of the power-on / off device according to an embodiment of this application; Figure 6 This is a schematic diagram of the hardware operating environment involved in the power on / off device in the embodiments of this application.

[0021] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] To make the above-mentioned objectives, features, and advantages of this application more apparent and understandable, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0023] The main solution of this application is: Currently, in the energy control and management scenarios of production equipment (such as manufacturing production lines, machining centers, etc.), in order to efficiently manage the energy consumption of production equipment and improve production efficiency, a simple rule-based equipment power-on and power-off control method is generally adopted, such as timed switching of equipment or setting fixed energy consumption thresholds for alarms.

[0024] However, due to the complexity and variability of the production environment, this simple method of controlling the power on and off of equipment is difficult to adapt to the dynamically changing production process. For example, in the event of a sudden equipment failure, simple timed switching rules are insufficient to adjust the start and stop of the equipment in a timely manner, which may lead to the stagnation of the production line; or when faced with urgent orders, frequent manual start and stop of equipment will also increase production time, resulting in low production efficiency.

[0025] To address the aforementioned issues, this application provides a power-on / off method. Upon receiving task change data, the method first acquires the production task sequence diagram and current equipment status of the production equipment. Then, based on this information, it performs probabilistic prediction of the production task requirements of the production equipment to obtain a probability distribution for a preset time period. Under preset optimization constraints, it optimizes the power-on / off timing of the production equipment during the production task process using the probability distribution to obtain a power-on / off strategy. Finally, it controls the equipment's power-on / off based on this strategy. Compared to existing equipment power-on / off control methods based on simple rules, this application can formulate a power-on / off strategy by comprehensively considering task change data and the current equipment status, adapting to complex and ever-changing production environments and thus improving production efficiency.

[0026] It should be noted that the executing entity of this application embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a personal computer or server, or an electronic device capable of realizing the above functions, or a power-on / off device executing the power-on / off method of this application (for example, the power-on / off device can be in the form of a controller or timer to control the power-on / off of production equipment). This embodiment does not limit this. The following uses a power-on / off device as an example to describe this embodiment and the following embodiments.

[0027] Based on this, this application proposes a power-on / off method according to the first embodiment, referring to... Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the power-on / off method of this application. In this embodiment, the power-on / off method may include steps S10 to S40: Step S10: Upon receiving task change data, obtain the production task sequence diagram of the production equipment and the current equipment status.

[0028] It should be noted that task change data can refer to information related to changes in production tasks within the context of production equipment energy control and management. For example, the original plan was to produce 1000 units of a certain product model, but an urgent order was received requiring the production of an additional 200 units of that model; or the original production of product A was to be switched to production of product B. These changes in production tasks directly impact the power on / off control of the production equipment.

[0029] It should also be noted that the current equipment status can be the actual operating status of the production equipment at the current moment, such as being in normal operation, standby, fault repair, starting preheating, or stopped. This embodiment does not limit this.

[0030] The production task sequence diagram can be a graphical representation of the time arrangement of each production stage of the production equipment throughout the entire production task cycle. For example, different equipment performing different tasks may have different warm-up times, production energy consumption curves, and safe rest periods after the task. This embodiment does not impose any limitations on this. It should be noted that this production task sequence diagram can be predetermined through production scheduling and is a planned task sequence diagram before any changes occur to the production task.

[0031] In practical use, when the power-on / off equipment receives task change data, it indicates that controlling the power on and off of the production equipment according to the original planned production task sequence diagram may result in excessive standby energy consumption when not in production, or repeated power-on resets and preheating after a power outage, affecting production efficiency. Therefore, in this case, it is necessary to obtain the production task sequence diagram and the current equipment status to optimize subsequent power on / off operations.

[0032] Step S20: Based on the production task timeline, the task change data, and the current equipment status, perform probability prediction on the production task demand of the production equipment to obtain the probability distribution of a preset time period.

[0033] Understandably, the probability distribution divides a preset time period (e.g., the next 2 hours, half a day, etc., this embodiment does not limit this) into a certain time interval, and then gives the probability that the production equipment will complete different production tasks within that time interval for each time interval.

[0034] For example, when faced with urgent order insertions, the probability of production demand within a preset time period can be assessed by combining the current operating status of the equipment and the remaining production task schedule. In this case, the next two hours can be divided into four 30-minute time periods. For each time period, the probability of the production equipment completing different quantities of processing tasks, such as 50 or 100 pieces, can be predicted, forming a probability distribution. Through probability prediction, the task demand and workload of the production equipment in different time periods can be understood in advance, providing a basis for subsequent power-on / off strategies.

[0035] In practical use, the probability of production task demand for the production equipment in the future period can be assessed based on the production task timeline, task change data and current equipment status, so as to obtain the probability distribution of the preset time period.

[0036] Step S30: Under preset optimization constraints, the power-on and power-off times of the production equipment during the production task are optimized using the probability distribution to obtain a power-on and power-off strategy. The preset optimization constraints are constructed based on equipment energy consumption, production delays, and / or start-up and shutdown losses.

[0037] Step S40: Based on the power on / off strategy, control the power on / off of the production equipment during the production task.

[0038] It should be noted that the preset optimization constraints are a series of limitations constructed based on factors such as equipment energy consumption, production delays, and / or start-up and shutdown losses. In the energy control and management of production equipment, equipment energy consumption is an important cost factor that needs to be minimized; production delays will affect order delivery; frequent equipment start-up and shutdown will generate start-up and shutdown losses, increasing equipment maintenance costs.

[0039] For example, constraints such as the maximum energy consumption limit per hour, the maximum allowable production delay time, and the maximum number of start-stop cycles per day can be set for the equipment. When formulating power-on / off strategies, these conditions must be met to ensure smooth production.

[0040] Understandably, power-on / off times can refer to the specific moments during a production task when equipment begins and ceases operation. For example, based on the production schedule, the equipment might be powered on at 8:00 AM for preheating and preparation, begin processing at 9:00 AM, be powered off for a lunch break from 12:00 PM to 1:00 PM, and then powered back on at 1:00 PM to continue processing until 6:00 PM when the day's tasks are completed and then powered off again. By optimizing these power-on / off times, unnecessary power outages can be avoided during urgent tasks, thus improving production efficiency.

[0041] Among them, the power on / off strategy is a power on / off control scheme obtained by optimizing the power on / off time of production equipment during the production task process under preset optimization constraints, taking into account factors such as the probability distribution of production task demand, equipment status, energy consumption, production delay and start-up / shutdown losses, etc. It clarifies when the equipment should be powered on and when it should be powered off at different time periods.

[0042] For example, powering on at the optimal time precisely meets preheating requirements and avoids premature idling; powering off at the optimal time precisely meets production task requirements and avoids premature power outages. This optimizes the start-up and shutdown process, precisely controls equipment power supply, eliminates ineffective standby during non-production periods, and reduces peak startup energy consumption. For short-interval tasks, entering a low-power hold state instead of a complete power cut reduces restart energy consumption and time, thus ensuring the optimal balance between production efficiency and energy utilization.

[0043] In practical use, preset optimization constraints are constructed based on equipment energy consumption, production delays, and / or start-up and shutdown losses. Under these constraints, the power-on and power-off timing of the production equipment during the production process is optimized to obtain a power-on / off strategy. Then, an intelligent power-on / off actuator (such as an intelligent circuit breaker) is controlled to execute this power-on / off strategy to control the production equipment to accurately switch power on and off during the production process.

[0044] Furthermore, in order to obtain the aforementioned production task sequence diagram, in this embodiment, the step of obtaining the production task sequence diagram of the production equipment may include: Step S11: Obtain the production plan scheduling data of the production equipment and determine the equipment type of the production equipment.

[0045] It should be noted that the production planning and scheduling data is detailed production arrangement information formulated for production equipment. For example, what products to be produced, the production quantity, and the order of production tasks are not limited in this embodiment. Equipment type is a category identifier for classifying production equipment according to its function or purpose. Different equipment undertakes different tasks in the production process, and due to the differences in equipment type and production tasks, there are also significant differences in preparation time, production energy consumption, and dormancy time.

[0046] Step S12: Based on the production plan scheduling data and the equipment type, query the preset equipment knowledge base to obtain the equipment preparation time, production energy consumption curve and hibernation time corresponding to the production plan scheduling data. The equipment knowledge base includes the mapping relationship between various types of production equipment and various types of production tasks.

[0047] Step S13: Based on the equipment preparation time, the production energy consumption curve, and the sleep time, construct the production task sequence diagram corresponding to the production equipment.

[0048] Understandably, the preset equipment knowledge base is a pre-built database containing the mapping relationship between various types of production equipment and various production tasks. It stores information such as equipment preparation time, production energy consumption curve, and hibernation time for different equipment under different production tasks.

[0049] The equipment preparation time is the time required for production equipment to go from receiving a production task instruction to being able to officially start production and reach a stable production state, including preheating and loading production programs. This embodiment does not impose any limitations on this. The production energy consumption curve describes the energy consumption of the production equipment over time during the execution of a production task, reflecting the energy consumption of the production equipment at different production stages. The sleep time is the duration during which the production equipment enters sleep mode after completing a production task or when it is in a non-production state.

[0050] It should be noted that the production task sequence diagram is a chart that uses time as the horizontal axis and graphically displays the key links in the production process of the production equipment in chronological order. It presents the entire time flow of the equipment from power-on, preparation for production, formal production, hibernation to power-off.

[0051] In practical use, refer to Figure 2 , Figure 2 This is an overall flowchart of the power-on / off control provided in Embodiment 1 of this application. For equipment to operate continuously, the system first retrieves production schedule data from the Advanced Planning and Scheduling (APS) system. Then, it parses the schedule, calls the built-in equipment knowledge base, and automatically calculates the required equipment preparation time, production energy consumption curve, and post-task safe sleep time for each production task, generating a time-dimensional, equipment-level, precise power-on or power-off task sequence diagram. Compared to frequent manual power-on / off operations, constructing a production task sequence diagram avoids the problem of disconnect between planning and energy control, enabling automatic power-on / off of equipment based on precise production plans.

[0052] This application provides a power-on / off method. Upon receiving task change data, the method first acquires the production task sequence diagram and current equipment status of the production equipment. Then, based on this information, it performs probability prediction on the production task requirements of the production equipment to obtain a probability distribution for a preset time period. Under preset optimization constraints, it optimizes the power-on / off timing of the production equipment during the production task process using the probability distribution to obtain a power-on / off strategy. Finally, it controls the equipment's power-on / off based on this strategy. Compared to existing equipment power-on / off control methods based on simple rules, this embodiment can formulate a power-on / off strategy by comprehensively considering task change data and the current equipment status, which can adapt to complex and ever-changing production environments, thereby improving production efficiency.

[0053] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to the above embodiment can be referred to the above description, and will not be repeated hereafter. On this basis, a second embodiment of the dialogue method of this application is proposed, please refer to... Figure 3 , Figure 3 This is a flowchart illustrating Embodiment 2 of the power-on / off method of this application. To obtain the above probability distribution, as... Figure 3 As shown, in this embodiment, the step of probabilistically predicting the production task demand of the production equipment based on the production task timeline, the task change data, and the current equipment status to obtain the probability distribution of a preset time period may include: Step S21: Perform structured encoding on the production task timing diagram, the task change data, and the current equipment status to obtain the corresponding timing vector, event vector, and state vector.

[0054] Step S22: Concatenate the time sequence vector, the event vector, and the state vector to obtain a composite vector.

[0055] It should be noted that the time sequence vector is a computer-understandable and processable vector obtained by structured encoding of the production task time sequence diagram, containing various information about the production task in the time dimension. The event vector is a vector obtained by structured encoding of task change data, representing various changes that occur during the execution of the production task. The state vector is a vector obtained by structured encoding of the current equipment state, used to characterize the current working status of the equipment.

[0056] Specifically, such as Figure 2 As shown, in the strategy generation process, the real-time equipment status of the acquired production equipment is first normalized and encoded into feature vectors using structured vectorization techniques. The production task time sequence diagram is then sorted by time and transformed into task sequence vectors. Task change data is encoded into event vectors. Next, a Long Short-Term Memory (LSTM) network is used to concatenate and fuse these three elements to generate a comprehensive context vector that simultaneously contains production time sequence and task change information.

[0057] Step S23: Based on the comprehensive vector, perform multi-step forward prediction on the production task requirements of the production equipment to obtain the probability value corresponding to the production task requirements in each time step.

[0058] Step S24: Determine the probability distribution of the production task demand within a preset time period based on the probability value at each time step.

[0059] Understandably, the probability value represents the likelihood of a production task demand occurring at each time step. For example, a probability value of 0.8 for predicting production task demand A in the next hour means that there is an 80% chance that demand A will occur during that time period. The closer the value is to 1, the greater the likelihood that the production task demand will occur at the corresponding time step.

[0060] It should be understood that a probability distribution describes the probabilistic patterns of various possible scenarios for production task demands within a preset time period. For example, a probability distribution can reveal the probability of various product production task demands occurring in different time periods.

[0061] Specifically, encoders can be used to perform multi-step forward prediction of production task requirements for production equipment, gradually extrapolating the probability, expected duration, and prediction confidence of task requirements at each future time point, thus forming probabilistic demand information.

[0062] Because this embodiment uses structured coding to transform production task-related data and equipment status into vectors and then concatenates them into a comprehensive vector, it comprehensively considers the interaction and relationship between various influencing factors, thereby enhancing the accuracy of prediction.

[0063] Furthermore, in order to obtain the aforementioned power-on / off strategy, in this embodiment, the step of optimizing the power-on / off time points of the production equipment during the production task process using the probability distribution under preset optimization constraints to obtain the power-on / off strategy may include: using the power-on / off time points of the production equipment as decision variables; constructing preset optimization constraints based on equipment energy consumption, production delays, and / or start-up / shutdown losses, and constructing uncertainty constraints based on the probability distribution; optimizing the decision variables using a mixed integer programming optimization algorithm under the preset optimization constraints and the uncertainty constraints to obtain the power-on / off command set of the production equipment during the production task process, and using the power-on / off command set as the power-on / off strategy.

[0064] It should be noted that when scheduling production tasks for multiple devices, the specific power-on and power-off times for each device need to be determined. These times are the decision variables, and the production plan is optimized by taking into account the values ​​of these variables. Uncertainty constraints are constructed based on probability distributions and are used to account for the impact of the uncertainty of production task requirements on the optimization of the power-on and power-off times of production equipment.

[0065] It should also be noted that mixed-integer programming optimization algorithm is a mathematical method used to solve optimization problems involving both integer and continuous variables. In this embodiment, the power-on and power-off times of the production equipment are used as decision variables, which may have both integer forms (such as specific hours or minutes) and continuous forms (such as precise power-on times within a certain time period). Furthermore, the optimization problem is also subject to preset optimization constraints and uncertainty constraints. The mixed-integer programming optimization algorithm can comprehensively consider these factors to find the optimal values ​​of the decision variables.

[0066] Specifically, the complex power on / off decision problem (i.e. Figure 2The process of optimizing power-on and power-off timing is transformed into a rigorous mixed-integer programming model. First, decision variables (i.e., power-on and power-off) are defined for each production device in each future time slice. Then, based on equipment energy consumption, production delays, and / or start-up / shutdown losses, a minimum total expectation (i.e., preset optimization constraints) is established to ensure that the optimization direction simultaneously considers energy saving and efficiency. Considering that production task demands may not be entirely in accordance with the plan and may have certain fluctuations and uncertainties, probability distributions are introduced into the uncertainty constraints. Finally, a mathematical programming solver is called to perform global optimization calculations on the decision variables, outputting the optimal power-on and power-off command sets for each production device in the next time period. These commands constitute the complete power-on and power-off strategy.

[0067] Because this embodiment uses a mixed-integer programming optimization algorithm, it can comprehensively consider multiple factors such as equipment energy consumption, production delays, and start-up / shutdown losses to find the optimal solution for the decision variable of power-on / off time. This solves the problem of static and rigid control strategies, enabling real-time seeking of the optimal balance between energy saving and efficiency in a changing production environment, thus achieving overall optimization of the production process.

[0068] Based on the first and / or second embodiments of this application, in the third embodiment of this application, the content that is the same as or similar to that in embodiments one and two above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 4 , Figure 4 This is a flowchart illustrating Embodiment 3 of the power-on / off method of this application. To improve the efficiency of the above probability prediction, such as... Figure 4 As shown, in this embodiment, before the step of obtaining the production task sequence diagram and current equipment status of the production equipment upon receiving task change data, the method further includes: Step S01: Extract sample equipment status from the historical production data of the production equipment, and extract the sample production task time sequence diagram and corresponding sample task change data corresponding to the sample equipment status.

[0069] It should be noted that historical production data can be a collection of various data recorded by production equipment during past production processes, including the equipment's operating status at different times (such as start-up, shutdown, running, fault, etc.), production task information, and equipment energy consumption data. Sample equipment status is representative equipment operating status information extracted from the historical production data. The sample production task time series diagram is a chart from the historical production data, using time series as the horizontal axis, showing the time arrangement and task sequence of the sample equipment at each stage of executing production tasks. Sample task change data can be relevant data from historical production data that has changed compared to the original planned tasks.

[0070] Step S02: Statistically analyze the probability distribution of the sample task change data in various production task requirements.

[0071] Understandably, the sample probability distribution can be obtained by statistically analyzing the sample task change data and showing the probability distribution of the sample task change data in various production task requirements, reflecting the degree of uncertainty of the production task.

[0072] Step S03: Train the model based on the sample equipment status, the sample production task time sequence diagram, the sample task change data, and the sample probability distribution to obtain a prediction model.

[0073] The step of probabilistically predicting the production task demand of the production equipment based on the production task timeline, the task change data, and the current equipment status to obtain the probability distribution over a preset time period includes: Step S201: Input the production task time sequence diagram, the task change data and the current equipment status into the prediction model to obtain the probability distribution of the production task demand in a preset time period.

[0074] It should be noted that the prediction model can be a mathematical model trained based on sample equipment status, sample production task time series diagrams, sample task change data, and sample probability distribution. It can learn the inherent relationships and patterns between the above data and predict changes in production tasks based on new input data. It can be trained using deep learning models such as Long Short-Term Memory networks and Convolutional Neural Networks; this embodiment does not impose any limitations on this.

[0075] In this embodiment, the sample equipment status, sample production task time sequence diagram, sample task change data, and sample probability distribution are input into the Long Short-Term Memory network for learning and training. This enables the model to learn the complex relationship between production tasks and equipment status more accurately, thereby improving the accuracy of predicting production task demand within a preset time period.

[0076] Furthermore, to improve the efficiency of optimizing power-on / off timing, in this embodiment, after the step of training the model based on the sample equipment status, the sample production task timeline, the sample task change data, and the sample probability distribution to obtain the prediction model, the method further includes: labeling the historical production data to obtain the sample power-on / off strategy corresponding to the sample equipment status; constructing preset optimization constraints with the equipment energy consumption, production delay, and / or start-up / shutdown losses of the production equipment as optimization objectives; and training the prediction model based on the sample power-on / off strategy under the preset optimization constraints to obtain the strategy generation model. The step of optimizing the power-on and power-off timing of the production equipment during the production task to obtain a power-on and power-off strategy includes: optimizing the power-on and power-off timing of the production equipment during the production task through the strategy generation model to obtain a power-on and power-off strategy.

[0077] It should be noted that the sample power-on / off strategy can be a power-on / off operation scheme corresponding to the equipment status obtained by labeling the sample equipment status in historical production data, which clarifies the optimal power-on / off time under different equipment statuses.

[0078] It should also be noted that the strategy generation model is a model trained on a prediction model based on sample power-on / off strategies under preset optimization constraints. It can generate power-on / off strategies that meet the optimization objectives based on input information such as equipment status and production tasks. Specifically, during the model training phase, physical and operational constraints such as equipment energy consumption, production delays, and / or start-up / shutdown losses can be transformed into penalty terms in the loss function. This allows the model to learn implicit rules from sample power-on / off strategies, and to immediately correct model parameters that violate constraints, ensuring that the output strictly meets operating conditions. Thus, the model parameters are adaptively adjusted within the constraint boundaries, ultimately achieving the generation of the strategy generation model.

[0079] Because this embodiment constructs a strategy generation model with the core objectives of minimizing total energy consumption, production delays, and equipment start-up and shutdown losses, it can automatically generate the optimal power-on / off strategy based on real-time equipment status and production task information, thereby improving the accuracy and timeliness of decision-making.

[0080] Furthermore, to further improve the accuracy of the model, in this embodiment, after the step of controlling the power on / off of the production equipment during the production task based on the power on / off strategy, the method further includes: obtaining the power on / off execution result of the production equipment after the production task is completed, and comparing the power on / off execution result with the power on / off strategy to obtain execution deviation data; optimizing the strategy generation model based on the execution deviation data to obtain an optimized strategy generation model; and based on the optimized strategy generation model, returning to the step of obtaining the production task sequence diagram and current equipment status of the production equipment when task change data is received.

[0081] It should be noted that the power on / off execution result refers to the actual power on and power off operations performed by the production equipment after it has completed its predetermined production tasks.

[0082] It should also be noted that the execution deviation data is the difference between the actual power-on and power-off results of the production equipment after the production task is completed and the pre-defined power-on and power-off strategy. This includes deviations in time (such as the actual power-on time being earlier or later than the time specified in the strategy) and duration (such as the actual power-on duration being inconsistent with the duration specified in the strategy).

[0083] In this embodiment, as Figure 2 As shown, after the above model outputs the power-on / off strategy, the power-on / off equipment enters the self-execution and control stage, executing the power-on / off strategy during the production task. However, considering that the power-on / off strategy is predicted and there are deviations in the actual situation, it is necessary to collect feedback data after execution to obtain the power-on / off execution result. Then, the deviation between the prediction (i.e., the power-on / off strategy) and the actual (i.e., the power-on / off execution result) is analyzed. Then, using these deviation data, the above strategy generation model is continuously learned and optimized through reinforcement learning (RL) algorithm. Specifically, the obtained deviation data can be used as feedback signals (i.e., reward or penalty values) in the reinforcement learning algorithm. If the actual power-on / off operation has a high degree of consistency with the power-on / off strategy (i.e., small deviation), a positive reward is given; if the consistency is low (i.e., large deviation), a negative penalty is given. Then, the equipment status, production task, and other information are used as state inputs, and the power-on / off strategy generated by the strategy generation model is used as action output. Through the reinforcement learning algorithm, the parameters of the strategy generation model are continuously learned from these inputs and outputs, and the parameters are adjusted according to the feedback deviation data to gradually reduce the execution deviation and continuously optimize the performance of the strategy generation model.

[0084] Simultaneously, the equipment knowledge base is updated based on the actual usage of the equipment (e.g., preheating time increases with age). Finally, based on the optimized strategy, the model is generated, and the process of obtaining the production task sequence diagram and current equipment status upon receiving task change data is repeated, entering the next loop. This forms a closed-loop management process from power-on / off strategy generation and execution result feedback to model optimization, enabling timely adaptation to changes in production tasks and dynamic adjustments to the production environment.

[0085] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the power-on and power-off method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0086] This application also provides a power-on / off device; please refer to... Figure 5 , Figure 5 This is a block diagram of the module structure of the power-on / off device according to an embodiment of this application; in this embodiment, the power-on / off device includes: The status module 501 is used to obtain the production task sequence diagram and the current equipment status of the production equipment when task change data is received. The prediction module 502 is used to predict the production task demand of the production equipment based on the production task time sequence diagram, the task change data and the current equipment status, and obtain the probability distribution of a preset time period. Optimization module 503 is used to optimize the power-on and power-off time points of the production equipment during the production task process through the probability distribution under preset optimization constraints to obtain a power-on and power-off strategy. The preset optimization constraints are constructed based on equipment energy consumption, production delay and / or start-up and shutdown losses. The control module 504 is used to control the power supply of the production equipment during the production task based on the power supply strategy.

[0087] This embodiment first acquires the production task sequence diagram and current equipment status of the production equipment upon receiving task change data. Then, based on this information, it performs probability prediction on the production task requirements of the production equipment to obtain a probability distribution for a preset time period. Under preset optimization constraints, it optimizes the power-on and power-off times of the production equipment during the production task process using the probability distribution to obtain a power-on / off strategy. Finally, it controls the equipment's power-on and power-off based on this strategy. Compared to existing equipment power-on / off control methods based on simple rules, this embodiment can formulate a power-on / off strategy by comprehensively considering task change data and the current equipment status, which can adapt to complex and ever-changing production environments, thereby improving production efficiency.

[0088] In one implementation, the prediction module 502 is further configured to perform structured encoding on the production task timeline diagram, the task change data, and the current equipment state to obtain corresponding timeline vectors, event vectors, and state vectors; concatenate the timeline vectors, event vectors, and state vectors to obtain a comprehensive vector; perform multi-step forward prediction on the production task demand of the production equipment based on the comprehensive vector to obtain the probability value corresponding to the production task demand in each time step; and determine the probability distribution of the production task demand within a preset time period based on the probability value of each time step.

[0089] In one implementation, the optimization module 503 is further configured to use the power-on and power-off times of the production equipment as decision variables; construct preset optimization constraints based on equipment energy consumption, production delays, and / or start-up and shutdown losses, and construct uncertainty constraints based on the probability distribution; under the preset optimization constraints and the uncertainty constraints, optimize the decision variables using a mixed integer programming optimization algorithm to obtain the power-on and power-off command set of the production equipment during the production task process, and use the power-on and power-off command set as the power-on and power-off strategy.

[0090] As one implementation, the power on / off device further includes a model module, used to extract sample equipment status from the historical production data of the production equipment, and to extract the sample production task time sequence diagram and corresponding sample task change data corresponding to the sample equipment status; to statistically analyze the sample probability distribution of the sample task change data in various production task requirements; and to train the model based on the sample equipment status, the sample production task time sequence diagram, the sample task change data, and the sample probability distribution to obtain a prediction model. The prediction module 502 is further configured to input the production task time sequence diagram, the task change data and the current equipment status into the prediction model to obtain the probability distribution of the production task demand over a preset time period.

[0091] As one implementation method, the model module is further used to annotate the historical production data to obtain the sample power-on / off strategy corresponding to the sample equipment status; construct preset optimization constraints with the equipment energy consumption, production delay and / or start-up / shutdown loss of the production equipment as optimization objectives, and train the prediction model according to the sample power-on / off strategy under the preset optimization constraints to obtain the strategy generation model. The optimization module 503 is further configured to optimize the power-on and power-off timing of the production equipment during the production task process using the strategy generation model, thereby obtaining a power-on and power-off strategy.

[0092] In one implementation, the model module is further configured to obtain the power-on / off execution results of the production equipment after the production task is completed, and compare the power-on / off execution results with the power-on / off strategy to obtain execution deviation data; optimize the strategy generation model based on the execution deviation data to obtain an optimized strategy generation model; and based on the optimized strategy generation model, return to execute the operation of obtaining the production task sequence diagram and current equipment status of the production equipment when task change data is received.

[0093] In one implementation, the status module 501 is further configured to acquire production planning and scheduling data of the production equipment and determine the equipment type of the production equipment; query a preset equipment knowledge base based on the production planning and scheduling data and the equipment type to obtain the equipment preparation time, production energy consumption curve and sleep time corresponding to the production planning and scheduling data, wherein the equipment knowledge base includes the mapping relationship between various types of production equipment and various types of production tasks; and construct a production task sequence diagram corresponding to the production equipment based on the equipment preparation time, the production energy consumption curve and the sleep time.

[0094] Other embodiments or specific implementations of the power-on / off device of this application can be found in the above-described method embodiments, and will not be repeated here.

[0095] The power on / off device provided in this application, employing the power on / off method described in the above embodiments, can solve the technical problem that traditional equipment power on / off control methods based on simple rules are difficult to adapt to complex and ever-changing production environments, leading to low production efficiency. Compared with the prior art, the beneficial effects of the power on / off device provided in this application are the same as those of the power on / off method provided in the above embodiments, and other technical features in the power on / off device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0096] This application provides a power-on / off device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the power-on / off methods in the above embodiments.

[0097] The following is for reference. Figure 6 , Figure 6 This is a schematic diagram of the hardware operating environment involved in the power-on / off device in the embodiments of this application, showing a structural schematic diagram suitable for implementing the power-on / off device in the embodiments of this application. The power-on / off device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (PADs), portable media players (PMPs), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6 The power on / off device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0098] like Figure 6As shown, the power-on / off device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in the read-only memory 1002 or a program loaded from the storage device 1003 into the random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the power-on / off device. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the power-on / off device to communicate wirelessly or wiredly with other devices to exchange data. Although power-on / off devices with various systems are shown in the figures, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0099] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0100] The power on / off device provided in this application, employing the power on / off method described in the above embodiments, can solve the technical problem that traditional power on / off control methods based on simple rules are difficult to adapt to complex and ever-changing production environments, leading to low production efficiency. Compared with the prior art, the beneficial effects of the power on / off device provided in this application are the same as those of the power on / off method provided in the above embodiments, and other technical features of this power on / off device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0101] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0102] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0103] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the power-on / off method in the above embodiments.

[0104] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, radio frequency (RF), etc., or any suitable combination thereof.

[0105] The aforementioned computer-readable storage medium may be included in the power-on / off device; or it may exist independently and not assembled into the power-on / off device.

[0106] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the power-on / off device, the power-on / off device: upon receiving task change data, acquires a production task sequence diagram and the current equipment status of the production equipment; performs probabilistic prediction of the production task demand of the production equipment based on the production task sequence diagram, the task change data, and the current equipment status, obtaining a probability distribution for a preset time period; under preset optimization constraints, optimizes the power-on / off time points of the production equipment during the production task process using the probability distribution, obtaining a power-on / off strategy, wherein the preset optimization constraints are constructed based on equipment energy consumption, production delays, and / or start-up / shutdown losses; and controls the power-on / off of the production equipment during the production task process based on the power-on / off strategy.

[0107] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0108] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0109] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0110] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described power-on / off method. This solves the technical problem that traditional equipment power-on / off control methods based on simple rules are difficult to adapt to complex and ever-changing production environments, leading to low production efficiency. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the power-on / off method provided in the above embodiments, and will not be repeated here.

[0111] The above description is only a part of the embodiments of this application and does not limit the scope of protection of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the scope of protection of this application.

Claims

1. A method for switching on and off power, characterized in that, The method includes: Upon receiving task change data, obtain the production task sequence diagram and current equipment status of the production equipment; Based on the production task timeline, the task change data, and the current equipment status, the production task demand of the production equipment is probabilistically predicted to obtain the probability distribution for a preset time period. Under preset optimization constraints, the power-on and power-off time points of the production equipment during the production task are optimized through the probability distribution to obtain the power-on and power-off strategy. The preset optimization constraints are constructed based on equipment energy consumption, production delay and / or start-up and shutdown losses. Based on the aforementioned power-on / off strategy, the power supply to the production equipment is controlled during the production process.

2. The method as described in claim 1, characterized in that, The step of probabilistically predicting the production task demand of the production equipment based on the production task timeline, the task change data, and the current equipment status to obtain the probability distribution over a preset time period includes: The production task timing diagram, the task change data, and the current equipment status are respectively structured and encoded to obtain corresponding timing vectors, event vectors, and status vectors; The timing vector, the event vector, and the state vector are concatenated to obtain a composite vector. Based on the comprehensive vector, the production task demand of the production equipment is predicted in multiple steps to obtain the probability value of the production task demand in each time step. Based on the probability value at each time step, the probability distribution of the production task demand within a preset time period is determined.

3. The method as described in claim 1, characterized in that, The step of optimizing the power-on and power-off timing of the production equipment during the production task process using the probability distribution under preset optimization constraints to obtain a power-on / power-off strategy includes: The power-on and power-off times of the production equipment are used as decision variables; Pre-defined optimization constraints are constructed based on equipment energy consumption, production delays, and / or start-up and shutdown losses, and uncertainty constraints are constructed based on the probability distribution. Under the preset optimization constraints and the uncertainty constraints, the decision variables are optimized by a mixed integer programming optimization algorithm to obtain the power-on and power-off command set of the production equipment during the production task, and the power-on and power-off command set is used as the power-on and power-off strategy.

4. The method as described in claim 1, characterized in that, Before the step of obtaining the production task sequence diagram and current equipment status of the production equipment upon receiving task change data, the method further includes: Extract sample equipment status from the historical production data of the production equipment, and extract the sample production task time sequence diagram and corresponding sample task change data corresponding to the sample equipment status; Statistically analyze the probability distribution of the sample task change data across various production task requirements. A prediction model is obtained by training the model based on the sample equipment status, the sample production task time sequence diagram, the sample task change data, and the sample probability distribution. The step of probabilistically predicting the production task demand of the production equipment based on the production task timeline, the task change data, and the current equipment status to obtain the probability distribution over a preset time period includes: The production task timeline, the task change data, and the current equipment status are input into the prediction model to obtain the probability distribution of the production task demand over a preset time period.

5. The method as described in claim 4, characterized in that, After the step of training the model based on the sample equipment status, the sample production task time sequence diagram, the sample task change data, and the sample probability distribution to obtain the prediction model, the method further includes: The historical production data is labeled to obtain the sample power-on / off strategy corresponding to the sample equipment status; A preset optimization constraint is constructed with the equipment energy consumption, production delay and / or start-up and shutdown loss of the production equipment as the optimization objective. Under the preset optimization constraint, the prediction model is trained according to the sample power on and off strategy to obtain the strategy generation model. The step of optimizing the power-on and power-off timing of the production equipment during the production task to obtain the power-on and power-off strategy includes: The power on / off timing of the production equipment during the production task is optimized using the strategy generation model to obtain the power on / off strategy.

6. The method as described in claim 5, characterized in that, After the step of controlling the power supply to the production equipment during the production task based on the power supply strategy, the method further includes: The power-on / off execution results of the production equipment after the production task is completed are obtained, and the power-on / off execution results are compared with the power-on / off strategy to obtain execution deviation data; The strategy generation model is optimized based on the execution deviation data to obtain an optimized strategy generation model; Based on the optimized strategy generation model, the process returns to the step of obtaining the production task sequence diagram and current equipment status of the production equipment upon receiving task change data.

7. The method according to any one of claims 1 to 6, characterized in that, The step of obtaining the production task sequence diagram of the production equipment includes: Obtain production planning and scheduling data for the production equipment and determine the equipment type of the production equipment; Based on the production plan scheduling data and the equipment type, the system queries a preset equipment knowledge base to obtain the equipment preparation time, production energy consumption curve, and sleep time corresponding to the production plan scheduling data. The equipment knowledge base includes the mapping relationship between various types of production equipment and various types of production tasks. Based on the equipment preparation time, the production energy consumption curve, and the sleep time, a production task sequence diagram corresponding to the production equipment is constructed.

8. A power-on / off device, characterized in that, The device includes: The status module is used to obtain the production task sequence diagram and current equipment status of the production equipment when task change data is received. The prediction module is used to perform probability prediction of the production task demand of the production equipment based on the production task time sequence diagram, the task change data and the current equipment status, and obtain the probability distribution of a preset time period. The optimization module is used to optimize the power-on and power-off time points of the production equipment during the production task process through the probability distribution under preset optimization constraints to obtain a power-on and power-off strategy. The preset optimization constraints are constructed based on equipment energy consumption, production delay and / or start-up and shutdown losses. The control module is used to control the power supply to the production equipment during the production task based on the power supply strategy.

9. A power switching device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the power-on / off method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the power-on / off method as described in any one of claims 1 to 7.

Images