Equipment operation control method and device, equipment and storage medium

Abstract

The invention discloses an equipment operation control method and apparatus, equipment and a storage medium. The method comprises the steps of obtaining demand order information obtained through prediction; on the basis of the demand order information, determining the demand goods passing quantity of each equipment group in the full-quantity equipment; determining suggested shutdown information of each equipment group in each unit time based on the required goods passing amount of each equipment group, the quota goods passing amount corresponding to each equipment group and a preset load threshold value; based on the suggested shutdown information and the equipment operation cost information under at least one dimension, determining a cost reduction value of each equipment group in each unit time; iteratively turning down the number of corresponding suggested shutdown devices in the suggested shutdown information until each device group meets a preset cost reduction condition, and obtaining a target device shutdown strategy; and controlling at least one device in the device group to execute a shutdown operation based on the target device shutdown strategy. According to the invention, the equipment shutdown control accuracy and the overall equipment shutdown effect are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of semiconductor manufacturing, and in particular to a device operation control method and device, equipment and storage medium. BACKGROUND

[0002] With the instability of the semiconductor market, the factory load is reduced and the volatility is increased, and the uncertainty of the device operation cost is also increased. The device operation cost is one of the costs with a large proportion in the factory production cost, and therefore, controlling the device operation cost is crucial for production.

[0003] In the related art, the device shutdown strategy is set by the month with the largest device load. However, with the increase in the number of products, types of products and number of devices in the factory, not only does it bring certain operation difficulty to the setting of the device shutdown strategy, but also the device shutdown strategy set in this case is often not optimal, resulting in the need for further improvement in the accuracy and effect of device operation control based on the device shutdown strategy. SUMMARY

[0004] To solve at least one of the technical problems in the related art, the present application aims to provide a device operation control method, device, equipment and storage medium.

[0005] To solve the above technical problems, on the one hand, the present application provides a device operation control method, comprising:

[0006] obtaining predicted demand order information;

[0007] determining the demand overage of each device group in the total devices based on the demand order information; the functions of each device included in the same device group are the same;

[0008] determining the recommended shutdown information of each device group in each unit time based on the demand overage of each device group, the quota overage corresponding to each device group and a preset load threshold;

[0009] obtaining device operation cost information in at least one dimension, and determining the cost reduction value of each device group in each unit time based on the recommended shutdown information and the device operation cost information;

[0010] iteratively reducing the number of recommended shutdown devices corresponding to the recommended shutdown information until the cost reduction values corresponding to each device group meet a preset cost reduction condition, to obtain a target device shutdown strategy for the total devices;

[0011] controlling at least one device in at least part of the device groups to perform a shutdown operation based on the target device shutdown strategy.

[0012] In some embodiments, the obtaining the predicted demand order information comprises:

[0013] obtaining historical production data of all the devices;

[0014] calling a trained neural network model to predict the historical production data to obtain demand order information of the all the devices in a first time period in the future.

[0015] In some embodiments, the determining the demand overstock of each device group in the all the devices based on the demand order information comprises:

[0016] classifying each predicted product indicated by the demand order information to obtain a plurality of product class groups;

[0017] selecting a representative predicted product in each product class group as a target product, and merging demand order sub-information of other predicted products in each product class group into demand order sub-information of the target product in the same product class group to obtain aggregated demand order sub-information of each target product;

[0018] determining the demand overstock of each device group in the all the devices based on the aggregated demand order sub-information of each target product and the device group corresponding to each target product.

[0019] In some embodiments, the determining the demand overstock of each device group in the all the devices based on the aggregated demand order sub-information of each target product and the device group corresponding to each target product comprises:

[0020] obtaining device capacity information of the device group corresponding to each target product;

[0021] calculating a production cycle of each target product based on the device capacity information;

[0022] segmenting a product line corresponding to each target product based on the production cycle to obtain a product line segment corresponding to each target product;

[0023] determining an estimated production running time corresponding to each product line segment, and calculating a demand overstock of each estimated production running time of the device group included in each product line segment in a second time period in the future based on the aggregated demand order sub-information of each target product, wherein the second time period includes a number of unit times that is less than a number of unit times included in the first time period.

[0024] In some embodiments, the determining of the recommended shutdown information of each of the device groups in each unit time based on the required overage of each of the device groups, the corresponding quota overage of each of the device groups, and the preset load threshold comprises:

[0025] determining the corresponding quota overage of each of the device groups;

[0026] determining the load information of each of the device groups based on the required overage of each of the device groups and the corresponding quota overage of each of the device groups;

[0027] determining the recommended shutdown information of each of the device groups in each unit time based on the load information of each of the device groups and the preset load threshold.

[0028] In some embodiments, the determining of the corresponding quota overage of each of the device groups comprises:

[0029] obtaining the device performance parameters and the actual production time of each of the device groups;

[0030] determining the corresponding quota overage of each of the device groups based on the corresponding overage, the corresponding device performance parameters, and the actual production time of each of the device groups; the overage represents the maximum overage quantity of each of the device groups per hour.

[0031] In some embodiments, the determining of the load information of each of the device groups based on the required overage of each of the device groups and the corresponding quota overage of each of the device groups comprises:

[0032] calculating the ratio of the required overage of each of the device groups and the corresponding quota overage of each of the device groups to determine the required device quantity of each of the device groups in each unit time;

[0033] obtaining the maximum device usage quantity of each of the device groups in each unit time, and calculating the ratio of the required device quantity of each of the device groups in each unit time and the corresponding maximum device usage quantity to obtain the load information of each of the device groups in each unit time.

[0034] In some embodiments, the preset load threshold comprises a first load threshold and a second load threshold, and the determining of the recommended shutdown information of each of the device groups in each unit time based on the load information of each of the device groups and the preset load threshold comprises:

[0035] for each of the device groups, if the device group is a single-device device after the shutdown of at least one device, and if the corresponding load information of the device group is less than or equal to the size of the first load threshold, it is determined that the device group can shut down the at least one device;

[0036] For each of the device groups, if the device group is not a standalone device after shutting down at least one device, and if the load information corresponding to the device group is less than or equal to the second load threshold, then it is determined that the device group can shut down at least one device, and the second load threshold is greater than the first load threshold.

[0037] By summarizing the maximum number of recommended shutdowns and the total number of recommended shutdown times for each equipment group within each unit of time, we can obtain the recommended shutdown information for each equipment group within each unit of time.

[0038] In some embodiments, the device operating cost information under the at least one dimension includes one or more of the following:

[0039] First equipment operating cost information used to characterize equipment maintenance dimensions;

[0040] Secondary equipment operating cost information used to characterize the power consumption dimension of equipment;

[0041] Third equipment operating cost information used to characterize the equipment shutdown dimension;

[0042] The fourth piece of equipment operating cost information is used to characterize the equipment restart dimension.

[0043] In some embodiments, when the equipment operating cost information in at least one dimension includes first equipment operating cost information characterizing equipment maintenance, second equipment operating cost information characterizing equipment electricity consumption, third equipment operating cost information characterizing equipment shutdown, and fourth equipment operating cost information characterizing equipment restart, determining the cost reduction value of each equipment group per unit time based on the suggested shutdown information and the equipment operating cost information includes:

[0044] Based on the first equipment operating cost information and the maximum recommended number of shutdowns for each equipment group in each unit of time, a first cost reduction score is obtained.

[0045] Based on the second equipment operating cost information and the total number of recommended shutdown unit times for each equipment group, a second cost reduction score is obtained.

[0046] Based on the operating cost information of the third equipment and the maximum recommended shutdown number of each equipment group in each unit of time, the first cost increment score is obtained.

[0047] Based on the fourth equipment operating cost information and the maximum recommended shutdown number of each equipment group in each unit of time, a second cost increment score is obtained.

[0048] Based on the first cost reduction score, the second cost reduction score, the first cost increment score, and the second cost increment score, the cost reduction value of each equipment group in each unit of time is obtained.

[0049] In some embodiments, the iterative reduction of the number of recommended shutdown devices in the recommended shutdown information until the cost reduction value corresponding to each device group meets the preset cost reduction condition, thereby obtaining the target device shutdown strategy for all devices, includes:

[0050] For each equipment group of the full set of equipment, if the cost reduction value corresponding to the equipment group is less than the preset cost reduction threshold, the number of recommended shutdown equipment in the recommended shutdown information corresponding to the equipment group is iteratively reduced to obtain the updated recommended shutdown information.

[0051] Based on the updated recommended shutdown information, determine the update cost reduction value for this equipment group in each unit of time.

[0052] Until the cost reduction value of each equipment group is less than the preset cost reduction threshold, it is determined that the cost reduction value of each equipment group meets the preset cost reduction condition, and the target equipment shutdown strategy of all equipment is obtained.

[0053] On the other hand, this application also provides a device for controlling the operation of an equipment, comprising:

[0054] The first acquisition module is used to acquire the predicted demand order information;

[0055] The first determining module is used to determine the required shipment volume of each equipment group in the full quantity of equipment based on the demand order information; the functions of each equipment included in the same equipment group are the same;

[0056] The second determining module is used to determine the recommended shutdown information of each equipment group in each unit of time based on the demand shipment volume of each equipment group, the quota shipment volume corresponding to each equipment group and the preset load threshold.

[0057] The cost reduction determination module is used to acquire equipment operating cost information in at least one dimension, and based on the suggested shutdown information and the equipment operating cost information, determine the cost reduction value of each equipment group in each unit time.

[0058] The iteration module is used to iteratively reduce the number of recommended shutdown devices in the recommended shutdown information until the cost reduction value corresponding to each device group meets the preset cost reduction condition, thereby obtaining the target device shutdown strategy for all devices.

[0059] The operation control module is used to control at least one device in at least a portion of the device group to perform a shutdown operation based on the target device shutdown strategy.

[0060] In some embodiments, the first acquisition module includes:

[0061] The information acquisition module is used to acquire historical production data for all equipment.

[0062] The demand forecasting module is used to call a trained neural network model to predict the historical production data and obtain the demand order information of all equipment in the first time period in the future.

[0063] In some embodiments, the first determining module includes:

[0064] The classification submodule is used to classify the predicted products indicated by the demand order information to obtain multiple product category groups;

[0065] The demand merging submodule is used to filter representative forecast products in each product category group as target products, and merge the demand order sub-information of other forecast products in each product category group into the demand order sub-information of the target product in the same product category group to obtain the summary demand order sub-information of each target product.

[0066] The first determining submodule is used to determine the demand throughput of each equipment group in the total number of equipment based on the aggregated demand order sub-information of each target product and the equipment group corresponding to each target product.

[0067] In some embodiments, the first determining submodule includes:

[0068] The first acquisition unit is used to acquire equipment capacity information of the equipment group corresponding to each target product;

[0069] The cycle determination unit is used to calculate the production cycle of each target product based on the equipment capacity information.

[0070] The segmentation unit is used to segment the product line corresponding to each target product based on the production cycle to obtain the product line segment corresponding to each target product.

[0071] The first determining unit is used to determine the estimated production operation time corresponding to each product line segment, and based on the aggregated demand order sub-information of each target product, calculate the demand throughput of each estimated production operation time of the equipment group included in each product line segment in the future second time period, wherein the quantity per unit time included in the second time period is less than the quantity per unit time included in the first time period.

[0072] In some embodiments, the second determining module includes:

[0073] The second determining submodule is used to determine the excess shipment volume corresponding to each of the equipment groups;

[0074] The load determination submodule is used to determine the load information of each equipment group based on the required shipment volume of each equipment group and the corresponding allowable shipment volume of each equipment group;

[0075] The shutdown information determination submodule is used to determine the recommended shutdown information for each of the device groups in each unit of time based on the load information and preset load threshold of each device group.

[0076] In some embodiments, the second determining submodule includes:

[0077] The second acquisition unit is used to acquire the equipment performance parameters and actual production time of each of the equipment groups;

[0078] The second determining unit is used to determine the quota of each equipment group based on the corresponding cargo quantity, the corresponding equipment performance parameters and the actual generation time; the cargo quantity represents the maximum cargo quantity that the equipment group can process per hour.

[0079] In some embodiments, the load determination submodule includes:

[0080] The demand quantity determination unit is used to calculate the ratio of the demand throughput of each equipment group to the corresponding allowance throughput of each equipment group, and to determine the number of machines required by each equipment group in each unit time.

[0081] The load determination unit is used to obtain the maximum number of machines used by each equipment group in each unit time, and calculate the ratio of the number of machines required by each equipment group in each unit time to the corresponding maximum number of machines used, so as to obtain the load information of each equipment group in each unit time.

[0082] In some embodiments, the preset load threshold includes a first load threshold and a second load threshold, and the shutdown information determination submodule includes:

[0083] The first shutdown determination unit is used to determine, for each of the device groups, if the device group is a single device after shutting down at least one device, and if the load information corresponding to the device group is less than or equal to the first load threshold, that the device group can shut down at least one device.

[0084] The second shutdown determination unit is used for each of the device groups. If the device group is not a single device after shutting down at least one device, and if the load information corresponding to the device group is less than or equal to the second load threshold, then it is determined that the device group can shut down at least one device, and the second load threshold is greater than the first load threshold.

[0085] The summarization unit is used to summarize the maximum number of recommended shutdowns and the total number of recommended shutdown times for each equipment group in each unit of time, so as to obtain the recommended shutdown information for each equipment group in each unit of time.

[0086] In some embodiments, the device operating cost information under the at least one dimension includes one or more of the following:

[0087] First equipment operating cost information used to characterize equipment maintenance dimensions;

[0088] Secondary equipment operating cost information used to characterize the power consumption dimension of equipment;

[0089] Third equipment operating cost information used to characterize the equipment shutdown dimension;

[0090] The fourth piece of equipment operating cost information is used to characterize the equipment restart dimension.

[0091] In some embodiments, where the equipment operating cost information in at least one dimension includes first equipment operating cost information characterizing equipment maintenance, second equipment operating cost information characterizing equipment electricity consumption, third equipment operating cost information characterizing equipment shutdown, and fourth equipment operating cost information characterizing equipment restart, the reduction determination module is further configured to:

[0092] Based on the first equipment operating cost information and the maximum recommended number of shutdowns for each equipment group in each unit of time, a first cost reduction score is obtained.

[0093] Based on the second equipment operating cost information and the total number of recommended shutdown unit times for each equipment group, a second cost reduction score is obtained.

[0094] Based on the operating cost information of the third equipment and the maximum recommended shutdown number of each equipment group in each unit of time, the first cost increment score is obtained.

[0095] Based on the fourth equipment operating cost information and the maximum recommended shutdown number of each equipment group in each unit of time, a second cost increment score is obtained.

[0096] Based on the first cost reduction score, the second cost reduction score, the first cost increment score, and the second cost increment score, the cost reduction value of each equipment group in each unit of time is obtained.

[0097] In some embodiments, the iteration module includes:

[0098] The update submodule is used to iteratively reduce the number of recommended shutdown devices in the recommended shutdown information for each device group of the full set of devices if the cost reduction value corresponding to the device group is less than the preset cost reduction threshold, so as to obtain the updated recommended shutdown information.

[0099] The re-determined submodule is used to determine the update cost reduction value for the device group in each unit of time based on the updated recommended shutdown information;

[0100] The shutdown strategy determination submodule is used to determine that the cost reduction value corresponding to each equipment group meets the preset cost reduction condition until the update cost reduction value corresponding to each equipment group is less than the preset cost reduction threshold, and to obtain the target equipment shutdown strategy for all equipment.

[0101] On the other hand, this application also provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement any of the device operation control methods described above.

[0102] On the other hand, this application also provides a computer-readable storage medium storing at least one instruction or at least one program, wherein the at least one instruction or the at least one program is loaded and executed by a processor to implement any of the device operation control methods described above.

[0103] On the other hand, this application also provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform any of the device operation control methods described above.

[0104] The device operation control method, apparatus, equipment, and storage medium disclosed in this application have at least the following beneficial effects:

[0105] By acquiring predicted demand order information; determining the demand throughput of each equipment group in the total number of devices based on the demand order information; ensuring that devices within the same equipment group have identical functions; determining the recommended shutdown information for each equipment group within each unit of time based on the demand throughput, the corresponding allowance throughput, and preset load thresholds; acquiring equipment operating cost information in at least one dimension, and determining the cost reduction value for each equipment group within each unit of time based on the recommended shutdown information and equipment operating cost information; iteratively reducing the number of recommended shutdown devices in the recommended shutdown information until the cost reduction value for each equipment group meets the preset cost reduction conditions, thus obtaining the target equipment shutdown strategy for the entire number of devices; and controlling at least one device in at least some equipment groups to perform shutdown operations based on the target equipment shutdown strategy. This approach constructs a better equipment shutdown strategy through dynamic iterative logic, proposing a more refined logical framework and operational process for equipment shutdown management. Consequently, the accuracy of equipment shutdown control based on this strategy is higher, and the management cost after equipment shutdown is greatly improved, effectively enhancing the overall equipment shutdown effect. Attached Figure Description

[0106] To more clearly illustrate the technical solutions and advantages 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, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0107] Figure 1 This is a flowchart of a device operation control method provided according to some embodiments of this application.

[0108] Figure 2 This is a flowchart of another device operation control method provided according to some embodiments of this application.

[0109] Figure 3 This is a schematic diagram illustrating a process for demand forecasting based on a neural network model, according to some embodiments of this application.

[0110] Figure 4 This is a schematic diagram of a process for determining the required throughput based on some embodiments of this application.

[0111] Figure 5 This is a schematic diagram illustrating a process for determining product categories involved in the demand throughput according to some embodiments of this application.

[0112] Figure 6 This is a schematic flowchart illustrating a process for determining recommended shutdown information according to some embodiments of this application.

[0113] Figure 7 This is a schematic diagram illustrating a process for determining recommended shutdown information according to some embodiments of this application.

[0114] Figure 8A This is a schematic diagram illustrating a process for determining the operating cost information of a third device according to some embodiments of this application.

[0115] Figure 8B This is a schematic diagram illustrating a process for determining the operating cost information of a fourth device according to some embodiments of this application.

[0116] Figure 9 This is a schematic diagram of the overall process of a device operation control method provided according to some embodiments of this application.

[0117] Figure 10 This is a schematic diagram of the structure of a device operation control device according to some embodiments of this application.

[0118] Figure 11 This is a schematic diagram of the structure of an electronic device provided according to some embodiments of this application. Detailed Implementation

[0119] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0120] The terms "some embodiments" or "embodiments" as used herein refer to specific features, structures, or characteristics that may be included in at least one implementation of this application. In the description of this application, unless otherwise expressly specified and limited, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. Furthermore, the terms "first," "second," etc., are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein.

[0121] To control equipment operating costs, related technologies often determine equipment shutdown strategies by selecting the month with the highest equipment load. However, as the number and types of products and equipment in a factory increase, not only does setting equipment shutdown strategies become more difficult, but the strategies set under these circumstances are often not optimal or even the best. Consequently, the accuracy and effectiveness of equipment operation control based on these shutdown strategies need further improvement.

[0122] In view of this, this application provides a method, apparatus, device, and storage medium for equipment operation control. The method involves: acquiring predicted demand order information; determining the demand throughput of each equipment group in the total number of equipment based on the demand order information; ensuring that the equipment in the same equipment group has the same function; determining the recommended shutdown information of each equipment group in each unit time based on the demand throughput of each equipment group, the corresponding allowable throughput of each equipment group, and a preset load threshold; acquiring equipment operating cost information in at least one dimension, and determining the cost reduction value of each equipment group in each unit time based on the recommended shutdown information and the equipment operating cost information; iteratively reducing the number of recommended shutdown equipment in the recommended shutdown information until the cost reduction value of each equipment group meets the preset cost reduction condition, thereby obtaining the target equipment shutdown strategy for the entire number of equipment; and controlling at least one equipment in at least some equipment groups to perform shutdown operations based on the target equipment shutdown strategy. By constructing a better equipment shutdown strategy through dynamic iterative logical thinking, a more refined logical framework and operation process for equipment shutdown management and control were proposed. Based on this equipment shutdown strategy, the accuracy of equipment shutdown control is higher, the management and control costs after equipment shutdown are greatly improved, and the overall equipment shutdown effect is effectively enhanced.

[0123] Figure 1 This is a flowchart illustrating a device operation control method according to some embodiments of this application. See also... Figure 1 As shown, the equipment operation control method includes the following steps:

[0124] In step S102, the predicted demand order information is obtained.

[0125] The demand order information represents the product order demand within a future first time period. This future first time period can include n future unit periods, where n can be a positive integer, and the unit period can be, for example, a week, month, quarter, or year. In this embodiment, taking a month as the unit period as an example, the future first time period can include the next 16 months, but is not limited to this. The product can be various intermediate or final device products involved in the semiconductor field.

[0126] In some embodiments, such as Figure 2 As shown, obtaining the predicted demand order information includes:

[0127] In step S202, historical production data for all equipment is obtained.

[0128] In step S204, a trained neural network model is invoked to predict historical production data and obtain the demand order information for all equipment in the first time period in the future.

[0129] In this context, "full-scale equipment" refers to the entire set of process equipment involved in product generation. For example, in the semiconductor field, full-scale equipment includes, but is not limited to, dry etching equipment, wet etching equipment, dicing equipment, polishing equipment, deposition equipment, and so on.

[0130] Historical production data is used to provide foundational data support for subsequent forecasting of demand and order information. For example, taking a month as the unit of time, historical production data may include, but is not limited to, one or more of the following: historical monthly sales data, historical monthly order data, historical monthly offline data, historical monthly output data, monthly capacity accuracy values, and capacity limits of various platforms.

[0131] Before predicting demand order information, a neural network model can be trained first. Then, based on the trained neural network model, predictions can be made using historical production data to obtain the demand order information for all equipment in the first future time period. This neural network model can be, for example, a BP artificial neural network, but is not limited to this.

[0132] In this embodiment, a BP artificial neural network is selected as the prediction model for demand orders. Appropriate model training input parameters are selected, and the production unit is monthly. The factory's historical data is divided into three parts: training set, validation set, and prediction set. The model is optimized and trained using the training set and validation set data. Then, the prediction set data is used to predict, for example, the order demand for the next 16 months in the optimized model.

[0133] Backpropagation (BP) artificial neural networks are a deep learning algorithm widely used in prediction. It is a multi-layer feedforward neural network that can be trained using the backpropagation algorithm. It mainly consists of three layers: an input layer, hidden layers, and an output layer (e.g., ...). Figure 3 (As shown). This algorithm performs well in nonlinear fitting and has good robustness against interference from unrelated variables. Furthermore, it only requires optimization and training of the input parameter data to establish an accurate prediction model. The specific process is as follows:

[0134] (1) Input Parameter Selection. For model training, appropriate parameters need to be selected as data inputs, mainly including monthly sales / order data, monthly offline / output data, monthly production capacity accuracy values, and capacity limits for each platform. The input data is divided into three parts according to the time series: training set, validation set, and prediction set. The input data is then cleaned to remove duplicates, invalid data, noisy data, and other outliers, resulting in cleaned data.

[0135] (2) Output parameter selection. This section mainly focuses on forecasting future order demand, so the output parameter is determined to be the order demand forecast for the next 16 months, which serves as the data basis for the capacity calculation module.

[0136] (3) Model training. The factory's historical data is divided into three parts: training data, validation data, and prediction data. The number of neurons L in the hidden layer of the BP artificial neural network algorithm is determined. The model is trained using the training set data. Then, the Levenberg-Marquardt optimization algorithm (i.e., the LM algorithm) is selected as the activation function using the validation set data, and the Mu parameter is used as the error function to continuously optimize the model. Finally, the model is trained iteratively until convergence, and the final trained model is obtained.

[0137] (4) Model usage. Input the prediction data into the trained model and run the model to obtain the order demand forecast for the next 16 months, which means obtaining the demand order information for all devices in the first time period in the future.

[0138] The above embodiments use a trained neural network model to predict demand order information in the first time period in the future, avoiding the errors of manual prediction, and improving the accuracy and efficiency of obtaining demand order information.

[0139] In step S104, based on the demand order information, the demand throughput of each equipment group in the total number of equipment is determined; the functions of each equipment in the same equipment group are the same.

[0140] In some embodiments, such as Figure 4 As shown, based on the demand order information, the required shipment volume for each equipment group in the total equipment inventory is determined as follows:

[0141] In step S402, the predicted products indicated by the demand order information are classified to obtain multiple product category groups.

[0142] Optionally, after forecasting the order demand for the next 16 months, the forecasted products can be classified based on, for example, the order demand information indicated by the Doc2Vec algorithm, to obtain multiple product category groups.

[0143] In practical applications, factory platforms are generally complex, and each platform contains a wide variety of products. To ensure computational accuracy while saving computing power and improving computational speed, products can be categorized, and representative products can be selected for capacity calculation. This part uses the Doc2vec algorithm to categorize product production lines (Flows). Doc2Vec is a neural network-based text representation learning algorithm that aims to represent text data using dense vectors. It is an unsupervised deep learning method. The algorithm takes the text data of each Flow as input and outputs a multi-dimensional vector representing the features of each text set, quantifying the features of each Flow. Then, it calculates the similarity between Flows based on the cosine similarity algorithm, and selects representative Flows from each platform based on the similarity threshold to complete the Flow categorization. Figure 5 As shown, the overall flow classification process can include the following steps:

[0144] Data cleaning: The order demand for the next 16 months is categorized by platform. Then, the product flow contained in each platform is cleaned, including removing special symbols, invalid data, and noisy data, to form standard data that can be used for model training.

[0145] Model training and output: Randomly select 10% of the cleaned data as the training set for model training. Continuously optimize the parameters to obtain the trained Doc2Vec model. Input all the cleaned data into the model and run the model to obtain the text-feature vector matrix.

[0146] Flow classification: Based on the obtained text-feature vector matrix, the similarity value between each flow is calculated using the cosine similarity algorithm. The calculation formula is as follows;

[0147]

[0148] Among them, S ij F represents the similarity value between the i-th Flow and the j-th Flow on the same platform. i Let F represent the i-th Flow. j This represents the j-th flow.

[0149] During the classification process, based on the quartile principle, flows with similarity values ​​between the upper quartile and 1 can be grouped into one category, and one flow can be selected as a representative flow in each category.

[0150] In step S404, representative predicted products in each product category group are selected as target products, and the demand order sub-information of other predicted products in each product category group is merged into the demand order sub-information of the target product in the same product category group to obtain the summary demand order sub-information of each target product.

[0151] Optionally, based on the product categories obtained from product classification, a representative predicted product is selected from each product category as the target product, and the demand order sub-information of other predicted products in each product category is merged into the demand order sub-information of the target product in the same product category to obtain the summary demand order sub-information of each target product. That is, the product order quantities of other predicted products in the same category are synchronously added to the representative target product, so as to perform subsequent capacity calculation based on the summary demand order sub-information of the target product.

[0152] In step S406, based on the summary demand order sub-information of each target product and the equipment group corresponding to each target product, the demand throughput of each equipment group in the total equipment is determined.

[0153] In some embodiments, such as Figure 6 As shown, based on the aggregated demand order sub-information for each target product and the corresponding equipment group for each target product, the demand throughput for each equipment group in the total equipment is determined as follows:

[0154] In step S602, the equipment capacity information of the equipment group corresponding to each target product is obtained.

[0155] In step S604, the production cycle of each target product is calculated based on the equipment capacity information.

[0156] In step S606, based on the production cycle, the product line corresponding to each target product is segmented to obtain the product line segment corresponding to each target product.

[0157] In step S608, the estimated production run time corresponding to each product line segment is determined, and based on the aggregated demand order sub-information of each target product, the demand throughput of each estimated production run time of the equipment group included in each product line segment in the future second time period is calculated. The quantity per unit time included in the second time period is less than the quantity per unit time included in the first time period.

[0158] Optionally, first, representative equipment groups corresponding to target products are identified from the full set of equipment. Then, based on the production cycle of each target product, the constructed Move discount strategy pool, and the aggregated demand order sub-information of that target product, the actual generated shipment volume (move volume) for each equipment group in the future second time period (e.g., monthly) is calculated, i.e., the demand shipment volume. The number of units in the second time period is less than the number of units in the first time period. For example, if the first time period is 16 months, the second time period can be 12 months.

[0159] In practical applications, determining demand overstock volume based on the constructed Move discount strategy pool can include the following process:

[0160] (1) Utilize the equipment capacity information (e.g., the number of days required to process each photomask layer) collected in real-time from online production for each target product, and then calculate the production cycle of representative target products based on this equipment capacity information. Optionally, the production cycle of a target product = product photo layer * dpl / 30 (converted to months). For example, if target product 1 includes 30 photo layers, and the equipment capacity information of the equipment group corresponding to target product 1 is 3 dpl (i.e., each photo layer requires three days to process), then the production cycle of target product 1 is 20 * 3 / 30 = 2 months.

[0161] (2) Divide the product line Flow of the target product into segments according to the production cycle and classify them into the corresponding months to be produced. Optionally, based on the production cycle, segment the product line corresponding to each target product in sequence to obtain the product line segment corresponding to each target product. For example, the production cycle of target product 1 is two months. Based on this, its overall product line Flow is divided into two segments in sequence, namely Flow1 and Flow2.

[0162] (3) Based on the product line Flow portion allocated to each corresponding month and the aggregated order demand, calculate the move quantity that each equipment group should produce each month in the next second time period (e.g., 12 months), i.e., the demand flow quantity. Optionally, first determine the estimated production run time corresponding to each product line segment, such as when each product line segment should start production, and then calculate the demand flow quantity of each equipment group included in each product line segment for each estimated production run time in the next second time period based on the aggregated demand order sub-information of each target product. This is used as the demand flow quantity of each equipment group in the total equipment. For example, if target product 1 has a demand in September, it is estimated that Flow1 should be produced in July and Flow2 should be produced in August. In July, Flow1 includes target product 1, with a demand of 100 in September; and Flow2 includes target product 2, with a demand of 200 in October. Both Flow1 and Flow2 contain equipment group 1, and the frequency of target product 1 in equipment group 1 is 2, while the frequency of target product 2 in equipment group 1 is 3. Therefore, the move quantity that equipment group 1 should produce in July is 100*2+300*3=800pcs.

[0163] The above embodiments determine the production cycle of the target product based on the equipment capacity information of the equipment group corresponding to the target product, and segment the product line according to the production cycle. By combining the aggregated demand order sub-information, the demand throughput of each equipment group included in each segmented product line is calculated for the estimated production operation time in the second time period. This is used as the demand throughput of each equipment group in the total equipment, realizing fine-grained calculation of the demand throughput of each equipment group, which helps to improve the accuracy and reliability of the equipment operation control method.

[0164] The above embodiments classify the predicted products indicated by the demand order information to filter representative target products, and merge the demand order sub-information of other products in the same product category group into the target product, thereby reducing the amount of computational data in the equipment operation control process, saving computing power and improving computational efficiency.

[0165] In step S106, based on the required shipment volume of each equipment group, the corresponding allowable shipment volume of each equipment group, and the preset load threshold, the recommended shutdown information of each equipment group in each unit of time is determined.

[0166] In some embodiments, the recommended shutdown information for each equipment group in each unit of time is determined based on the demand shipment volume of each equipment group, the corresponding allowable shipment volume of each equipment group, and a preset load threshold.

[0167] In step S1062, the excess shipment amount corresponding to each equipment group is determined.

[0168] In some embodiments, determining the allowable shipment quantity for each equipment group includes: obtaining the equipment performance parameters and actual production time of each equipment group; determining the allowable shipment quantity for each equipment group based on the shipment quantity, the corresponding equipment performance parameters, and the actual production time; the shipment quantity represents the maximum shipment quantity of the equipment group per hour.

[0169] The equipment performance parameters characterize the current real-time equipment performance of a equipment group. Different equipment groups have different equipment performance parameters. These parameters are related to throughput and are not specifically defined here.

[0170] The above embodiments determine the rated throughput of the equipment group in real time by using the equipment performance parameters and actual production conditions. This ensures the accuracy of the rated throughput of the equipment group, improves the accuracy of subsequent calculations of the load information of the equipment group, and further enhances the accuracy and reliability of the equipment operation control method.

[0171] In step S1064, the load information of each equipment group is determined based on the required shipment volume of each equipment group and the corresponding allowable shipment volume of each equipment group.

[0172] In some embodiments, determining the load information of each equipment group based on the demand shipment volume of each equipment group and the corresponding allowance shipment volume of each equipment group includes:

[0173] Calculate the ratio of the required shipment volume of each equipment group to the corresponding allowable shipment volume of each equipment group, and determine the number of machines required by each equipment group in each unit of time;

[0174] Obtain the maximum number of machines used by each equipment group in each unit of time, and calculate the ratio of the number of machines required by each equipment group in each unit of time to the corresponding maximum number of machines used, to obtain the load information of each equipment group in each unit of time.

[0175] Optionally, after determining the demand for each equipment group, the load of each equipment group in the next 12 months can be calculated by combining the current available machine resources, the hourly capacity of each equipment group, and the performance parameters of the machine equipment.

[0176] Specifically, the excess shipment volume corresponding to each equipment group can be expressed as:

[0177] PWPH i ·OEE i ·24·Md j ;

[0178] The required number of machines for each equipment group per unit time: EqAm ij , can be represented as:

[0179] EqAmij =Move ij (PWPH i ·OEE i ·24·Md j );

[0180] Then, the load information of each equipment group in each unit of time. ij It can be represented as:

[0181]

[0182] Among them, Move ij EqAm represents the demand turnover of the i-th equipment group in the j-th month; ij This represents the number of machines required by the i-th equipment group in the j-th month; AEqAm ij This represents the number of machines that the i-th equipment group can support in the j-th month; Load ij This represents the load of the i-th device group in the j-th month; PWPH i The actual number of moves that the i-th device group can operate per hour; OEE i The equipment performance parameters of the i-th equipment group; Md j The actual number of production days in month j.

[0183] In step S606, based on the load information of each device group and the preset load threshold, the recommended shutdown information for each device group in each unit of time is determined.

[0184] The number of preset load thresholds can be one or more.

[0185] Optionally, if the preset load threshold is one, the load information of each device group after shutting down the target number of devices can be compared with the preset load threshold. If the load information is less than the preset load threshold, the device group is determined to meet the condition of shutting down the target number of devices. That is, the recommended shutdown information for the device group is determined based on the target number. The target number can be the maximum number of devices that can be shut down in the device group or any suitable number less than the maximum number of devices that can be shut down.

[0186] In some embodiments, the preset load threshold includes a first load threshold and a second load threshold. Based on the load information of each device group and the preset load threshold, the recommended shutdown information for each device group in each unit of time includes:

[0187] For each device group, if the device group is a single device after shutting down at least one device, and if the load information corresponding to the device group is less than or equal to the first load threshold, then it is determined that the device group can shut down at least one device.

[0188] For each device group, if the device group is not a standalone device after shutting down at least one device, and if the load information corresponding to the device group is less than or equal to the second load threshold, then it is determined that the device group can shut down at least one device, and the second load threshold is greater than the first load threshold.

[0189] By summarizing the maximum number of recommended shutdowns and the total number of recommended shutdown times for each equipment group within each unit of time, we can obtain the recommended shutdown information for each equipment group within each unit of time.

[0190] The first load threshold is less than the second load threshold. For example, the first load threshold can be 75% and the second load threshold can be 85%. Of course, the first and second load thresholds are not limited to these and can be set to other suitable values.

[0191] Optionally, based on the determined load of each equipment group in, for example, the next 12 months, a capacity shutdown strategy (such as...) can be developed. Figure 7 (As shown). If the equipment group becomes a single machine after shutdown and the load is less than 75% after shutdown, shutdown is recommended; otherwise, shutdown is not recommended. If the equipment group is not a single machine after shutdown and the load is less than 85% after shutdown, shutdown is recommended; otherwise, shutdown is not recommended. Here, the recommended shutdown strategy is determined based on the equipment group load threshold, that is, the number of shutdowns for each equipment group each month is determined from the perspective of production capacity. Then, based on the determined number of shutdowns, the maximum recommended shutdown number for each equipment group in each unit of time can be determined, as well as the total number of recommended shutdowns per unit of time for each equipment group (e.g., the total number of months of recommended shutdowns), thus obtaining the recommended shutdown information for each equipment group in each unit of time.

[0192] The above embodiments determine the recommended shutdown information for the equipment group by setting a dual load threshold of a first load threshold and a second load threshold. This ensures that the determined recommended shutdown information takes into account both the equipment shutdown suggestion and the equipment performance after shutdown, thereby improving the reliability and long-term effectiveness of equipment shutdown control.

[0193] In step S108, equipment operating cost information in at least one dimension is obtained, and based on the recommended shutdown information and equipment operating cost information, the cost reduction value of each equipment group in each unit of time is determined.

[0194] In some embodiments, the device operating cost information in at least one dimension includes one or more of the following:

[0195] First equipment operating cost information used to characterize equipment maintenance dimensions;

[0196] Secondary equipment operating cost information used to characterize the power consumption dimension of equipment;

[0197] Third equipment operating cost information used to characterize the equipment shutdown dimension;

[0198] The fourth piece of equipment operating cost information is used to characterize the equipment restart dimension.

[0199] The four types of operating cost information mentioned above correspond to different cost strategies, and the corresponding operating cost information is calculated based on different cost strategies. The following sections will elaborate on the four types of operating cost information.

[0200] For the first piece of equipment operating cost information, a maintenance cost strategy is involved. This strategy is mainly used to predict the maintenance frequency of the equipment over the next 12 months, and then calculate the maintenance cost savings that can be achieved by shutting down the equipment. This part mainly uses the BP artificial neural network algorithm, selecting historical equipment maintenance data, historical monthly run data for each equipment group, historical monthly offline data, historical monthly output data, run and move data for each equipment group over the next 12 months obtained from the capacity prediction module, and predicted monthly output data. The model is trained using historical data and then optimized. The predicted data is then input into the optimized model, and the output parameter is the maintenance frequency required for each equipment group over the next 12 months. Based on this, a maintenance cost calculation strategy is constructed, and its calculation formula is as follows:

[0201]

[0202] Among them, PM i This represents the average maintenance cost per device in the i-th equipment group, i.e., the operating cost information of the first device; p i PA represents the predicted frequency of maintenance required for the i-th equipment group. j w represents the cost of the j-th component used in maintenance and repair. j AEqAm represents the quantity of the j-th component used in maintenance and repair. i This represents the number of devices in the i-th device group.

[0203] The second set of equipment operating cost information involves an electricity cost strategy. Electricity costs constitute a significant portion of equipment operating costs. When the factory is operating at low capacity, shutting down some idle machines can greatly reduce electricity costs. This strategy is primarily used to calculate the monthly electricity costs for idle machines, as shown in the following formula:

[0204]

[0205] Among them, D i This represents the electricity cost of a single device in the i-th device group when it is idle and waiting for goods, i.e., the operating cost information of the second device; DD i DP i DL i These represent the electricity costs during peak, off-peak, and low-peak hours, respectively, where k represents the cost. Dk P k L These represent the electricity consumption of a single device during the three time periods mentioned above.

[0206] In addition to the two cost information items mentioned above that are positively correlated with equipment shutdown, there are also the following two cost information items that are negatively correlated with equipment shutdown. This is because the equipment used in the semiconductor industry generally has high technical precision and complexity, and both shutdown and restart will incur certain costs.

[0207] The information regarding the operating costs of the third-party equipment involves equipment shutdown cost strategies. When shutting down some equipment, it is necessary to assess whether each component can be reused upon restarting. If it cannot be reused, that component will be scrapped, resulting in losses. Figure 8A As shown.

[0208] Regarding the fourth piece of equipment operating cost information, the restart cost strategy is involved. When deciding whether to shut down equipment, the restart cost must also be considered. Restarting generally requires re-maintenance and replacement of parts, and some machines need to be re-inspected. Furthermore, some parts involve issues such as letters of credit, and may be consumable products that are extremely difficult to purchase. The resulting costs can be considered substantial. Figure 8B As shown.

[0209] exist Figure 8A and Figure 8B In the middle, CC i NT represents the shutdown cost of a single device in the i-th device group. j T represents the unused lifespan of the j-th component. j PA represents the service life of the j-th component. j Let OC represent the cost of the j-th component. i WC represents the reactivation cost of a single device in the i-th device group. i TC represents the cost of repairing and maintaining the i-th device. i w represents the cost of re-inspecting the i-th device. j This indicates the quantity of the j-th component used.

[0210] The above embodiments, by introducing multi-dimensional equipment operating cost information and comprehensively considering the relationship between equipment shutdown and equipment operating cost information, can comprehensively optimize equipment shutdown strategies and improve the control effect and accuracy and reliability of target equipment shutdown strategies.

[0211] In this embodiment, the equipment operating cost information in at least one dimension includes cost operating cost information in four dimensions: a first dimension representing equipment maintenance, a second dimension representing equipment electricity consumption, a third dimension representing equipment shutdown, and a fourth dimension representing equipment restart. At this time, based on the recommended shutdown information and the equipment operating cost information, the cost reduction value of each equipment group per unit time is determined as follows:

[0212] Based on the first equipment operating cost information and the maximum recommended number of shutdowns for each equipment group in each unit of time, the first cost reduction score is obtained.

[0213] Based on the second equipment operating cost information and the total number of recommended shutdown unit times for each equipment group, the second cost reduction score is obtained.

[0214] Based on the third equipment operating cost information and the maximum recommended number of shutdowns for each equipment group in each unit of time, the first cost increment score is obtained.

[0215] Based on the fourth equipment operating cost information and the maximum recommended number of shutdowns for each equipment group in each unit of time, the second cost increment score is obtained.

[0216] Based on the first cost reduction score, the second cost reduction score, the first cost increment score, and the second cost increment score, the cost reduction value of each equipment group in each unit of time is obtained.

[0217] Optionally, after determining the first cost reduction score, the second cost reduction score, the first cost increment score, and the second cost increment score, they can be combined to calculate the total cost savings after shutting down the recommended number of machines, thus obtaining the cost reduction value of each equipment group per unit time.

[0218] As an example only, based on the above cost strategy, the cost reduction value CE of the i-th equipment group is constructed according to the recommended number of shutdowns based on capacity. i Its expression can be represented as:

[0219]

[0220] Among them, PM i ·Q m This represents the score for the first cost reduction measure. CC represents the second cost reduction score. i ·Q m OC represents the first cost increment score. i ·Q m This represents the second cost increment score. Q mD represents the maximum number of recommended shutdowns for each month of the i-th device group over the next 12 months. ij M represents the electricity cost of the j-th device in the i-th device group. j This represents the number of months in which devices dij in the i-th device group can be shut down.

[0221] The above embodiments introduce multi-dimensional equipment operating cost information to jointly determine the cost reduction value of each equipment group in each unit of time, thereby improving the comprehensiveness and reliability of the cost reduction value and facilitating further optimization of equipment shutdown strategies based on the cost reduction value.

[0222] In step S110, the number of recommended shutdown devices in the recommended shutdown information is iteratively reduced until the cost reduction value of each device group meets the preset cost reduction condition, thus obtaining the target device shutdown strategy for all devices.

[0223] In some embodiments, the number of recommended shutdown devices in the recommended shutdown information is iteratively reduced until the cost reduction value corresponding to each device group meets the preset cost reduction condition, resulting in a target device shutdown strategy for all devices, including:

[0224] For each equipment group of all equipment, if the cost reduction value corresponding to the equipment group is less than the preset cost reduction threshold, the number of recommended shutdown equipment in the recommended shutdown information corresponding to the equipment group is iteratively reduced to obtain the updated recommended shutdown information.

[0225] Based on the updated recommended shutdown information, determine the update cost reduction value for this equipment group in each unit of time.

[0226] Until the cost reduction value of each equipment group is less than the preset cost reduction threshold, it is determined that the cost reduction value of each equipment group meets the preset cost reduction condition, and the target equipment shutdown strategy for all equipment is obtained.

[0227] Optionally, for each equipment group of all equipment, if there exists a cost reduction value (CE) corresponding to a certain equipment group... i If the cost reduction is less than the preset cost reduction threshold α, the number of recommended shutdown devices in the recommended shutdown information for that equipment group is reduced. That is, based on the recommended shutdown number for production capacity, one device is removed from the equipment group each month. Based on the updated recommended shutdown information, the updated cost reduction value CE for that equipment group in each unit of time is determined. i If the updated cost reduction value CE is... i If the cost reduction threshold α is still less than the preset cost reduction threshold, the recommended number of shutdown devices will be further reduced. That is, based on the recommended shutdown number for production capacity, two more devices will be removed from this equipment group each month. Then, based on the updated recommended shutdown information, the updated cost reduction value CE for this equipment group in each unit of time will be determined.i Until the updated cost reduction value is greater than or equal to the preset cost reduction threshold α (CE) i Up to ≥α), once it is determined that the update cost reduction value corresponding to each equipment group is less than the preset cost reduction threshold, and the cost reduction value corresponding to each equipment group meets the preset cost reduction condition, the target equipment shutdown strategy for all equipment is obtained, which is determined as the optimal recommended shutdown strategy.

[0228] The above embodiments iteratively reduce the number of recommended shutdown devices in the recommended shutdown information until the update cost reduction value for each device group is less than a preset cost reduction threshold, thus obtaining the target device shutdown strategy for all devices. By continuously optimizing and adjusting the number of devices to be shut down based on dynamic iterative thinking, the determined target device shutdown strategy becomes more effective, improving the accuracy of device shutdown control and the overall device shutdown effect based on this strategy.

[0229] In step S112, based on the target device shutdown strategy, at least one device in at least a portion of the device groups is controlled to perform a shutdown operation.

[0230] Optionally, after determining the target device shutdown strategy, based on the target recommended shutdown quantity of at least a portion of the device groups corresponding to the target device shutdown strategy within a corresponding time period in the future, control at least one device in the device group to perform a shutdown operation.

[0231] To better understand this application, the following will be combined with... Figure 9 The overall technical framework of this application is described. The equipment operation control method of this application may include the following:

[0232] (1) Information Acquisition Section: Historical monthly sales and orders, output, basic information of machines and products, etc., to provide data support for subsequent modules;

[0233] (2) Demand forecasting section: Taking the month as the production unit, this module divides historical data into three parts: training data, validation data and forecast data. First, the training data is used to select the model input parameters and train the BP artificial neural network. Then, the validation data is selected to continuously optimize the model. Finally, based on the forecast data, the order demand for the next 16 months is predicted in the trained model.

[0234] (3) Capacity calculation part: Based on the order demand for the next 16 months obtained by the demand forecasting module, firstly, the flow classification of all forecasted products is completed based on Doc2Vec, and considering the production cycle and batch size of each product, the Move conversion rule is constructed to calculate the actual move quantity that each equipment group should produce in each month, and then the load of each equipment group in the next 12 months is calculated based on the actual resources that the current factory can support.

[0235] (4) Equipment shutdown section: Based on the load of each equipment group for the next 12 months obtained from the capacity calculation module, a capacity / cost rule pool is constructed, and an equipment shutdown mechanism is formulated based on dynamic iterative thinking.

[0236] (5) Equipment shutdown strategy for the next 12 months: Based on the shutdown mechanism established by the equipment shutdown module, formulate an equipment shutdown strategy for the next 12 months.

[0237] The overall framework is based on the monthly load of each equipment group, combined with factors such as capacity and cost, to build a capacity and cost screening mechanism, and to formulate shutdown strategies for each equipment group for the next 12 months based on dynamic iteration thinking.

[0238] The above embodiments construct a better equipment shutdown strategy through dynamic iterative logical thinking, and propose a more refined logical framework and operation process for equipment shutdown management and control. As a result, the accuracy of equipment shutdown control based on this equipment shutdown strategy is higher, and the management and control costs after equipment shutdown are greatly improved, and the overall equipment shutdown effect is effectively enhanced.

[0239] This application also provides a device for controlling the operation of an equipment. Figure 10 This is a schematic diagram of the structure of a device operation control apparatus according to some embodiments of this application. See also: Figure 10 As shown, the equipment operation control device includes:

[0240] The first acquisition module 1010 is used to acquire the predicted demand order information;

[0241] The first determining module 1020 is used to determine the required shipment volume of each equipment group in the full quantity of equipment based on the demand order information; the functions of each equipment in the same equipment group are the same.

[0242] The second determining module 1030 is used to determine the recommended shutdown information of each equipment group in each unit of time based on the demand throughput of each equipment group, the corresponding allowance throughput of each equipment group and the preset load threshold.

[0243] The cost reduction determination module 1040 is used to obtain equipment operating cost information in at least one dimension, and determine the cost reduction value of each equipment group in each unit of time based on the recommended shutdown information and equipment operating cost information.

[0244] The iteration module 1050 is used to iteratively reduce the number of recommended shutdown devices in the recommended shutdown information until the cost reduction value of each device group meets the preset cost reduction condition, and obtain the target device shutdown strategy for all devices.

[0245] The operation control module 1060 is used to control at least one device in at least a group of devices to perform a shutdown operation based on the target device shutdown strategy.

[0246] In some embodiments, the first acquisition module includes:

[0247] The information acquisition module is used to acquire historical production data for all equipment.

[0248] The demand forecasting module is used to call a trained neural network model to predict historical production data and obtain the demand order information for all equipment in the first time period in the future.

[0249] In some embodiments, the first determining module includes:

[0250] The classification submodule is used to classify the predicted products indicated by the demand order information to obtain multiple product category groups;

[0251] The demand merging submodule is used to filter representative forecast products in each product category group as target products, and merge the demand order sub-information of other forecast products in each product category group into the demand order sub-information of the target product in the same product category group to obtain the summary demand order sub-information of each target product.

[0252] The first determination submodule is used to determine the demand volume of each equipment group in the total number of equipment based on the aggregated demand order sub-information of each target product and the equipment group corresponding to each target product.

[0253] In some embodiments, the first determining submodule includes:

[0254] The first acquisition unit is used to acquire the equipment capacity information of the equipment group corresponding to each target product;

[0255] The cycle determination unit is used to calculate the production cycle of each target product based on equipment capacity information;

[0256] The segmentation unit is used to segment the product line corresponding to each target product based on the production cycle, so as to obtain the product line segment corresponding to each target product.

[0257] The first determining unit is used to determine the estimated production run time corresponding to each product line segment, and based on the aggregated demand order sub-information of each target product, calculate the demand throughput of each estimated production run time of the equipment group included in each product line segment in the future second time period. The quantity per unit time included in the second time period is less than the quantity per unit time included in the first time period.

[0258] In some embodiments, the second determining module includes:

[0259] The second determination submodule is used to determine the amount of goods overstocked corresponding to each equipment group;

[0260] The load determination submodule is used to determine the load information of each equipment group based on the required shipment volume of each equipment group and the corresponding allowable shipment volume of each equipment group.

[0261] The shutdown information determination submodule is used to determine the recommended shutdown information for each device group within each unit of time based on the load information and preset load threshold of each device group.

[0262] In some embodiments, the second determining submodule includes:

[0263] The second acquisition unit is used to acquire the equipment performance parameters and actual production time of each equipment group;

[0264] The second determining unit is used to determine the quota of each equipment group based on the corresponding cargo quantity, the corresponding equipment performance parameters and the actual generation time; the cargo quantity represents the maximum cargo quantity that the equipment group can process per hour.

[0265] In some embodiments, the load determination submodule includes:

[0266] The demand quantity determination unit is used to calculate the ratio of the demand throughput of each equipment group to the corresponding allowance throughput of each equipment group, and to determine the number of machines required by each equipment group in each unit of time.

[0267] The load determination unit is used to obtain the maximum number of machines used by each equipment group in each unit of time, and to calculate the ratio of the number of machines required by each equipment group in each unit of time to the corresponding maximum number of machines used, so as to obtain the load information of each equipment group in each unit of time.

[0268] In some embodiments, the preset load threshold includes a first load threshold and a second load threshold, and the shutdown information determination submodule includes:

[0269] The first shutdown judgment unit is used to determine that, for each device group, if the device group is a single device after shutting down at least one device, and if the load information corresponding to the device group is less than or equal to the size of the first load threshold, then the device group can shut down at least one device.

[0270] The second shutdown judgment unit is used to determine that, for each device group, if the device group is not a single device after shutting down at least one device, and if the load information corresponding to the device group is less than or equal to the size of the second load threshold, then the device group can shut down at least one device, and the second load threshold is greater than the first load threshold.

[0271] The summary unit is used to summarize the maximum number of recommended shutdowns and the total number of recommended shutdown times for each equipment group in each unit of time, so as to obtain the recommended shutdown information for each equipment group in each unit of time.

[0272] In some embodiments, the device operating cost information in at least one dimension includes one or more of the following:

[0273] First equipment operating cost information used to characterize equipment maintenance dimensions;

[0274] Secondary equipment operating cost information used to characterize the power consumption dimension of equipment;

[0275] Third equipment operating cost information used to characterize the equipment shutdown dimension;

[0276] The fourth piece of equipment operating cost information is used to characterize the equipment restart dimension.

[0277] In some embodiments, where the equipment operating cost information in at least one dimension includes first equipment operating cost information characterizing equipment maintenance, second equipment operating cost information characterizing equipment electricity consumption, third equipment operating cost information characterizing equipment shutdown, and fourth equipment operating cost information characterizing equipment restart, the reduction determination module is further configured to:

[0278] Based on the first equipment operating cost information and the maximum recommended number of shutdowns for each equipment group in each unit of time, the first cost reduction score is obtained.

[0279] Based on the second equipment operating cost information and the total number of recommended shutdown unit times for each equipment group, the second cost reduction score is obtained.

[0280] Based on the third equipment operating cost information and the maximum recommended number of shutdowns for each equipment group in each unit of time, the first cost increment score is obtained.

[0281] Based on the fourth equipment operating cost information and the maximum recommended number of shutdowns for each equipment group in each unit of time, the second cost increment score is obtained.

[0282] Based on the first cost reduction score, the second cost reduction score, the first cost increment score, and the second cost increment score, the cost reduction value of each equipment group in each unit of time is obtained.

[0283] In some embodiments, the iteration module includes:

[0284] The update submodule is used to iteratively reduce the number of recommended shutdown devices in the recommended shutdown information for each device group of all devices if the cost reduction value corresponding to the device group is less than the preset cost reduction threshold, so as to obtain the updated recommended shutdown information.

[0285] The re-determined submodule is used to determine the update cost reduction value for the device group in each unit of time based on the updated recommended shutdown information;

[0286] The shutdown strategy determination submodule is used to determine that the cost reduction value of each equipment group meets the preset cost reduction condition until the update cost reduction value of each equipment group is less than the preset cost reduction threshold, and to obtain the target equipment shutdown strategy for all equipment.

[0287] Some embodiments of this application also provide an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the device operation control method described in any embodiment of this application.

[0288] An optional hardware structure of the electronic device provided in some embodiments of this application can be as follows: Figure 11 As shown, it includes at least one processor 01, at least one communication interface 02, at least one memory 03, and at least one communication bus 04.

[0289] In this embodiment, the processor 01, communication interface 02, and memory 03 can communicate with each other via the communication bus 04. The processor 01 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. The communication interface 02 can be an interface for a communication module used for network communication, such as the interface of a GSM module. The memory 03 may include high-speed RAM or non-volatile memory, such as at least one disk storage device. The memory 03 may store at least one instruction or at least one program segment, which is loaded and executed by the processor 01 to implement the device operation control method provided in the embodiments of this application.

[0290] It should be noted that the above-described implementing electronic device may also include other devices (not shown) that may not be essential to understanding the content disclosed in the embodiments of this application; given that these other devices may not be essential to understanding the content disclosed in the embodiments of this application, they will not be described one by one in the embodiments of this application.

[0291] Some embodiments of this application also provide a computer-readable storage medium storing at least one instruction or at least one program, which is loaded and executed by a processor to implement the device operation control method described in any embodiment of this application.

[0292] Some embodiments of this application also provide a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform any of the device operation control methods described above.

[0293] The embodiments of this application can be implemented by various means, such as hardware, firmware, software, or combinations thereof. In a hardware configuration, the method according to the exemplary embodiments of this application can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, etc.

[0294] In firmware or software configuration, the embodiments of this application can be implemented in the form of modules, processes, functions, etc. Software code can be stored in a memory unit and executed by a processor. The memory unit is located inside or outside the processor and can send data to and receive data from the processor via various known means.

[0295] The technical effects achievable by the electronic device provided in this application are the same as those achievable by any of the above-described method embodiments, and will not be repeated here.

[0296] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0297] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for device, apparatus, or equipment embodiments, since they are basically similar to the method embodiments, the description is relatively simple; relevant parts can be referred to the description of the method embodiments.

[0298] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A device operation control method characterized by comprising: The method comprises: obtaining predicted demand order information; based on the demand order information, determining the demand overstock of each device group in the full amount of equipment; the functions of each device included in the same device group are the same; based on the demand overstock of each device group, the quota overstock corresponding to each device group and the preset load threshold, determining the recommended shutdown information of each device group in each unit time; obtain the equipment running cost information in at least one dimension, and based on the recommended shutdown information and the equipment running cost information, determine the cost reduction value of each device group in each unit time; iteratively adjust the recommended shutdown device quantity corresponding to the recommended shutdown information until the cost reduction value corresponding to each device group meets the preset cost reduction condition, and obtain the target device shutdown strategy of the full amount of equipment; based on the target device shutdown strategy, control at least one device in at least part of the device group to perform shutdown operation.

2. The method of claim 1, wherein, The method comprises: obtaining historical production data of the full amount of equipment; calling a trained neural network model to predict the historical production data and obtain the demand order information of the full amount of equipment in a future first time period.

3. The method of claim 1, wherein, The method comprises: classifying each predicted product indicated by the demand order information to obtain a plurality of product class groups; screening representative predicted products in each product class group as target products, and merging the demand order sub-information of other predicted products in each product class group into the demand order sub-information of the target product in the same product class group to obtain the summary demand order sub-information of each target product; based on the summary demand order sub-information of each target product and the device group corresponding to each target product, determining the demand overstock of each device group in the full amount of equipment.

4. The method of claim 1, wherein, The method comprises: obtaining the device capacity information of the device group corresponding to each target product; based on the device capacity information, calculating the production cycle of each target product; based on the production cycle, segmenting the product line corresponding to each target product to obtain the product line segment corresponding to each target product; determine the estimated production running time corresponding to each product line segment, and based on the summary demand order sub-information of each target product, calculate the demand overstock of each estimated production running time of the device group included in each product line segment in a future second time period, the number of unit time included in the second time period is less than the number of unit time included in the first time period.

5. The method of claim 1, wherein, The method comprises: determining the quota overstock corresponding to each device group; determine load information of each of the equipment groups based on the required overage of each of the equipment groups and the quota overage corresponding to each of the equipment groups; determine suggested shutdown information of each of the equipment groups in each unit time based on the load information of each of the equipment groups and a preset load threshold.

6. The method of claim 5, wherein, The determination of the quota overage corresponding to each of the equipment groups comprises: obtain equipment performance parameters and actual production time of each of the equipment groups; determine the quota overage corresponding to each of the equipment groups based on the corresponding overage, the corresponding equipment performance parameters and the actual production time of each of the equipment groups; the overage represents the maximum overage quantity of the equipment group per hour.

7. The method of claim 5, wherein, The determination of the load information of each of the equipment groups based on the required overage of each of the equipment groups and the quota overage corresponding to each of the equipment groups comprises: calculate the ratio of the required overage of each of the equipment groups and the quota overage corresponding to each of the equipment groups to determine the required equipment quantity of each of the equipment groups in each unit time; obtain the maximum equipment usage quantity of each of the equipment groups in each unit time, and calculate the ratio of the required equipment quantity of each of the equipment groups in each unit time and the corresponding maximum equipment usage quantity to obtain the load information of each of the equipment groups in each unit time.

8. The method of claim 5, wherein, The preset load threshold comprises a first load threshold and a second load threshold, and the determination of the suggested shutdown information of each of the equipment groups in each unit time based on the load information of each of the equipment groups and the preset load threshold comprises: for each of the equipment groups, if the equipment group is a single machine device after shutting down at least one device, and if the load information corresponding to the equipment group is less than or equal to the size of the first load threshold, it is determined that the equipment group can shut down the at least one device; for each of the equipment groups, if the equipment group is a non-single machine device after shutting down at least one device, and if the load information corresponding to the equipment group is less than or equal to the size of the second load threshold, it is determined that the equipment group can shut down the at least one device, and the second load threshold is greater than the first load threshold; sum up the maximum suggested shutdown quantity of each of the equipment groups in each unit time and the total number of suggested shutdown unit time to obtain the suggested shutdown information of each of the equipment groups in each unit time.

9. The method of claim 1, wherein, The equipment running cost information in at least one dimension comprises one or more of: first equipment running cost information for representing equipment maintenance dimension; second equipment running cost information for representing equipment power consumption dimension; third equipment running cost information for representing equipment shutdown dimension; fourth equipment running cost information for representing equipment restart dimension.

10. The method of claim 8, wherein, In the case that the equipment running cost information in at least one dimension comprises the first equipment running cost information for representing equipment maintenance dimension, the second equipment running cost information for representing equipment power consumption dimension, the third equipment running cost information for representing equipment shutdown dimension and the fourth equipment running cost information for representing equipment restart dimension, the determination of the cost reduction value of each of the equipment groups in each unit time based on the suggested shutdown information and the equipment running cost information comprises: obtaining a first cost reduction score based on the first device running cost information and the maximum recommended shutdown quantity of each of the device groups per unit time; obtaining a second cost reduction score based on the second device running cost information and the total recommended shutdown quantity of each of the device groups per unit time; obtaining a first cost increase score based on the third device running cost information and the maximum recommended shutdown quantity of each of the device groups per unit time; obtaining a second cost increase score based on the fourth device running cost information and the maximum recommended shutdown quantity of each of the device groups per unit time; obtaining a cost reduction value of each of the device groups per unit time based on the first cost reduction score, the second cost reduction score, the first cost increase score and the second cost increase score.

11. The method according to any one of claims 1 to 10, characterized in that, iteratively adjusting the recommended shutdown quantity of each of the device groups until the cost reduction value of each of the device groups meets a preset cost reduction condition, to obtain a target device shutdown strategy of the full set of devices. If the cost reduction value of a device group is less than a preset cost reduction threshold, iteratively adjusting the recommended shutdown quantity of the device group to obtain updated recommended shutdown information; obtaining an updated cost reduction value of the device group per unit time based on the updated recommended shutdown information; until the cost reduction value of each of the device groups is less than the preset cost reduction threshold, determining that the cost reduction value of each of the device groups meets the preset cost reduction condition, and obtaining the target device shutdown strategy of the full set of devices.

12. An apparatus operation control device characterized by comprising: comprising: a first obtaining module configured to obtain predicted demand order information; a first determining module configured to determine a demand overstock quantity of each of the device groups in the full set of devices based on the demand order information; each of the devices in the same device group has the same function; a second determining module configured to determine recommended shutdown information of each of the device groups per unit time based on the demand overstock quantity of each of the device groups, the quota overstock quantity corresponding to each of the device groups and a preset load threshold; a reduction determining module configured to obtain device running cost information in at least one dimension, and determine a cost reduction value of each of the device groups per unit time based on the recommended shutdown information and the device running cost information; an iteration module configured to iteratively adjust the recommended shutdown quantity of each of the device groups until the cost reduction value of each of the device groups meets a preset cost reduction condition, to obtain a target device shutdown strategy of the full set of devices; a running control module configured to control at least one device in at least part of the device groups to perform a shutdown operation based on the target device shutdown strategy.

13. A computer-readable storage medium, characterized in that, The computer readable storage medium stores at least one instruction or at least one program, which is loaded and executed by the processor to implement the device running control method according to any one of claims 1-11.

Images