Control method and system of high-precision brushless direct current motor

Abstract

The invention provides a control method and system for a high-precision brushless direct current motor, and relates to the technical field of motor control, and the method comprises the steps: determining the information of a plurality of washings based on the internal video of the test running speed of a washing machine; clustering the information of the multiple washings based on the K value of the clustering algorithm to obtain K clusters; processing the K clusters based on a velocity analysis model to determine the washing time and power of the cluster with the shortest washing time; based on the washing time and the power of the cluster with the shortest washing time, controlling the high-precision brushless direct current motor to carry out washing, and obtaining an internal video of the washing machine at the first washing time; determining subsequent working time and power of the high-precision brushless direct current motor based on the internal video of the washing machine at the first washing time; the high-precision brushless direct current motor is controlled based on the subsequent working time and power of the high-precision brushless direct current motor, and the method can efficiently and accurately determine the target washing strategy of the washing machine.

Description

Technical Field

[0001] The present invention relates to the technical field of motor control, and particularly to a control method and system for a high-precision brushless DC motor. Background Art

[0002] In the application scenarios of electrical appliances, washing machines have become essential household appliances for daily cleaning of laundry. Currently, most traditional washing machines adopt fixed washing modes, such as common standard wash, gentle wash, strong wash and other modes, and their washing strategies are usually pre-set. In actual use, users need to face a variety of laundry items to be washed simultaneously, ranging from delicate silk products to woolen items that are prone to deformation, and then to relatively tough synthetic fiber products, etc. Different laundry items vary greatly in terms of material characteristics and dirt levels. For example, when faced with multiple laundry items, if the gentle wash mode is selected, the laundry items with a relatively high dirt level may not achieve the washing effect; if the strong wash mode is adopted, the delicate laundry items are likely to be damaged, resulting in problems such as fiber breakage and surface wear. The design of this fixed mode causes users to rely on subjective experience to distinguish and select the washing mode when operating the washing machine, which is time-consuming and laborious and difficult to achieve the best washing effect.

[0003] Therefore, how to efficiently and accurately determine the target washing strategy of the washing machine is an urgent problem to be solved currently. Summary of the Invention

[0004] The main technical problem to be solved by the present invention is how to efficiently and accurately determine the target washing strategy of the washing machine.

[0005] According to the first aspect, the present invention provides a control method for a high-precision brushless DC motor, including: acquiring an internal video of the washing machine during the trial operation speed; determining information of multiple laundry items based on the internal video of the washing machine during the trial operation speed; determining the K value of the clustering algorithm based on the information of the multiple laundry items; clustering the information of the multiple laundry items based on the K value of the clustering algorithm to obtain K clusters; determining the washing time and power of the cluster with the shortest washing time by processing the K clusters based on the speed analysis model; controlling the high-precision brushless DC motor to wash based on the washing time and power of the cluster with the shortest washing time, and acquiring an internal video of the washing machine at the first washing time; when the first washing time is reached, notifying the user to take out the laundry items of the cluster with the shortest washing time, and determining the subsequent working time and power of the high-precision brushless DC motor based on the internal video of the washing machine at the first washing time; controlling the high-precision brushless DC motor based on the subsequent working time and power of the high-precision brushless DC motor.

[0006] In a possible implementation manner, determining the subsequent working time and power of the high-precision brushless DC motor based on the internal video of the washing machine for the first washing time includes:

[0007] Determining the remaining laundry information based on the internal video of the washing machine for the first washing time;

[0008] Generating multiple washing strategies and virtual generated videos for each washing strategy based on the remaining laundry information and the internal video of the washing machine for the first washing time, where each washing strategy includes the subsequent working time and power of the high-precision brushless DC motor;

[0009] Constructing a knowledge graph, which includes multiple washing strategy nodes and multiple edges between the multiple washing strategy nodes. The node feature of each washing strategy node includes the virtual generated video of each washing strategy, and the edges between the nodes represent the power difference and time difference between the washing strategies;

[0010] Processing the knowledge graph based on a graph neural network to determine the target washing strategy.

[0011] In a possible implementation manner, the speed analysis model is a long short-term neural network model.

[0012] In a possible implementation manner, the clustering algorithm is the K-means clustering algorithm.

[0013] According to a second aspect, the present invention provides a control system for a high-precision brushless DC motor, including:

[0014] An acquisition module, configured to acquire the internal video of the trial operation speed of the washing machine;

[0015] An information determination module, configured to determine the information of multiple pieces of laundry based on the internal video of the trial operation speed of the washing machine;

[0016] A K value determination module, configured to determine the K value of the clustering algorithm based on the information of multiple pieces of laundry;

[0017] A clustering module, configured to cluster the information of multiple pieces of laundry based on the K value of the clustering algorithm to obtain K clusters;

[0018] An analysis module, configured to process the K clusters based on the speed analysis model to determine the washing time and power of the cluster with the shortest washing time;

[0019] A first control module, configured to control the high-precision brushless DC motor to perform washing based on the washing time and power of the cluster with the shortest washing time, and acquire the internal video of the washing machine for the first washing time;

[0020] A strategy determination module, configured to notify the user to take out the laundry in the cluster with the shortest washing time when the first washing time is reached, and determine the subsequent working time and power of the high-precision brushless DC motor based on the internal video of the washing machine at the first washing time;

[0021] A second control module, configured to control the high-precision brushless DC motor based on the subsequent working time and power of the high-precision brushless DC motor.

[0022] In a possible implementation manner, the strategy determination module is further configured to:

[0023] Determine the remaining laundry information based on the internal video of the washing machine at the first washing time;

[0024] Generate multiple washing strategies and virtual generated videos for each washing strategy based on the remaining laundry information and the internal video of the washing machine at the first washing time, and each washing strategy includes the subsequent working time and power of the high-precision brushless DC motor;

[0025] Construct a knowledge graph, which includes multiple washing strategy nodes and multiple edges between the multiple washing strategy nodes. The node features of each washing strategy node include the virtual generated video of each washing strategy, and the edges between the nodes represent the power difference and time difference between the washing strategies;

[0026] Process the knowledge graph based on a graph neural network to determine the target washing strategy.

[0027] In a possible implementation manner, the speed analysis model is a long short-term neural network model.

[0028] In a possible implementation manner, the clustering algorithm is the K-means clustering algorithm.

[0029] According to a third aspect, an embodiment of the present invention provides an electronic device, including: a processor; a memory; and a computer program; wherein, the computer program is stored in the memory and configured to be executed by the processor to implement the method as described above. The method includes: obtaining an internal video of the trial operation speed of the washing machine; determining information of multiple pieces of laundry based on the internal video of the trial operation speed of the washing machine; determining the K value of the clustering algorithm based on the information of multiple pieces of laundry; clustering the information of multiple pieces of laundry based on the K value of the clustering algorithm to obtain K clusters; determining the washing time and power of the cluster with the shortest washing time by processing the K clusters based on the speed analysis model; controlling a high-precision brushless DC motor to perform washing based on the washing time and power of the cluster with the shortest washing time, and obtaining an internal video of the washing machine at the first washing time; when the first washing time is reached, notifying the user to take the laundry of the cluster with the shortest washing time, and determining the subsequent working time and power of the high-precision brushless DC motor based on the internal video of the washing machine at the first washing time; controlling the high-precision brushless DC motor based on the subsequent working time and power of the high-precision brushless DC motor.

[0030] According to a fourth aspect, this embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the control method of the high-precision brushless DC motor provided above. The method includes: obtaining an internal video of the trial operation speed of the washing machine; determining information of multiple pieces of laundry based on the internal video of the trial operation speed of the washing machine; determining the K value of the clustering algorithm based on the information of multiple pieces of laundry; clustering the information of multiple pieces of laundry based on the K value of the clustering algorithm to obtain K clusters; determining the washing time and power of the cluster with the shortest washing time by processing the K clusters based on the speed analysis model; controlling a high-precision brushless DC motor to perform washing based on the washing time and power of the cluster with the shortest washing time, and obtaining an internal video of the washing machine at the first washing time; when the first washing time is reached, notifying the user to take the laundry of the cluster with the shortest washing time, and determining the subsequent working time and power of the high-precision brushless DC motor based on the internal video of the washing machine at the first washing time; controlling the high-precision brushless DC motor based on the subsequent working time and power of the high-precision brushless DC motor.

[0031] A control method and system for a high-precision brushless DC motor provided by the present invention. The method includes: obtaining an internal video of the trial operation speed of the washing machine; determining information about multiple items to be washed based on the internal video of the trial operation speed of the washing machine; determining the value of K of the clustering algorithm based on the information about the multiple items to be washed; clustering the information about the multiple items to be washed based on the value of K of the clustering algorithm to obtain K clusters; determining the washing time and power of the cluster with the shortest washing time based on the speed analysis model for the K clusters; controlling the high-precision brushless DC motor to perform washing based on the washing time and power of the cluster with the shortest washing time, and obtaining an internal video of the washing machine at the first washing time; when the first washing time is reached, notifying the user to take out the items to be washed in the cluster with the shortest washing time, and determining the subsequent working time and power of the high-precision brushless DC motor based on the internal video of the washing machine at the first washing time; controlling the high-precision brushless DC motor based on the subsequent working time and power of the high-precision brushless DC motor. This method can efficiently and accurately determine the target washing strategy of the washing machine. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic flowchart of a control method for a high-precision brushless DC motor provided by an embodiment of the present invention;

[0033] Figure 2 It is a schematic flowchart of determining the subsequent working time and power of a high-precision brushless DC motor provided by an embodiment of the present invention;

[0034] Figure 3 It is a schematic diagram of a control system for a high-precision brushless DC motor provided by an embodiment of the present invention; DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] The present invention will be further described in detail below with reference to the accompanying drawings in specific embodiments. Similar elements in different embodiments are denoted by related similar element numbers. In the following embodiments, many details are described to enable a better understanding of the present invention. However, those skilled in the art can easily recognize that some of the features can be omitted in different situations, or can be replaced by other elements, materials, or methods. In some cases, some operations related to the present invention are not shown or described in the specification to avoid overshadowing the core part of the present invention. For those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations based on the description in the specification and the general technical knowledge in the art.

[0036] In an embodiment of the present invention, there is provided a control method for a high-precision brushless DC motor as shown in Figure 1 The control method for the high-precision brushless DC motor includes steps S1 to S8:

[0037] Step S1, obtain the internal video of the washing machine running at the trial operation speed.

[0038] The trial operation speed is the speed at which the washing machine runs before starting the formal washing to detect the state of the clothes inside the washing machine. The trial operation speed of the washing machine is lower than the maximum speed during normal washing.

[0039] The internal video is the video obtained by a high-speed camera installed at a specific position inside the washing machine. Through high-frame-rate shooting, the high-speed camera can capture the details of the images under extremely fast speed changes and record the real-time conditions inside the washing machine at the trial operation speed in the form of a continuous image sequence.

[0040] Step S2, determine the information of multiple items to be washed based on the internal video of the washing machine running at the trial operation speed.

[0041] In some embodiments, the information of multiple items to be washed can be determined based on the internal video of the washing machine running at the trial operation speed through a Transformer model. The input of the Transformer model is the internal video of the washing machine running at the trial operation speed, and the output of the Transformer model is the information of multiple items to be washed.

[0042] The Transformer model is a deep learning model based on the attention mechanism. Through the multi-head attention mechanism, the Transformer model can capture the dependencies between elements at different positions in the sequence and has strong feature extraction and sequence modeling capabilities.

[0043] The information of multiple items to be washed is the comprehensive information of various features related to the items to be washed inside the washing machine output by the Transformer model. The information of the items to be washed covers the type, cleanliness, stain type, stain area, pollution depth, preciousness, weight, etc. of the items to be washed.

[0044] The types of items to be washed include, but are not limited to, items to be washed made of materials such as cotton, silk, and chemical fiber.

[0045] The cleanliness is the cleanliness status evaluated based on the stain type, stain area, and pollution depth, etc.

[0046] The preciousness is the value level measured according to the rarity of the material, brand value, and special process value such as hand embroidery and special printing and dyeing.

[0047] The stain type includes information such as oil stain and pigment pollution.

[0048] The internal video of the washing machine's trial operation speed completely records information such as the appearance, stains, and movement state of the laundry. The Transformer model can infer the material through the texture and grain shown in the internal video of the washing machine's trial operation speed, and judge the cleanliness of the laundry by identifying characteristics such as the location and color of the stains. In addition, laundry items with different weights and materials have obvious differences in their movement states within the washing machine, and this difference information can provide clues for the Transformer model to judge the weight and quantity of the laundry. The Transformer model enables it to simultaneously focus on different regions and moments in the internal video of the washing machine's trial operation speed through the multi-head attention mechanism, and can analyze the changes and correlation information between consecutive video frames without missing key details, thereby accurately converting complex video information into information about multiple laundry items, and then can achieve accurate judgment of characteristics such as the type, quantity, and cleanliness of the laundry.

[0049] Step S3, determining the K value of the clustering algorithm based on the information about the multiple laundry items.

[0050] In some embodiments, the K value of the clustering algorithm can be determined using an information processing model based on the information about the multiple laundry items. The information processing model is a deep neural network model. The input of the information processing model is the information about the multiple laundry items, and the output of the information processing model is the K value of the clustering algorithm.

[0051] The deep neural network model includes a deep neural network (DNN), which is a powerful machine learning model. The deep neural network consists of an input layer, multiple hidden layers, and an output layer. The non-linear mapping ability of the deep neural network enables it to process complex data and tasks, and continuously adjusts the weights through the backpropagation algorithm, thereby optimizing the model's inference and calculation performance.

[0052] The clustering algorithm is the K-means clustering algorithm. The K-means clustering algorithm is an unsupervised learning algorithm that can divide the samples in the dataset into K different clusters. The K-means clustering algorithm classifies samples with high similarity into the same cluster by calculating the similarity between samples.

[0053] The K value is a key parameter in the K-means clustering algorithm output by the information processing model. The K value represents the number of clusters. A suitable K value can make the samples within each cluster have high similarity, while the samples between different clusters are significantly different. The complexity of the information about multiple laundry items makes it particularly important to determine a suitable K value. If the K value is too small, different types of data will be wrongly clustered together, resulting in the loss of data diversity; if the K value is set too large, the amount of data in each cluster will be too small, and the cluster division will be too fragmented, making it difficult to discover the internal laws of the data.

[0054] The information of multiple laundry items covers multiple characteristic dimensions such as the material, quantity, weight and preciousness of the laundry items. These characteristics are interrelated. For example, laundry items made of silk are often more precious, require higher washing methods and cannot be washed for a long time. These internal connections form a complex pattern, which provides a basis for determining the K value. The deep neural network model can classify laundry items with similar characteristics and washing requirements by comprehensively analyzing these internal connections.

[0055] With its powerful nonlinear fitting and feature learning capabilities, deep neural networks deeply mine the complex features in the information of multiple pieces of laundry through neuron connections and weight adjustment, thereby establishing the association between feature combinations and the number of clusters. Deep neural networks continuously optimize their own parameters to better fit the patterns in the data. Faced with multiple pieces of laundry information, deep neural networks can deeply analyze this information and mine potential classification patterns, thereby outputting a suitable K value for the clustering algorithm to achieve reasonable classification of laundry.

[0056] Step S4: clustering the information of the plurality of laundry items based on the K value of the clustering algorithm to obtain K clusters.

[0057] In some embodiments, K clusters and the cluster centers of each of the K clusters can be obtained by the following steps: randomly selecting K laundry information data points as initial cluster centers; then measuring the similarity between each laundry information data point and the K cluster centers by Euclidean distance, and dividing each data point into the cluster corresponding to the cluster center with the highest similarity; then recalculating the mean of all laundry information data points in each cluster to update the positions of the K cluster centers; repeating the above process of calculating similarity, dividing data points and updating cluster centers until the cluster centers no longer change significantly or the preset upper limit of the number of iterations is reached, and finally obtaining K clusters.

[0058] Each cluster is a collection of data samples with similar characteristics. In some embodiments, a cluster is a category group formed by dividing information of multiple pieces of laundry according to K value. The laundry information in the same cluster has high similarity in characteristics such as material and preciousness, and the characteristics of different clusters are significantly different.

[0059] Step S5: Process the K clusters based on the speed analysis model to determine the washing time and power of the cluster with the shortest washing time.

[0060] The speed analysis model is a long-short term neural network model, the input of the speed analysis model is K clusters, and the output of the speed analysis model is the washing time and power of a cluster with the shortest washing time.

[0061] The long short-term neural network model includes the Long Short-Term Memory network (LSTM). The long short-term neural network is a special type of recurrent neural network (RNN) composed of an input gate, a forget gate, and an output gate. The input gate controls the input of new information, the forget gate determines whether to retain or discard previous memory information, and the output gate decides the output content based on the current state and input. Through these gating mechanisms, the long short-term memory network can selectively remember or forget past information and make decisions based on the current input and historical memory.

[0062] The cluster with the shortest washing time is the set of categories with the shortest washing time. The laundry items within this cluster have the highest value attributes compared to those in other clusters. Since the fiber structure and chemical properties of the laundry items in this cluster are more sensitive and fragile, factors such as mechanical friction, chemical reagent erosion, and temperature changes during long-term washing are likely to cause irreversible damage, such as the loss of luster of silk and the fiber breakage of cashmere. Therefore, to protect the physical structure and appearance quality of such laundry items, their suitable washing time is shorter, and thus they are determined to be the cluster with the shortest washing time.

[0063] Each cluster contains various characteristic information of the laundry items. The long short-term neural network can selectively retain or forget information through the gating mechanism and capture the dynamic changes of these characteristics over time. The characteristic differences between different clusters, such as material, weight, and degree of dirt, provide rich comparison information for the model. By learning these differential characteristics, the model can more accurately identify the unique characteristic patterns of the cluster with the shortest washing time. And on this basis, by combining the pattern rules learned from historical data, it can accurately determine the suitable washing time and power for this cluster to ensure the best washing effect while protecting these high-value and vulnerable laundry items.

[0064] In some embodiments, the speed analysis model includes an information extraction layer, a washing parameter estimation layer, and a comparison and decision-making layer. The information extraction layer, the washing parameter estimation layer, and the comparison and decision-making layer all include long short-term neural network structures. The input of the information extraction layer is K clusters, and the output of the information extraction layer is the comprehensive characteristic information of each cluster, the differential information between the cluster with the shortest washing time and each other cluster. The input of the washing parameter estimation layer is the comprehensive characteristic information of each cluster, and the output of the washing parameter estimation layer is the estimated washing time range and the estimated washing power range for each cluster. The input of the comparison and decision-making layer is the differential information between the cluster with the shortest washing time and each other cluster, the estimated washing time range and the estimated washing power range for each cluster, and the output of the comparison and decision-making layer is the washing time and power of one cluster with the shortest washing time.

[0065] The comprehensive feature information of each cluster is a quantitative description of the overall characteristics of all the laundry items within the same cluster. The feature information integrates key information such as the material type, overall dirtiness level, total weight, commonalities in fiber structure and chemical properties of the laundry items within the cluster.

[0066] The difference information between the cluster with the shortest washing time and each of the other clusters is the degree of characteristic differences in material information, dirtiness level, weight, fiber structure, and chemical properties between the cluster with the shortest washing time and each of the other clusters. The material difference can be represented by a similarity percentage, the dirtiness level difference by a multiple, the weight difference by a specific difference value, and the fiber structure and chemical property difference by a comprehensive score.

[0067] Different layers perform different functions. The information extraction layer focuses on integrating the common features of each cluster from the K clusters that have been divided, and sorting out the key feature differences between the cluster with the shortest time and each of the other clusters; the washing parameter estimation layer preliminarily estimates the washing parameters of each cluster based on the comprehensive information of the common features to calculate the applicable range of washing power and washing time for each cluster; the comparison and decision-making layer then combines the difference information and the estimated parameters to accurately determine the washing time and power of the target cluster. The hierarchical processing breaks down the complex washing strategy decision-making task to improve the pertinence of information processing, thereby enhancing the model processing efficiency and the accuracy of decision-making.

[0068] Step S6, based on the washing time and power of the cluster with the shortest washing time, control the high-precision brushless DC motor to perform washing, and obtain the internal video of the washing machine at the first washing time.

[0069] The internal video of the washing machine at the first washing time is the internal video of the washing machine obtained by high-frame-rate shooting using a high-speed camera at a specific internal position during the period when the laundry items of the cluster with the shortest time are being washed.

[0070] Step S7, when the first washing time is reached, notify the user to take out the laundry items of the cluster with the shortest washing time, and determine the subsequent working time and power of the high-precision brushless DC motor based on the internal video of the washing machine at the first washing time.

[0071] In some embodiments, Figure 2 This is a schematic flowchart of a process for determining the subsequent working time and power of a high-precision brushless DC motor provided by an embodiment of the present invention. The determination of the subsequent working time and power of the high-precision brushless DC motor includes steps S21 to S24:

[0072] Step S21, determine the remaining laundry item information based on the internal video of the washing machine at the first washing time.

[0073] In some embodiments, the remaining laundry information is determined using a laundry determination model based on the internal video of the washing machine during the first washing time. The laundry determination model is a Transformer model. The input of the laundry determination model is the internal video of the washing machine during the first washing time, and the output of the laundry determination model is the remaining laundry information.

[0074] The remaining laundry information is the relevant characteristic information of the remaining laundry in the washing machine after being washed for the first washing time, including the type of the laundry, the degree of cleanliness, the type and location of the remaining stains, the remaining cleanliness difference of laundry of different materials, etc. The remaining laundry information can be used to more accurately control the subsequent working time and power of the washing machine.

[0075] The internal video of the washing machine during the first washing time records the dynamic changes in the state of the laundry during the washing process, including details such as stain residues. With the multi-head attention mechanism, the Transformer model can capture the key information in different frames and different regions of the video, and combined with its feature extraction and sequence modeling capabilities, it can accurately identify the remaining stain features, changes in the state of the laundry, etc. from the internal video of the washing machine during the first washing time, so as to determine the remaining laundry information.

[0076] Step S22: Generate multiple washing strategies and virtual generated videos for each washing strategy based on the remaining laundry information and the internal video of the washing machine during the first washing time. Each washing strategy includes the subsequent working time and power of the high-precision brushless DC motor.

[0077] In some embodiments, multiple washing strategies and virtual generated videos for each washing strategy can be generated using a strategy generation model based on the remaining laundry information and the internal video of the washing machine during the first washing time. The strategy generation model is a generative adversarial network. The input of the strategy generation model is the remaining laundry information and the internal video of the washing machine during the first washing time, and the output of the strategy generation model is multiple washing strategies and virtual generated videos for each washing strategy.

[0078] A generative adversarial network is a deep learning model composed of a generator and a discriminator. The generator generates new content based on the input data, and the discriminator judges the authenticity of the content. The two are continuously optimized through adversarial training to improve the generation quality.

[0079] The multiple washing strategies are a series of washing plans formulated for the remaining laundry in the washing machine, specifically including the setting of parameters such as the subsequent working time and power of the high-precision brushless DC motor, so as to achieve the best washing effect of high efficiency, energy saving and protecting the laundry.

[0080] The virtual generated video for each washing strategy is a simulated video generated by a generative adversarial network to display the washing process and effects that occur inside the washing machine under each washing strategy. Through the virtual generated video of the washing strategy, the washing effects that each strategy may bring can be analyzed more intuitively, so as to screen out the optimal washing strategy.

[0081] The video of the interior of the washing machine with the remaining laundry information and the first washing time contains rich details. The remaining laundry information details the current state of the laundry, including the types and locations of unwashed stains, the cleanliness differences of different materials, etc., which are the core basis for formulating washing strategies. The video of the interior of the washing machine at the first washing time visually presents the state changes of the laundry during the washing process through visual images, and complements the remaining laundry information.

[0082] The generative adversarial network has powerful feature learning and data generation capabilities. Its generator can learn the potential patterns and rules in the input data, extract key features from the remaining laundry information and videos, and thus transform them into various possible washing strategies and corresponding virtual videos. The discriminator evaluates the content output by the generator based on actual washing experience and logic to judge its rationality and effectiveness. In the continuous adversarial training, the generator can gradually optimize the generated washing strategies and virtual videos, making them not only accurately match the actual situation of the remaining laundry, but also meet the washing requirements under different materials and stain degrees.

[0083] Step S23, construct a knowledge graph. The knowledge graph includes multiple washing strategy nodes and multiple edges between the washing strategy nodes. The node features of each washing strategy node include the virtual generated video of each washing strategy, and the edges between the nodes represent the power difference and time difference between the washing strategies.

[0084] A knowledge graph is a data structure composed of nodes and edges. Among them, the nodes represent entities, the node features are the attribute information related to the nodes, and the edges connect the relationships between different nodes in the knowledge graph.

[0085] The knowledge graph can present complex washing strategies and their associations in an intuitive and structured form. Each node represents a specific washing strategy, the node features include the virtual generated video of each washing strategy, and the edges represent the power difference and time difference between the washing strategies.

[0086] Step S24, process the knowledge graph based on a graph neural network to determine the target washing strategy.

[0087] A Graph Neural Network (GNN) is a deep learning model that directly operates on knowledge graph data. By passing information between nodes and aggregating features, the graph neural network learns the feature representations of nodes and edges in the graph, enabling it to uncover potential patterns and relationships in the knowledge graph.

[0088] The target washing strategy is the washing plan selected through processing the knowledge graph by the graph neural network and is the most suitable for the current remaining laundry. The target washing strategy includes parameter settings for the subsequent working time and power of the high-precision brushless DC motor. The target washing strategy can achieve the purpose of energy conservation and protecting the laundry while ensuring the washing effect.

[0089] The knowledge graph clearly presents multiple washing strategies and the relationships between them. Nodes carry the specific information of each washing strategy and are the basis for constructing the knowledge graph and for the graph neural network to conduct analysis.

[0090] Node features enrich the information of the washing strategy nodes and enable the graph neural network to more comprehensively understand the characteristics and expected effects of each washing strategy, thus helping to evaluate and compare the washing strategies.

[0091] Edges can reflect the degree of difference between different washing strategies. Through the power difference and time difference represented by the edges, the graph neural network can be assisted in analyzing the similarities and differences between washing strategies.

[0092] The graph neural network is good at processing the knowledge graph. By passing information between adjacent nodes and weighted aggregating node features according to factors such as the weights of the edges, the feature representations of the nodes are updated to uncover potential patterns and relationships in the knowledge graph. When facing the knowledge graph, the graph neural network can make full use of the features of the washing strategy nodes and the relationship information contained in the edges to uncover the potential value of different washing strategies in meeting the needs of the remaining laundry. Through learning and analyzing the knowledge graph, the graph neural network can select the target washing strategy that best meets the actual needs from multiple washing strategies to achieve the decision-making of the washing strategy.

[0093] Step S8: Control the high-precision brushless DC motor based on the subsequent working time and power of the high-precision brushless DC motor.

[0094] When the target washing strategy is determined, control the high-precision brushless DC motor based on the subsequent working time and power of the high-precision brushless DC motor in the target washing strategy to complete the washing of the remaining laundry.

[0095] Based on the same inventive concept Figure 3A schematic diagram of a control system for a high-precision brushless DC motor provided by an embodiment of the present invention. The control system of the high-precision brushless DC motor includes:

[0096] An acquisition module 31 for acquiring an internal video of the trial operation speed of the washing machine;

[0097] An information determination module 32 for determining multi-piece washing object information based on the internal video of the trial operation speed of the washing machine;

[0098] A K-value determination module 33 for determining the K-value of the clustering algorithm based on the multi-piece washing object information;

[0099] A clustering module 34 for clustering the multi-piece washing object information based on the K-value of the clustering algorithm to obtain K clusters;

[0100] An analysis module 35 for processing the K clusters based on a speed analysis model to determine the washing time and power of the cluster with the shortest washing time;

[0101] A first control module 36 for controlling the high-precision brushless DC motor to perform washing based on the washing time and power of the cluster with the shortest washing time, and acquiring an internal video of the washing machine at the first washing time;

[0102] A strategy determination module 37 for notifying the user to take the washing objects of the cluster with the shortest washing time when the first washing time is reached, and determining the subsequent working time and power of the high-precision brushless DC motor based on the internal video of the washing machine at the first washing time;

[0103] A second control module 38 for controlling the high-precision brushless DC motor based on the subsequent working time and power of the high-precision brushless DC motor.

[0104] In addition, unless clearly stated in the claims, the order of the processing elements and sequences, the use of numbers, letters, or other names in this specification is not used to limit the order of the processes and methods in this specification. Although various examples are discussed in the above disclosure for some currently considered useful embodiments of the invention, it should be understood that such details are only for illustrative purposes. The appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only through software solutions, such as installing the described system on existing servers or mobile devices.

[0105] Similarly, it should be noted that, in order to simplify the presentation disclosed in this specification and thus assist in the understanding of one or more embodiments of the invention, in the foregoing description of the embodiments of this specification, multiple features are sometimes grouped into one embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the features required by the subject matter of this specification are more than those recited in the claims. In fact, the features of the embodiments are fewer than all the features of the individual embodiments disclosed above.

[0106] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be regarded as consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly presented and described in this specification.

Claims

1. A control method for a high-precision brushless DC motor, characterized in that, Including: Obtain the internal video of the washing machine during the trial operation speed; Determine the information of multiple pieces of laundry based on the internal video of the washing machine during the trial operation speed; Determine the K value of the clustering algorithm based on the information of multiple pieces of laundry; Cluster the information of multiple pieces of laundry based on the K value of the clustering algorithm to obtain K clusters; Process the K clusters based on the speed analysis model to determine the washing time and power of the cluster with the shortest washing time; Control the high-precision brushless DC motor for washing based on the washing time and power of the cluster with the shortest washing time, and obtain the internal video of the washing machine at the first washing time; When the first washing time is reached, notify the user to take the laundry of the cluster with the shortest washing time, and determine the subsequent working time and power of the high-precision brushless DC motor based on the internal video of the washing machine at the first washing time; Control the high-precision brushless DC motor based on the subsequent working time and power of the high-precision brushless DC motor.

2. The control method of the high-precision brushless DC motor according to claim 1, characterized in that, The determining the subsequent working time and power of the high-precision brushless DC motor based on the internal video of the washing machine at the first washing time includes: Determine the remaining laundry information based on the internal video of the washing machine at the first washing time; Generate multiple washing strategies and virtual generated videos for each washing strategy based on the remaining laundry information and the internal video of the washing machine at the first washing time. Each washing strategy includes the subsequent working time and power of the high-precision brushless DC motor; Construct a knowledge graph, which includes multiple washing strategy nodes and multiple edges between the multiple washing strategy nodes. The node features of each washing strategy node include the virtual generated video of each washing strategy, and the edges between the nodes represent the power difference and time difference between the washing strategies; Process the knowledge graph based on the graph neural network to determine the target washing strategy.

3. The control method of the high-precision brushless DC motor according to claim 1, characterized in that, The speed analysis model is a long short-term neural network model.

4. The control method of the high-precision brushless DC motor according to claim 1, characterized in that, The clustering algorithm is the K-means clustering algorithm.

5. A control system for a high-precision brushless DC motor, characterized in that, Including: An acquisition module, used to obtain the internal video of the washing machine during the trial operation speed; An information determination module, used to determine the information of multiple pieces of laundry based on the internal video of the washing machine during the trial operation speed; A K value determination module, used to determine the K value of the clustering algorithm based on the information of multiple pieces of laundry; A clustering module, used to cluster the information of multiple pieces of laundry based on the K value of the clustering algorithm to obtain K clusters; An analysis module, used to process the K clusters based on the speed analysis model to determine the washing time and power of the cluster with the shortest washing time; A first control module, used to control the high-precision brushless DC motor for washing based on the washing time and power of the cluster with the shortest washing time, and obtain the internal video of the washing machine at the first washing time; A strategy determination module, used to notify the user to take the laundry of the cluster with the shortest washing time when the first washing time is reached, and determine the subsequent working time and power of the high-precision brushless DC motor based on the internal video of the washing machine at the first washing time; A second control module, used to control the high-precision brushless DC motor based on the subsequent working time and power of the high-precision brushless DC motor.

6. The control system of the high-precision brushless DC motor according to claim 5, characterized in that The strategy determination module is further used for: Determine the remaining laundry information based on the internal video of the washing machine for the first washing time; Generate multiple washing strategies and virtual generated videos for each washing strategy based on the remaining laundry information and the internal video of the washing machine for the first washing time. Each washing strategy includes the subsequent working time and power of the high-precision brushless DC motor; Construct a knowledge graph, which includes multiple washing strategy nodes and multiple edges between the multiple washing strategy nodes. The node features of each washing strategy node include the virtual generated video of each washing strategy, and the edges between the nodes represent the power difference and time difference between the washing strategies; Process the knowledge graph based on the graph neural network to determine the target washing strategy.

7. The control system of the high-precision brushless DC motor according to claim 5, characterized in that, The speed analysis model is a long short-term neural network model.

8. The control system of the high-precision brushless DC motor according to claim 5, characterized in that, The clustering algorithm is the K-means clustering algorithm.

Images