Motor control method, device and storage medium of high-power electronic fan

Abstract

The application discloses a motor control method and device of a high-power electronic fan and a storage medium, and the method comprises the following steps: dividing a plurality of vehicles into a plurality of standard clusters according to test environment information and test operation information of the plurality of vehicles; in the standard cluster, performing start test on the vehicle and the high-power electronic fan according to the test operation information and a candidate gear parameter, and collecting a test temperature value of an engine of the vehicle; generating a heat dissipation efficiency of the high-power electronic fan according to the test operation information and the test temperature value; determining the candidate gear parameter applied by the standard cluster as a target gear parameter according to the heat dissipation efficiency; dividing a current vehicle into the standard cluster as a target cluster according to target environment information and target operation information of the current vehicle; and pushing the target gear parameter of the target cluster to the current vehicle. The target gear parameter for gradually improving the motor power is used to control the start of the high-power electronic fan, so that the sharp peak voltage can be effectively slowed down, and the probability of damage of the high-power electronic fan is reduced.

Description

Technical Field

[0001] This invention relates to the technical field of big data mining, and in particular to a motor control method, device and storage medium for a high-power electronic fan. Background Technology

[0002] For high-power motors in new energy vehicles, OEMs are gradually transitioning from configuring 3-4 low-power electric fans to configuring 1 high-power electric fan, which simplifies the vehicle wiring harness, reduces the overall size of the electric fan, and lowers the cost of the electric fan.

[0003] Currently, when a car starts, the high-power electric fan starts at its rated maximum power, which generates voltage spikes at the switching devices, increasing the probability of damage to the high-power electric fan.

[0004] Furthermore, for new energy vehicles, users often remotely start the car and perform operations such as turning on the air conditioning, adjusting the seat / steering wheel, preheating the battery, and cleaning the air circulation in the cabin in advance. The high-powered electric fan runs at its rated maximum power, which increases energy consumption. Summary of the Invention

[0005] In view of this, the present invention provides a motor control method, device and storage medium for a high-power electric fan, in order to reduce the peak voltage and energy consumption of a high-power electric fan in an automobile.

[0006] A first aspect of the present invention provides a motor control method for a high-power electric fan, wherein the high-power electric fan is an automotive engine cooling electric fan with a power exceeding a threshold, and is configured with multiple candidate gear parameters for progressively increasing motor power. The method includes:

[0007] Based on the test environment information and test operation information of multiple vehicles, the vehicles are divided into multiple standard clusters;

[0008] In the standard cluster, the vehicle and the high-power electric fan are tested for startup based on the test operation information and the candidate gear parameters, and the test temperature value of the vehicle engine is collected.

[0009] The heat dissipation efficiency of the high-power electronic fan is determined based on the test operation information and the test temperature value.

[0010] The candidate gear parameters for the standard cluster application are determined based on the heat dissipation efficiency and used as the target gear parameters;

[0011] Based on the target environment information and target operation information of the current vehicle, the current vehicle is classified into the standard cluster as the target cluster;

[0012] The target gear parameter of the target cluster is pushed to the current vehicle so that the high-power electric fan can be controlled to start when the current vehicle is started next time.

[0013] A second aspect of the present invention provides a motor control device for a high-power electric fan, wherein the high-power electric fan is an automotive engine cooling electric fan with a power exceeding a threshold, and is configured with multiple candidate gear parameters for progressively increasing motor power; the device includes:

[0014] The standard cluster partitioning module is used to partition the multiple vehicles into multiple standard clusters based on the test environment information and test operation information of the multiple vehicles;

[0015] The start-up test module is used to perform a start-up test on the vehicle and the high-power electric fan in the standard cluster according to the test operation information and the candidate gear parameters, and to collect the test temperature value of the vehicle engine.

[0016] A heat dissipation efficiency generation module is used to generate a heat dissipation efficiency for the high-power electronic fan based on the test operation information and the test temperature value.

[0017] The target gear parameter determination module is used to determine the candidate gear parameters of the standard cluster application based on the heat dissipation efficiency, and use them as the target gear parameters.

[0018] The target cluster division module is used to divide the current vehicle into the standard cluster as the target cluster based on the target environment information and target operation information of the current vehicle.

[0019] The start control module is used to push the target gear parameters of the target cluster to the current vehicle, so that when the current vehicle is started next time, the target gear parameters are used to control the high-power electric fan to start.

[0020] A third aspect of the present invention provides an electronic device comprising:

[0021] At least one processor; and

[0022] A memory communicatively connected to the at least one processor; wherein,

[0023] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the motor control method for a high-power electric fan as described in the first aspect above.

[0024] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the motor control method for a high-power electronic fan as described in the first aspect above.

[0025] A fifth aspect of the present invention provides a computer program product comprising a computer program that, when executed by a processor, implements the motor control method for a high-power electronic fan as described in the first aspect above.

[0026] In this embodiment, multiple vehicles are divided into several standard clusters based on their test environment and operation information. Within each standard cluster, a start-up test is performed on the vehicle and its high-power electric fan based on the test operation information and candidate gear parameters, and the engine temperature is collected. The high-power electric fan's heat dissipation efficiency is calculated based on the test operation information and temperature. Candidate gear parameters for the standard cluster are determined based on the heat dissipation efficiency, serving as target gear parameters. The current vehicle is assigned to a standard cluster based on its target environment and operation information, becoming a target cluster. The target gear parameters from the target cluster are then pushed to the current vehicle so that the high-power electric fan can be controlled to start using these parameters the next time the vehicle is started. On one hand, using target gear parameters that progressively increase motor power to control the high-power electric fan effectively mitigates voltage spikes and reduces the probability of damage to the high-power electric fan. On the other hand, selecting target gear parameters that align with user start-up habits reduces the high-power electric fan's energy consumption while maintaining effective heat dissipation.

[0027] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 This is a flowchart of a motor control method for a high-power electronic fan provided in Embodiment 1 of the present invention.

[0030] Figure 2 This is a front view of a high-power electronic fan provided in Embodiment 1 of the present invention.

[0031] Figure 3 This is a rear view of a high-power electronic fan provided in Embodiment 1 of the present invention.

[0032] Figure 4 This is an exploded view of a high-power electronic fan provided in Embodiment 1 of the present invention.

[0033] Figure 5 This is a schematic diagram of a heat dissipation detection network provided in Embodiment 1 of the present invention.

[0034] Figure 6 This is a schematic diagram of a multimodal fusion structure provided in Embodiment 1 of the present invention.

[0035] Figure 7 This is a schematic diagram of the motor control device for a high-power electronic fan provided in Embodiment 2 of the present invention.

[0036] Figure 8 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. Detailed Implementation

[0037] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0038] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention 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 used interchangeably where appropriate so that the embodiments of the invention described herein can cover implementations in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0039] Example 1

[0040] See Figure 1The diagram illustrates a flowchart of a motor control method for a high-power electronic fan according to Embodiment 1 of the present invention. This method can be executed by a motor control device for the high-power electronic fan, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0041] Step 101: Divide the multiple vehicles into multiple standard clusters based on the test environment information and test operation information of the multiple vehicles.

[0042] In this embodiment, the high-power electric fan is an automotive engine cooling electric fan, where high power means that its power is greater than a threshold (e.g., 1400W).

[0043] Specifically, high-power electric fans (refrigeration) refer to fan products used for cooling and heat dissipation of automobile engines, consisting mainly of fan blades and equipped with components such as metal support plates.

[0044] A high-powered electric fan (cooling) prevents the car engine from overheating and maintains the optimal operating temperature of the air conditioning system by expelling hot air and promoting efficient heat exchange, ensuring the smooth and reliable operation of the car engine and air conditioning functions.

[0045] For example, the maximum airflow of a 1500W high-power electric fan is usually greater than that of three 800W low-power electric fans (i.e., greater than 12000m³ / h at 100Pa), and the maximum airflow of a 2000W high-power electric fan is usually greater than that of four 800W low-power electric fans (i.e., greater than 16000m³ / h at 100Pa).

[0046] In a heat dissipation design, such as Figure 2 , Figure 3 and Figure 4 As shown, the structure of a certain high-power electronic fan includes a fan cover 401, a back cover 402, a wiring harness 403, a printed circuit board 404, a rotor 405, a stator 406, a housing 407, fan blades 408, etc.

[0047] In this embodiment, the high-power electric fan is configured with multiple candidate gear parameters that progressively increase the motor power. These candidate gear parameters can be set by technicians based on experience, or they can be generated using LLM (Large Language Model) in the automotive field based on the operating specifications of the high-power electric fan. This embodiment does not impose any restrictions on this.

[0048] Among them, the candidate gear parameters include the power of multiple gears and the interval between gears. The so-called gear-by-gear increase of motor power means increasing it sequentially from low to high.

[0049] For example, if the rated power of a high-power electric fan is 1500W, and a candidate speed setting parameter has 5 speeds with an interval of 30 seconds between each speed, the motor power of the 5 speeds is 300W, 600W, 900W, 1200W, and 1500W respectively. If a candidate speed setting parameter has 7 speeds with an interval of 40 seconds between each speed, the motor power of the 7 speeds is 250W, 500W, 750W, 1000W, 1250W, and 1500W respectively, and so on.

[0050] In this embodiment, simulation software can be used in a laboratory environment to simulate user operations and generate test environment and test operation information for the vehicle. Alternatively, test environment and test operation information for the vehicle can be collected from publicly available third-party databases. Furthermore, with user authorization, real environmental and operational information of the vehicle can be collected as test environment and test operation information. This embodiment does not impose any restrictions on these methods.

[0051] The test environment information includes information about the environment in which the car is located, such as latitude, longitude, altitude, temperature, humidity, etc. The test operation information includes operations triggered by the user remotely or at set times, operations triggered by the user inside the car, etc.

[0052] Generally, different users operate a car differently in different spaces and at different times.

[0053] Therefore, multiple vehicles (represented by IDs, etc.) can be clustered based on their test environment and test operation information, and divided into multiple standard clusters.

[0054] For example, test environment information and test operation information of multiple vehicles can be collected simultaneously for a period of time after startup (i.e., the initial startup period). As the vehicles run normally, the engine heat accumulates, and the high-power electric fan operates at its rated power to dissipate heat as much as possible.

[0055] Based on the type of test environment information and the type of test operation information, select an appropriate encoding tool, such as one-hot encoding or a pre-trained language model, and call the encoding tool to encode the corresponding test environment information and test operation information into original driving features.

[0056] K-means clustering was performed on multiple vehicles using the original driving characteristics to obtain multiple standard clusters.

[0057] Step 102: In the standard cluster, perform a start-up test on the car and the high-power electric fan based on the test operation information and candidate gear parameters, and collect the test temperature value of the car engine.

[0058] In this embodiment, an environment for a car and its high-powered electric fan can be set up in a laboratory to test the high-powered electric fan.

[0059] For each standard cluster of vehicles, multiple representative test operation information can be selected. This test operation information is then paired with any candidate gear parameter. In the test bench environment, the vehicle and the high-power electric fan are synchronously started based on the test operation information and the candidate gear parameter. The test operation information is used to control the vehicle to start and execute the specified operation, while the candidate gear parameter is used to control the motor of the high-power electric fan to increase its power gear by gear.

[0060] In the specific implementation, after controlling the car to start, the test operation information of the car in the neighborhood of the center point of the standard cluster is used to control the car's operation, and the candidate gear parameters are used to control the motor of the high-power electric fan to increase the power level by level.

[0061] The term "neighborhood" refers to the distance (such as Euclidean distance) between the original driving characteristics of a car and the center point of a standard cluster that is less than a certain threshold.

[0062] During this process, the test temperature value of the car engine is collected.

[0063] Step 103: Calculate the heat dissipation efficiency of the high-power electronic fan based on the test operation information and test temperature value.

[0064] Generally, if we analyze the airflow field inside a car using fluid dynamics theory to determine the heat dissipation efficiency of a high-power electric fan, this method has efficiency issues when dealing with a large number of candidate gear parameters.

[0065] Under specific automotive structure conditions (such as engine compartment layout and air intake location) and test operation information providing specified operations, the heat dissipation of the vehicle's interior can be predicted to a certain extent. The heat dissipation of high-power electric fans varies under different candidate gear parameters. These differences can reflect the relative heat dissipation efficiency of high-power electric fans under different candidate gear parameters. The relative heat dissipation efficiency can help in the design and development of high-power electric fans. Therefore, the relative heat dissipation efficiency of high-power electric fans can be evaluated based on the distribution of test temperature values, without relying on absolute heat dissipation efficiency, which is more in line with engineering practice.

[0066] In one embodiment of the present invention, step 103 may include the following steps:

[0067] Step 1031: Determine the heat dissipation detection network.

[0068] In this embodiment, a heat dissipation detection network can be built and trained based on deep learning. The heat dissipation detection network is used to detect the heat dissipation efficiency of a high-power electronic fan.

[0069] Among them, such as Figure 5 As shown, the heat dissipation detection network includes a first backbone structure Backbone_1, a second backbone structure Backbone_2, a multimodal fusion module (MFM), and a head structure.

[0070] Furthermore, the first backbone structure Backbone_1 is responsible for extracting the temporal features of the operation from the test operation information, the second backbone structure Backbone_2 is responsible for extracting the temporal features of the temperature from the test temperature value, the multimodal fusion structure MFM is responsible for fusing the temporal features of the operation and the temporal features of the temperature into multimodal features, and the head structure Head is responsible for performing the task of calculating the heat dissipation efficiency.

[0071] In one embodiment of the present invention, when training the heat dissipation detection network offline, step 1031 may include the following steps:

[0072] Step 10311: Collect sample data.

[0073] In this embodiment, sample data can be collected experimentally. The sample data includes sample operation information and sample engine temperature values ​​when the car is started based on the sample operation information.

[0074] In practical implementation, sample operation information can be constructed by constructing test operation information settings. After controlling the car to start, the sample operation information is used to control the car's operation, and different methods are used to control the motor start of the high-power electric fan.

[0075] During this process, sample temperature values ​​of the car engine are collected.

[0076] Step 10312: If the sample operation information in two sample data is the same, then configure a label for the heat dissipation efficiency represented by the sample temperature value for the two sample data to construct a sample pair.

[0077] If the sample operation information in two sample data is the same, but the way the motor of the high-power electronic fan is started is different, then the two can be evaluated in terms of heat dissipation efficiency (i.e., which one has higher heat dissipation efficiency and which one has lower heat dissipation efficiency) in dimensions such as heat dissipation speed and heat dissipation energy consumption. Thus, the two sample data are labeled with the heat dissipation efficiency represented by the sample temperature value to construct sample pairs.

[0078] Step 10313: Train the heat dissipation detection network using the pairing method based on the sample pairs.

[0079] In practical applications, the pairwise method learns the partial order relationship between samples by comparing pairs of samples. The requirement to detect the relative heat dissipation efficiency of high-power electronic fans under different start-up methods is to compare the heat dissipation performance of different start-up methods. Therefore, the heat dissipation detection network can be trained using the pairwise method based on sample pairs.

[0080] In training the heat dissipation detection network, functions such as BPR (Bayesian Personalized Ranking) and Hinge are used as loss functions.

[0081] Step 1032: Input the operation sequence composed of test operation information into the first main structure to extract operation timing features.

[0082] In this embodiment, the first backbone structure Backbone_1 can use structures such as Transformer to add time windows to the test operation information, and input the operation sequence composed of the test operation information within the time window into the first backbone structure Backbone_1 to extract features and obtain operation timing features.

[0083] Step 1033: Input the temperature sequence composed of the test temperature values ​​into the second backbone structure to extract the temperature time sequence features.

[0084] In this embodiment, the second backbone structure Backbone_2 can use structures such as LSTM (Long Short-Term Memory) and GRU (Gated Recurrent Unit) to add time windows to the test temperature values. The temperature sequence composed of the test temperature values ​​within the time window is input into the second backbone structure Backbone_2 to extract features and obtain temperature time series features.

[0085] Step 1034: Input the operation time series features and temperature time series features into the multimodal fusion structure and fuse them into multimodal time series features based on the attention mechanism.

[0086] In this embodiment, the operation timing features and temperature timing features are input into the multimodal fusion structure MFM to interact with each other, thereby fusing them into multimodal timing features based on the attention mechanism so that the two sequences pay attention to the part that has the greatest impact on heat dissipation.

[0087] For example, such as Figure 6 As shown, the multimodal fusion structure MFM includes a global pooling layer, a first attention module Attention_1, and a second attention module Attention_2.

[0088] In the Global Pooling layer, the most recent multiple time steps (t) are considered. i-h -t i-1 The operation time sequence feature Eo performs global pooling operations (such as average pooling, max pooling, etc.) to obtain global time sequence features, thereby filtering high-frequency noise in historical operation sequences, preserving long-term trends, and avoiding information redundancy caused by excessively long historical time sequences.

[0089] In the first attention module Attention_1, global temporal features are used as the query vector Q and the current time step t. i The temporal feature Eo of the operation is represented by the key vector K and the value vector V. The first attention weights of the most recent multiple operation sequences on the current operation sequence are calculated. This allows filtering out key information in the current operation that is strongly correlated with historical operation patterns.

[0090] Use functions such as Add and Concat to set the current time step t. i The operation sequence features are fused with the first attention weight to form the operation context features.

[0091] In the second attention module Attention_2, the operation context features are used as the query vector Q and the current time step t. i The temperature time series feature Et is represented by the key vector K and the value vector V. The current time step t is calculated using the historical operation sequence as an anchor point. i The operation sequence for the current time step t i The second attention weight for the temperature sequence. This allows the temperature sequence to focus on the parts affected by the current critical operation.

[0092] Use functions such as Add and Concat to set the current time step t. i The temperature time series feature Et is fused with the second attention weight to form a multimodal time series feature.

[0093] This embodiment extracts benchmarks from historical operations, selects current key operations, and then associates them with corresponding temperature changes. It aligns with historical operating habits to influence current operating decisions, and the current operation determines temperature changes. The temperature changes reflect the actual logic of heat dissipation performance, which conforms to the progressive focus of physical logic.

[0094] By filtering out historical redundancy, current operational noise, and temperature-irrelevant information through two attention screenings, robustness is effectively improved.

[0095] Furthermore, the visualization of the first and second attention weights facilitates developers' understanding of which operations the multimodal fusion structure (MFM) considers to have the greatest impact on heat dissipation and which temperature indicators best reflect heat dissipation performance. This enhances interpretability and provides a basis for subsequent optimization of high-power electronic fan control strategies.

[0096] Step 1035: Input the multimodal temporal features into the head structure to generate the heat dissipation efficiency of the high-power electronic fan.

[0097] In this embodiment, the head structure is a classification head, which may include fully connected layers (FC), activation functions (such as sigmoid), etc., and input multimodal temporal features into the head structure to generate heat dissipation efficiency for high-power electronic fans.

[0098] Step 104: Determine the candidate gear parameters for the standard cluster application based on the heat dissipation efficiency, and use them as the target gear parameters.

[0099] For each standard cluster, the heat dissipation effect of different candidate parameters can be compared using rules independent of the heat dissipation detection network. The evaluation results of the heat dissipation detection network can be corrected, thereby selecting one or more candidate parameters with better heat dissipation efficiency for each standard cluster as the target parameters for the application of the standard cluster.

[0100] In practical implementation, the heat dissipation efficiency can be averaged to obtain the heat dissipation capacity.

[0101] For the same candidate gear level parameter, the ratio between the number of target capabilities and the total number of heat dissipation capabilities is calculated as the confidence ratio; where the target capability is the heat dissipation capability that is greater than or equal to the capability level.

[0102] If the confidence ratio is greater than or equal to the proportionality, the candidate gear parameter with the most gears is selected as the reference gear parameter. The maximum number of gears is to minimize the increase in motor power of high-power electric fans and reduce peak voltage.

[0103] If the number of reference gear parameters is 1, then the reference gear parameters are determined to be applied to the standard cluster as target gear parameters.

[0104] If the number of reference gear parameters is greater than 1, the reference gear parameter with the longest gear interval is selected as the target gear parameter for application to the standard cluster. The longest gear interval is to extend the time that the motor of the high-power electric fan runs at low power as much as possible, thereby reducing energy consumption.

[0105] Step 105: Based on the current vehicle's target environment information and target operation information, classify the current vehicle into a standard cluster as the target cluster.

[0106] In practical applications, under the current user's authorization, the current user's car can upload its target environment information and target operation information to the cloud. In the cloud, the current car is divided into a standard cluster based on its target environment information and target operation information, and is recorded as the target cluster.

[0107] The target environment information is consistent with the test environment information, both being information about the environment in which the car is located. The target operation information is consistent with the test operation information, both including operations triggered by the user remotely or at set times on the car, and operations triggered by the user inside the car.

[0108] In one embodiment of the present invention, step 105 may include the following steps:

[0109] Step 1051: Collect candidate operation information of the current car after the most recent multiple starts.

[0110] Step 1052: Merge multiple candidate operation information into target operation information.

[0111] In practical applications, user control of a car has a certain degree of randomness. Therefore, it is possible to collect candidate operation information after the car has been started multiple times recently, and merge multiple candidate operation information into target operation information to reduce the fluctuations caused by randomness.

[0112] In one fusion method, the frequency of occurrence of various operation parameters (such as starting the air conditioner, the temperature of the air conditioner, etc.) can be counted in multiple candidate operation information. The frequency of occurrence of each operation parameter is compared, and the multiple operation parameters with the highest frequency of occurrence are selected as target parameters. Then, the target parameters are the single operations that the user has recently triggered frequently in the car.

[0113] At least two target parameters are combined into a parameter set, and the co-occurrence rate of the parameter set is calculated among multiple candidate operation information. Here, the co-occurrence rate refers to the frequency with which the target parameters in the parameter set appear simultaneously in the candidate operation information. Therefore, the parameter set is a combination of operations that the user has recently triggered frequently in the car (such as turning on the air conditioner to a certain temperature, heating the seats, etc.).

[0114] The co-occurrence rates of each parameter set are compared, and the parameter set with the highest co-occurrence rate is selected as the target set.

[0115] The candidate operation information containing the target set is input into the large language model LLM, and the target operation information is constructed while maintaining the existence of the target set.

[0116] Furthermore, the candidate operation information of the target set can be used to construct the prompt. In the large language model LLM that constructs the prompt, the large language model LLM uses the candidate operation information of the target set as a reference to generate more coherent target operation information that conforms to the user's car operation habits.

[0117] Step 1053: Collect target environment information of the current vehicle before the most recent time it was turned off.

[0118] In this embodiment, target environment information transmitted by the current vehicle before its most recent shutdown can be received.

[0119] Step 1054: Encode the target environment information and target operation information into target driving characteristics.

[0120] In this embodiment, an appropriate encoding tool, such as one-hot encoding or a pre-trained language model, can be selected based on the type of target environment information and the type of target operation information. The encoding tool is then called to encode the corresponding target environment information and target operation information into target driving features.

[0121] Step 1055: Calculate the distance between the target driving feature and the center point of each standard cluster.

[0122] In this embodiment, each standard cluster can be traversed to calculate the distance (such as Euclidean distance) between the target driving feature and the center point of each standard cluster.

[0123] Step 1056: Divide the current car into the standard cluster with the smallest distance, and use it as the target cluster.

[0124] In this embodiment, the distance between the current car and the center point of each standard cluster can be compared, and the current car can be assigned to the standard cluster with the smallest distance, which is denoted as the target cluster.

[0125] Step 106: Push the target gear parameters of the target cluster to the current vehicle so that the high-power electric fan can be controlled to start when the current vehicle is started next time.

[0126] In this embodiment, the target gear parameters of the target cluster are pushed to the current vehicle. The current vehicle sets a embedding program in the startup process. When the current vehicle starts up next time, the startup process is executed. When the embedding program is triggered, the target gear parameters are used to control the motor of the high-power electric fan to increase the power level by level.

[0127] In this embodiment, multiple vehicles are divided into several standard clusters based on their test environment and operation information. Within each standard cluster, a start-up test is performed on the vehicle and its high-power electric fan based on the test operation information and candidate gear parameters, and the engine temperature is collected. The high-power electric fan's heat dissipation efficiency is calculated based on the test operation information and temperature. Candidate gear parameters for the standard cluster are determined based on the heat dissipation efficiency, serving as target gear parameters. The current vehicle is assigned to a standard cluster based on its target environment and operation information, becoming a target cluster. The target gear parameters from the target cluster are then pushed to the current vehicle so that the high-power electric fan can be controlled to start using these parameters the next time the vehicle is started. On one hand, using target gear parameters that progressively increase motor power to control the high-power electric fan effectively mitigates voltage spikes and reduces the probability of damage to the high-power electric fan. On the other hand, selecting target gear parameters that align with user start-up habits reduces the high-power electric fan's energy consumption while maintaining effective heat dissipation.

[0128] Example 2

[0129] See Figure 7 This diagram illustrates the structure of a motor control device for a high-power electronic fan according to Embodiment 3 of the present invention. The high-power electronic fan is a car engine cooling electronic fan with a power exceeding a threshold, and is configured with multiple candidate gear parameters that progressively increase the motor power, such as... Figure 7 As shown, the device includes:

[0130] The standard cluster division module 701 is used to divide the multiple vehicles into multiple standard clusters based on the test environment information and test operation information of the multiple vehicles;

[0131] The start-up test module 702 is used to perform a start-up test on the car and the high-power electric fan in the standard cluster according to the test operation information and the candidate gear parameters, and to collect the test temperature value of the car engine.

[0132] The heat dissipation efficiency generation module 703 is used to generate a heat dissipation efficiency for the high-power electronic fan based on the test operation information and the test temperature value.

[0133] The target gear parameter determination module 704 is used to determine the candidate gear parameters of the standard cluster application based on the heat dissipation efficiency, and use them as the target gear parameters.

[0134] The target cluster division module 705 is used to divide the current vehicle into the standard cluster as a target cluster based on the target environment information and target operation information of the current vehicle.

[0135] The start control module 706 is used to push the target gear parameters of the target cluster to the current vehicle, so that when the current vehicle is started next time, the target gear parameters are used to control the high-power electric fan to start.

[0136] In one embodiment of the present invention, the standard cluster partitioning module 701 is further configured to:

[0137] Simultaneously collect test environment information and test operation information of multiple vehicles after startup;

[0138] The test environment information and the test operation information are encoded into original driving characteristics;

[0139] K-means clustering was performed on the original driving characteristics of the vehicles to obtain multiple standard clusters.

[0140] The startup test module 702 is also used for:

[0141] After the vehicle is started, the test operation information of the vehicle in the neighborhood of the center point of the standard cluster is used to control the operation of the vehicle, and the candidate gear parameters are used to control the motor of the high-power electric fan to increase the power of the motor in gear by gear.

[0142] In one embodiment of the present invention, the heat dissipation efficiency generation module 703 includes:

[0143] A heat dissipation detection network determination module is used to determine the heat dissipation detection network; the heat dissipation detection network includes a first backbone structure, a second backbone structure, a multimodal fusion structure, and a head structure;

[0144] The operation timing feature extraction module is used to input the operation sequence composed of the test operation information into the first main structure to extract operation timing features.

[0145] The temperature time series feature extraction module is used to input the temperature sequence composed of the test temperature values ​​into the second backbone structure to extract temperature time series features.

[0146] A multimodal temporal feature fusion module is used to input the operation temporal features and the temperature temporal features into the multimodal fusion structure and fuse them into multimodal temporal features based on an attention mechanism;

[0147] A heat dissipation efficiency generation module is used to input the multimodal timing features into the head structure to generate heat dissipation efficiency for the high-power electronic fan.

[0148] In one embodiment of the present invention, the multimodal fusion structure includes a global pooling layer, a first attention module, and a second attention module;

[0149] The multimodal temporal feature fusion module is also used for:

[0150] In the global pooling layer, a global pooling operation is performed on the operation time sequence features of the most recent multiple time steps to obtain global time sequence features;

[0151] In the first attention module, the global temporal features are used as the query vector, and the operation temporal features at the current time step are used as the key vector and value vector, to calculate the first attention weight of the most recent multiple operation sequences to the current operation sequence;

[0152] The operation timing features at the current time step are fused with the first attention weight to form operation context features;

[0153] In the second attention module, the operation context features are used as the query vector, and the temperature time sequence features of the current time step are used as the key vector and value vector, to calculate the second attention weight of the operation sequence of the current time step on the temperature sequence of the current time step.

[0154] The temperature time series features at the current time step are fused with the second attention weights to form a multimodal time series feature.

[0155] In one embodiment of the present invention, the heat dissipation detection network determination module is further configured to:

[0156] Collect sample data; the sample data includes sample operation information and sample temperature values ​​of the car engine when the car is started and tested based on the sample operation information;

[0157] If the sample operation information in two sample data is the same, then the two sample data are labeled with a tag indicating the heat dissipation efficiency represented by the sample temperature value, so as to construct a sample pair;

[0158] The heat dissipation detection network was trained using a pairwise method based on the sample pairs.

[0159] In one embodiment of the present invention, the target gear parameter determination module 704 is further configured to:

[0160] The heat dissipation capacity is obtained by calculating the average value of the heat dissipation efficiency.

[0161] For the same candidate gear level parameter, the ratio between the number of target capabilities and the total number of heat dissipation capabilities is calculated as a confidence ratio; the target capability is the heat dissipation capability that is greater than or equal to the capability level.

[0162] If the confidence ratio is greater than or equal to the proportionality, the candidate gear parameter with the most gear positions is selected as the reference gear parameter.

[0163] If the number of the reference gear parameters is 1, then the reference gear parameters are determined to be applied to the standard cluster as target gear parameters;

[0164] If the number of reference gear parameters is greater than 1, then the reference gear parameter with the longest gear interval is selected as the target gear parameter applied to the standard cluster.

[0165] In one embodiment of the present invention, the startup control module 706 is further configured to:

[0166] Collect candidate operation information of the vehicle after its most recent multiple starts;

[0167] The candidate operation information is fused into the target operation information;

[0168] Collect target environment information of the vehicle before its most recent engine shutdown;

[0169] The target environment information and the target operation information are encoded into target driving characteristics;

[0170] Calculate the distance between the target driving feature and the center point of each of the standard clusters;

[0171] The current vehicle is assigned to the standard cluster with the smallest distance, which is then used as the target cluster.

[0172] In one embodiment of the present invention, the startup control module 706 is further configured to:

[0173] The frequency of occurrence of various operation parameters is counted among multiple candidate operation information;

[0174] The operation parameters that appear most frequently are selected as target parameters;

[0175] Combine at least two of the target parameters into a parameter set;

[0176] The co-occurrence rate of the parameter set is calculated among multiple candidate operation information;

[0177] The parameter set with the highest co-occurrence rate is selected as the target set;

[0178] The candidate operation information containing the target set is input into the large language model, and the target operation information is constructed while keeping the target set present.

[0179] The motor control device for a high-power electronic fan provided in this embodiment of the invention can execute the motor control method for a high-power electronic fan provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the motor control method for a high-power electronic fan.

[0180] Example 3

[0181] See Figure 8 This diagram illustrates a structural schematic of an electronic device according to an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0182] like Figure 8 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0183] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0184] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the motor control method for a high-power electric fan.

[0185] In some embodiments, the motor control method for a high-power electric fan may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the motor control method for a high-power electric fan described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the motor control method for a high-power electric fan by any other suitable means (e.g., by means of firmware).

[0186] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0187] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0188] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0189] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0190] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0191] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0192] Example 4

[0193] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the motor control method for a high-power electronic fan as provided in any embodiment of this invention.

[0194] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0195] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0196] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A motor control method for a high-power electronic fan, characterized in that, The high-power electric fan is a car engine cooling electric fan with a power exceeding a threshold, and is configured with multiple candidate gear parameters for progressively increasing motor power. The method includes: Based on the test environment information and test operation information of multiple vehicles, the vehicles are divided into multiple standard clusters; In the standard cluster, the vehicle and the high-power electric fan are tested for startup based on the test operation information and the candidate gear parameters, and the test temperature value of the vehicle engine is collected. The heat dissipation efficiency of the high-power electronic fan is determined based on the test operation information and the test temperature value. The candidate gear parameters for the standard cluster application are determined based on the heat dissipation efficiency and used as the target gear parameters; Based on the target environment information and target operation information of the current vehicle, the current vehicle is classified into the standard cluster as the target cluster; The target gear parameter of the target cluster is pushed to the current vehicle so that the high-power electric fan can be controlled to start when the current vehicle is started next time.

2. The method according to claim 1, characterized in that, The process of dividing the multiple vehicles into multiple standard clusters based on their test environment and test operation information includes: Simultaneously collect test environment information and test operation information of multiple vehicles after startup; The test environment information and the test operation information are encoded into original driving characteristics; K-means clustering was performed on the original driving characteristics of the vehicles to obtain multiple standard clusters. The step of performing a start-up test on the vehicle and the high-power electric fan based on the test operation information and the candidate gear parameters includes: After the vehicle is started, the test operation information of the vehicle in the neighborhood of the center point of the standard cluster is used to control the operation of the vehicle, and the candidate gear parameters are used to control the motor of the high-power electric fan to increase the power of the motor in gear by gear.

3. The method according to claim 1, characterized in that, The step of generating a heat dissipation efficiency for the high-power electronic fan based on the test operation information and the test temperature value includes: A heat dissipation detection network is defined; the heat dissipation detection network includes a first backbone structure, a second backbone structure, a multimodal fusion structure, and a head structure. The operation sequence composed of the test operation information is input into the first main structure to extract operation timing features; The temperature sequence composed of the test temperature values ​​is input into the second backbone structure to extract temperature time-series features; The operation timing features and the temperature timing features are input into the multimodal fusion structure and fused into multimodal timing features based on an attention mechanism; The multimodal timing features are input into the head structure to generate the heat dissipation efficiency of the high-power electronic fan.

4. The method according to claim 3, characterized in that, The multimodal fusion structure includes a global pooling layer, a first attention module, and a second attention module; The step of inputting the operation timing features and the temperature timing features into the multimodal fusion structure and fusing them into multimodal timing features based on an attention mechanism includes: In the global pooling layer, a global pooling operation is performed on the operation time sequence features of the most recent multiple time steps to obtain global time sequence features; In the first attention module, the global temporal features are used as the query vector, and the operation temporal features at the current time step are used as the key vector and value vector, to calculate the first attention weight of the most recent multiple operation sequences to the current operation sequence; The operation timing features at the current time step are fused with the first attention weight to form operation context features; In the second attention module, the operation context features are used as the query vector, and the temperature time sequence features of the current time step are used as the key vector and value vector, to calculate the second attention weight of the operation sequence of the current time step on the temperature sequence of the current time step. The temperature time series features at the current time step are fused with the second attention weights to form a multimodal time series feature.

5. The method according to claim 3 or 4, characterized in that, The determination of the heat dissipation detection network includes: Collect sample data; the sample data includes sample operation information and sample temperature values ​​of the car engine when the car is started and tested based on the sample operation information; If the sample operation information in two sample data is the same, then the two sample data are labeled with a tag indicating the heat dissipation efficiency represented by the sample temperature value, so as to construct a sample pair; The heat dissipation detection network was trained using a pairwise method based on the sample pairs.

6. The method according to any one of claims 1-4, characterized in that, The step of determining the candidate gear parameters for the standard cluster application based on the heat dissipation efficiency, as the target gear parameters, includes: The heat dissipation capacity is obtained by calculating the average value of the heat dissipation efficiency. For the same candidate gear level parameter, the ratio between the number of target capabilities and the total number of heat dissipation capabilities is calculated as a confidence ratio; the target capability is the heat dissipation capability that is greater than or equal to the capability level. If the confidence ratio is greater than or equal to the proportionality, the candidate gear parameter with the most gear positions is selected as the reference gear parameter. If the number of the reference gear parameters is 1, then the reference gear parameters are determined to be applied to the standard cluster as target gear parameters; If the number of reference gear parameters is greater than 1, then the reference gear parameter with the longest gear interval is selected as the target gear parameter applied to the standard cluster.

7. The method according to any one of claims 1-4, characterized in that, The step of classifying the current vehicle into the standard cluster as a target cluster based on the current target environment information and target operation information of the vehicle includes: Collect candidate operation information of the vehicle after its most recent multiple starts; The candidate operation information is fused into the target operation information; Collect target environment information of the vehicle before its most recent engine shutdown; The target environment information and the target operation information are encoded into target driving characteristics; Calculate the distance between the target driving feature and the center point of each of the standard clusters; The current vehicle is assigned to the standard cluster with the smallest distance, which is then used as the target cluster.

8. The method according to claim 7, characterized in that, The step of fusing multiple candidate operation information into target operation information includes: The frequency of occurrence of various operation parameters is counted among multiple candidate operation information; The operation parameters that appear most frequently are selected as target parameters; Combine at least two of the target parameters into a parameter set; The co-occurrence rate of the parameter set is calculated among multiple candidate operation information; The parameter set with the highest co-occurrence rate is selected as the target set; The candidate operation information containing the target set is input into the large language model, and the target operation information is constructed while keeping the target set present.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the motor control method for a high-power electric fan as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the motor control method for a high-power electronic fan as described in any one of claims 1-8.

Images