Vehicle air blower control method and device, electronic equipment, vehicle and medium

Abstract

The embodiment of the invention provides a vehicle air blower control method and device, electronic equipment, a vehicle and a medium, and the method comprises the steps that N pieces of first measured data are obtained, and N is larger than or equal to 2; data analysis is conducted on the N pieces of first actual measurement data, M pieces of second actual measurement data are determined, the second actual measurement data are the first actual measurement data influencing the operation state of the air blower, and M is larger than or equal to 1 and smaller than or equal to N; determining target prediction data according to the second actual measurement data and the actual measurement operation data of the air blower; and based on the target prediction data, controlling the blower to execute adjustment work. According to the method and the device, the conversion of vehicle blower control from passive response to active adjustment is realized, the blower adjustment reasonability is improved, the operation efficiency and the temperature adjustment effect of the blower are improved, and the driving comfort experience is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of blower control technology, and in particular to a vehicle blower control method, device, electronic equipment, vehicle, and medium. Background Art

[0002] As a vehicle's air conditioning component, the blower's operating status directly impacts interior comfort and energy consumption. Existing vehicle blower control methods often rely on threshold-based logic based on the blower's actual operating parameters. This approach controls and adjusts the blower only in a passive manner, resulting in a lag in vehicle temperature regulation, reducing the blower's operating efficiency and effectiveness, and impacting vehicle energy consumption and passenger comfort. Summary of the Invention

[0003] The embodiments of the present application provide a vehicle blower control method, device, electronic device, vehicle, and medium, aiming to improve problems such as low operating efficiency and poor temperature regulation effect of vehicle blower control under passive response.

[0004] A vehicle blower control method, comprising: Obtain N first measured data, N ≥ 2; Performing data analysis on N first measured data to determine M second measured data, where the second measured data is first measured data that has an impact on the operating state of the blower, and 1≤M≤N; determining target prediction data based on the second measured data and measured operation data of the blower; Based on the target prediction data, the blower is controlled to perform an adjustment operation.

[0005] The above-mentioned vehicle blower control method can accurately filter out the second measured data from the first measured data by analyzing the impact of the first measured data on the operating state of the blower, thereby ensuring the effectiveness of subsequent blower adjustments. In addition, based on the second measured data and the measured operating data of the blower, target prediction data reflecting the changes in the operating state of the blower can be determined, so that the blower can be controlled and adjusted according to the target prediction data, realizing the transition from passive response to active adjustment, improving the rationality of blower adjustment, and improving the operating efficiency of the blower. Moreover, this embodiment improves the effect of temperature regulation through reasonable blower adjustment, avoids unnecessary energy consumption caused by temperature regulation lag, and improves the driving comfort experience.

[0006] Furthermore, performing data analysis on the N first measured data to determine M second measured data includes: Performing data analysis on the N first measured data using a preset impact analysis model to determine an output impact identifier corresponding to each first measured data; The output impact identifier is the first measured data with an impact identifier, and is determined as the second measured data.

[0007] This embodiment uses a trained preset impact analysis model to analyze the first measured data collected in real time one by one, and accurately screens out the second measured data that has an impact on the operating status of the blower. It can timely discover the factors affecting the operating status of the blower, ensure the rationality of the blower adjustment, and help improve the effectiveness of subsequent analysis and processing and blower adjustment, ensuring that the blower operates in the best condition.

[0008] Furthermore, the first measured data includes environmental data and vehicle status data; The environmental data includes at least one of an environmental temperature value, an environmental humidity value, and an environmental wind speed value; The vehicle status data includes at least one of a battery power status value and an in-vehicle temperature value.

[0009] This embodiment can quickly implement multi-dimensional parameter analysis by analyzing and judging the first measured data such as ambient temperature, ambient humidity, ambient wind speed, battery power status and vehicle interior temperature, thereby improving the comprehensiveness of factors affecting blower operation and the accuracy of screening the second measured data.

[0010] Further, the target prediction data includes at least one of predicted operation data of the blower and predicted vehicle interior temperature; The predicted operation data of the blower is output data obtained by processing the second measured data and the measured operation data of the blower based on a preset operation prediction model; The predicted in-vehicle temperature is output data obtained by processing the second measured data, the measured operation data of the blower, and the in-vehicle temperature value based on a preset temperature prediction model.

[0011] This embodiment uses a preset operation prediction model and a preset temperature prediction model to consider the impact of the second measured data on the blower operating status and the temperature inside the vehicle, accurately predict the changing trend of the blower operating status parameters and the temperature inside the vehicle, and thus formulate a suitable adjustment strategy based on the predicted operation data and the predicted temperature inside the vehicle, avoiding the lag of passive adjustment based on the actual blower operating status, realizing dynamic adjustment and control of the blower, and improving the flexibility and rationality of blower adjustment.

[0012] Furthermore, the target prediction data includes a prediction index value corresponding to at least one prediction index; the prediction index includes a current index, a voltage index, a speed index, and an in-vehicle temperature index; The step of controlling the blower to perform the adjustment operation based on the target prediction data includes: If the prediction indicator value corresponding to the prediction indicator is greater than the preset indicator threshold corresponding to the prediction indicator, the prediction indicator is determined as the indicator to be adjusted; Obtain a target indicator value corresponding to the indicator to be adjusted, and control the blower to perform adjustment work based on the target indicator value corresponding to the indicator to be adjusted, and the target indicator value corresponding to the indicator to be adjusted is less than the preset indicator threshold.

[0013] This embodiment implements multi-indicator fusion analysis using current, voltage, speed, and in-vehicle temperature indicators. When the predicted indicator value corresponding to a predicted indicator exceeds a preset indicator threshold, the blower's operating parameters are dynamically adjusted, preventing insufficient blower regulation due to a single indicator. Furthermore, based on the target indicator value corresponding to the indicator to be adjusted, the blower is controlled to perform regulation, improving the stability and reliability of blower regulation.

[0014] Furthermore, the index to be adjusted includes an in-vehicle temperature index; The step of obtaining a target indicator value corresponding to the indicator to be adjusted, and controlling the blower to perform an adjustment operation based on the target indicator value corresponding to the indicator to be adjusted, includes: Obtaining a target temperature value corresponding to the vehicle interior temperature index; Determining a predicted heat dissipation demand value based on a target temperature value and a predicted temperature value corresponding to the vehicle interior temperature index; Based on the predicted heat dissipation demand value, target operation data of the blower is determined, and based on the target operation data, the blower is controlled to perform an adjustment operation.

[0015] This embodiment first determines the predicted heat dissipation demand value based on the predicted vehicle interior temperature and target area temperature, and then converts the corresponding target operating data such as speed, current and voltage based on the predicted heat dissipation demand value, and adjusts the operating status parameters of the blower from the perspective of heat dissipation demand, thereby improving the accuracy of blower adjustment.

[0016] Furthermore, the step of determining the predicted heat dissipation requirement value based on the target temperature value and the predicted temperature value corresponding to the in-vehicle temperature index includes: Determine the ambient temperature value according to the first measured data, and determine the amount of natural heat dissipation according to the predicted temperature value and the ambient temperature value; A predicted heat dissipation demand value is determined according to the predicted temperature value, the target temperature value and the natural heat dissipation amount.

[0017] This embodiment takes into account the influence of natural heat dissipation and determines the predicted heat dissipation requirement value based on the predicted temperature value, the target temperature value and the calculation of the natural heat dissipation heat, thereby ensuring the accuracy of the predicted heat dissipation requirement value and helping to ensure the effect of subsequent temperature adjustment.

[0018] Furthermore, determining target operating data of the blower based on the predicted heat dissipation demand value includes: determining a predicted outlet temperature and a predicted inlet temperature of the blower based on a target temperature value corresponding to the vehicle interior temperature index; Target operating data of the blower is determined according to the predicted heat dissipation demand value, the predicted outlet temperature, and the predicted inlet temperature.

[0019] This embodiment calculates the predicted outlet temperature and predicted inlet temperature of the blower based on the target temperature value, and combines the influence of the inlet and outlet temperature difference of the blower to determine the second speed adjustment parameter based on the calculation of the predicted heat dissipation demand value, the predicted outlet temperature and the predicted inlet temperature, thereby ensuring the accuracy of the target operating data, helping to ensure the precise control of subsequent blowers and improving the efficiency of adjustment.

[0020] A vehicle blower control device, comprising: A data acquisition module is used to acquire N first measured data, where N is greater than or equal to 2; an impact analysis module, configured to perform data analysis on the N first measured data to determine M second measured data, where the second measured data is the first measured data that has an impact on the operating state of the blower, and 1≤M≤N; an operation prediction module, configured to determine target prediction data based on the second measured data and measured operation data of the blower; A control and adjustment module is used to control the blower to perform adjustment work based on the target prediction data.

[0021] An electronic device includes a processor and a memory, wherein: Memory for storing computer programs; The processor is used to execute the program stored in the memory to implement the above-mentioned vehicle blower control method.

[0022] A vehicle comprises the above-mentioned electronic device.

[0023] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the vehicle blower control method is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a flow chart of a vehicle blower control method provided by an embodiment of the present application; Figure 2 1 is a flow chart of step S20 in the vehicle blower control method provided by one embodiment of the present application; Figure 3 This is a flow chart of step S40 in the vehicle blower control method provided by one embodiment of the present application; Figure 4 This is a flow chart of step S402 in the vehicle blower control method provided by one embodiment of the present application; Figure 5 This is a flow chart of step S4022 in the vehicle blower control method provided by one embodiment of the present application; Figure 6 This is a flow chart of step S4023 in the vehicle blower control method provided by one embodiment of the present application; Figure 7 1 is a structural diagram of a vehicle blower control device provided by an embodiment of the present application; Figure 8 2 is a schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the technical problems, technical solutions and beneficial effects solved by this application more clearly understood, this application is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0026] Terminology In this application, the term "first measured data" refers to the collected indicator value corresponding to a pre-specified indicator that potentially affects the operating status of the blower. For example, the pre-specified indicator may include the ambient temperature outside the vehicle, and the corresponding collected indicator value is the real-time collected ambient temperature value. The term "second measured data" refers to the first measured data that is selected from the first measured data and actually affects the operating status of the blower.

[0027] The measured operating data of the blower refers to the parameter collection values used to characterize the operating status of the blower, such as the current, voltage and speed actually collected when the blower is running. The target prediction data refers to the value that may be reached after a specified time interval for the evaluation index that is pre-specified to evaluate whether the blower needs to be adjusted. The target prediction data includes a prediction index value corresponding to at least one prediction index. Among them, the prediction index is a pre-specified parameter feature used to evaluate whether the blower needs to be adjusted, that is, an evaluation index. The prediction index value corresponding to the prediction index refers to the value that the prediction index may reach after a specified time interval. For example, the prediction index may include the operating speed of the blower, and the corresponding prediction index value is the value that the operating speed of the blower may reach after a specified time interval.

[0028] The preset impact analysis model refers to a pre-trained neural network model used to determine whether the collected first measured data will have an impact on the operating state of the blower in the future. The preset operation prediction model refers to a pre-trained neural network model used to predict the values that the operating state parameters of the blower may reach after a specified time interval, taking into account the impact of the second measured data on the operating state of the blower. The operating state parameters of the blower refer to the current, voltage and speed of the blower. The preset temperature prediction model refers to a pre-trained neural network model used to predict the values that the vehicle interior temperature corresponding to the blower may reach after a specified time interval, taking into account the impact of the second measured data on the operating state of the blower.

[0029] The present invention provides a vehicle blower control method. The vehicle blower control method is described by taking the vehicle blower control method as an example. Please refer to Figure 1 , including the following steps: S10: Obtain N first measured data, where N≥2; S20: Analyze the N first measured data to determine M second measured data, where the second measured data is the first measured data that affects the operating state of the blower, and 1≤M≤N; S30: determining target prediction data based on the second measured data and the measured operation data of the blower; S40: Based on the target prediction data, control the blower to perform an adjustment operation.

[0030] Understandably, in actual applications, the interior space of a vehicle is divided into one or more zones, each equipped with an independent temperature sensor and blower to monitor and adjust the interior temperature of the respective zone. For example, the interior space of a vehicle can be treated as a whole vehicle zone, with all air outlets in the vehicle sharing a set of temperature sensors and blowers. Alternatively, the interior space of a vehicle can be divided into two zones, the front row and the rear row, with each zone's air outlet equipped with a set of temperature sensors and blowers. Alternatively, the interior space of a vehicle can be divided into three zones, the driver's seat, the front passenger seat, and the rear seat, with each zone's air outlet equipped with a set of temperature sensors and blowers.

[0031] As an example, in step S10, when at least one blower in the vehicle is in operation, the vehicle control unit can automatically trigger the process of the vehicle blower control method according to a fixed periodic schedule. For example, according to a 5-minute cycle, starting from obtaining N first measured data, analyzing whether each blower in operation needs to be adjusted based on the first measured data, and finally controlling the blowers that need to be adjusted to perform the adjustment work. The driver and passengers can also actively trigger the process of the vehicle blower control method as needed, starting from obtaining N first measured data, analyzing whether each blower in operation needs to be adjusted based on the first measured data, and finally controlling the blowers that need to be adjusted to perform the adjustment work.

[0032] The number N of first measured data refers to the number of index collected values corresponding to pre-specified indicators that potentially affect the operating status of the blower. To comprehensively consider the impact of multiple factors, at least two pre-specified indicators are present, and therefore at least two corresponding index collected values are present. That is, the number N of first measured data is a positive integer greater than or equal to 2.

[0033] As an example, in step S20, the collected indicator values corresponding to pre-specified indicators in the first measured data may vary over time at different collection times. This variation may affect heat exchange between the vehicle and the outside of the vehicle, directly or indirectly affecting the operating status of the blower, thereby requiring blower adjustment. The vehicle control unit analyzes whether each collected indicator value affects the operating status of the blower. M second measured data may be selected from the N first measured data. The second measured data are the first measured data that affect the operating status of the blower. The subsequent step of analyzing whether to adjust the blower is performed only when one or more collected indicator values in the first measured data have a significant impact on the operating status of the blower. Since the second measured data are the first measured data that affect the operating status of the blower, the number M of second measured data is a positive integer greater than or equal to 1 and less than or equal to N. If the collected indicator values corresponding to all indicators in the first measured data do not affect the operating status of the blower, or the impact is negligible, the subsequent step of analyzing whether to adjust the blower is unnecessary.

[0034] In the process of analyzing whether the collected values of each indicator have an impact on the operating status of the blower, different methods can be used as needed, including but not limited to threshold judgment analysis, visual chart analysis, and model analysis. For example, when using threshold judgment analysis, a threshold is determined for each pre-set indicator as the judgment standard for "impact on the operating status of the blower." When the collected value of the same indicator in the first measured data exceeds the threshold, it is considered to have an impact on the operating status, and the collected value of the indicator is determined as the second measured data.

[0035] As an example, in step S30, after determining the second measured data, the vehicle control unit can determine the target prediction data based on the measured operating data of the blower and taking into account the impact of the second measured data on the operating state of the blower. In the process of determining the target prediction data based on the second measured data and the measured operating data of the blower, different methods can be used as needed, including but not limited to model prediction analysis and curve fitting prediction analysis. For example, when using model prediction analysis, a neural network model can be trained based on historical data, and the trained neural network model can be used for model prediction. When using curve fitting prediction analysis, a curve fitting can be performed between the influential measured data and the operating state parameters of the blower based on historical data, and the fitted operating data change curve can be used for prediction. The operating data change curve is a function curve used to characterize how the operating state parameters of the blower change over time under different influencing measured data.

[0036] As an example, in step S40, after determining the target prediction data, the vehicle control unit determines whether the blower's operating parameters require adjustment based on the target prediction data, and controls the blower to adjust the required parameters. This means controlling the blower to perform adjustments to offset or mitigate future changes in the vehicle's interior temperature. For example, if the target prediction data determines that the blower's operating speed is too high, the blower's operating speed may be reduced by 100 rpm at a later time point to ensure that the adjusted blower speed is not too high.

[0037] In addition to controlling the blower to perform adjustments, the vehicle control unit can also generate warning messages corresponding to blower adjustments. Warning messages are used to notify the driver and passengers that the blower operating parameters need to be adjusted. Warning messages can be displayed via text messages or lights on the vehicle's instrument panel, or voice notifications can be provided to the driver and passengers.

[0038] Furthermore, when the blower needs to be controlled to perform regulation to lower the temperature inside the vehicle, the vehicle control unit can also control the vehicle temperature regulation components such as the heat exchanger, condenser, and evaporator to coordinate the regulation. For example, a high-efficiency heat exchanger is used to transfer the heat from the high-temperature air inside the vehicle to the outside environment, achieving effective heat transfer. For the condenser installed in the space outside the vehicle cabin, a fan is used to enhance the heat dissipation effect to ensure that the refrigerant can effectively dissipate heat to the outside of the vehicle. The refrigerant circulates in the air conditioning system, absorbs heat from the air inside the vehicle, and then releases the heat to the outside environment through the condenser. For the evaporator installed in the space inside the vehicle cabin, the refrigerant absorbs heat from the air inside the vehicle through the evaporation process, thereby lowering the temperature inside the vehicle. At the same time, the air ducts and air outlets can be optimized and a reasonable air circulation path can be designed to ensure that the cooled air can be distributed to various areas in the vehicle.

[0039] By analyzing the impact of the first measured data on the operating state of the blower, the embodiment of the present application can accurately filter out the second measured data from the first measured data, thereby ensuring the effectiveness of subsequent blower adjustments. In addition, based on the second measured data and the measured operating data of the blower, target prediction data reflecting the changes in the operating state of the blower can be determined, thereby controlling the blower for adjustment based on the target prediction data, achieving a transition from passive response to active adjustment, improving the rationality of blower adjustment, and improving the operating efficiency of the blower. Moreover, this embodiment improves the effect of temperature regulation through reasonable blower adjustment, avoids unnecessary energy consumption caused by temperature regulation lag, and improves the driving comfort experience.

[0040] In one embodiment, in step S20, please refer to Figure 2 , that is, performing data analysis on the N first measured data to determine M second measured data, includes the following steps: S201: Performing data analysis on N first measured data using a preset impact analysis model to determine an output impact identifier corresponding to each first measured data; S202: Determine the first measured data with the output impact identifier as the second measured data.

[0041] It is understandable that before performing data analysis on the N first measured data through the preset impact analysis model, it is necessary to complete the training of the preset impact analysis model. The training process of the preset impact analysis model is specifically as follows: multiple groups of different first measured data collected in advance are selected as sample data, and each sample data corresponds to an impact analysis model to be trained to identify the impact identification label of "influence" or "no influence"; after analyzing the sample data through the impact analysis model with initial parameters, the initial parameters are slightly adjusted according to the deviation between the output analyzed impact identification and the impact identification label corresponding to the sample data, until the deviation can be controlled within the preset threshold, which indicates that the training of the speech recognition model is successful, and finally a trained preset impact analysis model is obtained.

[0042] In one specific embodiment, historical data from a specified historical time period (e.g., six months) or vehicle blower test data under specified experimental conditions is obtained as sample data. The sample data is divided into a training set, a validation set, and a test set in a ratio of 70%:15%:15%. The input data is normalized to a mean of 0 and a variance of 1. An initial deep neural network model is constructed and trained as the impact analysis model. The model is iteratively trained using binary cross entropy as the loss function. The loss function is calculated and the model parameters are updated through backpropagation until the loss function converges or a preset number of iterations is reached. The iterations are terminated to obtain the trained preset impact analysis model. The Adam optimizer can also be used during the iteration process, with a learning rate set to 0.001. The initial deep neural network model includes an input layer, a hidden layer, and an output layer. The input data in the input layer has a dimension of n and a number of nodes in the input layer. For example, if the input is environmental data (e.g., ambient temperature, ambient humidity, ambient wind speed) and vehicle status data (e.g., battery state of charge, regional temperature), the dimension is 5. The hidden layer uses a multi-layer fully connected neural network. The number of nodes in each layer can be adjusted based on data complexity, and the ReLU activation function is used. For example, the number of hidden layers is 3-5, and the number of nodes in each layer is 64-256. The number of nodes in the output layer is m, and the activation function is selected based on the nature of the output data. The output of the impact analysis model is a categorical value (such as an impact identification label). The Softmax activation function is used, and the output value is 0 or 1, indicating whether there is an impact.

[0043] After the preset impact analysis model is trained, the vehicle control unit performs data analysis on the N first measured data through the preset impact analysis model to determine the output impact identifier corresponding to each first measured data, that is, the preset impact analysis model outputs N output impact identifiers. The first measured data with the output impact identifier as the impact identifier is determined as the second measured data, so as to filter out M second measured data from the N first measured data. The output impact identifier is an indication information used to characterize whether the indicator collection value corresponding to the pre-specified indicator in the first measured data will affect the operating status of the blower. The output impact identifier is divided into two types: an impact identifier and a non-impact identifier according to different types. The impact identifier is used to characterize the type of impact identifier that will have a significant impact on the operating status of the blower, and the non-impact identifier is used to characterize the type of impact identifier that will have no impact on the operating status of the blower or the impact is very small and can be ignored.

[0044] This embodiment uses a trained preset impact analysis model to analyze the first measured data collected in real time one by one, and accurately screens out the second measured data that has an impact on the operating status of the blower. It can timely discover the factors affecting the operating status of the blower, ensure the rationality of the blower adjustment, and help improve the effectiveness of subsequent analysis and processing and blower adjustment, ensuring that the blower operates in the best condition.

[0045] In one embodiment, the first measured data includes environmental data and vehicle status data; The environmental data includes at least one of an environmental temperature value, an environmental humidity value, and an environmental wind speed value; The vehicle status data includes at least one of a battery power status value and an in-vehicle temperature value.

[0046] Understandably, the first measured data includes environmental data and vehicle status data. Changes in environmental data will affect the heat exchange between the inside and outside of the vehicle, indirectly affecting the operating state of the blower, and thus the blower needs to be adjusted. Changes in vehicle status data will directly affect the operating state of the blower, and thus the blower needs to be adjusted. Environmental data refers to environmental index data in the vehicle's external space that potentially affects the heat exchange between the inside and outside of the vehicle, including at least one of ambient temperature, ambient humidity, and ambient wind speed. Vehicle status data refers to the vehicle's own index data that potentially affects the operating state of the blower, including at least one of the battery state of charge and the temperature inside the vehicle. The temperature inside the vehicle refers to the regional temperature of the area where each blower is located in the interior space of the vehicle, that is, the regional average temperature monitored by the temperature sensor configured in the same area as the blower.

[0047] Different ambient temperatures, humidity levels, wind speeds, battery state of charge, and vehicle interior temperature will have varying degrees of impact on the blower's operating state. Therefore, each of the ambient temperature, humidity, wind speed, battery state of charge, and vehicle interior temperature corresponds to a different impact indicator. In this case, the output impact indicators corresponding to the first measured data include an ambient temperature impact indicator corresponding to the ambient temperature, an ambient humidity impact indicator corresponding to the ambient humidity, an ambient wind speed impact indicator corresponding to the ambient wind speed, a battery impact indicator corresponding to the battery state of charge, and an interior temperature impact indicator corresponding to the blower's interior temperature. The ambient temperature impact indicator indicates whether the external ambient temperature affects the blower's operating state. The ambient humidity impact indicator indicates whether the external ambient humidity affects the blower's operating state. The ambient wind speed impact indicator indicates whether the external ambient wind speed affects the blower's operating state. The battery impact indicator indicates whether the battery state of charge affects the blower's operating state. The interior temperature impact indicator indicates whether the interior temperature of the vehicle in the area where the blower is located affects the blower's operating state. When at least one of the identification types of the ambient temperature impact flag, ambient humidity impact flag, ambient wind speed impact flag, battery impact flag, and in-vehicle temperature impact flag corresponding to the same blower is of an impact type, it can be determined that the environmental data and vehicle status data have an impact on the operating state of the blower, and a subsequent analysis is required to determine whether to adjust the blower. When the identification types of the ambient temperature impact flag, ambient humidity impact flag, ambient wind speed impact flag, battery impact flag, and in-vehicle temperature impact flag corresponding to the same blower are all of a non-impact type, it can be determined that the environmental data and vehicle status data have no impact on the operating state of the blower, and a subsequent analysis is not required to determine whether to adjust the blower.

[0048] In one specific embodiment, the output impact flag can be represented by a Boolean value, divided into two flag types: True and False. True indicates an impact flag, and False indicates no impact flag. In this case, the environmental data and vehicle status data are input as analysis data into a pre-trained, preset impact analysis model. The model outputs a Boolean value list, with each blower corresponding to its own Boolean value list. For example, the model input data corresponding to a blower is [ambient temperature, ambient humidity, ambient wind speed, battery state of charge, interior temperature], and the corresponding model output data is [True, False, True, False, False], which serves as the ambient temperature impact flag, ambient humidity impact flag, ambient wind speed impact flag, battery impact flag, and interior temperature impact flag corresponding to the blower. In this case, the Boolean value list indicates that the ambient temperature impact flag and the ambient wind speed impact flag are impact flags, while the ambient humidity impact flag, the battery impact flag, and the interior temperature impact flag are no impact flags. That is, the ambient temperature value and the ambient wind speed value in the first measured data will have a significant impact on the blower's operating state, while the other data items have no impact or a very small impact and can be ignored.

[0049] This embodiment can quickly implement multi-dimensional parameter analysis by analyzing and judging the first measured data such as ambient temperature, ambient humidity, ambient wind speed, battery power status and vehicle interior temperature, thereby improving the comprehensiveness of factors affecting blower operation and the accuracy of screening the second measured data.

[0050] In one embodiment, the target prediction data includes at least one of predicted operating data of the blower and predicted vehicle interior temperature; The predicted operation data of the blower is output data obtained by processing the second measured data and the measured operation data of the blower based on a preset operation prediction model; The predicted in-vehicle temperature is output data obtained by processing the second measured data, the measured operation data of the blower, and the in-vehicle temperature value based on a preset temperature prediction model.

[0051] It is understandable that the target prediction data includes at least one of the predicted operating data of the blower and the predicted in-vehicle temperature. The predicted operating data is the output data of processing the second measured data and the measured operating data of the blower based on a preset operation prediction model. That is, under the influence of the second measured data on the measured operating data of the blower, the value that the operating state parameter may reach after a preset prediction time interval. The predicted in-vehicle temperature is the output data of processing the second measured data, the measured operating data of the blower and the in-vehicle temperature value based on a preset temperature prediction model. That is, under the influence of the second measured data on the measured operating data of the blower, and the influence of the change in operating data on the in-vehicle temperature, the value that the in-vehicle temperature may reach after a preset prediction time interval. The preset prediction time interval is a fixed time interval set in advance for predicting the operating data and temperature. A default value can be set or adjusted as needed. For example, the default value is 1 minute.

[0052] Before performing data analysis using the preset operation prediction model and the preset temperature prediction model, the preset operation prediction model and the preset temperature prediction model must also be trained. The training process for the preset operation prediction model and the preset temperature prediction model is similar to the training method for the preset impact analysis model, using a deep neural network model for iterative training until the sum of the prediction errors converges. However, because the inputs and outputs of the preset operation prediction model and the preset temperature prediction model differ from those of the preset impact analysis model, the model parameters differ. For example, the preset operation prediction model outputs [speed, current, voltage], which are continuous values, so a linear activation function is used; the preset operation prediction model uses mean squared error as the loss function. When the predicted operation data includes predicted speed, predicted current, and predicted voltage, the preset operation prediction model can be a combination of a preset speed prediction sub-model, a preset current prediction sub-model, and a preset voltage prediction sub-model. The preset speed prediction sub-model is a pre-trained neural network model used to predict the speed value after a specified time interval under the influence of the second measured data on the blower. The preset current prediction sub-model is a pre-trained neural network model for predicting a current value after a specified time interval under the influence of the second measured data on the blower. The preset voltage prediction sub-model is a pre-trained neural network model for predicting a voltage value after a specified time interval under the influence of the second measured data on the blower.

[0053] This embodiment uses a preset operation prediction model and a preset temperature prediction model to consider the impact of the second measured data on the blower operating status and the temperature inside the vehicle, accurately predict the changing trend of the blower operating status parameters and the temperature inside the vehicle, and thus formulate a suitable adjustment strategy based on the predicted operation data and the predicted temperature inside the vehicle, avoiding the lag of passive adjustment based on the actual blower operating status, realizing dynamic adjustment and control of the blower, and improving the flexibility and rationality of blower adjustment.

[0054] In step S40, please refer to Figure 3 The target prediction data includes a prediction index value corresponding to at least one prediction index; the prediction index includes a current index, a voltage index, a speed index, and an in-vehicle temperature index; that is, controlling the blower to perform the adjustment operation based on the target prediction data includes the following steps: S401: If the prediction indicator value corresponding to the prediction indicator is greater than the preset indicator threshold corresponding to the prediction indicator, the prediction indicator is determined as an indicator to be adjusted; S402: Obtain a target indicator value corresponding to the indicator to be adjusted, and control the blower to perform an adjustment operation based on the target indicator value corresponding to the indicator to be adjusted, and the target indicator value corresponding to the indicator to be adjusted is less than the preset indicator threshold.

[0055] It is understandable that the target prediction data includes a prediction index value corresponding to at least one prediction index, and the prediction index includes but is not limited to the current index, voltage index, speed index of the blower and the in-vehicle temperature index corresponding to the blower. Each prediction index has a corresponding prediction index value and a preset index threshold. The prediction index is a pre-specified parameter feature used to evaluate whether the blower needs to be adjusted, and the prediction index value corresponding to the prediction index refers to the value that the prediction index may reach after a specified time interval. The preset index threshold is a pre-set critical value of the prediction index used to determine whether the blower needs to be adjusted. The indicator to be adjusted refers to the prediction index that triggers the adjustment of the blower. The target index value refers to the expected value of the indicator that is pre-set to make the indicator to be adjusted at a reasonable level after the blower is adjusted, so the target index value corresponding to the same indicator to be adjusted is less than the preset index threshold.

[0056] In a specific embodiment, when the prediction indicators are current, voltage, and speed indicators, the corresponding prediction indicator values are the predicted current, predicted voltage, and predicted speed, respectively, representing the values of the current, voltage, and speed that the blower may reach after a preset prediction time interval. When the predicted current reaches a preset current threshold, the vehicle control unit determines the current indicator as the indicator to be adjusted, determines a first current adjustment parameter based on a target current value corresponding to the current indicator, and controls the blower to perform adjustment operations based on the first current adjustment parameter. The first current adjustment parameter is a current adjustment value used to maintain stable operation of the blower by varying the current. When the predicted voltage reaches a preset voltage threshold, the vehicle control unit determines the voltage indicator as the indicator to be adjusted, determines a first voltage adjustment parameter based on a target voltage value corresponding to the voltage indicator, and controls the blower to perform adjustment operations based on the first voltage adjustment parameter. The first voltage adjustment parameter is a voltage adjustment value used to maintain stable operation of the blower by varying the voltage. When the predicted speed reaches a preset speed threshold, the vehicle control unit determines the speed indicator as the indicator to be adjusted, determines a first speed adjustment parameter based on the target speed value corresponding to the speed indicator, and controls the blower to perform adjustment operations based on the first speed adjustment parameter. The first speed adjustment parameter is a speed adjustment value used to maintain a stable operating state of the blower by varying the speed. For a blower, one or more of the first current adjustment parameter, the first voltage adjustment parameter, and the first speed adjustment parameter may exist simultaneously, enabling comprehensive adjustment of the blower's operating parameters.

[0057] This embodiment implements multi-indicator fusion analysis using current, voltage, speed, and in-vehicle temperature indicators. When the predicted indicator value corresponding to a predicted indicator exceeds a preset indicator threshold, the blower's operating parameters are dynamically adjusted, preventing insufficient blower regulation due to a single indicator. Furthermore, based on the target indicator value corresponding to the indicator to be adjusted, the blower is controlled to perform regulation, improving the stability and reliability of blower regulation.

[0058] In step S402, please refer to Figure 4 The index to be adjusted includes an interior vehicle temperature index; that is, obtaining a target index value corresponding to the index to be adjusted, and controlling the blower to perform adjustment based on the target index value corresponding to the index to be adjusted, comprises the following steps: S4021: Obtaining a target temperature value corresponding to the vehicle interior temperature index; S4022: Determine a predicted heat dissipation demand value based on a target temperature value and a predicted temperature value corresponding to the vehicle interior temperature index; S4023: Determine target operating data of the blower based on the predicted heat dissipation demand value, and control the blower to perform an adjustment operation based on the target operating data.

[0059] It is understandable that when the predicted in-car temperature reaches a preset temperature threshold, the indicator to be adjusted includes the in-car temperature indicator. At this time, the target operating data of the blower is determined based on the predicted in-car temperature, and based on the target operating data, the blower is controlled to perform the adjustment work. The target operating data is an operating data adjustment value used to maintain the stable in-car temperature by changing the blower operating state parameters. When the indicator to be adjusted includes the in-car temperature index, the vehicle control unit needs to first obtain the target temperature value corresponding to the in-car temperature index, and then determine the predicted heat dissipation demand value based on the target temperature value and the predicted temperature value corresponding to the in-car temperature index, and finally determine the target operating data of the blower based on the predicted heat dissipation demand value. The predicted temperature value refers to the predicted value of the in-car temperature index corresponding to the area where the blower is located. The predicted heat dissipation demand value refers to the heat value that needs to be dissipated through heat exchange in order to eliminate the gap between the predicted in-car temperature and the target area temperature.

[0060] The target operating data includes a second speed adjustment parameter, a second current adjustment parameter, and a second voltage adjustment parameter. The second speed adjustment parameter refers to the speed adjustment value used to maintain a stable temperature inside the vehicle by changing the blower operating speed parameter, the second current adjustment parameter refers to the current adjustment value used to maintain a stable temperature inside the vehicle by changing the blower operating current parameter, and the second voltage adjustment parameter refers to the voltage adjustment value used to maintain a stable temperature inside the vehicle by changing the blower operating voltage parameter. Heat dissipation is achieved through the rotation of the blower. The speed of the blower directly affects the heat exchange between the inside and outside of the vehicle. Therefore, the second speed adjustment parameter can be determined based on the predicted heat dissipation demand value. During the operation of the blower, there is a conversion relationship between current, voltage, and speed. Different current and voltage combinations can match different speeds. Therefore, based on the conversion relationship between current, voltage, and speed, the second speed adjustment parameter can be converted into a second current adjustment parameter and a second voltage adjustment parameter.

[0061] When controlling the blower to perform adjustments based on target operating data, the vehicle control unit needs to determine whether the indicator to be adjusted only includes the interior temperature indicator. If the indicator to be adjusted only includes the interior temperature indicator, the blower is controlled to perform adjustments based on the second speed adjustment parameter, the second current adjustment parameter, and the second voltage adjustment parameter in the target operating data. If the indicator to be adjusted also includes the interior temperature indicator and at least one of the current, voltage, and speed indicators, the target operating data is corrected (e.g., using a weighted summation calculation) based on at least one of the corresponding first current adjustment parameter, first voltage adjustment parameter, and first speed adjustment parameter, and the blower is controlled to perform adjustments using the corrected operating parameters.

[0062] This embodiment first determines the predicted heat dissipation demand value based on the predicted vehicle interior temperature and target area temperature, and then converts the corresponding target operating data such as speed, current and voltage based on the predicted heat dissipation demand value, and adjusts the operating status parameters of the blower from the perspective of heat dissipation demand, thereby improving the accuracy of blower adjustment.

[0063] In step S4022, please refer to Figure 5 , that is, determining the predicted heat dissipation demand value based on the target temperature value and the predicted temperature value corresponding to the vehicle interior temperature index, includes the following steps: S40221: Determine an ambient temperature value based on the first measured data, and determine a natural heat dissipation amount based on the predicted temperature value and the ambient temperature value; S40222: Determine a predicted heat dissipation demand value based on the predicted temperature value, the target temperature value, and the natural heat dissipation amount.

[0064] Understandably, when achieving heat exchange between the inside and outside of the vehicle through a blower, the factor of natural heat dissipation also needs to be considered. When the first measured data includes the ambient temperature, the vehicle control unit can parse the ambient temperature from the first measured data and determine the natural heat dissipation heat value based on the predicted in-vehicle temperature and the ambient temperature. When the first measured data does not include the ambient temperature, the vehicle control unit directly obtains the ambient temperature through the external ambient temperature sensor and determines the natural heat dissipation heat value based on the predicted in-vehicle temperature and the ambient temperature. The natural heat dissipation heat refers to the heat value of natural heat dissipation through heat exchange between the predicted in-vehicle temperature and the ambient temperature without considering the effect of the blower operation.

[0065] In practical applications, the interior space of a vehicle is divided into one or more areas, and each area is equipped with an independent blower. When the area is large, the natural heat dissipation can be calculated using the formula, which is as follows: in, Indicates natural heat dissipation; Indicates the natural heat dissipation coefficient; Indicates the first The predicted temperature value of the area at the preset prediction time interval t; Indicates the ambient temperature value.

[0066] Furthermore, the vehicle control unit determines a predicted heat dissipation requirement value based on the predicted temperature value, the target temperature value, and the natural heat dissipation amount. The predicted heat dissipation requirement value can also be calculated using a formula, which is as follows: in, Indicates the first The predicted cooling demand value of the region at the preset prediction time interval t; Indicates natural heat dissipation; represents the specific heat capacity of air; Indicates the air quality of heat dissipation per unit time; Indicates the first The predicted temperature value of the area at the preset prediction time interval t; Indicates the target temperature value.

[0067] This embodiment takes into account the influence of natural heat dissipation and determines the predicted heat dissipation requirement value based on the predicted temperature value, the target temperature value and the calculation of the natural heat dissipation heat, thereby ensuring the accuracy of the predicted heat dissipation requirement value and helping to ensure the effect of subsequent temperature adjustment.

[0068] In step S4023, please refer to Figure 6 , that is, determining the target operating data of the blower based on the predicted heat dissipation demand value, includes the following steps: S40231: Determining a predicted outlet temperature and a predicted inlet temperature of the blower based on a target temperature value corresponding to the vehicle interior temperature index; S40232: Determine target operating data of the blower according to the predicted heat dissipation demand value, the predicted outlet temperature, and the predicted inlet temperature.

[0069] It is understandable that the vehicle control unit needs to consider the outlet temperature and inlet temperature of the blower in the process of determining the target operating data based on the predicted heat dissipation demand value. There is a mapping relationship between the regional temperature inside the vehicle and the outlet temperature and inlet temperature of the blower, that is, the interior temperature of a region corresponds to a group of blower outlet temperature and blower inlet temperature. This embodiment can pre-establish an association data table between different interior temperatures and different groups of blower outlet temperatures and blower inlet temperatures, so as to find the predicted outlet temperature and predicted inlet temperature of the blower corresponding to the target temperature value based on the association data table. The predicted outlet temperature refers to the blower outlet temperature that matches the target temperature value, and the predicted inlet temperature refers to the blower inlet temperature that matches the target temperature value.

[0070] The vehicle control unit can determine the second speed adjustment parameter in the target operation data according to the predicted heat dissipation demand value, the predicted outlet temperature and the predicted inlet temperature, and convert the second current adjustment parameter and the second voltage adjustment parameter based on the second speed adjustment parameter.

[0071] This embodiment calculates the predicted outlet temperature and predicted inlet temperature of the blower based on the target temperature value, and combines the influence of the inlet and outlet temperature difference of the blower to determine the second speed adjustment parameter based on the calculation of the predicted heat dissipation demand value, the predicted outlet temperature and the predicted inlet temperature, thereby ensuring the accuracy of the target operating data, helping to ensure the precise control of subsequent blowers and improving the efficiency of adjustment.

[0072] The present application also provides a vehicle blower control device 10, please refer to Figure 7 , comprising: a data acquisition module 110, configured to acquire N first measured data, where N ≥ 2. An impact analysis module 120, configured to perform data analysis on the N first measured data to determine M second measured data, where the second measured data is first measured data that has an impact on the operating state of the blower, where 1 ≤ M ≤ N. An operation prediction module 130, configured to determine target predicted data based on the second measured data and the measured operating data of the blower. A control and adjustment module 140, configured to control the blower to perform adjustment work based on the target predicted data.

[0073] The present application also provides an electronic device 20, please refer to Figure 8 , including a memory 210 and a processor 220, wherein the memory 210 is used to store computer programs; the processor 220 is used to execute the programs stored in the memory 210 to implement the vehicle blower control method introduced in any embodiment of the present application.

[0074] An embodiment of the present application further provides a vehicle, which includes an electronic device 20 .

[0075] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the vehicle blower control method introduced in any embodiment of the present application is implemented.

[0076] In this application, a plurality refers to two or more.

[0077] The terms "first," "second," "third," "fourth," etc. (if any) in this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence.

[0078] The term "and / or" in this application simply describes an association between related objects, indicating that three possible relationships exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this application generally indicates that the related objects are in an "or" relationship.

[0079] Unless otherwise specified, all steps of this application may be performed sequentially or randomly. For example, "the method includes steps A and B" means that the method may include steps A and B performed sequentially, or may include steps B and A performed sequentially. For example, "the method may also include step C" means that step C may be added to the method in any order. For example, the method may include steps A, B, and C, or steps A, C, and B, or steps C, A, and B, etc.

[0080] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A vehicle blower control method, characterized in that: include: Obtain N first measured data, N ≥ 2; Performing data analysis on N first measured data to determine M second measured data, where the second measured data is first measured data that has an impact on the operating state of the blower, and 1≤M≤N; determining target prediction data based on the second measured data and measured operation data of the blower; Based on the target prediction data, the blower is controlled to perform an adjustment operation.

2. The vehicle blower control method according to claim 1, characterized in that: The performing data analysis on the N first measured data to determine M second measured data includes: Performing data analysis on the N first measured data using a preset impact analysis model to determine an output impact identifier corresponding to each first measured data; The output impact identifier is the first measured data with an impact identifier, and is determined as the second measured data.

3. The vehicle blower control method according to claim 1, characterized in that: The first measured data includes environmental data and vehicle status data; The environmental data includes at least one of an environmental temperature value, an environmental humidity value, and an environmental wind speed value; The vehicle status data includes at least one of a battery power status value and an in-vehicle temperature value.

4. The vehicle blower control method according to claim 1, characterized in that: The target prediction data includes at least one of predicted operation data of the blower and predicted vehicle interior temperature; The predicted operation data of the blower is output data obtained by processing the second measured data and the measured operation data of the blower based on a preset operation prediction model; The predicted in-vehicle temperature is output data obtained by processing the second measured data, the measured operation data of the blower, and the in-vehicle temperature value based on a preset temperature prediction model.

5. The vehicle blower control method according to claim 1, characterized in that: The target prediction data includes a prediction index value corresponding to at least one prediction index; the prediction index includes a current index, a voltage index, a speed index and an in-vehicle temperature index; The step of controlling the blower to perform the adjustment operation based on the target prediction data includes: If the prediction indicator value corresponding to the prediction indicator is greater than the preset indicator threshold corresponding to the prediction indicator, the prediction indicator is determined as the indicator to be adjusted; Obtain a target indicator value corresponding to the indicator to be adjusted, and control the blower to perform adjustment work based on the target indicator value corresponding to the indicator to be adjusted, and the target indicator value corresponding to the indicator to be adjusted is less than the preset indicator threshold.

6. The vehicle blower control method according to claim 5, characterized in that: The index to be adjusted includes an in-vehicle temperature index; The step of obtaining a target indicator value corresponding to the indicator to be adjusted, and controlling the blower to perform an adjustment operation based on the target indicator value corresponding to the indicator to be adjusted, includes: Obtaining a target temperature value corresponding to the vehicle interior temperature index; Determining a predicted heat dissipation demand value based on a target temperature value and a predicted temperature value corresponding to the vehicle interior temperature index; Based on the predicted heat dissipation demand value, target operation data of the blower is determined, and based on the target operation data, the blower is controlled to perform an adjustment operation.

7. The vehicle blower control method according to claim 6, characterized in that: The step of determining a predicted heat dissipation requirement value based on a target temperature value and a predicted temperature value corresponding to the vehicle interior temperature index includes: Determine the ambient temperature value according to the first measured data, and determine the amount of natural heat dissipation according to the predicted temperature value and the ambient temperature value; A predicted heat dissipation demand value is determined according to the predicted temperature value, the target temperature value and the natural heat dissipation amount.

8. The vehicle blower control method according to claim 6, characterized in that: The step of determining target operating data of the blower based on the predicted heat dissipation demand value includes: determining a predicted outlet temperature and a predicted inlet temperature of the blower based on a target temperature value corresponding to the vehicle interior temperature index; Target operating data of the blower is determined according to the predicted heat dissipation demand value, the predicted outlet temperature, and the predicted inlet temperature.

9. A vehicle blower control device, characterized in that: include: A data acquisition module is used to acquire N first measured data, where N is greater than or equal to 2; an impact analysis module, configured to perform data analysis on the N first measured data to determine M second measured data, where the second measured data is the first measured data that has an impact on the operating state of the blower, and 1≤M≤N; an operation prediction module, configured to determine target prediction data based on the second measured data and measured operation data of the blower; A control and adjustment module is used to control the blower to perform adjustment work based on the target prediction data.

10. An electronic device, characterized in that: comprising a processor and a memory, wherein Memory for storing computer programs; The processor is configured to execute a program stored in the memory to implement the vehicle blower control method according to any one of claims 1 to 8.

11. A vehicle, characterized in that: The vehicle includes the electronic device according to claim 10.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the vehicle blower control method according to any one of claims 1 to 8 is implemented.

Images