Control method, device, vehicle, processor and electronic device for vehicle air conditioner

Abstract

The present invention discloses a control method, device, vehicle, processor and electronic device for a vehicle air conditioner. The method comprises: detecting the vehicle running state, the environmental state and the working state of the vehicle air conditioner during the actual working process to obtain a target state sequence; analyzing the target state sequence using a target network model to obtain a target prediction result; performing a state evaluation on the target prediction result according to preset state indicators of multiple dimensions to obtain an evaluation result; and adjusting the target control parameters of the vehicle air conditioner based on the evaluation result. The present invention solves the technical problems in the related art that the adjustment process is cumbersome and the adjustment efficiency is low due to the fact that the vehicle air conditioner parameters are affected by multiple test factors.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle thermal management, and in particular to a control method, device, vehicle, processor and electronic device for a vehicle air conditioner. Background Art

[0002] As vehicles become more intelligent, people have higher and higher requirements for thermal comfort in vehicles. In related technologies, the vehicle's air conditioning system usually maintains the temperature of the passenger compartment at around the preset value, which cannot adapt to the passengers' comfort. The adjustment of the preset value needs to be completed through experiments, but the adjustment process is easily affected by the test environment, test season, and test personnel, which leads to cumbersome adjustment process of vehicle air conditioning parameters and low adjustment efficiency.

[0003] To the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present invention provide a control method, device, vehicle, processor and electronic device for a vehicle air conditioner, so as to at least solve the technical problems in the related art that the adjustment process is cumbersome and the adjustment efficiency is low due to the vehicle air conditioner parameters being affected by various test factors.

[0005] According to one embodiment of the present invention, a control method for a vehicle air conditioner is provided, comprising: detecting a vehicle operating state, an environmental state and a working state of the vehicle air conditioner during actual working of the vehicle air conditioner to obtain a target state sequence; analyzing the target state sequence using a target network model to obtain a target prediction result, wherein the target prediction result is used to represent a predicted environmental state of a target object in the vehicle, and the target network model is a network model obtained by machine learning training using multiple groups of sample data; performing a state evaluation on the target prediction result according to preset state indicators of multiple dimensions to obtain an evaluation result, wherein the evaluation result is used to represent a state prediction level applicable to the target object; and adjusting a target control parameter of the vehicle air conditioner based on the evaluation result, wherein the target control parameter is used to control the working state of the vehicle air conditioner.

[0006] Optionally, the control method of the vehicle air conditioner also includes: obtaining a sampling data set and a verification data set; using the sampling data set to perform multiple rounds of training on the initial network model to obtain multiple candidate network models; and using the verification data set to determine the target network model from the multiple candidate network models.

[0007] Optionally, using a verification data set to determine a target network model from multiple candidate network models includes: using a three-dimensional virtual model to annotate the verification data set to obtain a target annotation result, wherein the three-dimensional virtual model is used to obtain a simulated environmental state of a target object in a vehicle; using multiple candidate network models to analyze the verification data set to obtain multiple candidate prediction results; comparing the target annotation result with the multiple candidate prediction results to obtain a comparison result, wherein the comparison result is used to represent an error between the target annotation result and the multiple candidate prediction results; and selecting a target network model from multiple candidate network models based on the comparison result.

[0008] Optionally, a state evaluation is performed on the target prediction result according to preset state indicators of multiple dimensions, and the evaluation result includes: obtaining a preset evaluation rule corresponding to the preset state indicator, wherein the preset evaluation rule is used to record the correspondence between the environmental state interval of the target object and the preset state level; and determining the evaluation result of the target prediction result based on the preset evaluation rule.

[0009] Optionally, adjusting the target control parameters of the vehicle air conditioner based on the evaluation results includes: obtaining an expected state level of the target object; and continuously adjusting the target control parameters of the vehicle air conditioner based on the evaluation results, taking the expected state level as a reference.

[0010] Optionally, the vehicle running state includes the vehicle speed; the environmental state of the vehicle air conditioner includes at least one of the following: vehicle body ambient temperature, light intensity, outlet air temperature and outlet air humidity; the working state of the vehicle air conditioner includes at least one of the following: the damper state of the air conditioning system, internal and external circulation mode; the target prediction result includes the air temperature, air humidity and average wind speed within a preset range around the target object; the target control parameters include at least one of the following parameter information: the damper opening of the vehicle air conditioner, the blower air volume, the compressor speed and the outlet angle.

[0011] According to one embodiment of the present invention, there is also provided a control device for a vehicle air conditioner, comprising: a detection module, used to detect the vehicle operating state, the environmental state and the working state of the vehicle air conditioner during the actual working process, and obtain a target state sequence; an analysis module, used to analyze the target state sequence using a target network model, and obtain a target prediction result, wherein the target prediction result is used to represent the predicted environmental state of the target object in the vehicle, and the target network model is a network model obtained by machine learning training using multiple groups of sample data; an evaluation module, used to perform a state evaluation on the target prediction result according to preset state indicators of multiple dimensions, and obtain an evaluation result, wherein the evaluation result is used to represent the state prediction level applicable to the target object; an adjustment module, used to adjust the target control parameters of the vehicle air conditioner based on the evaluation result, wherein the target control parameters are used to control the working state of the vehicle air conditioner.

[0012] Optionally, the control device of the vehicle air conditioner also includes: an acquisition module for acquiring a sampling data set and a verification data set; a training module for performing multiple rounds of training on the sampling data set using the initial network model to obtain multiple candidate network models; and a determination module for determining a target network model from multiple candidate network models using the verification data set.

[0013] Optionally, the determination module is also used to: use a three-dimensional virtual model to annotate a verification data set to obtain a target annotation result, wherein the three-dimensional virtual model is used to obtain a simulated environmental state of a target object in a vehicle; use multiple candidate network models to analyze the verification data set to obtain multiple candidate prediction results; compare the target annotation result with the multiple candidate prediction results to obtain a comparison result, wherein the comparison result is used to indicate an error between the target annotation result and the multiple candidate prediction results; and select a target network model from multiple candidate network models based on the comparison result.

[0014] Optionally, the evaluation module is also used to: obtain preset evaluation rules corresponding to preset state indicators, wherein the preset evaluation rules are used to record the correspondence between the environmental state interval of the target object and the preset state level; and determine the evaluation result of the target prediction result based on the preset evaluation rules.

[0015] Optionally, the adjustment module is further used to: obtain the expected state level of the target object; and continuously adjust the target control parameters of the vehicle air conditioner based on the evaluation results, taking the expected state level as a reference.

[0016] According to one embodiment of the present invention, a vehicle is provided, and the vehicle is used to execute any of the above-mentioned methods for controlling a vehicle air conditioner.

[0017] According to one embodiment of the present invention, a processor is further provided, and the processor is used to run a program, wherein the program is configured to execute any of the above-mentioned vehicle air conditioner control methods when running.

[0018] According to one embodiment of the present invention, there is also provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute any of the above-mentioned vehicle air conditioner control methods.

[0019] In an embodiment of the present invention, the environmental state around the vehicle occupants is obtained through the vehicle operating state, the environmental state and the working state of the vehicle air-conditioning detected by the vehicle air-conditioning during actual operation. There is no need to calibrate the vehicle air-conditioning through experiments, and the above environmental state can be evaluated according to multiple human comfort indicators. The control parameters of the vehicle air-conditioning are further adjusted to ensure that the control parameters of the vehicle air-conditioning can accurately reflect the comfort of the human body, thereby achieving the purpose of adjusting the vehicle air-conditioning parameters according to multiple human comfort indicators and predicted environmental states, thereby achieving the technical effect of simplifying the adjustment process of the vehicle air-conditioning parameters and improving the adjustment efficiency, and further solving the technical problems in the related art that the adjustment process is cumbersome and the adjustment efficiency is low due to the vehicle air-conditioning parameters being affected by multiple test factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0021] Figure 1 is a flow chart of a method for controlling a vehicle air conditioner according to one embodiment of the present invention;

[0022] Figure 2 is a schematic diagram of an initial network model training process according to one embodiment of the present invention;

[0023] Figure 3 is a schematic diagram of a method for controlling a vehicle air conditioner according to one embodiment of the present invention;

[0024] Figure 4 The present invention is a structural block diagram of a vehicle air conditioner control device according to one embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] According to an embodiment of the present invention, a method for controlling a vehicle air conditioner is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0028] The method embodiment can be executed in an electronic device or similar computing device containing a memory and a processor in a vehicle. Taking running on a vehicle terminal as an example, the vehicle terminal may include one or more processors (processors may include but are not limited to central processing units (CPU), graphics processing units (GPU), digital signal processing (DSP) chips, microprocessors (MCU), programmable logic devices (Field Programmable Gate Array, FPGA), neural network processors (Neural-network Processor Unit, NPU), tensor processors (TensorProcessing Unit, TPU), artificial intelligence (Artificial Intelligence, AI) type processors and other processing devices) and a memory for storing data. Optionally, the above-mentioned vehicle terminal may also include a transmission device for communication functions. It can be understood by those of ordinary skill in the art that the above-mentioned structural description is only for illustration and does not limit the structure of the above-mentioned vehicle terminal. For example, the vehicle terminal may also include more or fewer components than the above-mentioned structural description, or have a configuration different from the above-mentioned structural description.

[0029] The memory can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the vehicle air conditioner control method in the embodiment of the present invention. The processor executes various functional applications and data processing by running the computer program stored in the memory, that is, the above-mentioned vehicle air conditioner control method is realized. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include a memory remotely arranged relative to the processor, and these remote memories can be connected to the vehicle terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0030] The transmission device is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the vehicle terminal. In one example, the transmission device includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet wirelessly.

[0031] Figure 1 is a flow chart of a method for controlling a vehicle air conditioner according to one embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0032] Step S12, detecting the vehicle running state, the environmental state and the working state of the vehicle air conditioner during the actual working process, and obtaining a target state sequence;

[0033] Step S14, analyzing the target state sequence using the target network model to obtain a target prediction result, wherein the target prediction result is used to represent the predicted environmental state of the target object in the vehicle, and the target network model is a network model obtained by machine learning training using multiple sets of sample data;

[0034] Step S16, performing a state evaluation on the target prediction result according to preset state indicators of multiple dimensions to obtain an evaluation result, wherein the evaluation result is used to indicate a state prediction level applicable to the target object;

[0035] Step S18, adjusting the target control parameters of the vehicle air conditioner based on the evaluation result, wherein the target control parameters are used to control the working state of the vehicle air conditioner.

[0036] Optionally, the vehicle running state includes the vehicle speed; the environmental state of the vehicle air conditioner includes at least one of the following: vehicle body ambient temperature, light intensity, outlet air temperature and outlet air humidity; the working state of the vehicle air conditioner includes at least one of the following: the damper state of the air conditioning system, internal and external circulation mode; the target prediction result includes the air temperature, air humidity and average wind speed within a preset range around the target object; the target control parameters include at least one of the following parameter information: the damper opening of the vehicle air conditioner, the blower air volume, the compressor speed and the outlet angle.

[0037] Specifically, the running state of the above-mentioned vehicle, the environmental state and the working state of the vehicle air conditioner can be collected by sensors.

[0038] The target state sequence can be obtained by processing the running state of the vehicle, the environmental state and the working state of the vehicle air conditioner using methods such as the inverse M sequence and the random number sequence.

[0039] The target object is the vehicle occupant. By analyzing the target state sequence using the target network model trained by machine learning, the air temperature, air humidity and average wind speed within the preset range of the vehicle occupant can be obtained. For example, the target network model trained by machine learning can be used to analyze the vehicle body environment temperature of 30°C and the light intensity of 15000W / m 2 , the vehicle speed is 60km / h, the air door state of the air conditioning system is open, the internal and external circulation mode is the internal circulation mode, the air temperature at the air outlet is 26℃ and the air humidity at the air outlet is 20%. It can be obtained that the air temperature within a radius of 4mm around the vehicle occupants is 28℃, the air humidity is 22% and the average wind speed is 0.2m / s.

[0040] The preset state indicators of the above-mentioned multiple dimensions are multiple human comfort indicators. By using multiple human comfort indicators to perform state evaluation on the target prediction results, a state prediction level suitable for vehicle occupants can be obtained, which is used to predict the comfort of vehicle occupants.

[0041] The vehicle occupant's state prediction level can be used to adjust parameters such as the air door opening, blower air volume, compressor speed, and air outlet angle of the vehicle air conditioner, thereby controlling the working state of the vehicle air conditioner.

[0042] Based on the above steps S12 to S18, the environmental state around the vehicle occupants is obtained through the vehicle operating state, the environmental state and the working state of the vehicle air-conditioning detected by the vehicle air-conditioning during actual operation. There is no need to calibrate the vehicle air-conditioning through experiments, and the above environmental state can be evaluated according to multiple human comfort indicators. The control parameters of the vehicle air-conditioning are further adjusted to ensure that the control parameters of the vehicle air-conditioning can accurately reflect the comfort of the human body, thereby achieving the purpose of adjusting the vehicle air-conditioning parameters according to multiple human comfort indicators and the predicted actual environmental state, thereby achieving the technical effect of simplifying the adjustment process of the vehicle air-conditioning parameters and improving the adjustment efficiency, and further solving the technical problems in the related technology that the adjustment process is cumbersome and the adjustment efficiency is low due to the vehicle air-conditioning parameters being affected by various test factors.

[0043] Optionally, the vehicle air conditioner control method further includes:

[0044] Step S131, obtaining a sampling data set and a verification data set;

[0045] Step S132, using the sampled data set to perform multiple rounds of training on the initial network model to obtain multiple candidate network models;

[0046] Step S133, using the verification data set to determine the target network model from multiple candidate network models.

[0047] Specifically, the vehicle operating status, environmental status and working status data of the vehicle air conditioner under multiple different working conditions are obtained, and the above data are divided into a sampling data set and a verification data set, wherein the working conditions of the data in the sampling data set are different from those of the data in the verification data set.

[0048] The initial network model can be a nonlinear autoregressive (narxnet) neural network model, including an input layer, a hidden layer and an output layer, wherein the number of layers of the input layer is determined according to the number of data in the input data set, the hidden layer is 5-15 layers, and the number of layers of the output layer is determined according to the number of data in the output data set. A closed-loop structure is selected, the time delay is 2-5 steps, and the training function can select a Bayesian regularization algorithm (trainbr) with strong generalization energy. The sampling data set is used as the input layer, and the initial network model is trained N times to obtain N candidate network models. Finally, a network model is determined as the target network model from the N candidate network models using the verification data set. For example, the sampling data set is used as the input layer, and the initial network model is trained 1000 times, and candidate network model 1, candidate network model 2, ..., candidate network model 1000 can be obtained. Finally, a candidate network model i is determined as the target network model from the 1000 candidate network models using the verification data set.

[0049] Based on the above steps S131 to S133, the initial network model is trained through the sampling data set, and the trained candidate network models are screened through the verification data set to accurately obtain the target network model and improve the prediction accuracy of the actual environmental state.

[0050] Optionally, in step S133, determining the target network model from a plurality of candidate network models using the verification data set includes:

[0051] Step S1331, annotating the verification data set using the three-dimensional virtual model to obtain a target annotation result, wherein the three-dimensional virtual model is used to obtain a simulated environment state where the target object in the vehicle is located;

[0052] Step S1332, using multiple candidate network models to analyze the verification data set to obtain multiple candidate prediction results;

[0053] Step S1333, comparing the target labeling result with the multiple candidate prediction results to obtain a comparison result, wherein the comparison result is used to indicate the error between the target labeling result and the multiple candidate prediction results;

[0054] Step S1334: selecting a target network model from multiple candidate network models based on the comparison result.

[0055] Specifically, the three-dimensional virtual model is a three-dimensional (3D) model of the vehicle and the occupant, wherein the 3D model is a mathematical model containing multiple parameters, and different simulated environmental states around the vehicle occupants can be obtained by changing the parameters. The simulated environmental state around the vehicle occupants can be obtained by annotating the verification data set using the three-dimensional virtual model, including the simulated environmental data around the vehicle occupants, without the need to obtain the environmental state around the occupants through experiments, thereby simplifying the process of obtaining the environmental data around the vehicle occupants.

[0056] By analyzing the validation data set using the multiple candidate network models obtained through training, candidate prediction results can be obtained, including the predicted air temperature, air humidity, and average wind speed around the vehicle occupants. For example, by analyzing the validation data set using the candidate network models 1, 2, ..., and 1000 obtained through training, multiple predicted environmental states around the vehicle occupants can be obtained, including air temperature 1, air humidity 1, and average wind speed 1 around the vehicle occupants, air temperature 2, air humidity 2, and average wind speed 2 around the vehicle occupants, ..., air temperature 1000, air humidity 1000, and average wind speed 1000 around the vehicle occupants.

[0057] By comparing the target annotation result with multiple candidate prediction results, multiple errors between the target annotation result and the multiple candidate prediction results can be obtained. For example, by comparing the simulated environment state around the vehicle occupant obtained by the three-dimensional virtual model with the predicted environment state around the vehicle occupant obtained by 1000 candidate network models, 1000 errors between the simulated environment state around the vehicle occupant and the predicted environment state around the 1000 vehicle occupants can be obtained, which are error 1, error 2, ..., error 1000.

[0058] After obtaining the comparison results, the network model with the smallest error is selected from the multiple candidate network models as the target network model. After obtaining the comparison results, the network model i with the smallest error is selected from the 1000 errors between the simulated environmental state around the vehicle occupants and the predicted environmental state around the 1000 vehicle occupants as the target network model.

[0059] Based on the above steps S1331 to S1334, the verification data set is annotated by using the three-dimensional model of the vehicle and the occupant to obtain the real environmental state corresponding to different verification data sets, and the error between the real environmental state and the candidate predicted environmental state is used to improve the selection accuracy of the target network model, so that the environmental state of the occupant calculated by the target network model is closer to the real environmental state.

[0060] Figure 2 FIG. 1 is a schematic diagram of a process for determining a target network model according to one embodiment of the present invention. Figure 2 As shown in Figure 1, the process of determining the target network model mainly includes three processes, namely training, verification and comparison.

[0061] Firstly, the initial network model is trained multiple times using the running status of the vehicle, the environmental status and the working status of the vehicle air conditioner in the sampling data set, and multiple candidate network models can be obtained.

[0062] Furthermore, by annotating the validation dataset using the three-dimensional models of the vehicle and the occupants, the target annotation results can be obtained, thereby obtaining the simulated environmental state around the vehicle occupants.

[0063] Subsequently, the trained multiple candidate network models are verified using the vehicle body ambient temperature, light intensity, vehicle speed, air door status of the air conditioning system, internal and external circulation modes, air outlet air temperature, and air outlet air humidity in the verification data set, and multiple candidate prediction results can be obtained, thereby obtaining multiple predicted environmental states around the vehicle occupants.

[0064] Finally, the target labeling result is compared with multiple candidate prediction results, that is, the simulated environmental state around the vehicle occupants is compared with multiple predicted environmental states around the vehicle occupants, and multiple errors can be obtained. The candidate network model corresponding to the smallest error is selected from the multiple errors, and the candidate network model corresponding to the smallest error is determined as the target network model.

[0065] Optionally, in step S16, the target prediction result is evaluated according to preset status indicators of multiple dimensions, and the evaluation results obtained include:

[0066] Step S161, obtaining a preset evaluation rule corresponding to a preset state indicator, wherein the preset evaluation rule is used to record the corresponding relationship between the environmental state interval of the target object and the preset state level;

[0067] Step S162, determining the evaluation result of the target prediction result based on the preset evaluation rules.

[0068] Specifically, the preset status indicators of multiple dimensions are multiple human comfort indicators, which may include Predicted Mean Vote (PMV), Dynamic thermal sensation (DTS), and comfort (Zhang-comfort). Among them, PMV is calculated by air temperature, average radiant temperature, air velocity and relative humidity environmental parameters as well as metabolic rate and clothing thermal resistance, and is divided into 7 comfort evaluation levels, namely -3 (cold), -2 (cool), -1 (slightly cool), 0 (comfortable), +1 (slightly warm), +2 (warm), +3 (hot).

[0069] The preset evaluation rule is used to record the correspondence between the target object's environmental state interval and the preset state level. For example, the preset evaluation rule PMV is used to record the correspondence between the target object's environmental state interval and the preset state level of PMV; the preset evaluation rule DTS is used to record the correspondence between the target object's environmental state interval and the preset state level of DTS; the preset evaluation rule Zhang-comfort is used to record the correspondence between the target object's environmental state interval and the preset state level of Zhang-comfort.

[0070] Obtain the preset evaluation rule PMV corresponding to the preset status rule indicator PMV, the preset evaluation rule DTS corresponding to the preset status rule indicator DTS, and the preset evaluation rule Zhang-comfort corresponding to the preset status rule indicator Zhang-comfort.

[0071] Determine the interval in which the target prediction result is located, and determine the state preset level PMV, state preset level DTS and state preset level Zhang-comfort corresponding to the interval in which the target prediction result is located in the preset evaluation rule PMV, the preset evaluation rule DTS and the preset evaluation rule Zhang-comfort.

[0072] The above-mentioned state preset level PMV, state preset level DTS and state preset level Zhang-comfort may be processed in an average or weighted manner to obtain an evaluation result.

[0073] Specifically, the correspondence between the environmental state interval where the above target object is located and the preset status levels of PMV can be shown in Table 1. According to Table 1, when the air temperature (Temperature, T) is in the interval of A1 ≤ T < A2, the air humidity (Relative Humidity, RH) is in the interval of B1 ≤ RH < B2, and the average wind speed (V) is in the interval of C1 ≤ V < C2, the corresponding preset status level is -3, indicating that the target object feels cold and extremely uncomfortable; when the air temperature is in the interval of A2 ≤ T < A3, the air humidity is in the interval of B2 ≤ RH < B3, and the average wind speed is in the interval of C2 ≤ V < C3, the corresponding preset status level is -2, indicating that the target object feels cool and uncomfortable; when the air temperature is in the interval of A3 ≤ T < A4, the air humidity is in the interval of B3 ≤ RH < B4, and the average wind speed is in the interval of C3 ≤ V < C4, the corresponding preset status level is -1, indicating that the target object feels slightly cool and relatively comfortable; when the air temperature is in the interval of A4 ≤ T < A5, the air humidity is in the interval of B4 ≤ RH < B5, and the average wind speed is in the interval of C4 ≤ V < C5, the corresponding preset status level is 0, indicating that the target object feels comfortable; when the air temperature is in the interval of A5 ≤ T < A6, the air humidity is in the interval of B5 ≤ RH < B6, and the average wind speed is in the interval of C5 ≤ V < C6, the corresponding preset status level is 1, indicating that the target object feels slightly warm and relatively comfortable; when the air temperature is in the interval of A6 ≤ T < A7, the air humidity is in the interval of B6 ≤ RH < B7, and the average wind speed is in the interval of C6 ≤ V < C7, the corresponding preset status level is 2, indicating that the target object feels warm and uncomfortable; when the air temperature is in the interval of A7 ≤ T < A8, the air humidity is in the interval of B7 ≤ RH < B8, and the average wind speed is in the interval of C7 ≤ V < C8, the corresponding preset status level is 3, indicating that the target object feels hot and extremely uncomfortable.

[0074] Table 1 Correspondence Table between Environmental State Interval where the Target Object is Located and Preset Status Levels of PMV

[0075]

[0076] According to Table 1, the preset status level of PMV corresponding to the target prediction result can be determined. For example, when in the target prediction result, the air temperature is in the interval of A1 ≤ T < A2, the air humidity is in the interval of B1 ≤ RH < A2, and the average wind speed is in the interval of C1 ≤ V < C2, according to Table 1, the preset status level of PMV corresponding to this target prediction result is -3, indicating that the target object feels cold and extremely uncomfortable.

[0077] It should be noted that Table 1 is only a schematic illustration of the correspondence between the environmental state interval in which the target object is located and the preset state levels of PMV. The environmental state interval in which the target object is located and the corresponding preset state levels are not limited to Table 1, and there may be other possible correspondence relationships.

[0078] The correspondence between the environmental state interval in which the target object is located and the preset state levels of the preset state indicators Zhang - comfort and DTS is similar to that in Table 1 and will not be elaborated here.

[0079] The preset state levels of PMV, DTS, and Zhang - comfort corresponding to the interval where the target prediction result is located can be processed by averaging or weighting to obtain an evaluation result.

[0080] For example, if the preset state levels of PMV, DTS, and Zhang - comfort corresponding to the interval where the target prediction result is located are - 3, - 2, and - 1 respectively, the three preset state levels can be averaged to obtain an evaluation result with a preset state level of - 2, indicating that the vehicle occupants feel cold and uncomfortable.

[0081] Based on the above steps S161 to S162, by obtaining the correspondence between the environmental state around the occupant and the preset state levels of each human comfort index, and then determining the occupant comfort feelings corresponding to multiple human comfort indexes based on this correspondence, so as to adjust the parameters of the air conditioner based on the comfort feelings of the occupant, make the environmental temperature adapt to the needs of the occupant, and thus greatly improve the comfort experience of the occupant.

[0082] Optionally, in step S18, adjusting the target control parameters of the vehicle air conditioner based on the evaluation result includes:

[0083] Step S181, obtaining the expected state level of the target object;

[0084] Step S182, taking the expected state level as a reference benchmark, continuously adjusting the target control parameters of the vehicle air conditioner based on the evaluation result.

[0085] Specifically, the expected state level of the target object represents the expected state level obtained according to the habits of the target object. For example, when the air temperature is A1℃, in the interval A1 ≤ T < A2, the air humidity is B1%, in the interval B1 ≤ RH < B2, and the average wind speed is C1m / s, in the interval C1 ≤ V < C2, the corresponding preset state level is - 1, indicating that the occupant feels slightly cold and relatively comfortable. And in this environment, occupant 1 feels comfortable. Therefore, for occupant 1, the expected state level corresponding to this environment is 0.

[0086] The target control parameters of the vehicle air conditioner are continuously adjusted based on the state prediction level, taking the state prediction level of the target object as a reference. For example, when the state prediction level is 0, occupant 1 still feels a little cool, and the state prediction level of occupant 1 is 1. The throttle opening and compressor speed of the vehicle air conditioner can be reduced based on the state prediction level of occupant 1, so that the ambient temperature around occupant 1 increases, thereby making occupant 1 feel comfortable.

[0087] Based on the above steps S181 to S182, by evaluating the environmental conditions around the occupants according to the occupants' habits and multiple human comfort indicators, the control parameters of the vehicle air conditioner are further adjusted to ensure that the control parameters of the vehicle air conditioner can accurately reflect human comfort.

[0088] Figure 3 is a schematic diagram of a method for controlling a vehicle air conditioner according to one embodiment of the present invention, such as Figure 2 As shown, the control method of the vehicle air conditioner mainly includes the following execution steps:

[0089] First, the vehicle body ambient temperature, light intensity, vehicle speed, throttle status, internal and external circulation modes, air outlet air temperature and air outlet air humidity are inputted through the working condition data input module, and the working condition data are divided into a sampling data set and a verification data set. The initial network model is trained multiple times using the sampling data set to obtain multiple candidate network models, and the verification data set is analyzed using multiple candidate network models to obtain multiple candidate prediction results. Secondly, the verification data set is annotated using a three-dimensional virtual model to obtain a simulated human body environment in the vehicle, including air temperature, air humidity and average wind speed. Again, the simulated human body environment in the vehicle is compared with multiple candidate prediction results to determine the target network model; then, the vehicle body ambient temperature, light intensity, vehicle speed and other data in the actual working process are collected through sensors, and the target network model is used to analyze the vehicle body ambient temperature, light intensity, vehicle speed and other data in the actual working process to obtain the predicted air temperature, air humidity and average wind speed around the human body; then, the predicted air temperature, air humidity and average wind speed around the human body are evaluated by the human body comfort calculation module to obtain the human body's comfort feeling, wherein the human body comfort calculation module includes sub-modules reflecting different groups of people and sub-modules reflecting clothing resistance index; finally, based on the human body's comfort feeling, the air conditioning control module controls the heating, ventilation and air conditioning (HVAC) actuator to adjust the damper opening, blower air volume, compressor speed and outlet angle of the vehicle air conditioner to make the vehicle's environmental state meet the comfort requirements of the target object.

[0090] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, or by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a vehicle-mounted terminal to execute the methods described in each embodiment of the present invention.

[0091] In an embodiment of the present invention, a control device for a vehicle air conditioner is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0092] Figure 4 is a structural block diagram of a vehicle air conditioner control device according to one embodiment of the present invention. Figure 4 As shown, the device comprises:

[0093] The detection module 401 is used to detect the vehicle operation state, the environmental state and the working state of the vehicle air conditioner during the actual working process, and obtain the target state sequence; the analysis module 402 is used to analyze the target state sequence using the target network model to obtain the target prediction result, wherein the target prediction result is used to represent the predicted environmental state of the target object in the vehicle, and the target network model is a network model obtained by machine learning training using multiple groups of sample data; the evaluation module 403 is used to perform state evaluation on the target prediction result according to preset state indicators of multiple dimensions to obtain an evaluation result, wherein the evaluation result is used to represent the state prediction level applicable to the target object; the adjustment module 404 is used to adjust the target control parameters of the vehicle air conditioner based on the evaluation result, wherein the target control parameters are used to control the working state of the vehicle air conditioner.

[0094] Optionally, the control device of the vehicle air conditioner also includes: an acquisition module 405, used to acquire a sampling data set and a verification data set; a training module 406, used to perform multiple rounds of training on the sampling data set using the initial network model to obtain multiple candidate network models; a determination module 407, used to determine the target network model from multiple candidate network models using the verification data set.

[0095] Optionally, the determination module 407 is also used to: use the three-dimensional virtual model to annotate the verification data set to obtain a target annotation result, wherein the three-dimensional virtual model is used to obtain the simulated environmental state of the target object in the vehicle; use multiple candidate network models to analyze the verification data set to obtain multiple candidate prediction results; compare the target annotation result with the multiple candidate prediction results to obtain a comparison result, wherein the comparison result is used to represent the error between the target annotation result and the multiple candidate prediction results; select the target network model from the multiple candidate network models based on the comparison result.

[0096] Optionally, the evaluation module 403 is also used to: obtain preset evaluation rules corresponding to preset state indicators, wherein the preset evaluation rules are used to record the correspondence between the environmental state interval of the target object and the preset state level; and determine the evaluation result of the target prediction result based on the preset evaluation rules.

[0097] Optionally, the adjustment module 404 is further used to: obtain the expected state level of the target object; and continuously adjust the target control parameters of the vehicle air conditioner based on the evaluation results, taking the expected state level as a reference.

[0098] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0099] According to one embodiment of the present invention, a vehicle is provided, and the vehicle is used to execute the steps in any of the above method embodiments.

[0100] Optionally, in this embodiment, the vehicle may be configured to perform the following steps by a computer program:

[0101] Step S1, detecting the vehicle running state, the environmental state and the working state of the vehicle air conditioner during the actual working process, and obtaining a target state sequence;

[0102] Step S2, using the target network model to analyze the target state sequence to obtain a target prediction result, wherein the target prediction result is used to represent the predicted environmental state of the target object in the vehicle, and the target network model is a network model obtained by machine learning training using multiple sets of sample data;

[0103] Step S3, performing a state evaluation on the target prediction result according to preset state indicators of multiple dimensions to obtain an evaluation result, wherein the evaluation result is used to indicate a state prediction level applicable to the target object;

[0104] Step S4, adjusting the target control parameters of the vehicle air conditioner based on the evaluation result, wherein the target control parameters are used to control the working state of the vehicle air conditioner.

[0105] According to one embodiment of the present invention, a processor is further provided, and the processor is used to run a program, wherein the program is configured to execute the steps of any of the above method embodiments when running.

[0106] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0107] Step S1, detecting the vehicle running state, the environmental state and the working state of the vehicle air conditioner during the actual working process, and obtaining a target state sequence;

[0108] Step S2, using the target network model to analyze the target state sequence to obtain a target prediction result, wherein the target prediction result is used to represent the predicted environmental state of the target object in the vehicle, and the target network model is a network model obtained by machine learning training using multiple sets of sample data;

[0109] Step S3, performing a state evaluation on the target prediction result according to preset state indicators of multiple dimensions to obtain an evaluation result, wherein the evaluation result is used to indicate a state prediction level applicable to the target object;

[0110] Step S4, adjusting the target control parameters of the vehicle air conditioner based on the evaluation result, wherein the target control parameters are used to control the working state of the vehicle air conditioner.

[0111] According to one embodiment of the present invention, there is further provided an electronic device, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0112] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0113] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0114] Step S1, detecting the vehicle running state, the environmental state and the working state of the vehicle air conditioner during the actual working process, and obtaining a target state sequence;

[0115] Step S2, using the target network model to analyze the target state sequence to obtain a target prediction result, wherein the target prediction result is used to represent the predicted environmental state of the target object in the vehicle, and the target network model is a network model obtained by machine learning training using multiple sets of sample data;

[0116] Step S3, performing a state evaluation on the target prediction result according to preset state indicators of multiple dimensions to obtain an evaluation result, wherein the evaluation result is used to indicate a state prediction level applicable to the target object;

[0117] Step S4, adjusting the target control parameters of the vehicle air conditioner based on the evaluation result, wherein the target control parameters are used to control the working state of the vehicle air conditioner.

[0118] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0119] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0120] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0121] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0122] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0123] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0124] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions for a vehicle terminal to execute all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0125] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for controlling a vehicle air conditioner, characterized in that: include: Detecting the vehicle running state, the environmental state and the working state of the vehicle air conditioner during the actual working process to obtain a target state sequence; Analyzing the target state sequence using a target network model to obtain a target prediction result, wherein the target prediction result is used to represent the predicted environmental state of the target object in the vehicle, and the target network model is a network model obtained by machine learning training using multiple sets of sample data; Performing a state evaluation on the target prediction result according to preset state indicators of multiple dimensions to obtain an evaluation result, wherein the evaluation result is used to indicate a state prediction level applicable to the target object; The target control parameter of the vehicle air conditioner is adjusted based on the evaluation result, wherein the target control parameter is used to control the working state of the vehicle air conditioner.

2. The control method of the vehicle air conditioner according to claim 1, characterized in that: The method further comprises: Get the sampling data set and the validation data set; Using the sampled data set to perform multiple rounds of training on the initial network model to obtain multiple candidate network models; The target network model is determined from the multiple candidate network models using the verification data set.

3. The control method of the vehicle air conditioner according to claim 2, characterized in that: Determining the target network model from the plurality of candidate network models using the verification data set includes: Annotating the verification data set using a three-dimensional virtual model to obtain a target annotation result, wherein the three-dimensional virtual model is used to obtain a simulated environment state in which a target object in the vehicle is located; Analyzing the verification data set using the multiple candidate network models to obtain multiple candidate prediction results; Comparing the target labeling result with the multiple candidate prediction results to obtain a comparison result, wherein the comparison result is used to indicate an error between the target labeling result and the multiple candidate prediction results; The target network model is selected from the multiple candidate network models based on the comparison result.

4. The control method of the vehicle air conditioner according to claim 1, characterized in that: The target prediction result is evaluated according to the preset status indicators of the multiple dimensions to obtain The assessment results include: Obtaining a preset evaluation rule corresponding to the preset state indicator, wherein the preset evaluation rule is used to record the corresponding relationship between the environmental state interval of the target object and the preset state level; An evaluation result of the target prediction result is determined based on the preset evaluation rule.

5. The control method of the vehicle air conditioner according to claim 1, characterized in that: Adjusting the target control parameter of the vehicle air conditioner based on the evaluation result includes: Obtaining the expected level of the state of the target object; The target control parameter of the vehicle air conditioner is continuously adjusted based on the evaluation result, taking the expected state level as a reference.

6. The control method of the vehicle air conditioner according to claim 1, characterized in that: The vehicle running state includes the vehicle speed; the environmental state of the vehicle air conditioner includes at least one of the following: vehicle body ambient temperature, light intensity, air outlet air temperature and air outlet air humidity; the working state of the vehicle air conditioner includes at least one of the following: air door state of the air conditioning system, internal and external circulation mode; The target prediction result includes the air temperature, air humidity and average wind speed within a preset range around the target object; The target control parameter includes at least one of the following parameter information: the air door opening, the blower air volume, the compressor speed and the air outlet angle of the vehicle air conditioner.

7. A control device for a vehicle air conditioner, characterized in that: include: A detection module, used to detect the vehicle running state, the environmental state and the working state of the vehicle air conditioner during the actual working process, and obtain a target state sequence; An analysis module, used to analyze the target state sequence using a target network model to obtain a target prediction result, wherein the target prediction result is used to represent the predicted environmental state of the target object in the vehicle, and the target network model is a network model obtained by machine learning training using multiple sets of sample data; An evaluation module, used to perform a state evaluation on the target prediction result according to preset state indicators of multiple dimensions to obtain an evaluation result, wherein the evaluation result is used to indicate a state prediction level applicable to the target object; An adjustment module is used to adjust a target control parameter of the vehicle air conditioner based on the evaluation result, wherein the target control parameter is used to control the working state of the vehicle air conditioner.

8. A vehicle, characterized in that: The vehicle is used to execute the vehicle air conditioner control method described in any one of claims 1 to 6.

9. A processor, characterized in that: The processor is used to run a program, wherein the program is configured to execute the vehicle air conditioner control method described in any one of claims 1 to 6 when running.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the method for controlling the vehicle air conditioner as described in any one of claims 1 to 6.

Images