An intelligent temperature control system for car seats based on YOLOv5 algorithm

Abstract

The present invention is applicable to the field of automobile technology and provides an intelligent temperature control system for automobile seats based on the YOLOv5 algorithm, including a detection module, a control module and a heating module. The system uses an intelligent camera equipped with the YOLOv5 algorithm and various sensors to intelligently identify passenger information and determine the heating temperature; at the same time, an error feedback control mode is used to heat the seat to reduce heating energy consumption. On the one hand, it meets people's requirements for the comfort of the automobile passenger compartment, and on the other hand, it adapts to the development needs of new energy vehicles and achieves the purpose of energy conservation and emission reduction.

Description

Technical Field

[0001] The present invention belongs to the field of automobile technology, and in particular relates to an intelligent temperature control system for automobile seats based on a YOLOv5 algorithm. Background Art

[0002] In recent years, with the rapid development of new energy vehicles, the development of automobile intelligence has also shown a promising trend. As a means of transportation closely related to people's daily travel, the comfort of automobiles has been increasingly valued by people. With the advent of the era of intelligence and digitalization, more and more advanced technologies have begun to be decentralized and applied in the automotive field.

[0003] Today's car cabins are no longer limited to meeting people's most basic travel needs, and have begun to develop personalized sensory experiences. At the same time, with the development of automobile-related technologies, people's requirements for the comfort of automobile passenger cabins are gradually increasing. The thermal comfort control of automobile passenger cabins has also evolved from relying solely on natural ventilation through windows at the beginning, to installing air conditioners, to realizing air conditioning zoned air supply, and now more and more models are equipped with seat ventilation and seat heating, and the functions are gradually improved.

[0004] However, most of the existing seat heating modes are still traditional switch control modes. Relying on traditional threshold control cannot achieve the goal of energy conservation and emission reduction; at the same time, it also cannot take into account the different thermal comfort needs of different passengers. Summary of the invention

[0005] The purpose of the embodiment of the present invention is to provide a car seat intelligent temperature control system based on the YOLOv5 algorithm, aiming to solve the problems raised in the above background technology.

[0006] The embodiment of the present invention is implemented as follows: an intelligent temperature control system for automobile seats based on the YOLOv5 algorithm, comprising a detection module, a control module and a heating module;

[0007] The detection module is used to collect the average radiation temperature in the cabin, the current temperature of the car seat and the air flow rate in the cabin, and use the trained YOLOv5 target detection network to identify the passenger's clothing and collect the thermal resistance of the passenger's clothing;

[0008] The control module is used to receive information from the detection module, calculate the equivalent temperature of the passenger at this time based on the equivalent temperature EQT evaluation model, and compare it with the equivalent temperature comfort range to obtain a thermal comfort evaluation value; at the same time, an error feedback control mode is adopted to adjust the heating voltage according to the difference between the real-time equivalent temperature and the thermal comfort evaluation value;

[0009] The heating module is used to heat the seat according to the heating voltage of the control module, and collect the real-time seat temperature and transmit it to the control module.

[0010] According to a further technical solution, the detection module includes a seat temperature sensor, a cabin temperature meter, an air flow velocity sensor and a camera;

[0011] The seat temperature sensor is arranged on the seat surface to monitor T i Seat temperature at time t a The cabin thermometer is used to measure the average radiation temperature t r The air velocity sensor is responsible for detecting the air velocity v around the driver's body. air The camera cooperates with the YOLOv5 algorithm to identify the type of clothing the driver is wearing, and thus gives the clothing thermal resistance I cl .

[0012] According to a further technical solution, the control module includes an automobile ECU, which is used to process, judge and make decisions on various information and transmit them to the heating module.

[0013] According to a further technical solution, the heating module includes a heating element, which is arranged inside the driver's seat to heat the seat.

[0014] According to a further technical solution, the heating element may be an electric heating wire.

[0015] In a further technical solution, the YOLOv5 target detection network pre-training process for identifying thermal resistance of passenger clothing includes the following steps:

[0016] S101. Data preparation:

[0017] Prepare a large number of passenger winter clothing images as training sets, preprocess the images, including resizing, normalization, enhancement, etc., to ensure that the input images meet the input requirements of the model; use lamblimg to select and annotate; the final generated data set includes clothing images and corresponding label types;

[0018] S102, Model selection:

[0019] Select the YOLO v5 model for architecture, and adjust and optimize it according to the task requirements (type of clothing, driving posture); select the pre-trained YOLO v5 weights, and use the sorted data to train the weights suitable for detecting clothing;

[0020] S103, model training:

[0021] Use the prepared dataset to train the YOLOv5 model; during the training process, adjust various parameters based on the training information and results to improve the model accuracy.

[0022] In a further technical solution, the workflow of the detection module includes the following steps:

[0023] S201, collecting seat surface temperature t a , collecting the current seat temperature through a temperature sensor arranged on the seat surface;

[0024] S202, collecting the average radiation temperature t in the cabin r The current average radiation temperature t in the cabin is obtained by using the cabin thermometer arranged in the cabin r ;

[0025] S203, collecting the air velocity v around the passenger's body air , the current air velocity parameters are obtained by arranging the air velocity sensor in the cabin;

[0026] S204, collect passenger clothing thermal resistance I cl ,The driver's clothing is recognized by the camera arranged in the cabin, and the YOLOv5 target detection network carried by the camera is combined to send the thermal resistance parameters of the passenger's clothing to the control module.

[0027] According to a further technical solution, the workflow of the control module includes the following steps:

[0028] S301, calculate equivalent temperature: calculate equivalent temperature by using the simplified formula of equivalent temperature EQT evaluation model:

[0029] ;

[0030] in, t a is the seat temperature, t r is the cabin temperature, v air is the air velocity around the passenger's body, I cl Thermal resistance of clothing worn by passengers;

[0031] S302, determining the heating target temperature to be 26.5°C: Since the temperature sensor is arranged at the seat cushion and in contact with the human thigh, the thermal comfort of the human thigh is evaluated and 26.5°C is selected as the heating target temperature;

[0032] S303: Real-time equivalent temperature of passengers obtained through each sampling T eq With target temperature T s The error determines the size of the heating voltage U. The maximum output voltage of the passenger car seat heating function is 12V. The specific voltage adjustment method is as follows:

[0033] ;

[0034] Finally, when T eq It reaches 26.5℃, the output voltage is 0.6V, and the seat cushion temperature is maintained at the target temperature.

[0035] In a further technical solution, the heating module workflow includes the following steps:

[0036] S401, the heating element starts to heat up after receiving the voltage signal;

[0037] S402. The temperature sensor arranged on the seat surface collects the current seat surface temperature and transmits it to the control module, thereby completing the system closed loop.

[0038] An embodiment of the present invention provides an intelligent temperature control system for automobile seats based on the YOLOv5 algorithm, and its beneficial effects are as follows:

[0039] (1) In order to solve the problem of high energy consumption in the traditional seat threshold control heating mode, the error feedback control mode is adopted to significantly reduce heating energy consumption and promote energy conservation and emission reduction;

[0040] (2) The YOLOv5 target detection network is combined with a camera for clothing recognition to accurately capture the type of clothing worn by passengers, thereby deriving the thermal resistance of the clothing, providing the control system with more accurate thermal comfort evaluation parameters and improving the system's ability to respond to passengers' personalized needs;

[0041] (3) By acquiring dynamic parameters through a variety of sensors and performing processing, judgment and signal transmission, the seat heating temperature can be controlled as necessary to ensure riding comfort;

[0042] (4) The EQT equivalent temperature evaluation model is introduced. This model combines multiple parameters and, through complex calculations and evaluations, derives the equivalent temperature of passengers at a specific moment. By comparing it with the equivalent temperature comfort range, the thermal comfort of passengers can be evaluated more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A schematic diagram of the structure of an intelligent temperature control system for automobile seats based on the YOLOv5 algorithm provided in an embodiment of the present invention;

[0044] Figure 2 Schematic diagram of the pre-training process for the YOLOv5 target network to identify the thermal resistance of passenger clothing;

[0045] Figure 3 This is the working flow diagram of the detection module of the intelligent temperature control system of the car seat;

[0046] Figure 4This is the working flow chart of the control module of the intelligent temperature control system of the car seat;

[0047] Figure 5 It is the thermal comfort assessment range of various parts of the human body;

[0048] Figure 6 This is the working flow diagram of the heating module of the intelligent temperature control system for car seats. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0050] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0051] An embodiment of the present invention provides an intelligent temperature control system for automobile seats based on the YOLOv5 algorithm, comprising a detection module, a control module and a heating module;

[0052] The detection module is used to collect the average radiation temperature in the cabin, the current temperature of the car seat and the air flow rate in the cabin, and use the trained YOLOv5 target detection network to identify the passenger's clothing and collect the thermal resistance of the passenger's clothing;

[0053] The control module is used to receive information from the detection module, calculate the equivalent temperature of the passenger at this time based on the equivalent temperature EQT evaluation model, and compare it with the equivalent temperature comfort range to obtain a thermal comfort evaluation value; at the same time, an error feedback control mode is adopted to adjust the heating voltage according to the difference between the real-time equivalent temperature and the thermal comfort evaluation value;

[0054] The heating module is used to heat the seat according to the heating voltage of the control module, and collect the real-time seat temperature and transmit it to the control module.

[0055] like Figure 1 As shown in FIG. 1 , as a preferred embodiment of the present invention, the detection module includes a seat temperature sensor, a cabin temperature meter, an air flow velocity sensor and a camera. The seat temperature sensor is arranged on the seat surface to monitor T i Seat temperature at time t a The cabin thermometer is used to measure the average radiation temperature t r The air velocity sensor is responsible for detecting the air velocity v around the driver's body. air The camera cooperates with the YOLOv5 algorithm to identify the type of clothing the driver is wearing, and thus gives the clothing thermal resistance I cl .

[0056] like Figure 1 As shown, as a preferred embodiment of the present invention, the control module includes an automobile ECU, which is used to process, judge and make decisions on various information and transmit them to the heating module.

[0057] like Figure 1 As shown, as a preferred embodiment of the present invention, the heating module includes a heating element, which is arranged inside the driver's seat to heat the seat.

[0058] In the embodiment of the present invention, the heating element may be an electric heating wire.

[0059] As a preferred embodiment of the present invention, the YOLOv5 target detection network recognizes the thermal resistance of passenger clothing pre-training process as follows: Figure 2 As shown, the process includes the following steps:

[0060] S101. Data preparation:

[0061] Prepare a large number of passenger winter clothing images as training sets, preprocess the images, including resizing, normalization, enhancement, etc., to ensure that the input images meet the input requirements of the model; use lamblimg to select and annotate; the final generated data set includes clothing images and corresponding label types;

[0062] S102, Model selection:

[0063] Select the YOLOv5 model for architecture, and adjust and optimize it according to the task requirements (type of clothing, driving posture); select the pre-trained YOLOv5 weights, and use the sorted data to train the weights suitable for detecting clothing;

[0064] S103, model training:

[0065] Use the prepared dataset to train the YOLOv5 model; during the training process, adjust various parameters based on the training information and results to improve the model accuracy.

[0066] As a preferred embodiment of the present invention, the working process of the detection module is as follows: Figure 3 As shown, the process includes the following steps:

[0067] S201, collecting seat surface temperature t a , collecting the current seat temperature through a temperature sensor arranged on the seat surface;

[0068] S202, collecting the average radiation temperature t in the cabin r The current average radiation temperature t in the cabin is obtained by using the cabin thermometer arranged in the cabin r ;

[0069] S203, collecting the air velocity v around the passenger's body air , the current air velocity parameters are obtained by arranging the air velocity sensor in the cabin;

[0070] S204, collect passenger clothing thermal resistance I cl ,The driver's clothing is recognized by the camera arranged in the cabin, and the YOLOv5 target detection network carried by the camera is combined to send the thermal resistance parameters of the passenger's clothing to the control module.

[0071] As a preferred embodiment of the present invention, the working process of the control module is as follows: Figure 4 As shown, the process includes the following steps:

[0072] S301, calculate equivalent temperature: calculate equivalent temperature by using the simplified formula of equivalent temperature EQT evaluation model:

[0073] ;

[0074] in, t a is the seat temperature, t r is the cabin temperature, v air is the air velocity around the passenger's body, I cl Thermal resistance of clothing worn by passengers;

[0075] S302, determine the heating target temperature to be 26.5°C: Since the temperature sensor is located at the seat cushion and in contact with the human thigh, the thermal comfort of the human thigh should be evaluated with reference to the evaluation. Figure 5 The human body (thermal comfort assessment range of various parts of the human body) shows that the temperature range of the human thigh in winter is from "neutral" to "hot but comfortable" is 24.5℃ to 27.5℃, and 26.5℃ is selected as the target temperature for heating;

[0076] S303: Real-time equivalent temperature of passengers obtained through each sampling T eq With target temperature T s The error determines the heating voltage U (the target temperature Ts =26.5°C). In some embodiments, the maximum output voltage of the passenger car seat heating function is 12V, and the specific voltage adjustment method is as follows:

[0077] ;

[0078] Finally, when T eqIt reaches 26.5℃, the output voltage is 0.6V, and the seat cushion temperature is maintained at the target temperature.

[0079] As a preferred embodiment of the present invention, the heating module working process is as follows Figure 6 As shown, the process includes the following steps:

[0080] S401, the heating element starts to heat up after receiving the voltage signal;

[0081] S402. The temperature sensor arranged on the seat surface collects the current seat surface temperature and transmits it to the control module, thereby completing the system closed loop.

[0082] Through the above three modules and four steps, the interaction between passengers and seats can be realized, energy consumption can be effectively reduced, and the personalization and energy saving of seat heating function can be improved.

[0083] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent temperature control system for car seats based on the YOLOv5 algorithm, characterized in that: It includes a detection module, a control module and a heating module; The detection module is used to collect the average radiation temperature in the cabin, the current temperature of the car seat and the air flow rate in the cabin, and use the trained YOLOv5 target detection network to identify the passenger's clothing and collect the thermal resistance of the passenger's clothing; The control module is used to receive information from the detection module, calculate the equivalent temperature of the passenger at this time based on the equivalent temperature EQT evaluation model, and compare it with the equivalent temperature comfort range to obtain a thermal comfort evaluation value; at the same time, an error feedback control mode is adopted to adjust the heating voltage according to the difference between the real-time equivalent temperature and the thermal comfort evaluation value; The heating module is used to heat the seat according to the heating voltage of the control module, and collect the real-time seat temperature and transmit it to the control module; The YOLOv5 target detection network pre-training process for identifying thermal resistance of passenger clothing includes the following steps: S101. Data preparation: Prepare a large number of passenger winter clothing images as training sets, preprocess the images to ensure that the input images meet the model's input requirements; use lamblimg to select and annotate; the final generated data set includes clothing images and corresponding label types; S102, Model selection: Select the YOLOv5 model for architecture, and adjust and optimize it according to task requirements; select the pre-trained YOLOv5 weights, and use the sorted data to train the weights suitable for detecting clothing; S103, model training: Use the prepared dataset to train the YOLOv5 model; during the training process, adjust various parameters based on the training information and results to improve the model accuracy; The workflow of the detection module includes the following steps: S201, collecting seat surface temperature t a , collecting the current seat temperature through a temperature sensor arranged on the seat surface; S202, collecting the average radiation temperature t in the cabin r The current average radiation temperature t in the cabin is obtained by using the cabin thermometer arranged in the cabin r ; S203, collecting the air velocity v around the passenger's body air , the current air velocity parameters are obtained by arranging the air velocity sensor in the cabin; S204, collect passenger clothing thermal resistance I cl , the driver's clothing is recognized by the camera arranged in the cabin, and the YOLOv5 target detection network carried by the camera is combined to send the thermal resistance parameters of the passenger clothing to the control module; The workflow of the control module includes the following steps: S301, calculate equivalent temperature: calculate equivalent temperature by using the simplified formula of equivalent temperature EQT evaluation model: ； in, t a is the seat temperature, t r is the cabin temperature, v air is the air velocity around the passenger's body, I cl Thermal resistance of clothing worn by passengers; S302, determining the heating target temperature to be 26.5°C: Since the temperature sensor is arranged at the seat cushion and in contact with the human thigh, the thermal comfort of the human thigh is evaluated and 26.5°C is selected as the heating target temperature; S303: Real-time equivalent temperature of passengers obtained through each sampling T eq With target temperature T s The error determines the size of the heating voltage U. The maximum output voltage of the passenger car seat heating function is 12V. The specific voltage adjustment method is as follows: ； Finally, when T eq It reaches 26.5℃, the output voltage is 0.6V, and the seat cushion temperature is maintained at the target temperature.

2. According to the YOLOv5 algorithm-based intelligent temperature control system for automobile seats according to claim 1, it is characterized in that: The detection module includes a seat temperature sensor, a cabin temperature gauge, an air flow velocity sensor and a camera; The seat temperature sensor is arranged on the seat surface to monitor T i Seat temperature at time t a ; The cabin thermometer is used to measure the average radiation temperature t r ; The air velocity sensor is responsible for detecting the air velocity v around the driver's body air ; The camera cooperates with the YOLOv5 algorithm to identify the type of clothing the driver is wearing, and thus gives the clothing thermal resistance I cl .

3. The car seat intelligent temperature control system based on the YOLOv5 algorithm according to claim 1 is characterized in that: The control module includes an automobile ECU, which is used to process, judge and make decisions on various information and transmit them to the heating module.

4. The car seat intelligent temperature control system based on the YOLOv5 algorithm according to claim 1 is characterized in that: The heating module includes a heating element, which is arranged inside the driver's seat to heat the seat.

5. The car seat intelligent temperature control system based on the YOLOv5 algorithm according to claim 1 is characterized in that: The heating module workflow includes the following steps: S401, the heating element starts to heat up after receiving the voltage signal; S402. The temperature sensor arranged on the seat surface collects the current seat surface temperature and transmits it to the control module, thereby completing the system closed loop.

Images