Intelligent cabin environmental pollution prevention and control system

Abstract

The invention relates to the technical field of automobile intelligent cabin environment control, and discloses an intelligent cabin environment pollution prevention and control system, which comprises a multi-dimensional environment sensing module, an intelligent cabin environment pollution prevention and control module and an intelligent cabin environment pollution prevention and control module, the state vector construction unit is used for combining the six environment parameters collected by the multi-dimensional environment sensing module into a six-dimensional environment state vector; the execution instruction generation module is used for mapping the six-dimensional environment state vector into a five-dimensional execution action vector according to a preset mapping function; and the execution mechanism control unit is used for adjusting a corresponding execution mechanism according to the five-dimensional execution action vector, and dynamically maintaining comprehensive optimization of air quality, energy consumption and passenger comfort in the cabin. According to the intelligent cabin environmental pollution prevention and control system, the problems of large sensing blind area, rough control strategy, low energy efficiency and poor comfort in the prior art are solved, and accurate and efficient mapping from environmental sensing to execution control is realized.

Description

Technical Field

[0001] This invention relates to the field of automotive intelligent cockpit environmental control technology, specifically to an intelligent cockpit environmental pollution prevention and control system. Background Technology

[0002] Currently, most vehicle intelligent cockpit environmental control systems (such as Tesla's "Bio Mode") employ a single-parameter triggering mechanism. They primarily rely on PM2.5 sensors to determine when to activate the air conditioning filtration system, and use a crude "maximum power activation" control strategy. This technology has significant limitations and three major drawbacks: 1. The perception dimension is limited, making it unable to effectively detect colorless and odorless but highly hazardous harmful gases such as carbon monoxide (CO), nitrogen oxides (NOx), and volatile organic compounds (VOCs), resulting in safety blind spots; 2. Crude control strategy: It only operates in "on / off" mode, responding with a fixed maximum power regardless of pollutant concentration. This results in extremely low energy efficiency on moderately polluted roads, severely wasting the driving range of electric vehicles. Furthermore, the maximum airflow generates tremendous noise, affecting driving comfort. 3. Lack of systematic optimization: Long-term closed operation will lead to the accumulation of carbon dioxide concentration in the vehicle, causing fatigue and drowsiness of passengers. Without considering the synergistic integration with functions such as oxygen generation and pressurization, it is unable to cope with complex and ever-changing driving environments.

[0003] Therefore, there is an urgent need for an intelligent system that can achieve comprehensive protection against multiple pollutants, optimize energy consumption, and maintain a stable cabin environment. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of the aforementioned technologies by providing an intelligent cockpit environmental pollution prevention and control system, thereby solving the problems of large sensing blind spots, crude control strategies, low energy efficiency, and poor comfort in existing technologies.

[0005] To achieve the above objectives, the intelligent cockpit environmental pollution prevention and control system designed in this invention includes: Multi-dimensional environmental perception module: collects environmental parameters inside or outside the vehicle in real time; State vector construction unit: combines the six environmental parameters collected by the multi-dimensional environment perception module into a six-dimensional environmental state vector; Execution instruction generation module: Maps the six-dimensional environment state vector into a five-dimensional execution action vector according to a preset mapping function; Actuator control unit: Adjusts the corresponding actuators according to the five-dimensional actuator vector to dynamically maintain the optimal overall balance between cabin air quality, energy consumption, and occupant comfort.

[0006] Preferably, the environmental parameters include particulate matter concentration (PM2.5), carbon monoxide (CO) concentration, nitrogen oxide (NOx) concentration, volatile organic compound (VOCs) concentration, oxygen concentration, and air pressure.

[0007] Preferably, the components of the five-dimensional execution action vector correspond to the damper opening, oxygen generator power, air conditioner power, booster pump power, and air purifier power, respectively.

[0008] Preferably, the mapping function is F(S), which maps any point S in the six-dimensional environment state space to the optimal point A in the five-dimensional execution action space through the mapping function F(S)=A. The input is the six-dimensional environment state vector S=[S1,S2,S3,S4,S5,S6]. TT ∈R 6 The output is a five-dimensional action vector A=[a1,a2,a3,a4,a5] T ∈[0,1] 5 .

[0009] The preferred and optimal optimization objectives comprehensively weigh indoor air quality, total system energy consumption, and equipment operating costs.

[0010] Preferably, the mapping function F is obtained through offline simulation training, and the reward function R(S,A)=-C(S,A)=α·||X_desired-X_sim(S,A)|| 2 +β·(c1·a1+c2·a2+c3·a3+c4·a4+c5·a5)+γ·||A-A_previous|| 2 +δ·K(S,A), where α is the weighting coefficient of comfort deviation, X_desired is the target cabin state vector, X_sim(S,A) is the cabin state predicted by the high-fidelity model, β is the weighting coefficient of energy consumption, c1, c2, c3, c4, c5 are the energy consumption coefficients of actuators, a1, a2, a3, a4, a5 are the execution commands, γ is the weighting coefficient of equipment loss, A_previous is the execution command at the previous moment, δ is the weighting coefficient of safety risk, and K(S,A) is the indicator function. When any component of X_sim(S,A) exceeds the safety range, K→∞; otherwise, K=0. After training, a vector containing (S... j A j The lookup table (LUT) for the optimal pair is used as an offline strategy library for the mapping function F.

[0011] Preferably, during online runtime, real-time interpolation calculations are performed, including the following steps: Location: Real-time acquisition of environmental parameters, standardized into a current six-dimensional environmental state vector S. t Find the enclosing S in the lookup table LUTt The hypercube unit consists of 2 6 = It consists of 64 vertices; Look up the table and calculate the weights: Read the pre-stored optimal instruction A for the 64 vertices. j Calculate the current point S t The distance to each vertex j in each dimension is calculated, and then the interpolation weight W of each vertex instruction is calculated. j ; Interpolation: The optimal instruction A for 64 vertices. j According to its weight W j Perform a weighted average to obtain the final optimal output instruction A. t A t =(∑(W j ·A j )) / (∑W j ).

[0012] Preferably, during the process of looking up the table and calculating the weights, the distance of the vertex from S t The closer, the higher its weight W j The larger.

[0013] Preferably, the weight calculation uses a linear kernel function: W j =Π(1-|s {t,i} -s {j,i} | / d), calculate the distance ratio in each dimension and then multiply them.

[0014] Preferably, the actuator control unit controls each actuator in a continuous stepless manner, and the adjustment process is precise and smooth.

[0015] Compared with the prior art, the present invention has the following advantages: 1. High efficiency and energy saving: Energy consumption is dynamically matched with the degree of pollution. It operates at low power when the pollution is light, which greatly saves energy and extends the driving range. It only operates at full power in extreme cases to maximize energy efficiency. 2. Dynamic balance: Multiple actuators work together to maintain O2 / CO2 balance and prevent occupant drowsiness; 3. Smooth and precise: The actions of all actuators are gradual and seamless, and the changes in in-vehicle environmental parameters are stable, ensuring the continuity and smoothness of control output, achieving stepless adjustment, and optimizing energy consumption and experience. Detailed Implementation

[0016] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0019] A smart cockpit environmental pollution prevention and control system includes: Multi-dimensional environmental perception module: Real-time collection of environmental parameters inside or outside the vehicle. In this embodiment, the environmental parameters include particulate matter concentration (PM2.5), carbon monoxide (CO) concentration, nitrogen oxides (NOx) concentration, volatile organic compounds (VOCs) concentration, oxygen concentration, and air pressure. State vector construction unit: combines the six environmental parameters collected by the multi-dimensional environment perception module into a six-dimensional environmental state vector; The instruction generation module maps the six-dimensional environmental state vector into a five-dimensional execution action vector according to a preset mapping function. In this embodiment, the components of the five-dimensional execution action vector correspond to the damper opening, oxygen generator power, air conditioner power, booster pump power, and air purifier power, respectively. The mapping function is F(S). Any point S in the six-dimensional environmental state space is mapped to the optimal point A in the five-dimensional execution action space through the mapping function F(S)=A. The input is the six-dimensional environmental state vector S=[S1,S2,S3,S4,S5,S6]. T ∈R 6 The output is a five-dimensional action vector A=[a1,a2,a3,a4,a5] T ∈[0,1] 5 ; Actuator control unit: Adjusts the corresponding actuators according to the five-dimensional actuator vector to dynamically maintain the overall optimal balance between cabin air quality, energy consumption and occupant comfort. The optimal optimization target comprehensively balances indoor air quality, total system energy consumption and equipment operating costs.

[0020] In this embodiment, S1 is the state vector of particulate matter concentration PM2.5, S1 = PM2.5 current PM2.5max PM2.5 current This represents the current PM2.5 concentration. max S1 represents the sensor's maximum range; the closer the value is to 1, the more severe the pollution. S2 is the carbon monoxide (CO) concentration state vector, where S2 = CO. current / CO max CO current Given the current carbon monoxide concentration, CO max S3 represents the sensor's maximum range; S3 is the state vector for nitrogen oxide (NOx) concentration, where S3 = NOx. current / NOx max NOx current For current nitrogen oxides (NOx), NOx max S4 represents the maximum range of the sensor; S4 is the state vector of volatile organic compound (VOC) concentration, where S4 = VOC. current / VOC max VOC current This represents the current concentration of volatile organic compounds (VOCs). max S5 represents the maximum range of the sensor; S5 is the state vector representing the degree of hypoxia, S5 = 1 - (O 2current -O 2min ) / (O 2normal -O 2min ), O 2current The current oxygen concentration, O 2normal This is the normal concentration of oxygen in the atmosphere (20.9%). 2min The minimum permissible concentration (e.g., 17.5%), S5=0 indicates sufficient oxygen, S5=1 indicates severe hypoxia; S6 is the pressure state vector, S6=|P current - P setpoint | / P max-deviation P current P represents the current air pressure. setpoint For the target air pressure, P max-deviation The larger the S6 value, the higher the risk of pressure runaway.

[0021] In this embodiment, a1 is the damper opening, 0 is completely closed (internal circulation), and 1 is completely open (external circulation); a2 is the oxygen concentrator power, 0 is off, and 1 is operating at rated maximum power; a3 is the air conditioning system power, 0 is off, and 1 is operating at maximum cooling / heating power; a4 is the booster pump power, 0 is off, and 1 is operating at maximum power; a5 is the air purifier power, 0 is off, and 1 is operating at maximum power.

[0022] Specifically, in this embodiment, the mapping function F is obtained through offline simulation training, and the reward function R(S,A)=-C(S,A), C(S,A)=α·||X_desired-X_sim(S,A)|| 2 +β·(c1·a1+c2·a2+c3·a3+c4·a4+c5·a5)+γ·||A-A_previous|| 2 +δ·K(S,A), where α is the weighting coefficient of comfort deviation, X_desired is the target cabin state vector, X_sim(S,A) is the cabin state predicted by the high-fidelity model, β is the weighting coefficient of energy consumption, c1, c2, c3, c4, c5 are the energy consumption coefficients of actuators, a1, a2, a3, a4, a5 are the execution commands, γ is the weighting coefficient of equipment loss, A_previous is the execution command at the previous moment, δ is the weighting coefficient of safety risk, and K(S,A) is the indicator function. When any component of X_sim(S,A) exceeds the safety range, K→∞; otherwise, K=0. After training, a vector containing (S... j A j The lookup table (LUT) for the optimal pair is used as an offline strategy library for the mapping function F.

[0023] When this system is running online, it performs real-time interpolation calculations, including the following steps: Location: Real-time acquisition of environmental parameters, standardized into a current six-dimensional environmental state vector S. t Find the enclosing S in the lookup table LUT t The hypercube unit consists of 2 6 = It consists of 64 vertices; Look up the table and calculate the weights: Read the pre-stored optimal instruction A for the 64 vertices. j Calculate the current point S t The distance to each vertex j in each dimension is calculated, and then the interpolation weight W of each vertex instruction is calculated. j ; Interpolation: The optimal instruction A for 64 vertices. j According to its weight W j Perform a weighted average to obtain the final optimal output instruction A. t A t =(∑(W j ·A j )) / (∑W j ).

[0024] During the process of looking up the table and calculating the weights, the distance of the vertex from S t The closer, the higher its weight W j The larger the value, the more linear the kernel function used for weight calculation: W. j=Π(1-|s {t,i} -s {j,i} | / d), calculate the distance ratio in each dimension and then multiply them.

[0025] Finally, in summary, the actuator control unit provides continuous stepless adjustment for each actuator, and the adjustment process is precise and smooth.

[0026] This invention's intelligent cockpit environmental pollution prevention and control system simultaneously monitors six parameters—particulate matter (PM2.5), carbon monoxide (CO), nitrogen oxides (NOx), volatile organic compounds (VOCs), oxygen concentration (O2), and air pressure—using multiple sensors to construct a six-dimensional environmental state vector, achieving comprehensive quantitative perception of the external environment. Simultaneously, based on calibration and pre-calculation of the optimal execution commands corresponding to possible environmental states, its optimization objective comprehensively balances indoor air quality, total system energy consumption, and equipment operating costs. During online operation, the system matches the real-time collected environmental vector with the calibration results, and calculates a set of optimal five-dimensional execution commands using a multi-dimensional linear interpolation algorithm. This precisely and smoothly controls the damper opening, oxygen generator power, air conditioning power, booster pump power, and air purifier power, thereby achieving precise and efficient mapping from environmental perception to execution control.

[0027] The system consists of six sensors that detect particulate matter, carbon monoxide, nitrogen oxides, volatile organic compounds, oxygen concentration, and air pressure, forming a six-axis coordinate system. The concentrations detected by each sensor form a comprehensive graph. This graph is then correlated with graphs showing the opening of the damper, the power of the oxygen generation system, the power of the air conditioning system, the power of the pressurization system, and the power of the air purification system, achieving dynamic adjustment. No matter how the external environment changes, there is always a most efficient and energy-saving treatment method.

[0028] This invention relates to an intelligent cockpit environmental pollution prevention and control system. Energy consumption is dynamically matched to the pollution level. It operates at low power during periods of mild pollution, significantly saving energy and extending driving range. It only operates at full power in extreme conditions, maximizing energy efficiency. Dynamic balance is achieved through the collaborative work of multiple actuators to maintain O2 / CO2 balance and prevent occupant drowsiness. Smooth and precise operation is ensured by the gradual and seamless movement of all actuators, resulting in stable changes in in-vehicle environmental parameters. This guarantees the continuity and smoothness of control output, achieving stepless adjustment and optimizing both energy consumption and user experience.

[0029] It should be noted that the above description of the technical solutions is exemplary, and this specification may be embodied in different forms and should not be construed as limiting it to the technical solutions set forth herein. Rather, providing these descriptions will ensure that the disclosure of this invention is thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. Furthermore, the technical solutions of this invention are defined only by the scope of the claims.

[0030] The shapes, dimensions, ratios, angles, and figures disclosed in the description of various aspects of this specification and claims are merely examples, and therefore, this specification and claims are not limited to the details shown. In the following description, detailed descriptions of relevant known functions or configurations will be omitted where it would be determined that they unnecessarily obscure the focus of this specification and claims.

[0031] When using the terms “comprising,” “having,” and “including” as described in this specification, there may be another part or other part unless used, and the terms used are generally singular but may also be plural.

[0032] It should be noted that although various components may appear and be described in this specification using terms such as "first," "second," "top," "bottom," "one side," "the other side," "one end," "the other end," etc., these components and parts should not be limited by these terms. These terms are only used to distinguish one component and part from another. For example, without departing from the scope of this specification, a first component may be referred to as a second component, and similarly, a second component may be referred to as a first component; top and bottom components may, under certain circumstances, be interchanged or converted; and components at one end and the other end may have the same or different performance characteristics.

[0034] Finally, it should be noted that the above embodiments are merely representative examples of the present invention. Obviously, the present invention is not limited to the above embodiments and many variations are possible. Any simple modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of the present invention should be considered within the protection scope of the present invention.

Claims

1. An intelligent cockpit environmental pollution prevention and control system, characterized in that: include: Multi-dimensional environmental perception module: collects environmental parameters inside or outside the vehicle in real time; State vector construction unit: combines the six environmental parameters collected by the multi-dimensional environment perception module into a six-dimensional environmental state vector; Execution instruction generation module: Maps the six-dimensional environment state vector into a five-dimensional execution action vector according to a preset mapping function; Actuator control unit: Adjusts the corresponding actuators according to the five-dimensional actuator vector to dynamically maintain the optimal overall balance between cabin air quality, energy consumption, and occupant comfort.

2. The intelligent cockpit environmental pollution prevention and control system as described in claim 1, characterized in that: The environmental parameters include particulate matter concentration (PM2.5), carbon monoxide (CO), nitrogen oxides (NOx), volatile organic compounds (VOCs), oxygen concentration, and air pressure.

3. The intelligent cockpit environmental pollution prevention and control system as described in claim 1, characterized in that: The components of the five-dimensional execution action vector correspond to the damper opening, oxygen generator power, air conditioner power, booster pump power, and air purifier power, respectively.

4. The intelligent cockpit environmental pollution prevention and control system as described in claim 1, characterized in that: The mapping function is F(S), which maps any point S in the six-dimensional environment state space to the optimal point A in the five-dimensional execution action space. The input is the six-dimensional environment state vector S=[S1,S2,S3,S4,S5,S6]. TT ∈R 6 The output is a five-dimensional action vector A=[a1,a2,a3,a4,a5] T ∈[0,1] 5 .

5. The intelligent cockpit environmental pollution prevention and control system as described in claim 4, characterized in that: The optimal optimization objective comprehensively balances indoor air quality, total system energy consumption, and equipment operating costs.

6. The intelligent cockpit environmental pollution prevention and control system as described in claim 4, characterized in that: The mapping function F is obtained through offline simulation training, and the reward function R(S,A)=-C(S,A), C(S,A)=α·||X_desired-X_sim(S,A)|| 2 +β·(c1·a1+c2·a2+c3·a3+c4·a4+c5·a5)+γ·||A-A_previous|| 2 +δ·K(S,A), where α is the weighting coefficient of comfort deviation, X_desired is the target cabin state vector, X_sim(S,A) is the cabin state predicted by the high-fidelity model, β is the weighting coefficient of energy consumption, c1, c2, c3, c4, c5 are the energy consumption coefficients of actuators, a1, a2, a3, a4, a5 are the execution commands, γ is the weighting coefficient of equipment loss, A_previous is the execution command at the previous moment, δ is the weighting coefficient of safety risk, and K(S,A) is the indicator function. When any component of X_sim(S,A) exceeds the safety range, K→∞; otherwise, K=0. After training, a vector containing (S... j A j The lookup table (LUT) for the optimal pair is used as an offline strategy library for the mapping function F.

7. The intelligent cockpit environmental pollution prevention and control system as described in claim 6, characterized in that: During online runtime, real-time interpolation calculations are performed, including the following steps: Location: Real-time acquisition of environmental parameters, standardized into a current six-dimensional environmental state vector S. t Find the enclosing S in the lookup table LUT t The hypercube unit consists of 2 6 = It consists of 64 vertices; Look up the table and calculate the weights: Read the pre-stored optimal instruction A for the 64 vertices. j Calculate the current point S t The distance to each vertex j in each dimension is calculated, and then the interpolation weight W of each vertex instruction is calculated. j ; Interpolation: The optimal instruction A for 64 vertices. j According to its weight W j Perform a weighted average to obtain the final optimal output instruction A. t A t =(∑(W j ·A j )) / (∑W j ).

8. The intelligent cockpit environmental pollution prevention and control system as described in claim 7, characterized in that: During the process of looking up the table and calculating the weights, the distance of the vertex from S t The closer, the higher its weight W j The larger.

9. The intelligent cockpit environmental pollution prevention and control system as described in claim 7, characterized in that: Weight calculation uses a linear kernel function: W j =Π(1-|s {t,i} -s {j,i} | / d), calculate the distance ratio in each dimension and then multiply them.

10. The intelligent cockpit environmental pollution prevention and control system as described in claim 1, characterized in that: The actuator control unit provides continuous stepless adjustment for each actuator, with a precise and smooth adjustment process.