Search

Traditional vehicle exhaust pollutant detection methods, such as bench test and remote sensing detection, have problems such as large volume, high cost, complex process, long waiting time, etc. In this paper, according to the main components of vehicle exhaust pollutants, an electronic nose with 12 gas sensors was designed independently for real-time and rapid detection of vehicle exhaust pollutants. In order to verify that the designed electronic nose based on machine learning classification method can accurately identify the exhaust pollutants from different engines or different concentration levels from the same engine. After feature extraction of the collected data, Random Forest (RF) was used as the classifier, and the average classification accuracy reached 99.92%. This result proved that the designed electronic nose combined with RF method can accurately and sensitively judge the concentration level of vehicle exhaust pollutants.. Then, in order to enable the electronic nose to be vehicle-mounted and to achieve real-time and rapid detection of vehicle exhaust pollutants. We used Recursive Feature Elimination with Cross Validation (RFECV), Random Forest Feature Selector (RFFS) and Principal Component Analysis (PCA) to optimize the sensor array. The results showed that these methods can effectively simplify the sensor array while ensuring the RF classifier’s classification recognition rate. After using RFECV and RFFS to optimize the sensor array, the RF classifier’s classification recognition rate of the optimized sensor arrays for vehicle exhaust pollutants reached 99.77% and 99.44%, respectively. The numbers of sensors in the optimized sensor arrays were six and eight respectively, which achieved the miniaturization and low-cost of the electronic nose. With the limitation of six sensors, RFECV is the best sensor array optimization method among the three methods.

Gas detection in enclosed cabins is a challenging concern in the industry to ensure the safety of cabin operations and personnel driving. There has been a growing development in the detection of safety in enclosed cabin operations based on volatile organic compounds, which have unique characteristics. The air pollution in closed cabins seriously affects the driver’s health, and the accuracy of the detection directly affects the operation safety of the cabin. However, until today, gas detection in enclosed cabins has relied on traditional methods that are expensive and time-consuming, and it cannot be detected in real time. This paper focuses on the potential and capability of electronic nose applications for gas detection in enclosed cabins. Since the electronic nose is a good substitute for the closed cabin, people’s attention to it has increased greatly. The characteristics of hazardous gas and warning gas in closed cabins are also discussed. In addition, this paper provides important insights into the challenges and future trends of the electronic nose, a low-cost, high-precision, and fast detection method, in more applications in closed compartments.

Driving safety issues, such as drunk driving, have drawn a lot of attention since the advent of shared automobiles. We used an electronic nose (EN) detection device as an onboard system for shared automobiles to identify drunk driving. The sensors in the EN, however, can stray in cold winter temperatures. We suggested an independent component analysis (ICA) correction model to handle the data collected from the EN in order to lessen the impact of low temperature on the device. Additionally, it was contrasted with both the mixed temperature correction model and the single temperature model. As samples, alcohol mixed with concentrations of 0.1 mg/L and 0.5 mg/L were tested at (20 ± 2) °C, (−10 ± 2) °C, and (−20 ± 2) °C. The results showed that the ICA correction model outperformed the other models with an accuracy of 1, precision of 1, recall of 1, and specificity of 1. As a result, this model can be utilized to lessen the impact of low temperature on the EN’s ability to detect the presence of alcohol in the driver’s inhaled gas, strongly supporting its use in car-sharing drink driving. Other ENs that need to function in frigid conditions can also use this technique.

Driver behavior is considered one of the most important factors in the genesis of dilemma zones and the safety of driver-vehicle-environment systems. An accurate driver behavior model can improve the traffic signal control efficiency and decrease traffic accidents in signalized intersections. This paper uses a mathematical modeling method to study driver behavior in a dilemma zone based on stochastic model predictive control (SMPC), along with considering the dynamic characteristics of human cognition and execution, aiming to provide a feasible solution for modeling driver behavior more accurately and potentially improving the understanding of driver-vehicle-environment systems in dilemma zones. This paper explores the modeling framework of driver behavior, including the perception module, decision-making module, and operation module. The perception module is proposed to stimulate the ability to perceive uncertainty and select attention in the dilemma zone. An SMPC-based driver control modeling method is proposed to stimulate decision-making behavior in the dilemma zone. The operation module is proposed to stimulate the execution ability of the driver. Finally, CarSim, the well-known vehicle dynamics analysis software package, is used to verify the proposed models of this paper. The simulation results show that the SMPC-based driver behavior model can effectively and accurately reflect the vehicle motion and dynamics under driving in the dilemma zone.

In order to address the difficulty of arranging large calibration objects and the low measurement accuracy of small calibration objects in traffic accident scene photogrammetry, a photogrammetric method based on a composite of small calibration objects is proposed. Several small calibration objects are placed around the traffic accident scene, and the coordinate system of the composite calibration object is given based on one of them. By maintaining the relative position and coplanar relationship of the small calibration objects, the local coordinate system of each small calibration object is transformed into the coordinate system of the composite calibration object. The two-dimensional direct linear transformation method is improved based on minimizing the reprojection error of the calibration points of all objects. A rectified image is obtained using the nonlinear optimization method. The increased accuracy of traffic accident scene photogrammetry using a composite small calibration object is demonstrated through the analysis of field experiments and case studies.