In order to deeply explore Yolo target detection algorithm and its development direction in the field of autonomous driving, this paper reviewed the research progress and main accomplishments of YOLO algorithms (YOLOv1~YOLOv8), analyzed and expounded its application in relevant detection tasks including vehicles, lane lines, pedestrians and traffic signs in the field of autonomous driving. Combining the characteristics of Yolo series algorithms, the paper analyzed and summarized the future improvement ideas and research trends of Yolo algorithm.

The A/B system upgrading technology is proposed to solve the problem that the System on Chip (SoC) Electronic Control Unit (ECU) cannot roll back the software when the Over-The-Air (OTA) upgrading failed. The technology downloads the program to the backup slot by reading the MISC of ECU slot information, and starts the installation by designing the priority level of the A/B system to select the active partition or rolls back the software in case of upgrading failed. At the same time, the differential graded technology of A/B system is designed. The ECU using this technology can perform software rollback when upgrading fails,and the feasibility, effectiveness and stability of rolling back software technology are verified by building a test environment.

To analyze the performance of the battery direct cooling and heating management system coupled with passenger cabin air conditioning, a power battery thermal management system model is established based on AMESim software. The charging time of typical liquid cooling and direct cooling and heating management systems under high-temperature fast charging conditions is compared. The results show that under the same fast charging MAP, the charging time of the direct cooling system is shortened by 7.6% compared with the liquid cooling system. The passenger cabin air conditioning and battery thermal management system is further coupled, and a thermal management control strategy is designed with the goal of controlling the temperature of the passenger cabin and the maximum temperature of the battery cells. Results show that compared with the uncoupled system, the maximum temperature difference on the top of the battery increases by 2.9 ℃ when using the coupled system, but the charging time is shortened by 4.9%.

In view of the problem that the variable window Adaptive Unscented Kalman Filter (AUKF) algorithm has a large mutation when the window changes, and the window sequence data decreases sharply, resulting in the increase of error, stability and accuracy decline in state estimation, this paper uses the Forgetting Factor Recursive Least Square (FFRLS) algorithm to identify parameters based on the second-order RC equivalent circuit model, combined with the improved variable window AUKF algorithm to estimate the State of Charge (SOC) of lithium battery, it is verified by the Urban Dynamometer Driving Schedule (UDDS) cycle test, and compared with Unscented Kalman Filter (UKF), AUKF and variable window AUKF algorithms. The test results show that the improved AUKF algorithm can control the average error within 0.38%, with higher accuracy and convergence.

For the issue of driving style identification, this paper proposes a method based on subjective and objective fusion. Firstly, the subjective style scale is developed and transformed into subjective factors. Secondly, a data acquisition system is implemented to gather the natural driving data and the basic behavior scenarios of car following and lane changing are mined. Thirdly, the fusion of subjective and objective identification system of driving style is constructed by extracting the key behavioral characteristics and subjective factors. Based on Principal Component Analysis (PCA) and K-means methods, the sample set is processed and the clustering results are verified. Finally, specific characteristics with physical significance are introduced to identify radical, moderate and conservative driving styles. The results reveal a strong correlation between the distribution of subjective style factors and objective behavioral characteristics, and the fusion method can be used to identify driving style effectively.

In the road test, an electric vehicle was found brake stall under high SOC, and paused under low SOC when it was running at full throttle, it was found and confirmed that irrational current signal parameters injected by the harmonics of the inverter software triggered resonance of the vehicle electrical network, which caused voltage jump. The resonance was analyzed, and a vehicle electrical network model was established, and the resonance point was calculated, the harmonic injection strategy was optimized. Vehicle test shows that under the new strategy, the voltage jump has been reduced and it does not cause new NVH problems.

To tackle the challenge of exhaust gas leak detection, this paper proposes an exhaust gas leakage detection method based on distributed fiber optic vibration sensing technology. Firstly, sensors are mounted on the vehicle’s exhaust pipe to detect variations in both intensity and phase of the optical fiber light signal, which arise from local pressure disturbances associated with exhaust gas leaks. A distributed vibration sensing system that utilizes a dual Mach-Zehnder interferometer setup is applied with a differential cross-correlation algorithm for demodulating vibrations captured at both ends. Secondly, a cross-correlation delay algorithm is used to precisely pinpoint any leakage locations. In simulation test, leak scenarios are emulated using a piezoelectric ceramic device along with a designated fiber length of 2 m, achieving remarkable positioning accuracy of 0.01 m and validating the feasibility of this proposed method.

This paper took noise generated from air suspension modulation of a vehicle as research object. Through transmission path study, the paper determined that the noise was mainly generated through the body structure excited by the air compressor. Through theoretical analysis, it was found that the main factors affecting air suspension noise transmission were the air compressor system modal frequency and Noise Transfer Function (NTF) from the body attaching point to the vehicle interior. The paper proposed optimization schemes including power supply wiring harness wrapping material optimization, bracket vibration isolation and bracket reinforcement + NTF. The results show that bracket vibration isolation is the best scheme, after implementation, the 1^st order noise order of air compressor was reduced by 4 dB, 2^nd order noise was reduced by 14 dB, and the sound quality in the vehicle was significantly improved.

To address the issue of deterioration of soot caused by EGR technology, a shunt centrifugal oil filter is introduced based on the principle of centrifugal sedimentation, and its structure principle, critical characteristic and influencing factors are systematically reviewed. A magneto-electric test system based on speed characteristics is developed, and the key points of adaptive design of centrifugal oil filter are explored. The soot-removal effects of the centrifugal oil filter are analyzed from the aspects of physical and chemical testing of oil products, plugging life of filter element and driving test. The results show that the soot-filtration effect of centrifugal oil filter is more obvious for EGR models, but slightly redundant for SCR models. The paper analyzes the influence of soot on oil viscosity and the benefit mathematical model of centrifugal rotor filter on fuel consumption builds based on the relationship between oil viscosity on fuel economy.

To improve the static comfort of normal family cars, this paper proposes the seat static comfort simulation analysis method including H-point position prediction and seat cushion pressure distribution uniformity based on SAE J826 tooling finite element model and the 50^th percentile flexible human body FE model provided by CASIMIR software, and the static comfort performance is improved by HyperStudy optimization tool. The simulation results are consistent with the experiments results.

In order to solve the problem of abnormal vibration and noise generated by the Electric Power Steering (EPS) system of passenger cars under bumpy road conditions, this paper proposed a new damped block structure by adding an O-ring at the EPS block position. By analyzing the influence of O-ring static compression and stiffness on damping performance, the optimal compression of O-ring was confirmed to be 0.5 mm. The EPS endurance test was carried out with the road spectrum of the vehicle. The results show that the performance of vibration noise deteriorates after a long mileage with increase of EPS block gap. Subsequently, the bench noise test of the EPS with traditional block and new block under different block gap was conducted. The results show that the vibration acceleration of the EPS with the new damped block structure is reduced by a maximum of 9 m/s² and 6.2 m/s² at the bushing end and block end, respectively, proving that the new damped block structure has a significant optimization effect on the vibration noise of the EPS system under bumpy road conditions.

In order to solve the problem of difficulty in Computer Aided Engineering (CAE) evaluation of forming failure of small fillet feature line, for a door outer panel with such feature, AutoForm was used to control the material inflow by adjusting the drawbead, and four kinds of door outer panel models with different forming states are obtained. Meanwhile, the forming condition and practical stamping condition with and without thickness stress are analyzed respectively. The results show that the forming limit of small size fillet feature line is reduced due to the influence of thickness stress, and uneven plastic deformation will occur in further forming, so the traditional formability CAE evaluation method is not suitable for small size fillet feature lines. Finally, a CAE method for evaluating the formability of small fillet feature lines combined with slippage is proposed, that is, when the slippage is less than 5mm and the thickness reduction rate and maximum nonlinear failure value meet the requirements, it can be considered that there is no formability risk of small fillet feature lines.

To obtain engine braking power accurately, this paper proposed a method of engine braking road test based on the momentum conservation law. A vehicle braking power equation based on speed and gear was built to provide a warning of downhill shifts and AT gear selection. Braking power test result obtained with the proposed test method was compared with dynamometer test result, with a difference range of -2.7%~3.4%, demonstrating accuracy and effectiveness of this method.

This paper introduces the monitoring requirements, diagnostic principles and calibration objectives of the CN6 On-Board Diagnostic (OBD) on cooling system. For the traditional calibration method which has a huge workload and a long calibration period, Simulink was used to build the monitoring model of the cooling system in the controller, and the off-line calibration method was used to calibrate the cooling system of a 1.2 L direct-injection supercharged gasoline vehicle. The off-line calibration results meet the development objectives, and the calibration cost and calibration cycle are reduced by more than 2/3.

The rainwater pollution on vehicle side window affects driver’s safety critically, it is necessary to study this kind of water management situations. By improving the key parameters of windshield water bar, and in combination of vehicle climate wind tunnel test results of different windshield water bars of a SUV, this article quantiataively analyzes water pollution area of the front side window and the exterior rear view mirror area by image processing technology, and proposes an evaluation method considering the lateral and rearview field comprehensively. It is found that increasing the height of the windshield water bar and the water storage area can reduce the water flow to the side window and weaken the water pollution of the side window. Finally, a water bar scheme for the front wind window with better visual field and engineering feasibility is obtained.