Search Results

The driver's face detection and tracking method important for Advanced Driver Assistance Systems (ADAS) and autonomous driving in various situations. The deep SORT algorithm has integrated appearance information, the motion model and the intersection-over-union (IOU) distance methods, and has been applied to face tracking, but it depends on detection information in every frame. Once the detection information lacks, the deep SORT algorithm will wait until the target detects bounding boxes appear again, even if the target didn’t disappear or shield. Hence, we propose to use a new tracker that not completely depend on the detection algorithm to cascade with the deep SORT algorithm to realize stable driver's face tracking. At first, the driver's face detection and tracking will be accomplished by the MTCNN-deep-SORT algorithm.

Micro-machined planar orifice nozzles have been developed and used with commercially produced diesel injection systems. Such a system may have the capability to improve the spray characteristics in DI diesel engines. The availability of a MEMS (Micro-Electro-Mechanical-Systems) processing sequence supported the construction of micro-planar orifice nozzles, and micro-systems technology was also employed in our macro-instrumentation. To demonstrate this process, fourteen MEMS nozzles were fabricated with deep X-ray lithography and electroplating technology. The circular orifice diameters were varied from 40 to 260 microns and the number of orifices varied from one to 169. Three plates with non-circular orifices were also fabricated to examine the effect of orifice shape on spray characteristics. These nozzles were then attached to commercial injectors and the associated injection systems were used for the spray experiments.

This paper presents advanced and cost-reducing technologies of a motor drive system with reduced permanent magnets but without a position sensor. The key enabler is the integration of novel designs of flux-intensifying interior permanent magnet synchronous machines (FI-IPMSMs) and position self-sensing control technologies. In this paper, we focus on two advantages of FI-IPMSM over conventional flux-weakening interior permanent magnet synchronous machines (FW-IPMSMs). The first benefit is that thinner magnets are possible and there is less concern for demagnetization because of its significantly smaller flux-weakening current. This paper presents two design examples of FI-IPMSMs, one of which has not only smaller magnets but also similar power conversion capability. The second advantage is reduced saturation and cross-saturation effect, which leads to improved position self-sensing capability.

The effect of wall temperature on single surface flame quenching and flame structure of an atmospheric premixed methane-air flame was studied. The luminous region of a laminar flame was located at an angle of 45 degrees to a temperature- controlled surface. C2 laser-induced fluorescence was used as an indicator of flame position while Raman spectroscopy was used to determine gas temperature profiles near the surface. These measurements were conducted for wall positions (vertical distance from the surface) ranging from 50 mm to 1.0 mm and wall temperatures ranging from 150 °C to 600 °C. C2 laser-induced fluorescence measurements indicated flame position is affected by the presence of a surface and the surface temperature. Larger C2 fluorescence intensity values were observed for higher wall temperatures at all distances from the surface.

This paper presents a novel encoding scheme as an alternative to Analog amplitude encoding for communicating sensor signals. The scheme has the potential of becoming a non-proprietary industrial standard for communicating sensor information to electronic control modules. Key features of the encoding scheme are the ability to communicate two sensor values using only 3 wires (power, ground and signal) with 12 bit resolution within 1ms. The scheme includes a checksum for error detection and a mechanism for reporting serial data such as low rate sensor information, part numbers or fault codes. Data is communicated to the receiving module by varying the time between discrete (single edge polarity) transitions. The encoding is self-calibrating and does not require an expensive crystal in the sending module (assumed to be a low-cost ASIC) to maintain signal integrity.

Recent advances in ANN (Artificial Neural Network) technology enable new methods to be developed in sensor technology. There are a large number of cases where there exists a causal relationship between one or more inputs and a physical quantity, but where an easily implemented analytical relationship between the inputs and the output can not easily be found. In such cases, machine learning techniques, such as artificial neural networks, are able to model that functional relationship. However, using conventional computing hardware, these methods, while theoretically attractive, are too computationally intensive for field deployment in real-time systems. Using a hardware implementation of an artificial neural network architecture, these computational restrictions can be eliminated.

We have developed and used micro-machined injector nozzles with commercially produced diesel injection systems that have the capability to improve the spray characteristics in DI diesel engines. The availability of a MEMS (Micro-Electro-Mechanical-Systems) processing sequence supported the construction of micro-diesel injector nozzles, and micro-systems technology was also employed in our macro-instrumentation. Fourteen different circular plates (nickel-iron alloy) were fabricated with deep X-ray lithography and electroplating technology. Five plates that have a single orifice were fabricated to investigate the effect of orifice diameter on spray characteristics; i.e., 40 to 260 microns. The spacing between multiple orifices was also varied; e.g., two plates that each had 41 orifices and 169 orifices, respectively, with a diameter of 40 microns. Finally, three plates with non-circular orifices were also made to examine the effect of orifice shape on spray characteristics.

Active Hall Effect Sensors are used in numerous automotive applications where direction, position, and speed sensing capabilities are required. The primary usage of these devices is in the areas of engine and transmission controls as well as ABS speed monitoring systems. To reliably employ these sensors in such applications requires a thorough understanding of the device electronics and how this component interprets the magnetic fields produced by a ferromagnetic target. The traditional methods involving the construction and test of prototype sensors and targets have been costly, time consuming, and rarely resulted in a robust design. To resolve this problem General Motors Powertrain and Ansoft Corporation have jointly developed the capability to accurately model active Hall Effect Sensors.

The around view monitor (AVM) system for the long-body road vehicle with multiple articulated carriages usually suffers from the incomplete distortion rectification of fisheye cameras and the irregular image stitching area caused by the change of relative position of the cameras on different carriages while the vehicle is in motion. In response to these problems, a set of calibration and stitching methods of AVM are proposed. First, a radial-distortion-based rectification method is adopted and improved. This method establishes two lost functions and solves the model parameters with the two-step optimization method. Then, AVM system calibration is conducted, and the perspective transformation matrix is calculated. After that, a static basic look-up table is generated based on the distortion rectification model and perspective transformation matrix.

The temperature monitoring of the lithium-ion battery is crucial for the advanced battery thermal management systems (BTMS) to improve performance and ensure operational safety and reliability of the battery system. In real applications, the core temperature of the battery is unfortunately unmeasurable due to the impracticality of placing a sensor inside the core, and has to be estimated online in real-time. Meanwhile, only the measurement of battery surface temperature can not meet the need for advanced BTMS due to the impact of the large temperature gradient between the surface and internal in high power applications. The battery core temperature estimation will become challenging when encountering sensor bias and noise.