Search Results

This article characterizes the special features of drilling of CFRP/Titanium and -Aluminium stacks. Simplified theoretic models will show how CFRP/Titanium stacks should be machined without scratches and burn marks contacting carbon. Low axial forces and smart chip removal technology are the main characteristics of the drilling tool technology, optimized to reach H8 quality in one shot operation. Presenter Peter Mueller-Hummel, Cutting Tools Inc.

Exatec� PC glazing technology team, has developed advanced weathering and abrasion resistant coatings technology that can be applied to protect polycarbonate. It is of particular interest to quantify and understand the factors that determine the surface abrasion performance of coated PC in rear window and backlight applications that have a wiper system. In the present study we describe Exatec's lab scale wiper testing equipment and test protocols. We also describe adaptation of optical imaging system to measure contrast and nano-profiling using nano-indenter, as post wiper surface characterization methods. These methods are more sensitive to fine scratches on glazing surface than standard haze measurement and mechanical profilometry. Three coating systems were investigated; Siloxane wetcoat (A), Siloxane wetcoat (B), and Siloxane wetcoat (B) plus plasma coat (Exatec� E900 coating). The performance comparisons were made using all these surface characterization methods.

Abstract Lane changes are stressful maneuvers for drivers, particularly during high-speed traffic flows. However, modeling driver’s lane-changing decision and implementation process is challenging due to the complexity and uncertainty of driving behaviors. To address this issue, this article presents a personalized Lane-Changing Model (LCM) for Advanced Driver Assistance System (ADAS) based on deep learning method. The LCM contains three major computational components. Firstly, with abundant inputs of Root Residual Network (Root-ResNet), LCM is able to exploit more local information from the front view video data. Secondly, the LCM has an ability of learning the global spatial-temporal information via Temporal Modeling Blocks (TMBs). Finally, a two-layer Long Short-Term Memory (LSTM) network is used to learn video contextual features combined with lane boundary based distance features in lane change events.

Abstract Real-time reconstruction of 3D environment attributed with semantic information is significant for a variety of applications, such as obstacle detection, traffic scene comprehension and autonomous navigation. The current approaches to achieve it are mainly using stereo vision, Structure from Motion (SfM) or mobile LiDAR sensors. Each of these approaches has its own limitation, stereo vision has high computational cost, SfM needs accurate calibration between a sequences of images, and the onboard LiDAR sensor can only provide sparse points without color information. This paper describes a novel method for traffic scene semantic segmentation by combining sparse LiDAR point cloud (e.g. from Velodyne scans), with monocular color image. The key novelty of the method is the semantic coupling of stereoscopic point cloud with color lattice from camera image labelled through a Convolutional Neural Network (CNN).

Abstract In this paper, an efficient lane detection using deep feature extraction method is proposed to achieve real-time lane detection in diverse road environment. The method contains three main stages: 1) pre-processing, 2) deep lane feature extraction and 3) lane fitting. In pre-processing stage, the inverse perspective mapping (IPM) is used to obtain a bird's eye view of the road image, and then an edge image is generated using the canny operator. In deep lane feature extraction stage, an advanced lane extraction method is proposed. Firstly, line segment detector (LSD) is applied to achieve the fast line segment detection in the IPM image. After that, a proposed adaptive lane clustering algorithm is employed to gather the adjacent line segments generated by the LSD method. Finally, a proposed local gray value maximum cascaded spatial correlation filter (GMSF) algorithm is used to extract the target lane lines among the multiple lines.

Abstract Obstacle avoidance is an important function in self-driving vehicle control. When the vehicle move from any arbitrary start positions to any target positions in environment, a proper path must avoid both static obstacles and moving obstacles of arbitrary shape. There are many possible scenarios, manually tackling all possible cases will likely yield a too simplistic policy. In this paper reinforcement learning is applied to the problem to form effective strategies. There are two major challenges that make self-driving vehicle different from other robotic tasks. Firstly, in order to control the vehicle precisely, the action space must be continuous which can’t be dealt with by traditional Q-learning. Secondly, self-driving vehicle must satisfy various constraints including vehicle dynamics constraints and traffic rules constraints. Three contributions are made in this paper.

Abstract The dynamic characteristics of tires are critical in the overall vibrations of vehicles because the tire-road interface is the only medium of energy transfer between the vehicle and the road surface. Obtaining the natural frequencies and mode shapes of the tire helps in improving the comfort of the passengers. The vibrational characteristics of structures are usually obtained by performing conventional impact hammer modal testing, in which the structure is excited with an impact hammer and the response of the structure under excitation is captured using accelerometers. However, this approach only provides the response of the structure at a few discrete locations, and it is challenging to use this procedure for rotating structures. Digital Image Correlation (DIC) helps in overcoming these challenges by providing the full-field response of the structure.

Abstract The use of nanomaterials and nanostructures have been revolutionizing the advancements of science and technology in various engineering and medical fields. As an example, Carbon Nanotubes (CNTs) have been extensively used for the improvement of mechanical, thermal, electrical, magnetic, and deteriorative properties of traditional composite materials for applications in high-performance structures. The exceptional materials properties of CNTs (i.e., mechanical, magnetic, thermal, and electrical) have introduced them as promising candidates for reinforcement of traditional composites. Most structural configurations of CNTs provide superior material properties; however, their geometrical shapes can deliver different features and characteristics. As one of the unique geometrical configurations, helical CNTs have a great potential for improvement of mechanical, thermal, and electrical properties of polymeric resin composites.

Abstract The present study aims to join the dissimilar materials such as Dual-Phase (DP) 600 Steel and AA6082-T6 Aluminum (Al) alloy via the friction stir welding (FSW) process with a reduced intermetallic compound (IMC) layer. The five different tool tilt angles of 0°, 0.5°, 1°, 1.5°, and 2° were selected to fabricate the joints. The weld characteristics such as tensile strength, hardness, macrostructure, and microstructure were analyzed. The weld interface was studied by employing an optical microscope and scanning electron microscope (SEM) equipped with energy-dispersive X-ray spectroscopy (EDS) and X-ray diffraction (XRD) techniques. The joint produced with a 0.5° tilt angle has achieved the highest ultimate tensile strength (UTS) of 240 MPa. The IMCs were identified as Fe2Al8 and FeAl2 from the joint interface studies.

Abstract Vaporizing foil actuator welding (VFAW) created nominally solid-state spot welds between high-strength DP980 steel and 6022 T4 aluminum. The effects of varying the impact velocity and angle between the Al flyer and target steel sheets on the structure and properties of the joints were evaluated using photonic Doppler velocimetry (PDV), scanning electron microscopy (SEM), fractography, and energy-dispersive spectroscopy (EDS) analysis. The incident angle and velocity of the flyer plate were quantified using PDV, and their relations to the structure and properties of the joint were assessed with microscopy and strength testing. Impact velocity and average impact angle increase with the increasing standoff. Lower impact angles and higher impact velocities promoted interfacial failure due to increased melting, higher intermetallic thickness, and lower wave amplitude and wavelength.

Abstract The causes of failure due to cracking in the resistance spot welding of the advanced high-strength steels dual-phase 590 (DP590) were investigated using scanning electron microscopy (SEM), optical microscopy, and the tensile-shear test. The results showed that by increasing the current amount, the formation of the melting zone occurred in the heat-affected zone, leading to the cracking in this area, reducing the tensile strength and decreasing the mechanical properties; the initiation and growth of cracking and failure in this region also happened. In the heat-affected zone, by increasing the current amount with the softening phenomenon, the recrystallized coarse grains also occurred, eventually resulting in the loss of mechanical properties. The results of the tensile-shear test also indicated that by increasing the current up to 12 kA, the strength was raised, but the ductility was reduced.

Abstract This paper presents a machine learning application of the force/torque sensor in a human-robot collaborative manufacturing scenario. The purpose is to simplify the programming for physical interactions between the human operators and industrial robots in a hybrid manufacturing cell which combines several robotic applications, such as parts manipulation, assembly, sealing and painting, etc. A multiclass classifier using Light Gradient Boosting Machine (LightGBM) is first introduced in a robotic application for discriminating five different contact states w.r.t. the force/torque data. A systematic approach to train machine-learning based classifiers is presented, thus opens a door for enabling LightGBM with robotic data process. The total task time is reduced largely because force transitions can be detected on-the-fly. Experiments on an ABB force sensor and an industrial robot demonstrate the feasibility of the proposed method.

Abstract In an automated machining process, monitoring the conditions of the tool is essential for deciding to replace or repair the tool without any manual intervention. Intelligent models built with sensor information and machine learning techniques are predicting the condition of the tool with good accuracy. In this study, statistical models are developed to identify the conditions of the abrasive grinding wheel using the Acoustic Emission (AE) signature acquired during the surface grinding operation. Abrasive grinding wheel conditions are identified using the abrasive wheel wear plot established by conducting experiments. The piezoelectric sensor is used to capture the AE from the grinding process, and statistical features of the abrasive wheel conditions are extracted in time and wavelet domains of the signature. Machine learning algorithms, namely, Classification and Regression Trees (CART) and Support Vector Classifiers (SVC), are used to build statistical models.

Abstract Future SAE Level 4 and Level 5 autonomous vehicles (AV) will require novel applications of localization, perception, control, and artificial intelligence technology in order to offer innovative and disruptive solutions to current mobility problems. This article concentrates on low-speed autonomous shuttles that are transitioning from being tested in limited traffic, dedicated routes to being deployed as SAE Level 4 automated driving vehicles in urban environments like college campuses and outdoor shopping centers within smart cities. The Ohio State University has designated a small segment in an underserved area of the campus as an initial AV pilot test route for the deployment of low-speed autonomous shuttles. This article presents initial results of ongoing work on developing solutions to the localization and perception challenges of this planned pilot deployment.

Abstract To evaluate that automated vehicle is as safe as a human driver, a following question is studied: how does an automated vehicle react under extreme conditions close to collision? In order to understand the collision avoidance capability of an automated vehicle, we should analyze not only such post-extreme condition behavior but also pre-extreme condition behavior. We present a theory to analyze the collision avoidance capability of automated driving technologies. We also formulate a collision avoidance equation on the theory. The equation has two types of solutions: response driving plans and preparation driving plans. The response driving plans are supported by response strategy on which the vehicle reacts after detection of a hazard and they are highly efficient in terms of travel time.

Abstract Management of expressway networks has been mainly focused on defect management without looking at the correlations with accidental risks. This causes unsustainability in expressway infrastructure maintenance since such defects may not be a contributing factor toward public safety. Thus it is necessary to incorporate accidental events for decision-making in infrastructure management. This study has developed a novel approach to machine learning (ML) that incorporates actual primary data from the last 10 years of single-vehicle accidents (SVA) by collisions with motorway facilities, or so-called single-vehicle collisions with fixed objects. The ML is firstly aimed at identifying the influential factors of SVA in relation to finding effective countermeasures for accidents by integrating the correlation analysis, multiple regression analysis, and ML techniques. The study reveals that wet pavement conditions have a significant effect on SVA.

Diesel injection parameters effect on liquid-phase diesel spray penetration after the end-of-injection (EOI) is investigated in a constant-volume chamber over a range of ambient and injector conditions typical of a diesel engine. Our past work showed that the maximum liquid penetration length of a diesel spray may recede towards the injector after EOI at some conditions. Analysis employing a transient jet entrainment model showed that increased fuel-ambient mixing occurs during the fuel-injection-rate ramp-down as increased ambient-entrainment rates progress downstream (i.e. the entrainment wave), permitting complete fuel vaporization at distances closer to the injector than the quasi-steady liquid length. To clarify the liquid-length recession process, in this study we report Mie-scatter imaging results near EOI over a range of injection pressure, nozzle size, fuel type, and rate-of-injection shape. We then use a transient jet entrainment model for detailed analysis.

Quantitative planar laser-induced fluorescence (PLIF) of gaseous acetone as a fuel-tracer has been used in an optically accessible engine, fueled by direct hydrogen injection. The purpose of this article is to assess the accuracy and precision of the measurement and the associated data reduction procedures. A detailed description of the acetone seeding system is given as well. The key features of the experiment are a high-pressure bubbler saturating the hydrogen fuel with acetone vapor, direct injection into an optical engine, excitation of acetone fluorescence with an Nd:YAG laser at 266 nm, and detection of the resulting fluorescence by an unintensified camera. Key steps in the quantification of the single-shot imaging data are an in-situ calibration and a correction for the effect of local temperature on the fluorescence measurement.