Search Results

Early fault detection is vital in maintaining system stability and to decrease the cost associated with maintenance. This paper presents an approach to identify the fuel line failure for a diesel engine based on vibration signals and machine learning. Vibration measurements are performed on the fuel line of the engine for both normal and faulty conditions for engine ramp up condition. After acquiring the time domain vibration signals, various features were extracted and have been analyzed in time and time-frequency domains. Based on the most effective feature, a machine learning model (i.e., support vector machine (SVM)) for fault diagnosis is developed. Results showed that the proposed SVM based model can detect the fuel line fault correctly. This study can be useful for early detection of this critical fault in diesel engine and take useful decision before any catastrophic failure happens because of this fault.

In the main phase of the European research program PROMETHEUS, a series of innovative traffic information and control systems has been defined and specified. The present paper deals with PROMETHEUS systems supporting longitudinal traffic flow control. The traffic control strategies of these systems are described and their effects on the overall traffic conditions are depicted based on an ad-hoc assessment and a simulation case study.

With the development of automotive industry and transport infrastructure, the number of drivers continues to grow rapidly, and fatigue driving becomes increasingly prominent as one of the major factors causing traffic accidents. Relevant researches show that many traffic accidents can be effectively avoided if the fatigue state of the drivers is monitored in real-time and corresponding alerts are issued in the early period of fatigue driving. At present, driving fatigue state has been recognized through diverse technologies, with the main detection methods based on driving operation data, facial data, or physiological data. The detection method based on driving operation data is the most traditional method and is easy to implement. Nevertheless, due to the influences of road conditions, operation habits and climate conditions, the accuracy is relatively low.

The recent adoption of the ISO26262 Functional Safety Standard has lead to the need for a greater degree of rigor in the technical, organizational and process aspects of electronic ECU engineering. One new facet of this standard also covers (in part 9.7) the analysis of dependent failures at manufacturing time, not only the microcontroller, but also for the plethora of connected system ASICs, input circuits, output drivers and communication devices in the PCB of the ECU. This paper will describe the CAN based end of line ECU self test system that was implemented at a major tier 1 supplier to address the issues of efficiently gaining a high degree of diagnostic coverage of single point faults and latent faults in highly integrated automotive ECUs.

Andrew Grove (founder CEO Intel) defines strategic inflectionpoints as what happens to a business when a major event alters itsfundamentals. The Covid-19 pandemic is one such historic event thatis changing fundamental business assumptions in the Oil industry.Companies with a hunter-gatherer mindset will ride this wave withthe help of technologies that make their operations lean andefficient. Current developments in AI, specifically aroundCognitive Sciences is one such area that will empower the earlyadopters to a many-fold improvement in engineering and researchproductivity. This paper explores 'how to augment the humanintelligence with insights from engineering literature, leveragingCognitive AI techniques?'.

This paper introduces an intelligent energy distribution scheme for series plug-in hybrid electric vehicles (PHEVs) which incorporates the complexity of human driving behavior. Driving styles can have a significant impact on fuel consumption, but it is often unclear how one should drive to get the optimal fuel efficiency. Hybrid electric vehicles have been shown to improve fuel economy, reduce vehicle emissions and maintain drivability by incorporating electric motors into the drivetrain. Due to the highly complex system design and vehicle architecture, sophisticated energy management strategies (EMS) are required to optimize the vehicle performance. Currently, the power management system is based on static thresholds optimized on a fixed drive cycle for a given vehicle. This paper introduces an adaptive control method for EMS utilizing the complexity of human driving patterns for energy distribution in a series PHEV.

Hybrid electric vehicles (HEV's) are facing increasing challenges in optimizing the energy flow through a vehicle system, in order to improve both fuel economy and vehicle emissions. Energy management of HEV's is a difficult task due to the complexity of the total system in terms of electrical, mechanical and thermal behavior. In this paper, an advanced control strategy for a parallel hybrid vehicle is developed. Four main steps are presented, particularly to achieve a reduction in fuel consumption. The first step is the development of a highly complex HEV model, including dynamic and thermal behavior. Second, a heuristical control strategy is developed to determine the HEV modes and third, a State of Charge (SoC) leveling is developed with the interaction of a fuzzy logic controller. It is proposed to calculate the load point shifting of the Internal Combustion Engine (ICE) and the desired battery SoC.

In the handheld industry the carburetor controlled 2-stroke engine is still the mostly used power source. The current carburetor as a fixed geometric and hydraulic system is not capable of compensating varying fuel specifications. Electronic engine management systems offer the adjustment of varying ambient conditions and fuel qualities. State of the art systems of common vehicle applications use various sensors and actuators which increase the complexity and the costs of the engine. A smart alternative is an engine control based upon processing of already existing information in a small handheld engine. This paper presents the concept, the configuration and the design parameters of such a system.

Active control of vehicle suspension systems typically relies on linear, time-invariant, lumped-parameter dynamic models. While these models are convenient, nominally accurate, and tractable due to the abundance of linear control techniques, they neglect potentially significant nonlinearities and time-varying dynamics present in real suspension systems. One approach to improving the effectiveness of such linear control applications is to introduce time and spatially-dependent coefficients, making the model adaptable to parameter variations and unmodeled dynamics. In this paper, the authors demonstrate an intelligent parameter estimation approach, using structured artificial neural networks, to continually adapt the lumped parameters of a linear, quarter-car suspension model. Results are presented for simulated and experimental quarter-vehicle suspension system data, and clearly demonstrate the viability of this approach.

October 2010 has brought major change over in Indian Auto Industries, with all India going BS-III Emission compliant (Metro with BS-IV Emission norms). During that time majority of the utility segment vehicles were having diesel engine with simple mechanical fuel injection system. To make these vehicles BS-III compliance cost effectively, with same fuel economy and reliability, was a challenging task. To enable this, Exhaust Gas Recirculation (EGR) through simple pneumatic EGR valve was the optimum technique. The EGR valve was controlled by means of simple Electronic Control Unit (ECU). Limitations of mechanical diesel fuel injection pump, stringent emission regulations, coupled with production constraints and variations, calls for robust control logics for governing EGR. The present work describes the robust strategies and logics of intelligent EGR governing of a 2.5 l, four Cylinder turbocharged, mechanical pump diesel engine for a BS-III compliant multi utility vehicle.

According to the situation analysis of automotive dynamic assembly in using, and the fault diagnosis and inspection in production, a set of intelligent fault diagnosis and inspection system was developed based on sound intensity identification. By analyzing the system requirements and defining the design rules, the whole architecture was given, and its work principle was studied systematically. The software that was used in data process, control and fault diagnosis was developed, several key problems were discussed during software was developed, including of building knowledge base, designing the intelligent fault diagnosis model, and describing input/output mode etc. All of these work would provide guarantee for putting this system in practice.

This paper describes two smart fault tolerant systems (EURECA TCU and Pump Package ECU) that have been studied by MICROTECNICA in the frame of European Space programs. EURECA TCU: The TCU is the electronic unit of the FURECA Thermal Control System and consists of two cold redundant sections each with the prime task of controlling the temperature of 129 points on the carrier. It does this by switching on and off the appropriate heater, according to the temperature measured by the dedicated thermistors. Each control loop (thermistor, TCU, heater) is dual redundant and con be in case of one failure. The system can tolerate one failure without the loss of the correspondent control function. PUMP PACKAGE ECU: This is a proposed system to act as the electronic unit for the control and regulation of the mass Flow of a water and/or freon pump package. It consists of two redundant electronic control channels.

In the filter industry conventional differential pressure indicator devices, which are mounted into the filter housing, generally have only one actuation setting. This setting is based on a predetermined value of differential pressure across the filter element (i.e., the difference in pressure measured upstream and downstream of the filter). When the differential pressure exceeds a certain preload setting, a “pop-up” button and/or electrical signal is activated. Normally the user does not know how long it will take for the filter element to become clogged by the contaminants it continually captures. The user only becomes aware upon actuation that this differential pressure has been reached. The purpose of this paper is to describe a hydraulic fluid monitoring device which has been developed to provide real time, continuous data for the differential pressure developed across a filter within the hydraulic system.

In this paper, we show an application for controlling a fleet of vehicles, specially designed for Transport Companies. The main goal of this application is to achieve an optimized resources management for a transport company, as well as a more efficient and safe transport of goods. The system has built-in intelligent modules to perform optimization tasks related to route planning, pickup and delivery of goods, and transport costs estimation based on historical and current data. Also, a Geographic Information System was developed and included as an active component of our system, to represent the vehicle location obtained by means of GPS and transmitted via GSM/SMS. The user interface is the front/end tool of the fleet operator in order to manage all resource and track their usage.

This paper summarizes the development of multi-functional intelligent flexible materials for deployable space structures, otherwise known as the InFlex program. The goal of the work was to enhance the capabilities of inflatable structures for exploration activities such as habitats, airlocks, and space suits, with improved materials ultimately to reduce crew burden and lifecycle costs, improve system safety, and reduce system mass and launch volume. Several technical areas were investigated concurrently in an effort to combine functions and create efficient structures. These included self-healing materials, structural health monitoring systems, radiation protective materials, reduced permeability materials, anti-microbial materials, and embedded power generation and storage technologies. Methods of signal transfer were also studied in conjunction with a centralized display and warning system to interact with systems operations personnel.

This paper summarizes an effort to develop and demonstrate an Intelligent Flight Trainer (IFT) for Initial Entry Rotary Wing (IERW) training. Demonstration of concept feasibility relies on an Intelligent Tutoring System (ITS) architecture incorporating Adaptive Training to progressively improve student pilot proficiency. The IFT structure includes: a teacher model which includes algorithmic and expert system assessments of student performance; a domain expert model which maintains knowledge of maneuver criteria and strategies; and a student model which reflects student proficiency. Under an initial feasibility effort we implemented the IFT, integrated it with the UH-1 Training Research Simulator (UH-1TRS) at Fort Rucker, and demonstrated real-time operation in teaching student pilots elementary hover maneuvers.

The authors have developed an intelligent four-wheel drive system (I-4WD) designed to distribute the driving force to the front and rear wheels at the optimum ratio according to the running condition of the vehicle. The I-4WD consists of a center differential which distributes 30 percent of the driving force to front wheels and 70 percent to rear wheels (30:70), a hydraulic multi-disk clutch, an electronic control unit and a hydraulic control circuit. The driving force distribution can be steplessly varied from 30:70 up to the rigid state by controlling the hydraulic pressure on the clutch. The main control algorithm is based on the“yaw velocity model following control.” This composition has allowed us to accurately balance the cornering performance and stability without spoiling the critical limit predictability which is that the driver knows in advance the critical limit of vehicle dynamics.

After comparing magnetosensor technologies for automotive use the system aspects of wheelspeed sensors for vehicle stability systems are discussed. A new generation of intelligent differential Hall Effect-based sensors is described focussing on technology, operating principle and circuitry of the Hall IC. The final realization of the wheel speed sensor is presented concluding with a summary of the main advantages of this concept.

By using telecommunications, Intelligent Transport Systems (ITS) improve traffic safety and efficiency, facilitating an integral transport of people and goods. Even with the benefits obtained through ITS Systems nowadays, significant innovations will take place in the following years such as the ubiquitous and integral use of computer vision, or the development and future implementation of Cooperative ITS (C-ITS) that will allow a direct communication between vehicles (Vehicle-to-Vehicle, V2V) and with the roadside elements (Vehicle-to-Infrastructure, V2I) by means of mobile and wireless communication. In this context, the INTELVIA project was implemented, with the clear objective of developing ITS technologies and Intelligent Human-Machine Interfaces (HMI) to obtain the advantages of using information and communication technologies in the field of road transport and traffic management.

Lighting and signaling functions are key factors for road safety and driving comfort at night. Night-time traffic represents 20 % of total mileage, but generates more than 50 % of fatalities. This percentage is even nigher in adverse weather conditions. New developments are being proposed to improve safety when driving at night. Systems which take account of environmental factors modify the beam pattern in accordance with driving conditions. Automatic beam modification is one of several projects grouped together in the wider approach known as Intelligent lighting. This approach differs from current vehicle lighting techniques which, being based on legal and regulatory requirements, entail design and testing in static conditions. Intelligent lighting involves electronic data acquisition and processing, with the target of altering the shape, the relative intensity, the aim and the direction of the headlamps in accordance with the prevailing conditions.