Search Results

Signal processing incorporating Artificial Neural Networks (ANN) has been shown to be well suited for modeling engine-related performance indicators [ 1 , 2 , 3 ] that require multi-dimensional parametric calibration space. However, to obtain acceptable accuracy, traditional ANN implementation may require processing resources beyond the capability of current engine controllers. This paper explores the practicality of implementing an ANN-based algorithm performing real-time calculations of the volumetric efficiency (VE) for an engine with variable valve actuation (phasing and lift variation). This alternative approach was considered attractive since the additional degree of freedom introduced by variable lift would be cumbersome to add to the traditional multi-dimensional table-based representation of VE.

The purpose of the present paper is to develop an engine simulation tool in a commercial CFD code to study the spray and mixing process that can be used to access the performance of a Gasoline Direct Injection (GDI) engine. The ignition, combustion and pollutant formation are strongly dependent on the quality of the fuel-air mixture. The fuel is injected directly into the combustion chamber by high-pressure fuel injector. The fuel atomization and evaporation process takes place due to the interaction of the small fuel particles generated by the injector and the in-cylinder air motion. Experimental study on the spray and mixing process is difficult and expensive, which has been recognized as a major obstacle towards the optimization of the combustion chamber geometry, engine components and the injection strategies.

The Curtain Airbag (CAB) is used currently to provide head and neck protection for the front-seat and rear-seat vehicle occupants during side-impact collisions and vehicle rollovers. The coated fabric materials are used in CABs for occupant protection in side impact and rollover events. In this paper the design and development study of CABs is described by using simulation and physical tests. The mechanical properties for the airbag material are determined by uniaxial test in the fill and warp directions. Shear strength is also evaluated by using the uniaxial test, but the specimen is cut along 45° angle. These test values are used in the finite element (FE) simulations. In this paper, a methodology of the design study is discussed. A Free Motion Headform (FMH) impacting a pole with a pillow shaped airbag is used in the design study. The influences of CAB design parameters such as pressure, chamber width, impact speed and hit location are evaluated.

In embedded system software architectural design, the Real-Time (RT) behavior estimation needs special care and contains many technical challenges. Most of the current approaches depend on either the engineering judgment or the actual measurements that are performed during the integration-testing phase. Both approaches may cause errors that lead to violations in the RT constraints. Both approaches are not error proof and can yield to RT constraints violations discovered during simulation of RT architectural design or during product validation. Impact on project could even be a Central Processing Unit (CPU) change. In this work, Operating System (OS) process Execution Time (ET) is considered the basic element of RT architectural design. Each process ET is predicted based on previous software releases, using Machine Learning (ML) algorithms.

Engine ECU testing requires sophisticated sensor simulation and event capture equipment. FPGAs are the ideal devices to address these requirements. Their high performance and high flexibility are perfectly suited to the rapidly changing test needs of today's advanced ECUs. FPGAs offer significant advantages such as parallel processing, design scalability, ultra-fast pin-to-pin response time, design portability, and lifetime upgradability. All of these benefits are highly valuable when validating constantly bigger embedded software in shorter duration. This paper discusses the collaboration between Valeo and NI to define, implement, and deploy a graphical, open-source, FPGA-based engine simulation library for ECU verification.

In the rapidly evolving era of software and autonomous driving systems, there is a pressing demand for extensive validation and accelerated development. This necessity arises from the need for copious amounts of data to effectively develop and train neural network algorithms, especially for autonomous vehicles equipped with sensor suites encompassing various specialized algorithms, such as object detection, classification, and tracking. To construct a robust system, sensor data fusion plays a vital role. One approach to ensure an ample supply of data is to simulate the physical behavior of sensors within a simulation framework. This methodology guarantees redundancy, robustness, and safety by fusing the raw data from each sensor in the suite, including images, polygons, and point clouds, either on a per-sensor level or on an object level. Creating a physical simulation for a sensor is an extensive and intricate task that demands substantial computational power.

The inverter of the electrical driven compressor (EDC) is subjected to high thermal loads which are resulting from external temperature exposure and from compressor solicitations from the vehicle thermal loop (refrigerant nature, flow rate, compression rate, initial temperature). An incorrect thermal management of the inverter might lead to a significant decrease of efficiency which degrades the performance, product lifetime (electronics components failure) and even worse, might lead to a hazardous thermal event (HTE). The need of the automotive market to drastically decrease project development time, requires decreasing design and simulation activities lead time without degrading the design robustness, which is one additional complexity and challenge for the R&D team.