Lightweight Engine Research Articles

The Development of a Fillet Design Tool Based on Light-Weight Marine Diesel Engine Crankshafts

The Development of a Fillet Design Tool Based on Light-Weight Marine Diesel Engine Crankshafts

Accelerating page loads via streamlining JavaScript engine for distributed learning

Distributed learning based on JavaScript-based frontends is typically implemented at the endpoint to maximize performance. Yet, JavaScript-based frontends often experience suboptimal performance. To reconcile these disparities in performance between EDGE and endpoint deployments, strategic optimization is essential, particularly for preserving privacy in distributed learning. Real-time streaming optimizations are imperative to align the performance of disparate components for smooth integration. The reliance on JavaScript for various web functionalities can lead to increased resource consumption and slower page loads. Thus, we introduce a streamlined JavaScript engine designed to optimize structural patterns in JavaScript code, with three key enhancements. Firstly, we reduce the computational burden of the JavaScript engine necessary for setting up the browser's runtime environment. Secondly, we refine the parsing process for specific code patterns, boosting the efficiency of our lightweight engine. Thirdly, we streamline the Inter-Process Communication (IPC) to maintain high performance, even with limited memory resources. Our evaluations demonstrate that our approach reduces the median Total Computation Time (TCT) by 45.2%, and surpasses existing leading solutions, Siploader and Prepack, with improvements ranging from 1.13× to 1.39×.

Study on acoustic properties of ultra-low-density polyurethane with Nano-Cellulose

Recently, polyurethane materials are commonly used as engine room sound-absorbing materials to reduce the weight of automobiles. Polyurethane materials have excellent sound absorption performance in the 800~2,000 Hz frequency range due to the structural characteristics of the material, but the sound absorption performance of more than 2,000 Hz is insufficient. In the case of electric vehicles, it is important to improve the high frequency noise generated by the motor, and the need for modification of polyurethane materials has increased. High frequency performance can be improved by improving the air permeability of polyurethane cells through the bonding structure of polyurethane materials, optimization of blowing and gelling reactivity, and the amount of foaming gas. Increased air permeability of polyurethane materials reduces density and strength. In this study, Nano-cellulose is a highly functional new material with light and high mechanical properties through a chain bundle structure. The dispersibility is improved by optimizing the content and particle size of nano-cellulose. The goal is to develop ultra-low-density polyurethane with excellent sound absorption performance in high frequency areas over 2,000 Hz and improved strength. The strength of hood insulation and dash outer products can be improved by applying the developed polyurethane material. In addition, the quality of lightweight engine room sound absorbing materials for electric vehicles can be improved.

Abstract 16973: Using an in-vitro and ex-vivo Test Platform for Evaluation of a Pen-Sized Ultrasound Vascular Access Device (Vu-Path)

Introduction: Despite several off-the-shelf ultrasound systems being used for large vessel access, reliable and safe vascular access remains a problem. This is especially true during combat casualty care where skilled operators may not be available. We tested a novel small-footprint platform for efficacy and timeliness of large vessel access at normovolemic and hypovolemic states Hypothesis: A custom-designed device with optimized ergonomics and workflow will yield high success rates and low training needs for large vessel access Methods: Vu-Path has a pen-size 10 mm ultrasound transducer with a proprietary needle guide and a lightweight engine deployed with a tablet or laptop. The display has an overlay showing the needle insertion path. Once the vessel is visible within the overlay, insertion of the needle using the needle guide directs insertion to the vessel. We used 3 models to simulate femoral vessel access: 1) a commercially available phantom (CAE Blue Phantom); 2) a custom in-vitro tissue phantom mimicking swine normovolemic and hypovolemic femoral vascular states; 3) an ex-vivo model of a euthanized swine lower-body section with canulated femoral vessels looped with a peristaltic pump to simulate normovolemic and hypovolemic states. Results: Vu-Path tested in these 3 models resulted in 87% successful insertions across all models and conditions; 100% success on the commercial model versus 83% in the custom tissue phantoms. In every model, 2 metrics were evaluated as summarized in Figure: total time to align vessel in the needle track window, and total time after aligning to confirmed insertion. Mean attempts needed to gain system expertise was 6. Conclusions: Vu-Path had high success rates for vessel visualization and needle access guidance in 3 models simulating normovolemic and hypovolemic conditions. Training requirements were minimal. These data suggest Vu-Path is capable of potentially improving safety and reliability of large vessel access.

Very High Cycle Fatigue Properties and Damage Evolution in Al-Si Cast Alloys

Abstract The steady progress in electro mobility increases the demand for lightweight space frame and engine solutions. Advanced aluminum-silicon cast alloys with additions of magnesium, copper, or both for precipitation hardening are promising candidates for lightweight structures because of their high strength-to-weight ratio. For a reliable design, the fatigue performance in the very high cycle fatigue (VHCF) regime must be understood. Therefore, this study deals with the influence of frequency on VHCF properties as well as fatigue damage evolution in AlSi7Mg and AlSi10Mg sand-cast alloys. The VHCF tests were performed using a resonant (70 Hz), a high-frequency resonant (1 kHz), and an ultrasonic (20 kHz) fatigue testing system. Thereby, a significant frequency effect could be determined that resulted in an increased fatigue lifetime by 1 decade at 1 kHz and by 2 decades at 20 kHz, whereas no significant change in fatigue limit could be determined. Moreover, the fatigue crack initiation mechanisms change from surface crack initiation at 70 Hz and 1 kHz to volume crack initiation at 20 kHz. Using the defect-based Murakami approach, including a lightweight extension of Noguchi, a defect-induced (size, location) frequency effect could be excluded. Based on damage monitoring, the effect could be related to the crack propagation phase, which is accelerated at low frequencies (<100 Hz) because of a humidity reaction with the fatigue crack surface and the formation of atomic hydrogen resulting in a saturated hydrogen embrittlement per cycle. At high frequencies of 1 kHz and 20 kHz, no saturated hydrogen embrittlement per cycle can be reached.

INDIANA—In-Network Distributed Infrastructure for Advanced Network Applications

Data volumes are exploding as sensors proliferate and become more capable. Edge computing is envisioned as a path to distribute processing and reduce latency. Many models of Edge computing consider small devices running conventional software. Our model includes a more lightweight execution engine for network microservices and a network scheduling framework to configure network processing elements to process streams and direct the appropriate traffic to them. In this article, we describe INDIANA, a complete framework for in-network microservices. We will describe how the two components-the INDIANA network Processing Element (InPE) and the Flange Network Operating System (NOS)-work together to achieve effective in-network processing to improve performance in edge to cloud environments. Our processing elements provide lightweight compute units optimized for efficient stream processing. These elements are customizable and vary in sophistication and resource consumption. The Flange NOS provides first-class flow based reasoning to drive function placement, network configuration, and load balancing that can respond dynamically to network conditions. We describe design considerations and discuss our approach and implementations. We evaluate the performance of stream processing and examine the performance of several exemplar applications on networks of increasing scale and complexity.

Enabling Fast and Memory-Efficient Acceleration for Pattern Matching Workloads: The Lightweight Automata Processing Engine

Growing pattern matching applications are employing finite automata as their basic processing model. These applications match tens to thousands of patterns on a large amount of data, which brings a great challenge to conventional processors. Therefore hardware-based solutions have emerged frequently and achieved high throuphput automata processing. However, existing methods are generally difficult to achieve both processing speed and storage efficiency, and are often too heavy to be integrated into a small chip and have to rely on off-chip DRAMs or other high capacity memories even on some simple data sets, leading to the potential area and power consumption issues. In this paper, we focus on building a more lightweight automata processing engine, hoping to store the whole automata model into on-chip memory and run effectively and independently. We propose LAP, a lightweight automata processing engine. Powered with a novel automata model (A-DFA) and efficient packing algorithms, extremely high storage efficiency compared with traditional DFA is achieved in LAP. Meanwhile, we identify the key parallelization factors in the A-DFA model and then propose a specialized microarchitecture with novel instructions to further accelerate the state transition process. As a result, LAP can obtain more effective trade-off between processing speed and storage efficiency. Evaluation results show that LAP achieves extremely high storage efficiency on simple data sets, exceeding IBM's RegX by 8×, and achieves significant improvements in processing speed ranging from 1.32× to 1.91× compared with previous lightweight hardware implementations. Moreover, LAP has good scalability in hardware architecture. It is easy to build an acceleration system with higher throughput by increasing the number of cores. We prototype a 16-core system into Xilinx ZC702 FPGA and a 64-core system into Xilinx ZCU102 FPGA respectively. The prototype system on ZC702 on average achieves 3.5 GB/s throughput on simple data sets, and the prototype system on ZCU102 can obtain higher throughput and compute density values on part of large datasets in ANMLZoo compared with modern in-memory NFA-based solutions.

Heat transfer enhancement of the air-cooled engine fins through geometrical and material analysis: A review

Energy crisis and air pollution are the two leading scientific issues that require global attention. The fundamental reason for the rise in energy costs is the rapid depletion of fossil fuels which has raised fuel prices. Analysis of IC engines suggests thatthermodynamic constraints cause more than half of energy derived from fossil fuels to be lost to the environment. Prolonged working at high temperatures can alter an engine's performance and characteristics. One way of minimizing these losses is to regulate and keep the engine's temperature within the permissible range. Thus, cylinder blocks often include extended surfaces called finsto transfer away the heat from the engine surface. This study focuses on explaining the effect of variation in material, type, design, number of fins, and other parameters in improving fins' efficiency and enhancing the engine's performance. It has been observed that the optimum number of fins can significantly improve fin efficiency, and a 5% to 13% enhancement in heat transfer is possible through fin extension. Elliptical shape fins perform better than triangular and rectangular fins. However, circular and curved fins increase engine efficiency by reducing engine weight. Amongst various fin materials like Cast Iron, Copper, Magnesium, Aluminum, and its alloys, etc., more thermal flux has been observed for Aluminium Alloy 6082. Finally, authors have come to a conclusion that circular fins with holes and slots offer a higher heat transfer rate and improved engine performance at reduced material requirements. The circular fin geometry with slots and holes provides further scope of improvement by optimizing fin thickness, number of holes and slots, their dimensions and spacing to come with a combination that provides effective cooling along with ease of manufacturing in case of lightweight engines.

Lightweight and Identifier-Oblivious Engine for Cryptocurrency Networking Anomaly Detection

The distributed cryptocurrency networking is critical because the information delivered through it drives the mining consensus protocol and the rest of the operations. However, the cryptocurrency peer-to-peer (P2P) network remains vulnerable, and the existing security approaches are either ineffective or inefficient because of the permissionless requirement and the broadcasting overhead. We design and build a Lightweight and Identifier-Oblivious eNgine (LION) for the anomaly detection of the cryptocurrency networking. LION is not only effective in permissionless networking but is also lightweight and practical for the computation-intensive miners. We build LION for anomaly detection and use traffic analyses so that it minimally affects the mining rate and is substantially superior in its computational efficiency than the previous approaches based on machine learning. We implement a LION prototype on an active Bitcoin node to show that LION yields less than 1% of mining rate reduction subject to our prototype, in contrast to the state-of-the-art machine-learning approaches costing 12% or more depending on the algorithms subject to our prototype as well, while having detection accuracy of greater than 97% F1-score against the attack prototypes and real-world anomalies. LION therefore can be deployed on the existing miners without the need to introduce new entities in the cryptocurrency ecosystem.

LeiMot – lightweight engine helps reducing CO2 emissions

Weight reduction remains a primary focus for vehicles to achieve lower CO2 emissions. FEV has collaborated with six other partners on its LeiMot project (“Lightweight Engine”) to demonstrate how much potential internal combustion engines can offer. Major components of a baseline modern Diesel-powered passenger car engine can be made roughly 22 percent lighter thanks to additive manufacturing methods and increased usage of composite materials. At the same time, it was possible to increase the efficiency of engine through optimization of the cooling and oil circuits. Results of this research can be transferred to different engines with fossil, regenerative and renewable fuels as well as to the other powertrain components.

Numerical Prediction of Internal Flows in He/LOx Seals for Liquid Rocket Engine Cryogenic Turbopumps

Cryogenic turbopumps are used in high-performance, lightweight liquid rocket engines for space applications. The development of bearings and shaft seals for cryogenic turbopumps requires detailed characterization of the internal flow, taking into account the effects of boiling and multi-component two-phase flow. Here, a flow network solver was developed to analyse the secondary flow circuit of a cryogenic turbopump where the propellant is mixed with high-temperature helium after bearing cooling. The network solver is based on an extension of a classic 1D homogeneous model, originally developed for a pure substance, to the case of two-phase multi-component flow. The solver is capable of predicting pressures, temperatures, flow rates, and species concentrations in a complex two-phase flow in the presence of non-condensable gases. The unsteady mass, momentum, and energy conservation equations are implemented in conjunction with the thermodynamic equations of state using a general-purpose finite volume formulation, where the pressure drop and the heat transfer are calculated using correlations. The numerical tool was validated by comparing its predictions with experimental data obtained during tests on the secondary circuit of an oxygen turbopump developed at Avio S.p.A. A number of engine operating conditions were considered (inlet helium temperature in the range of 250–280 K, helium/liquid oxygen drain in the range of 165–230 K). The predicted temperature values showed good agreement with the experimental data in most conditions.

EfficientWord-Net: An Open Source Hotword Detection Engine Based on Few-Shot Learning

Voice assistants like Siri, Google Assistant and Alexa are used widely across the globe for home automation. They require the use of unique phrases, also known as hotwords, to wake them up and perform an action like “Hey Alexa!”, “Ok, Google!”, “Hey, Siri!”. These hotword detectors are lightweight real-time engines whose purpose is to detect the hotwords uttered by the user. However, existing engines require thousands of training samples or is closed source seeking a fee. This paper attempts to solve the same, by presenting the design and implementation of a lightweight, easy-to-implement hotword detection engine based on few-shot learning. The engine detects the hotword uttered by the user in real-time with just a few training samples of the hotword. This approach is efficient when compared to existing implementations because the process of adding a new hotword to the existing systems requires enormous amounts of positive and negative training samples, and the model needs to retrain for every hotword, making the existing implementations inefficient in terms of computation and cost. The architecture proposed in this paper has achieved an accuracy of 95.40%.

Achieving enhanced high-temperature mechanical properties in Mg-Nd-Sm-Zn-Ca-Zr alloy by Ag addition

Mg alloys have been attracting particular interests in industrial manufacture. Nevertheless, the poor high-temperature mechanical properties of Mg alloys limit their further practical applications. Thus, as-cast Mg-2.5Nd-1.0Sm-0.4Zn-0.1Ca-0.5Zr-xAg (x = 0, 0.5, 1.0, 1.5, 2.0 wt%) alloys were designed and fabricated to overcome this shortcoming in this study. The influences of Ag addition on the microstructures and mechanical properties of Mg alloys were analyzed in detail. The results indicated that the microstructures of the alloy were composed of equiaxed α-Mg grains and β phase. The content of the β phase increased from 5.56% to 8.91% upon increasing the content of Ag from 0 wt% to 2.0 wt%, indicating that Ag can promote the formation of the β phase significantly. Moreover, the first-principles calculations supported that the formation enthalpy for the β phase was reduced with the doping of Ag resulting in increased stability of the β phase. Ag also enhanced the bulk modulus and ductility of the β phase. Meanwhile, the Young's modulus and elastic anisotropy of the β phase was diminished by Ag addition. The addition of Ag increased the strength and decreased the elongation of the as-cast alloys. The as-cast alloy with 2.0 wt% Ag addition achieved comprehensive mechanical properties. Furthermore, the as-cast alloy with 2.0 wt% Ag addition showed the least decrease in ultimate tensile strength with increasing temperature compared to the other alloys. The ultimate tensile strength of the as-cast alloy with 2.0 wt% Ag addition decreased from 196.0 MPa to 188.8 MPa as the temperature changed from 25 °C to 275 °C. The increase in strength and heat resistance of the alloys is mainly attributed to the increased β phase content and stability. Overall, this work developed a new heat resistant Mg-Nd-Sm-Zn-Ca-Zr-Ag alloy with excellent high-temperature mechanical properties. This suggests that it helps to improve the high-temperature mechanical properties and reliability of new aero engines and promote applications of lightweight engines.

Low Friction and High Wear Resistance of Plasma Electrolytic Oxidation (PEO)-Coated AZ31 Mg Alloy Sliding against Hydrogenated DLC (a-C-H) at Elevated Temperatures

Plasma electrolytic oxidation (PEO) treatment of Mg alloys improves their wear resistance by increasing their surface hardness, but also leads to high coefficient of friction (COF) values. The sliding counterfaces and the conditions under which PEO-coated Mg alloys operate affect their COFs. PEO-coated AZ31 alloy sliding against hydrogenated DLC (a-C-H) coated steel yields a low COF of 0.13 under the ambient conditions. The current study investigates the effect of the test temperature on the tribological behavior of PEO-coated AZ31 Mg samples sliding against the a-C-H coated counterface at temperatures up to 300 °C. According to the COF vs. wear rate diagram constructed in the temperature range of 25–250 °C, lower COF values and wear rates were exhibited by PEO-coated AZ31 sliding against a-C-H compared to uncoated AZ31 sliding against a-C-H, and PEO coated AZ31 sliding against an uncoated ASTM 52100 steel. The PEO-coated AZ31 produced the lowest COF of 0.03 at 200 °C. The application of PEO to the Mg alloy automotive cylinder bores running against DLC-coated piston rings and/or PEO-coated Mg alloy pistons running against DLC-coated bores could provide a new approach for the prevention of seizure and hot scuffing in lightweight engines in the temperature range between 150–250 °C.

Optimization and Verification of the Lightweight Engine Room Bracketof Electrical Vehicle

Optimization and Verification of the Lightweight Engine Room Bracketof Electrical Vehicle

In-circuit tuning of deep learning designs

This paper presents OTune, a novel overlay-based approach for rapid in-circuit debugging and tuning of Deep Neural Network (DNN) designs targeting Field-Programmable Gate Array (FPGA). We first propose overlay-based instruments that provide hardware profiling information to FPGA-based DNN developers for tuning and debugging their designs. Our instrumentation is optimized to take advantage of characteristics of the DNN application domain and traces useful information for in-circuit domain-specific development. Besides, a light-weight overlay-based DNN processing engine is implemented to support rapid word length tuning, which allows adjusting each DNN layer’s datapath without time-consuming FPGA compilation. Furthermore, our approach enables tuning of FPGA-based DNN designs for edge systems, which would benefit developing adaptive learning systems. Evaluation results show that OTune can tune a fixed-point design to the same accuracy as a floating-point one with less than 4% added FPGA area.

Prediction and validation of dynamic characteristics of a valve train system with flexible components and gyroscopic effect

Flexibility and inner stress of transmission components are main considerations in the development of high-precision and lightweight engines. Gyroscopic effect of rotary shaft and rotor should also be considered in high-speed engines. Therefore, an elastic dynamic model of a valve train system is proposed. The model includes multiaxial flexibilities of camshaft and linkages, gyroscopic effect of the camshaft and cam rotor, centrifugal force of cams and friction force and moment of the cam–tappet pair. Then, the natural frequency, mode shape, pushrod stress and housing vibration are predicted using the proposed model. Results show that the gyroscopic effect of the rotors and camshaft apparently affects the natural frequency of the system by changing the camshaft stiffness. The proposed model can effectively predict the dynamic stress, as proven by a stress experiment. In addition, idling and maximum working speeds are recommended using the predicted model and verified by a vibration experiment. Thus, the proposed model can be an important reference in engine adjustment, improvement of component durability and determination of idling and maximum speeds.

MemEnc: A Lightweight, Low-Power, and Transparent Memory Encryption Engine for IoT

Recent advancement in technologies has led to the widespread adoption and deployment of Internet-of-Things devices. Because of the ubiquitous nature of these devices, they process large amounts of personal and sensitive data. These data are typically stored on DRAM chips, and hence becomes an easy target for attackers. Memory encryption is a commonly adopted solution to provide confidentiality. However, realizing a lightweight, low-latency, low-power solution for resource-constrained devices is a challenge. To address this, we designed MemEnc, a purely hardware-based solution that performs encryption on-the-fly and handles memory requests transparently without any OS intervention. MemEnc runs at a maximum frequency of 401 MHz and requires about 23.2 kGE (gate equivalents) on 65-nm ASIC and consumes only 1.9 mW of power at 250 MHz. Using comprehensive benchmarking, we also analyze the applicability of the proposed solution on real-world workloads. Our experiments show that certain real-time applications can run with full memory encryption and still meet system requirements. Moreover, we integrated our memory encryption engine with ARM TrustZone and present comparative results for the different case studies with Intel SGX. We show that static and dynamic efficiency-security tradeoff is necessary for all scenarios.

Spray Characteristics of Air-Assisted Injector Under Different Ambient Pressures

Spray atomization of liquid fuel plays an important role in droplet evaporation, combustible mixture formation and subsequent combustion process. Well-atomized liquid spray contributes to high fuel efficiency and low pollutant emissions. Gasoline direct injection(GDI) has been recognized as one of the most effective ways to improve fuel atomization. As a special direct injection method, the air-assisted direct injection utilizes high-speed flow of high-pressure air at the injector exit to assist liquid fuel injection and promote spray atomization at a low injection pressure. This injection method has excellent application potential and advantages for high performance and lightweight engines. In this study, the hollow cone spray emerging from an air-assisted injector was studied in a constant volume chamber with the ambient pressures ranging from 5 kPa to 300 kPa. External macro characteristics of spray were obtained using high speed backlit imaging. Phase Doppler particle analyzer(PDPA) was utilized to study the microcosmic spray characteristics. The results show that under the flash boiling condition, the spray will generate a strong flash boiling point which causes the cone shape spray to expand both inwards and outwards. The axisymmetric inward expansion would converge together and form a lathy aggregation area below the nozzle and the axisymmetric outward expansion greatly increases the spray width. The sauter mean diameter (SMD) of flash boiling condition can be reduced to 5 μm compared to the level close to 10 μm in the non-flash boiling condition.

Developing an Open-Source Lightweight Game Engine with DNN Support

With the growth of artificial intelligence and deep learning technology, we have many active research works to apply the related techniques in various fields. To test and apply the latest machine learning techniques in gaming, it will be very useful to have a light-weight game engine for quick prototyping. Our game engine is implemented in a cost-effective way, in comparison to well-known commercial proprietary game engines, by utilizing open source products. Due to its simple internal architecture, our game engine is especially beneficial for modifying and reviewing the new functions through quick and repetitive tests. In addition, the game engine has a DNN (deep neural network) module, with which the proposed game engine can apply deep learning techniques to the game features, through applying deep learning algorithms in real-time. Our DNN module uses a simple C++ function interface, rather than additional programming languages and/or scripts. This simplicity enables us to apply machine learning techniques more efficiently and casually to the game applications. We also found some technical issues during our development with open sources. These issues mostly occurred while integrating various open source products into a single game engine. We present details of these technical issues and our solutions.