: This thesis applies neural network feature selection techniques to multivariate time series data to improve prediction of a target time series. Two approaches to feature selection are used. First, a subset enumeration method is used to determine which financial indicators are most useful for aiding in prediction of the S&P 500 futures daily price. The candidate indicators evaluated include RSI, Stochastics and several moving averages. Results indicate that the Stochastics and RSI indicators result in better prediction results than the moving averages. The second approach to feature selection is calculation of individual saliency metrics. A new decision boundary-based individual saliency metric, and a classifier independent saliency metric are developed and tested. Ruck's saliency metric, the decision boundary based saliency metric, and the classifier independent saliency metric are compared for a data set consisting of the RSI and Stochastics indicators as well as delayed closing price values. The decision based metric and the Ruck metric results are similar, but the classifier independent metric agrees with neither of the other metrics. The nine most salient features, determined by the decision boundary based metric, are used to train a neural network and the results are presented and compared to other published results. (AN)

/pdf/nonlinear-time-series-analysis-1j3a35n4y3.pdf

Nonlinear Time Series Analysis.

Investigation on the influence of work holding equipment errors on contact characteristics of face-hobbed hypoid gear

Multi-objective optimization of hypoid gears to improve operating characteristics

With more and more stringent regulations related to emissions, the increasing requirement of energy conservation, and the growing concern for global warming, battery electric vehicles are gaining increasing popularity in the market and that may eventually supplant their counterparts, the internal combustion engine and hybrid electric vehicles. Currently, one can classify battery electric vehicles based on their propulsion type, namely: single-motor drive and multi-motor drive. In this paper, a review of architectures and control strategies for the dual-motor coupling propulsion system used in battery electric vehicles is presented. The paper describes different architectures, reviews the means of mechanical coupling and transmission, electromechanical configurations, and summarizes approaches to the control of this emerging class of battery electric vehicles. A comparison of the advantages and disadvantages of dual-motor coupling propulsion system technology for battery electric vehicles is highlighted, and research challenges and prospects are also discussed. This paper intends to serve as a state-of-the-art reference for researchers in the field of dual-motor coupling propulsion systems used in battery electric vehicle development, control, and optimization. 

A review of architectures and control strategies of dual-motor coupling powertrain systems for battery electric vehicles

Heavy goods vehicles exhibit poor braking performance in emergency situations when compared to other vehicles. Part of the problem is caused by sluggish pneumatic brake actuators, which limit the control bandwidth of their antilock braking systems. In addition, heuristic control algorithms are used that do not achieve the maximum braking force throughout the stop. In this article, a novel braking system is introduced for pneumatically braked heavy goods vehicles. The conventional brake actuators are improved by placing high-bandwidth, binary-actuated valves directly on the brake chambers. A made-for-purpose valve is described. It achieves a switching delay of 3–4 ms in tests, which is an order of magnitude faster than solenoids in conventional anti-lock braking systems. The heuristic braking control algorithms are replaced with a wheel slip regulator based on sliding mode control. The combined actuator and slip controller are shown to reduce stopping distances on smooth and rough, high friction (μ = 0.9) surfaces by 10% and 27% respectively in hardware-in-the-loop tests compared with conventional ABS. On smooth and rough, low friction (μ = 0.2) surfaces, stopping distances are reduced by 23% and 25%, respectively. Moreover, the overall air reservoir size required on a heavy goods vehicle is governed by its air usage during an anti-lock braking stop on a low friction, smooth surface. The 37% reduction in air usage observed in hardware-in-the-loop tests on this surface therefore represents the potential reduction in reservoir size that could be achieved by the new system.

Designing and testing an advanced pneumatic braking system for heavy vehicles

Dual-motor Electric Drive Tracked Vehicles (DDTVs) have attracted increasing attention due to their high transmission efficiency and economical fuel consumption. A test bench for the development and validation of new DDTV technologies is necessary and urgent. How to load the vehicle on a DDTV test bench exactly the same as on a real road is a crucial issue when designing the bench. This paper proposes a novel dynamic load emulation method to address this problem. The method adopts dual dynamometers to simulate both the road load and the inertia load that are imposed on the dual independent drive systems. The vehicle’s total inertia equivalent to the drive wheels is calculated with separate consideration of vehicle body, tracks and road wheels to obtain a more accurate inertia load. A speed tracking control strategy with feedforward compensation is implemented to control the dual dynamometers, so as to make the real-time dynamic load emulation possible. Additionally, a MATLAB/Simulink model of the test bench is built based on a dynamics analysis of the platform. Experiments are finally carried out on this test bench under different test conditions. The outcomes show that the proposed load emulation method is effective, and has good robustness and adaptability to complex driving conditions. Besides, the accuracy of the established test bench model is also demonstrated by comparing the results obtained from the simulation model and experiments.

Design and Modeling of a Test Bench for Dual-Motor Electric Drive Tracked Vehicles Based on a Dynamic Load Emulation Method.

This study aims to investigate the hysteresis characteristics of a pneumatic braking system for multi-axle heavy vehicles (MHVs). Hysteresis affects emergency braking performance severely. The fact that MHVs have a large size and complex structure leads to more nonlinear coupling property of the pneumatic braking system compared to normal two-axle vehicles. Thus, theoretical analysis and simulation are not enough when studying hysteresis. In this article, the hysteresis of a pneumatic brake system for an eight-axle vehicle in an emergency braking situation is studied based on a novel test bench. A servo drive device is applied to simulate the driver’s braking intensions normally expressed by opening or moving speed of the brake pedal. With a reasonable arrangement of sensors and the NI LabVIEW platform, both the delay time of eight loops and the response time of each subassembly in a single loop are detected in real time. The outcomes of the experiment show that the delay time of each loop gets longer with the increase of pedal opening, and a quadratic relationship exists between them. Based on this, the pressure transient in the system is fitted to a first-order plus time delay model. Besides, the response time of treadle valve and controlling pipeline accounts for more than 80% of the loop’s total delay time, indicating that these two subassemblies are the main contributors to the hysteresis effect.

https://www.mdpi.com/2076-3417/7/8/799/pdf

An Experimental Study on Hysteresis Characteristics of a Pneumatic Braking System for a Multi-Axle Heavy Vehicle in Emergency Braking Situations

Purpose




The purpose of this paper is to reduce the drag loss and study the effects of operating conditions and groove parameters such as flow rate and temperature of automatic transmission fluid, clearance between plates, groove depth and groove ratio on the drag torque of a wet clutch for vehicles, parametric analysis of the drag torque model of wet multi-plate friction clutch with groove consideration.




Design/methodology/approach




Both experimental and numerical research was carried out in this work. Parametric groove models, full film lubrication flow model and pressure distribution model are established to investigate the effects of the grooves on drag torque of a wet clutch. Multigrid method is used to simplify the solution.




Findings




In this paper, a drag torque model of a wet multi-plate friction clutch based on the basic theory of viscous fluid dynamics is examined through experimental and numerical methods that take grooves into account, and the change trend of drag torque with operating conditions and groove parameters is analyzed.




Originality/value




Multigrid method is used to solve the governing equations, which simplifies the solution process because of the restrictions and interpolation operations between the adjacent layers of coarser and fine grids. These works provide insight into the effect regularity of operating conditions and groove parameters on drag torque of a wet multi-plate friction clutch. Furthermore, variable test conditions and sufficient experimental data are the main functions in the experimental research.

Parametric analysis of the drag torque model of wet multi-plate friction clutch with groove consideration

In this paper, quasi-static tooth contact analysis of hypoid gear drive with coaxiality deviations was presented. Firstly, coaxiality deviations of hypoid gear drive were defined, and the multi-tooth meshing equation with coaxiality deviations was established, as well as the process of multi-tooth contact analysis (MTCA). Secondly, a hypoid gear drive was chosen for the case studies and the effects of coaxiality deviations on the meshing characteristics were obtained. The combined effect of coaxiality deviations was obtained, and the optimal setting method of the initial phase angles of the gear and the pinion axis eccentricities on the transmission error was discussed. Furthermore, the FEM of a simplified hypoid gear drive system has been set up, which results confirm the correctness of the formula calculation method. The research provided a theoretical reference for optimal design, dynamic analysis, mounting adjustment, performance testing, etc., of spiral bevel and hypoid gear drives.

Quasi-static tooth contact analysis of hypoid gear drive with coaxiality deviations

Dual-motor electric drive tracked vehicles (DDTVs) have drawn much attention in the trends of hybridization and electrification for tracked vehicles. Their transmission chains differ significantly from the traditional ones. Due to the complication and slug of a traditional tracked vehicle braking system, as well as the difference of track-ground with tire-road, research of antilock braking control of tracked vehicles is rather lacking. With the application of permanent magnet synchronous motors (PMSMs), applying an advanced braking control strategy becomes practical. This paper develops a novel emergency braking control strategy using a sliding mode slip ratio controller and a rule-based braking torque allocating method. Simulations are conducted under various track-ground conditions for comparing the control performance of the proposed strategy with three other strategies including the full braking strategy, traditional antilock braking strategy, as well as sliding mode slip ratio strategy without the use of motors. For an initial speed of 80 km/h, simulation results show that the proposed control strategy performs the best among all strategies mentioned above. Several hardware-in-the-loop (HIL) experiments are conducted under the same track-ground conditions as the ones in the simulations. The experiment results verified the validity of the proposed emergency braking control strategy.

Xiaojun Zhou

Papers

Design and Modeling of a Test Bench for Dual-Motor Electric Drive Tracked Vehicles Based on a Dynamic Load Emulation Method.

An Experimental Study on Hysteresis Characteristics of a Pneumatic Braking System for a Multi-Axle Heavy Vehicle in Emergency Braking Situations

Parametric analysis of the drag torque model of wet multi-plate friction clutch with groove consideration

Quasi-static tooth contact analysis of hypoid gear drive with coaxiality deviations

A Novel Emergency Braking Control Strategy for Dual-Motor Electric Drive Tracked Vehicles Based on Regenerative Braking