Neural Network Based Automotive Clutch Model for Dynamic Engagement Analysis With Variable Time Steps

2000 ◽  
Author(s):  
M. Cao ◽  
K. W. Wang ◽  
Y. Fujii ◽  
W. E. Tobler
Keyword(s):  
Neural Network ◽  
Automatic Transmission ◽  
Operating Conditions ◽  
Hybrid Network ◽  
Time Step ◽  
Neural Network Approach ◽  
Time Pattern ◽  
Variable Time ◽  
Powertrain System ◽  
Wide Range

Abstract The lubricated clutch in an automatic transmission plays an important role in the performance and comfort of passenger vehicles. Therefore, an accurate and easy-to-implement dynamic clutch model is necessary for powertrain system design and performance studies. A neural network approach recently developed by Parvataneni et al. [1999] for clutch modeling has illustrated some very promising results. However, this model has complex architecture that may cause slow training and testing. Also, due to the lack of time information, the network cannot adapt to time step variations. Therefore, it cannot be easily integrated with powertrain system models, which in general require variable time steps for a superior numerical integration performance. In this paper, a new first-principle-based hybrid network clutch model is derived for dynamic engagement analysis with variable time steps. With improvement over the previous work by Parvataneni et al. [1999], the time pattern information is added to the inputs and a simpler architecture is developed through more explicit utilization of the physical laws. A second order training algorithm with dynamic derivatives is also used to improve the training efficiency and accuracy. With these new features, this model can significantly outperform the previous approach in terms of accuracy and efficiency. The network is trained and tested using experimental data as well as analytical results. It is shown that this new model can compensate for time step variations and can predict the clutch torque accurately for a wide range of operating conditions.

Automatic Transmission Shift Calibration Based on Parallel-Modulated Neural Network (PMNN) Friction Component Model

2004 ◽  
Author(s):  
M. Cao ◽  
K. W. Wang ◽  
Y. Fujii ◽  
W. E. Tobler
Keyword(s):  
Neural Network ◽  
Controller Design ◽  
Automatic Transmission ◽  
Applied Pressure ◽  
Operating Conditions ◽  
Component Model ◽  
Powertrain System ◽  
Friction Component ◽  
Wide Range ◽  
Shift Dynamics

The parallel-modulated-neural-network (PMNN) -based friction component model [19] provides a simple pressure-torque formula, which possesses much improved scalability with respect to the applied pressure. In this paper, the PMNN friction component model is implemented within a comprehensive powertrain model, to simulate the shifting process of an automatic transmission (AT) system under various operating conditions. Simulation results demonstrate that the PMNN model can be effectively applied as a part of powertrain system model to accurately predict transmission shift dynamics. A pressure-profiling scheme through a quadratic polynomial pressure-torque relationship from the PMNN model is developed for the transmission shifting optimization. This scheme is implemented to improve the transmission shifting quality under certain operating conditions. The pressure profiling results illustrate that the proposed pressure profiling technique can be potentially applied to a wide range of operating conditions. This study demonstrates that the PMNN architecture not only outperforms the conventional network modeling techniques in accuracy and numerical efficiency, but is also a new tool for AT controller design.

Development of a Friction Component Model for Automotive Powertrain System Analysis and Shift Controller Design based on Parallel-Modulated Neural Networks

2004 ◽  
Vol 127 (3) ◽  
pp. 382-405 ◽  
Author(s):  
M. Cao ◽  
K. W. Wang ◽  
Y. Fujii ◽  
W. E. Tobler
Keyword(s):  
Neural Network ◽  
Controller Design ◽  
Automatic Transmission ◽  
Analytical Data ◽  
Operating Conditions ◽  
Component Model ◽  
System Model ◽  
Powertrain System ◽  
Friction Component ◽  
Wide Range

In this study, a new hybrid-neural-network-based friction component model is developed for powertrain (PT) dynamic analysis and controller design. This new model, with significantly improved input-output scalability over conventional neural network configuration, has the capability to serve as a forward as well as an inverse system model. The structural information of the available physical and empirical correlations is utilized to construct a parallel-modulated neural network (PMNN) architecture consisting of small parallel sub-networks reflecting specific mechanisms of the friction component engagement process. The PMNN friction component model isolates the contribution of engagement pressure on engagement torque while identifying the nonlinear characteristics of the pressure-torque correlation. Furthermore, it provides a simple torque formula that is scalable with respect to engagement pressure. The network is successfully trained, tested and analyzed, first using analytical data at the component level and then using experimental data measured in a transmission system. The PMNN friction component model, together with a comprehensive powertrain model, is implemented to simulate the shifting process of an automatic transmission (AT) system under various operating conditions. Simulation results demonstrate that the PMNN model can be effectively applied as a part of powertrain system model to accurately predict transmission shift dynamics. A pressure-profiling scheme using a quadratic polynomial pressure-torque relationship of the PMNN model is developed for transmission shift controller design. The results illustrate that the proposed pressure profiling technique can be applied to a wide range of operating conditions. This study demonstrates the potential of the PMNN architecture as a new dynamic system-modeling concept: It not only outperforms the conventional network modeling techniques in accuracy and numerical efficiency, but also provides a new tool for transmission controller design to improve shift quality.

Development of a Hybrid Artificial Neural Network and Genetic Algorithm Model for Regime Identification of Slurry Transport in Pipelines

2009 ◽  
Vol 4 (1) ◽  
Author(s):  
Sandip K Lahiri ◽  
Kartik Chandra Ghanta
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Artificial Neural Network ◽  
Operating Conditions ◽  
Misclassification Error ◽  
Wide Range ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Pipeline Design ◽  
Hybrid Artificial Neural Network

Four distinct regimes were found existent (namely sliding bed, saltation, heterogeneous suspension and homogeneous suspension) in slurry flow in pipeline depending upon the average velocity of flow. In the literature, few numbers of correlations has been proposed for identification of these regimes in slurry pipelines. Regime identification is important for slurry pipeline design as they are the prerequisite to apply different pressure drop correlation in different regime. However, available correlations fail to predict the regime over a wide range of conditions. Based on a databank of around 800 measurements collected from the open literature, a method has been proposed to identify the regime using artificial neural network (ANN) modeling. The method incorporates hybrid artificial neural network and genetic algorithm technique (ANN-GA) for efficient tuning of ANN meta parameters. Statistical analysis showed that the proposed method has an average misclassification error of 0.03%. A comparison with selected correlations in the literature showed that the developed ANN-GA method noticeably improved prediction of regime over a wide range of operating conditions, physical properties, and pipe diameters.

Unsteady Conjugate Heat Transfer Investigation of a Multistage Steam Turbine in Warm-Keeping Operation With Hot Air

2018 ◽  
Author(s):  
Piotr Łuczyński ◽  
Dennis Toebben ◽  
Manfred Wirsum ◽  
Wolfgang F. D. Mohr ◽  
Klaus Helbig
Keyword(s):  
Heat Transfer ◽  
Conjugate Heat Transfer ◽  
Flow Patterns ◽  
Operating Conditions ◽  
Angle Of Incidence ◽  
Time Step ◽  
Hot Air ◽  
Wide Range ◽  
Vortex Systems ◽  
Operating Points

In recent decades, the rising share of commonly subsidized renewable energy especially affects the operational strategy of conventional power plants. In pursuit of flexibility improvements, extension of life cycle, in addition to a reduction in start-up time, General Electric has developed a product to warm-keep high/intermediate pressure steam turbines using hot air. In order to optimize the warm-keeping operation and to gain knowledge about the dominant heat transfer phenomena and flow structures, detailed numerical investigations are required. Considering specific warm-keeping operating conditions characterized by high turbulent flows, it is required to conduct calculations based on time-consuming unsteady conjugate heat transfer (CHT) simulations. In order to investigate the warm-keeping process as found in the presented research, single and multistage numerical turbine models were developed. Furthermore, an innovative calculation approach called the Equalized Timescales Method (ET) was applied for the modeling of unsteady conjugate heat transfer (CHT). The unsteady approach improves the accuracy of the stationary simulations and enables the determination of the multistage turbine models. In the course of the research, two particular input variables of the ET approach — speed up factor (SF) and time step (TS) — have been additionally investigated with regard to their high impact on the calculation time and the quality of the results. Using the ET method, the mass flow rate and the rotational speed were varied to generate a database of warm-keeping operating points. The main goal of this work is to provide a comprehensive knowledge of the flow field and heat transfer in a wide range of turbine warm-keeping operations and to characterize the flow patterns observed at these operating points. For varying values of flow coefficient and angle of incidence, the secondary flow phenomena change from well-known vortex systems occurring in design operation (such as passage, horseshoe and corner vortices) to effects typical for windage, like patterns of alternating vortices and strong backflows. Furthermore, the identified flow patterns have been compared to vortex systems described in cited literature and summarized in the so-called blade vortex diagram. The comparison of heat transfer in the form of charts showing the variation of the Nusselt-numbers with respect to changes in angle of incidence and flow coefficients at specific operating points is additionally provided.

scholarly journals Classification of 41 Hand and Wrist Movements via Surface Electromyogram Using Deep Neural Network

2021 ◽  
Vol 9 ◽  
Author(s):  
Panyawut Sri-iesaranusorn ◽  
Attawit Chaiyaroj ◽  
Chatchai Buekban ◽  
Songphon Dumnin ◽  
Ronachai Pongthornseri ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Low Cost ◽  
Sampling Rate ◽  
Assessment Procedure ◽  
Semg Signal ◽  
Neural Network Approach ◽  
Assessment Protocol ◽  
Wide Range

Surface electromyography (sEMG) is a non-invasive and straightforward way to allow the user to actively control the prosthesis. However, results reported by previous studies on using sEMG for hand and wrist movement classification vary by a large margin, due to several factors including but not limited to the number of classes and the acquisition protocol. The objective of this paper is to investigate the deep neural network approach on the classification of 41 hand and wrist movements based on the sEMG signal. The proposed models were trained and evaluated using the publicly available database from the Ninapro project, one of the largest public sEMG databases for advanced hand myoelectric prosthetics. Two datasets, DB5 with a low-cost 16 channels and 200 Hz sampling rate setup and DB7 with 12 channels and 2 kHz sampling rate setup, were used for this study. Our approach achieved an overall accuracy of 93.87 ± 1.49 and 91.69 ± 4.68% with a balanced accuracy of 84.00 ± 3.40 and 84.66 ± 4.78% for DB5 and DB7, respectively. We also observed a performance gain when considering only a subset of the movements, namely the six main hand movements based on six prehensile patterns from the Southampton Hand Assessment Procedure (SHAP), a clinically validated hand functional assessment protocol. Classification on only the SHAP movements in DB5 attained an overall accuracy of 98.82 ± 0.58% with a balanced accuracy of 94.48 ± 2.55%. With the same set of movements, our model also achieved an overall accuracy of 99.00% with a balanced accuracy of 91.27% on data from one of the amputee participants in DB7. These results suggest that with more data on the amputee subjects, our proposal could be a promising approach for controlling versatile prosthetic hands with a wide range of predefined hand and wrist movements.

Development of optimal diesel injection strategy based on the prediction of performance and emissions using deep neural network

2021 ◽  
pp. 146808742110577
Author(s):  
Erdoğan Güner ◽  
Aliriza Kaleli ◽  
Kadir Bakirci ◽  
Mehmet Akif Ceviz
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Operating Conditions ◽  
Exhaust Emission ◽  
Pilot Injection ◽  
Data Set ◽  
Injection Strategy ◽  
Wide Range ◽  
Performance And Emissions ◽  
Main Injection

This study aims to determine the optimal injection strategy by predicting the performance and exhaust emission parameters of a four-cylinder CRDI engine under several operating conditions. The experimental determination procedure is challenging and expensive calibration task since it requires a high number of tests. Many studies have focused on a limited level of parameters. In this study, design of experiments technique and deep neural network (DNN) modeling are used together. The experimental data set for the model is created using Taguchi L16 and L32 orthogonal arrays. The DNN model is developed to predict [Formula: see text], [Formula: see text], HC, and CO emissions with speed, torque, injection timings and fuel quantities of each injection called as pilot1, pilot2, main, and post. In this way, it has become possible to evaluate the effects of a larger number of operating parameters in a wide range than the literature. The developed DNN model predicts the [Formula: see text], [Formula: see text], HC, and CO with R2 0.939, 0.943, 0.963, and 0.966, respectively. Additionally, RMSE and MAE values for the model are between 0.024 and 0.048. The proposed method compared with the conventional look-up table method performs better in reducing the complexity and cost of experiments and exploration of the effects of injection parameters on engine emission and performance characteristics in a wide engine operating range. In conclusion, until 2300 rpm at specified torque (90 Nm), it is found that 70% of fuel quantity should inject in main injection to minimize [Formula: see text] and [Formula: see text] emissions. The post injection quantity should be increased by reducing the amount of main injection from this operating condition on. Furthermore, it is observed that the ratios of pilot injection durations do not change with increasing engine speed, but quantity of first pilot injection is more than that of second pilot injection.

A NEURAL NETWORK APPROACH TO REAL-TIME PATTERN RECOGNITION

2001 ◽  
Vol 15 (06) ◽  
pp. 937-947 ◽  
Author(s):  
JINWEN MA
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Real Time ◽  
Error Probability ◽  
Time Constraints ◽  
Network Approach ◽  
Noisy Environment ◽  
Neural Network Approach ◽  
Time Pattern ◽  
Perceptive Field

This paper presents a new neural network approach to real-time pattern recognition on a given set of binary (or bipolar) sample patterns. The perceptive neuron of a binary pattern is defined and constructed as a binary neuron with a neighborhood perceptive field. Letting its hidden units be the respective perceptive neurons of the patterns, a three-layer forward neural network is constructed to recognize these patterns with minimum error probability in a noisy environment. The theoretical and simulation analyses show that the network is effective for pattern recognition and can be under strict real-time constraints.

Development of a Semi-implicit Solver for Detailed Chemistry in Internal Combustion Engine Simulations

2006 ◽  
Vol 129 (1) ◽  
pp. 271-278 ◽  
Author(s):  
Long Liang ◽  
Song-Charng Kong ◽  
Chulhwa Jung ◽  
Rolf D. Reitz
Keyword(s):  
Internal Combustion ◽  
Operating Conditions ◽  
Explicit Methods ◽  
Time Step ◽  
Ic Engine ◽  
Specific Internal Energy ◽  
Detailed Chemistry ◽  
Key Species ◽  
Wide Range ◽  
Implicit Solver

An efficient semi-implicit numerical method is developed for solving the detailed chemical kinetic source terms in internal combustion (IC) engine simulations. The detailed chemistry system forms a group of coupled stiff ordinary differential equations (ODEs), which presents a very stringent time-step limitation when solved by standard explicit methods, and is computationally expensive when solved by iterative implicit methods. The present numerical solver uses a stiffly stable noniterative semi-implicit method. The formulation of numerical integration exploits the physical requirement that the species density and specific internal energy in the computational cells must be non-negative, so that the Lipschitz time-step constraint is not present and the computation time step can be orders of magnitude larger than that possible in standard explicit methods. The solver exploits the characteristics of the stiffness of the ODEs by using a sequential sort algorithm that ranks an approximation to the dominant eigenvalues of the system to achieve maximum accuracy. Subcycling within the chemistry solver routine is applied for each computational cell in engine simulations, where the subcycle time step is dynamically determined by monitoring the rate of change of concentration of key species, which have short characteristic time scales and are also important to the chemical heat release. The chemistry solver is applied in the KIVA-3V code to diesel engine simulations. Results are compared to those using the CHEMKIN package, which uses the VODE implicit solver. Good agreement was achieved for a wide range of engine operating conditions, and 40-70% CPU time savings were achieved by the present solver compared to the standard CHEMKIN.

scholarly journals Multi-Degree of Freedom Propeller Force Models Based on a Neural Network and Regression

2020 ◽  
Vol 8 (2) ◽  
pp. 89 ◽  
Author(s):  
Bradford Knight ◽  
Kevin Maki
Keyword(s):  
Neural Network ◽  
Stokes Equations ◽  
Equations Of Motion ◽  
Open Water ◽  
Small Time ◽  
Training Data ◽  
Step Size ◽  
Time Step ◽  
Neural Network Approach ◽  
Time Step Size

Accurate and efficient prediction of the forces on a propeller is critical for analyzing a maneuvering vessel with numerical methods. CFD methods like RANS, LES, or DES can accurately predict the propeller forces, but are computationally expensive due to the need for added mesh discretization around the propeller as well as the requisite small time-step size. One way of mitigating the expense of modeling a maneuvering vessel with CFD is to apply the propeller force as a body force term in the Navier–Stokes equations and to apply the force to the equations of motion. The applied propeller force should be determined with minimal expense and good accuracy. This paper examines and compares nonlinear regression and neural network predictions of the thrust, torque, and side force of a propeller both in open water and in the behind condition. The methods are trained and tested with RANS CFD simulations. The neural network approach is shown to be more accurate and requires less training data than the regression technique.

Using Artificial Neural Network (ANN) for Manipulating Energy Gain of Nansulate Coating

2011 ◽  
Vol 2 (1) ◽  
Author(s):  
Hadi Salehi ◽  
Mosayyeb Amiri ◽  
Morteza Esfandyari
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Artificial Neural Network ◽  
Energy Gain ◽  
Operating Conditions ◽  
Maximum Relative Error ◽  
Ann Model ◽  
Wide Range ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

In this work, an extensive experimental data of Nansulate coating from NanoTechInc were applied to develop an artificial neural network (ANN) model. The Levenberg–Marquart algorithm has been used in network training to predict and calculate the energy gain and energy saving of Nansulate coating. By comparing the obtained results from ANN model with experimental data, it was observed that there is more qualitative and quantitative agreement between ANN model values and experimental data results. Furthermore, the developed ANN model shows more accurate prediction over a wide range of operating conditions. Also, maximum relative error of 3% was observed by comparison of experimental and ANN simulation results.

Sign in / Sign up

Export Citation Format

Share Document