Application of neural networks to improve forging technology of crankshaft forgings to ensure their balancibility

Abstract For many biological applications, exploration of the massive parametric space of a mechanism-based model can impose a prohibitive computational demand. To overcome this limitation, we present a framework to improve computational efficiency by orders of magnitude. The key concept is to train a neural network using a limited number of simulations generated by a mechanistic model. This number is small enough such that the simulations can be completed in a short time frame but large enough to enable reliable training. The trained neural network can then be used to explore a much larger parametric space. We demonstrate this notion by training neural networks to predict pattern formation and stochastic gene expression. We further demonstrate that using an ensemble of neural networks enables the self-contained evaluation of the quality of each prediction. Our work can be a platform for fast parametric space screening of biological models with user defined objectives.

Download Full-text

Optimization of control program for CNC machines with regarding dynamic stability of cutting process and optimum modes of treatment in conditions of digital production

MATEC Web of Conferences ◽

10.1051/matecconf/201822604016 ◽

2018 ◽

Vol 226 ◽

pp. 04016

Author(s):

Yuri G. Kabaldin ◽

Dmitrii A. Shatagin ◽

Pavel V. Kolchin

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Neural Networks ◽

Dynamic Stability ◽

Control Program ◽

Cutting Process ◽

Cnc Machines ◽

Control Programs ◽

Digital Production ◽

Optimizing Control

The method for optimizing control programs for CNC machines based on artificial intelligence approaches, in particular, the apparatus of artificial neural networks, is outlined. A neural network model of the dynamic stability of the cutting process is proposed, which makes it possible to simulate the dynamics of the cutting process using the CAM system.

Download Full-text

Neural Networks for Postprocessing Ensemble Weather Forecasts

Monthly Weather Review ◽

10.1175/mwr-d-18-0187.1 ◽

2018 ◽

Vol 146 (11) ◽

pp. 3885-3900 ◽

Cited By ~ 43

Author(s):

Stephan Rasp ◽

Sebastian Lerch

Keyword(s):

Neural Network ◽

Neural Networks ◽

Predictive Distribution ◽

Predictor Variables ◽

Specific Information ◽

Observation Data ◽

Neural Network Approach ◽

Weather Forecasts ◽

Probabilistic Forecasts ◽

Trained Neural Network

Abstract Ensemble weather predictions require statistical postprocessing of systematic errors to obtain reliable and accurate probabilistic forecasts. Traditionally, this is accomplished with distributional regression models in which the parameters of a predictive distribution are estimated from a training period. We propose a flexible alternative based on neural networks that can incorporate nonlinear relationships between arbitrary predictor variables and forecast distribution parameters that are automatically learned in a data-driven way rather than requiring prespecified link functions. In a case study of 2-m temperature forecasts at surface stations in Germany, the neural network approach significantly outperforms benchmark postprocessing methods while being computationally more affordable. Key components to this improvement are the use of auxiliary predictor variables and station-specific information with the help of embeddings. Furthermore, the trained neural network can be used to gain insight into the importance of meteorological variables, thereby challenging the notion of neural networks as uninterpretable black boxes. Our approach can easily be extended to other statistical postprocessing and forecasting problems. We anticipate that recent advances in deep learning combined with the ever-increasing amounts of model and observation data will transform the postprocessing of numerical weather forecasts in the coming decade.

Download Full-text

Use of a Multilayer Perceptron to Automate Terrain Assessment for the Needs of the Armed Forces

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi7110430 ◽

2018 ◽

Vol 7 (11) ◽

pp. 430 ◽

Cited By ~ 3

Author(s):

Krzysztof Pokonieczny

Keyword(s):

Neural Network ◽

Neural Networks ◽

Multilayer Perceptron ◽

Learning Algorithm ◽

Armed Forces ◽

Shuttle Radar Topography Mission ◽

Terrain Classification ◽

The Neural Network ◽

Data Configuration ◽

Trained Neural Network

The classification of terrain in terms of passability plays a significant role in the process of military terrain assessment. It involves classifying selected terrain to specific classes (GO, SLOW-GO, NO-GO). In this article, the problem of terrain classification to the respective category of passability was solved by applying artificial neural networks (multilayer perceptron) to generate a continuous Index of Passability (IOP). The neural networks defined this factor for primary fields in two sizes (1000 × 1000 m and 100 × 100 m) based on the land cover elements obtained from Vector Smart Map (VMap) Level 2 and Shuttle Radar Topography Mission (SRTM). The work used a feedforward neural network consisting of three layers. The paper presents a comprehensive analysis of the reliability of the neural network parameters, taking into account the number of neurons, learning algorithm, activation functions and input data configuration. The studies and tests carried out have shown that a well-trained neural network can automate the process of terrain classification in terms of passability conditions.

Download Full-text

Numerical Simulation of Hot Die Forging Process of Ti-6Al-4V Alloy Blade

Materials Science Forum ◽

10.4028/www.scientific.net/msf.898.1325 ◽

2017 ◽

Vol 898 ◽

pp. 1325-1331 ◽

Cited By ~ 2

Author(s):

Jia Hao Chen ◽

Jin Shan Li ◽

Bin Tang ◽

Li Hua Du ◽

Hong Chao Kou

Keyword(s):

Numerical Simulation ◽

Finite Element Method ◽

Stress Distribution ◽

Strain Distribution ◽

3D Finite Element ◽

Forging Process ◽

Die Forging ◽

3D Finite Element Method ◽

Deformation Area ◽

Hot Die Forging

Ti-6Al-4V alloy is used extensively in aerospace industries due to its excellent properties. In this paper, the hot die forging process of the Ti-6Al-4V alloy blade was simulated by using 3D finite element method. Based on the model, the effect of process parameters on the deformation was investigated. The results show that the increase of temperature is beneficial to improving the uniformity of stress distribution. The slower the declining velocity of upper die is, the larger the strain gradient of severe deformation area will be. In addition, the stress distribution gets uniform with velocity decreasing. The large friction coefficient can make strain distribution uneven and cause symmetry of stress distribution. The proposed numerical simulation of hot die forging of blade in the present work may yield important information for the development of hot die forging techniques and the manufacture of blade.

Download Full-text

Methods for maintenance of neural networks in continual learning scenarios

10.36227/techrxiv.14565078.v1 ◽

2021 ◽

Author(s):

Bhasker Sri Harsha Suri ◽

Manish Srivastava ◽

Kalidas Yeturu

Keyword(s):

Neural Network ◽

Neural Networks ◽

Production Systems ◽

Image Data ◽

Training Data ◽

Learning Loss ◽

Unseen Data ◽

Scoring Schemes ◽

The Difference ◽

Continual Learning

Neural networks suffer from catastrophic forgetting problem when deployed in a continual learning scenario where new batches of data arrive over time; however they are of different distributions from the previous data used for training the neural network. For assessing the performance of a model in a continual learning scenario, two aspects are important (i) to compute the difference in data distribution between a new and old batch of data and (ii) to understand the retention and learning behavior of deployed neural networks. Current techniques indicate the novelty of a new data batch by comparing its statistical properties with that of the old batch in the input space. However, it is still an open area of research to consider the perspective of a deployed neural network’s ability to generalize on the unseen data samples. In this work, we report a dataset distance measuring technique that indicates the novelty of a new batch of data while considering the deployed neural network’s perspective. We propose the construction of perspective histograms which are a vector representation of the data batches based on the correctness and confidence in the prediction of the deployed model. We have successfully tested the hypothesis empirically on image data coming MNIST Digits, MNIST Fashion, CIFAR10, for its ability to detect data perturbations of type rotation, Gaussian blur, and translation. Upon new data, given a model and its training data, we have proposed and evaluated four new scoring schemes, retention score (R), learning score (L), Oscore and SP-score for studying how much the model can retain its performance on past data, how much it can learn new data, the combined expression for the magnitude of retention and learning and stability-plasticity characteristics respectively. The scoring schemes have been evaluated MNIST Digits and MNIST Fashion data sets on different types of neural network architectures based on the number of parameters, activation functions, and learning loss functions, and an instance of a typical analysis report is presented. Machine learning model maintenance is a reality in production systems in the industry, and we hope our proposed methodology offers a solution to the need of the day in this aspect.

Download Full-text

Using Domain-specific Fingerprints Generated Through Neural Networks to Enhance Ligand-based Virtual Screening.

10.26434/chemrxiv.12894800.v1 ◽

2020 ◽

Author(s):

Janosch Menke ◽

Oliver Koch

Keyword(s):

Neural Network ◽

Neural Networks ◽

Virtual Screening ◽

Molecular Fingerprint ◽

Molecular Fingerprints ◽

Domain Specific ◽

Trained Neural Network ◽

Hidden Layer ◽

Graph Neural Networks ◽

Combine Information

Molecular fingerprints are essential for different cheminformatics approaches like similarity-based virtual screening. In this work, the concept of neural (network) fingerprints in the context of similarity search is introduced in which the activation of the last hidden layer of a trained neural network represents the molecular fingerprint. The neural fingerprint performance of five different neural network architectures was analyzed and compared to the well-established Extended Connectivity Fingerprint (ECFP) and an autoencoder-based fingerprint. This is done using a published compound dataset with known bioactivity on 160 different kinase targets. We expect neural networks to combine information about the molecular space of<br>already known bioactive compounds together with the information on the molecular structure of the query and by doing so enrich the fingerprint. The results show that indeed neural fingerprints can greatly improve the performance of similarity searches. Most importantly, it could be shown that the neural fingerprint performs well even for kinase targets that were not included in the training. Surprisingly, while Graph Neural Networks (GNNs) are thought to offer an advantageous alternative, the best performing neural fingerprints were based on traditional fully connected layers using the ECFP4 as input. The best performing kinase-specific neural fingerprint will be provided for public use.

Download Full-text

Neural networks for modelling the energy consumption of metro trains

Proceedings of the Institution of Mechanical Engineers Part F Journal of Rail and Rapid Transit ◽

10.1177/0954409719861595 ◽

2019 ◽

Vol 234 (7) ◽

pp. 722-733 ◽

Cited By ~ 2

Author(s):

Pablo Martínez Fernández ◽

Pablo Salvador Zuriaga ◽

Ignacio Villalba Sanchís ◽

Ricardo Insa Franco

Keyword(s):

Neural Network ◽

Neural Networks ◽

Energy Consumption ◽

Mean Square Error ◽

Mean Square ◽

The Neural Network ◽

Train Speed ◽

Input Variables ◽

Trained Neural Network ◽

Traction Power

This paper presents the application of machine learning systems based on neural networks to model the energy consumption of electric metro trains, as a first step in a research project that aims to optimise the energy consumed for traction in the Metro Network of Valencia (Spain). An experimental dataset was gathered and used for training. Four input variables (train speed and acceleration, track slope and curvature) and one output variable (traction power) were considered. The fully trained neural network shows good agreement with the target data, with relative mean square error around 21%. Additional tests with independent datasets also give good results (relative mean square error = 16%). The neural network has been applied to five simple case studies to assess its performance – and has proven to correctly model basic consumption trends (e.g. the influence of the slope) – and to properly reproduce acceleration, holding and braking, although it tends to slightly underestimate the energy regenerated during braking. Overall, the neural network provides a consistent estimation of traction power and the global energy consumption of metro trains, and thus may be used as a modelling tool during further stages of research.

Download Full-text

Methods for maintenance of neural networks in continual learning scenarios

10.36227/techrxiv.14565078 ◽

2021 ◽

Author(s):

Bhasker Sri Harsha Suri ◽

Manish Srivastava ◽

Kalidas Yeturu

Keyword(s):

Neural Network ◽

Neural Networks ◽

Production Systems ◽

Image Data ◽

Training Data ◽

Learning Loss ◽

Unseen Data ◽

Scoring Schemes ◽

The Difference ◽

Continual Learning

Neural networks suffer from catastrophic forgetting problem when deployed in a continual learning scenario where new batches of data arrive over time; however they are of different distributions from the previous data used for training the neural network. For assessing the performance of a model in a continual learning scenario, two aspects are important (i) to compute the difference in data distribution between a new and old batch of data and (ii) to understand the retention and learning behavior of deployed neural networks. Current techniques indicate the novelty of a new data batch by comparing its statistical properties with that of the old batch in the input space. However, it is still an open area of research to consider the perspective of a deployed neural network’s ability to generalize on the unseen data samples. In this work, we report a dataset distance measuring technique that indicates the novelty of a new batch of data while considering the deployed neural network’s perspective. We propose the construction of perspective histograms which are a vector representation of the data batches based on the correctness and confidence in the prediction of the deployed model. We have successfully tested the hypothesis empirically on image data coming MNIST Digits, MNIST Fashion, CIFAR10, for its ability to detect data perturbations of type rotation, Gaussian blur, and translation. Upon new data, given a model and its training data, we have proposed and evaluated four new scoring schemes, retention score (R), learning score (L), Oscore and SP-score for studying how much the model can retain its performance on past data, how much it can learn new data, the combined expression for the magnitude of retention and learning and stability-plasticity characteristics respectively. The scoring schemes have been evaluated MNIST Digits and MNIST Fashion data sets on different types of neural network architectures based on the number of parameters, activation functions, and learning loss functions, and an instance of a typical analysis report is presented. Machine learning model maintenance is a reality in production systems in the industry, and we hope our proposed methodology offers a solution to the need of the day in this aspect.

Download Full-text