Control of properties in injection molding by neural networks

Adequate control of product properties in injection molded plastics requires very accurate predictions. The problem is that the mechanical properties of these plastics, such as tensile modulus, are highly non-linear with the process variables, hence they are tough to predict. Consequently, up to date, injection molding machines include only closed loop control of process variables. Control of product properties is virtually non-existent.

We show here for the first time, that mechanical properties, such as tensile modulus values, can be predicted using Artificial Neural Networks quite accurately within a reasonable time. This is a major step towards an integrated self-taught control mechanism for the injection molded plastics industry.     

A sub-space artificial neural network for mold cooling in injection molding

The applications of artificial intelligence (AI) have considerably expanded over recent years. A new class of industrial systems is beginning to evolve that incorporates using high volume data and advanced analytics to better optimize product quality while reducing energy consumption. Artificial neural networks (ANN) when combined with advanced modeling and control, begins to form an AI platform that can be further enhanced for factories of the future. This paper provides a demonstration of such initial work that can be further developed for future systems in a generic way. When considering polymer processing such as plastic injection molding, the mold cavity temperature (MCT) profile directly relates to part quality and part reject rates. Therefore, it is desirable to optimize the mold cooling process using real time control of MCT as it directly affect part quality. However, MCT is affected by a number of interacting nonlinear dynamic parameters that are often neglected due to the challenge of quantifying such parameters. Advanced model based control algorithms are often used for providing improved control of complex systems. However, they depend on good model formulations that are analytically insufficient. An online intelligent system identification approach for the mold cooling process is developed and tested. An ANN is designed to adjust online sub-space parameters that govern a mold cooling model. Results demonstrate that this online ANN approach can be used to accurately predict the dynamic behavior of mold cavity surface temperature. This is key to many industrial systems where their states are not directly observable and uncertainties are unknown. The methodology can be readily adapted for different operating conditions as in this case of polymer processing and has good potential for its integration with advanced model based control schemes and cloud computing approaches for the next generation of machines.     

A comparison of neural networks to SPC charts

A comparison of the performance of a synthetic neural network to several traditional statistical control chart decision criteria is drawn using computer simulation experiments.     

The application of neural networks to the papermaking industry

This paper describes the application of neural network techniques to the papermaking industry, particularly for the prediction of paper "curl". Paper curl is an important quality measure that can only be measured reliably off-line after manufacture, making it difficult to control. Here, we predict, before paper manufacture from characteristics of the current reel, whether the paper curl will be acceptable and the level of curl. For both issues the case of predicting the probability that paper will be "out-of-specification" and that of predicting the level of curl, we include confidence intervals indicating to the machine operator whether the predictions should be trusted. The results and the associated discussion describe a successful application of neural networks to a difficult, but important, real-world task taken from the papermaking industry. In addition the techniques described are widely applicable to industry where direct prediction of a quality measure and its acceptability are desirable.     

A neural network-based approach for dynamic quality prediction in a plastic injection molding process

This paper presents an innovative neural network-based quality prediction system for a plastic injection molding process. A self-organizing map plus a back-propagation neural network (SOM-BPNN) model is proposed for creating a dynamic quality predictor. Three SOM-based dynamic extraction parameters with six manufacturing process parameters and one level of product quality were dedicated to training and testing the proposed system. In addition, Taguchi’s parameter design method was also applied to enhance the neural network performance. For comparison, an additional back-propagation neural network (BPNN) model was constructed for which six process parameters were used for training and testing. The training and testing data for the two models respectively consisted of 120 and 40 samples. Experimental results showed that such a SOM-BPNN-based model can accurately predict the product quality (weight) and can likely be used for various practical applications.     

Correction to: A compiler framework for the reduction of worst-case execution times

Real-Time Systems - The article A compiler framework for the reduction of worst-case execution times, written by Heiko Falk and Paul Lokuciejewski, was originally published electronically on the...     

A compiler framework for the reduction of worst-case execution times

The current practice to design software for real-time systems is tedious. There is almost no tool support that assists the designer in automatically deriving safe bounds of the worst-case execution time (WCET) of a system during code generation and in systematically optimizing code to reduce WCET.     

Competitiveness analysis of automotive industry in Turkey using Bayesian networks

The purpose of this study is to analyze the relations between the factors that enable national competitive advantage and the establishment of competitive superiority in automotive industry through a comprehensive analytical model. Bayesian networks (BN) are used to investigate the associations of different factors in the automotive industry which lead to competitive advantage. The results of the study focus on building a road map for the automotive sector policy makers in their way to improve the competitiveness through scenario analysis. Using the probabilistic dependency structure of the Bayesian network all of the variables in the model can be estimated. Thus, with the proposed model the automotive industry can be analyzed as a whole system and not only in terms of single variables. Findings of the model indicate that technological developments in automotive industry can alter the nature of competition in this industry.     

A comparison between functional networks and artificial neural networks for the prediction of fishing catches

In recent years, functional networks have emerged as an extension of artificial neural networks (ANNs). In this article, we apply both network techniques to predict the catches of the Prionace Glauca (a class of shark) and the Katsowonus Pelamis (a variety of tuna, more commonly known as the Skipjack). We have developed an application that will help reduce the search time for good fishing zones and thereby increase the fleets competitivity. Our results show that, thanks to their superior learning and generalisation capacities, functional networks are more efficient than ANNs. Our data proceeds from remote sensors. Their spectral signatures allow us to calculate products that are useful for ecological modelling. After an initial phase of digital image processing, we created a database that provides all the necessary patterns to train both network types.     

The exploitation of neural networks in automotive engine management systems

The use of electronic engine control systems on spark ignition engines has enabled a high degree of performance optimisation to be achieved. The range of functions performed by these systems, and the level of performance demanded, is rising and thus so are development times and costs. Neural networks have attracted attention as having the potential to simplify software development and improve the performance of this software. The scope and nature of possible applications is described. In particular, the pattern recognition and classification abilities of networks are applied to crankshaft speed fluctuation data for engine-fault diagnosis, and multidimensional mapping capabilities are investigated as an alternative to large ‘lookup’ tables and calibration functions.     

Artificial neural networks application to predict the compressive damage of lightweight geopolymer

In this work, compressive strength of lightweight geopolymers produced by fine fly ash and rice husk–bark ash together with palm oil clinker (POC) aggregates has been investigated experimentally and modeled based on artificial neural networks. Different specimens made from a mixture of fine fly ash and rice husk–bark ash with and without POC were subjected to compressive strength tests at 2, 7, and 28 days of curing. A model based on artificial neural networks for predicting the compressive strength of the specimens has been presented. To build the model, training and testing using experimental results from 144 specimens were conducted. The data used in the multilayer feed-forward neural networks models are arranged in a format of six input parameters that cover the quantity of fine POC particles, the quantity of coarse POC particles, the quantity of FA + RHBA mixture, the ratio of alkali activator to ashes mixture, the age of curing and the test trial number. According to these input parameters, in the neural networks model, the compressive strength of each specimen was predicted. The training and testing results in the neural networks model have shown a strong potential for predicting the compressive strength of the geopolymer specimens in the considered range.     

Using neural networks to predict the design load of cold-formed steel compression members

The paper considers the use of neural networks to predict the failure load of cold-formed steel compression members. The objective is to provide a fast method of predicting the failure load, so that the method can be used in other design algorithms, such as optimisation routines. Three types of symmetric sections are considered, and the results of neural network predictions compared with results from BS5950 Part 5. The results are in good agreement with the results from design codes. Moreover, a trained neural network gives the results significantly more quickly than a computer implementation of the code.     

A comparison of artificial neural networks learning algorithms in predicting tendency for suicide

New approaches adopted by behavioral science researchers to use modern modeling and predicting tools such as artificial neural networks have necessitated the study and comparison of the efficiency of different learning algorithms of these networks for various applications. By using well-known and different learning algorithms, this study examines and compares the Perceptron artificial neural network as predicting tendency for suicide based on risk factors within 33 input parameters framework used in neural network. To find the “best” learning algorithm, the algorithms were compared in terms of train and capability. The experimental data were collected through questionnaires distributed among 800 university students. All questionnaires used in this research were standardized with appropriate validity and reliability. The study findings indicated that LM and BFG algorithms had close evaluation in terms of performance index and true acceptance rate (TAR), and they showed higher predictive accuracy than the other algorithms. Furthermore, CFG algorithm had the minimum training time.     

A continuous simulation approach for supply chains in the automotive industry

In the automotive industry supply chains, several factories collaborate to manufacture a product (car, engines, etc.). In order to fulfill customers’ needs, they have to be designed and organized in the proper way. The dynamic analysis of their behavior through simulation provides important information to improve their performances. Most existing research works addressing the modeling and simulation of supply chains are generally based on a discrete event worldview. We are concerned here with medium or long term decision problems, which necessitate “macroscopic” models of the supply chain. At these levels, the representation of the individual flows of the numerous parts that circulates in the supply chain being quite difficult, given the objectives considered, we chose a continuous worldview. The models are based on Forrester’s system dynamic paradigms. The proposed approach is actually applied to a large French company, in the automotive industry. The supply chain presented in this article is composed of five existing plants, located in two different production areas. The results show the concrete benefits that can be achieved. Several research directions are suggested.     

Using neural networks to predict workability of concrete incorporating metakaolin and fly ash

This paper details the development of neural network models that provide effective predictive capability in respect of the workability of concrete incorporating metakaolin (MK) and fly ash (FA). The predictions produced reflect the effect of graduated variations in pozzolanic replacement in Portland cement (PC) of up to 15% MK and 40% FA. The results show that the models are reliable and accurate and illustrate how neural networks can be used to beneficially predict the workability parameters of slump, compacting factor and Vebe time across a wide range of PC–FA–MK compositions.     

Comparison of neural networks and statistical models to predict gestational age at birth

The aim of this study was to produce models for the prediction of high risk pregnancies, with particular emphasis on pre-term delivery. Neural network and logistic regression models have been developed utilising pregnancy and delivery data spanning a period of seven years. Five input factors were used as explanatory variables: age, number of previous still births, gestational age at first clinical assessment, diabetes and a measure of socio-economic status. There was little difference between average model performance for the two techniques: optimal neural network performance was achieved with a fully connected feed forward network comprising a single hidden layer of three nodes and single output node. This produced a Receiver Operating Characteristic (ROC) curve area of 0.700. The ROC area for logistic regression models was 0.695. The performance of these models reflected weak associations within the data. However, performance is encouraging given the relatively limited number of predictive inputs.     

From local neural networks to granular neural networks: A study in information granulation

In this study, we are concerned with a construction of granular neural networks (GNNs)—architectures formed as a direct result reconciliation of results produced by a collection of local neural networks constructed on a basis of individual data sets. Being cognizant of the diversity of the results produced by the collection of networks, we arrive at the concept of granular neural network, producing results in the form of information granules (rather than plain numeric entities) that become reflective of the diversity of the results generated by the contributing networks. The design of a granular neural network exploits the concept of justifiable granularity. Introduced is a performance index quantifying the quality of information granules generated by the granular neural network. This study is illustrated with the aid of machine learning data sets. The experimental results provide a detailed insight into the developed granular neural networks.     

Artificial neural networks workflow and its application in the petroleum industry

We develop a neural network workflow, which provides a systematic approach for tackling various problems in petroleum engineering. The workflow covers several design issues for constructing neural network models, especially in terms of developing the network structure. We apply the model to predict water saturation in an oilfield in Oman. Water saturation can be accurately obtained from data measured from cores removed from the oil field, but this information is limited to a few wells. Wireline log data are more abundantly available in most wells, and they provide valuable, but indirect, information about rock properties. A three-layered neural network model with five hidden neurons and a resilient back-propagation algorithm is found to be the best design for the saturation prediction. The input variables to the model are density, neutron, resistivity, and photo-electric wireline logs, and the model is trained using core water saturation. The model is able to predict the saturation directly from wireline logs with a correlation coefficient (r) of 0.91 and an error of 2.5 saturation units on the testing data.     

Artificial neural networks application to predict the ultimate tensile strength of X70 pipeline steels

The paper presents some results of the research connected with the development of new approach based on the artificial neural network (ANN) of predicting the ultimate tensile strength of the API X70 steels after thermomechanical treatment. The independent variables in the model are chemical compositions (carbon equivalent), based upon the International Institute of Welding equation (CE_IIW), the carbon equivalent, based upon the chemical portion of the Ito-Bessyo carbon equivalent equation (CE_Pcm), the sum of the niobium, vanadium and titanium concentrations (VTiNb), the sum of the niobium and vanadium concentrations (NbV), the sum of the chromium, molybdenum, nickel and copper concentrations (CrMoNiCu), Charpy impact energy at ?10 °C (CVN) and yield strength at 0.005 offset (YS). For purpose of constructing these models, 104 different data were gathered from the experimental results. The data used in the ANN model is arranged in a format of seven input parameters that cover the chemical compositions, yield stress and Charpy impact energy, and output parameter which is ultimate tensile strength. In this model, the training, validation and testing results in the ANN have shown strong potential for prediction of relations between chemical compositions and mechanical properties of API X70 steels.