Neural Network Applications in Manufacturing and Controls

Neural networks provide significant benefits in manufacturing and controls. Below we have listed some of the common applications of neural networks in manufacturing and controls. If you are currently using neural networks in your manufacturing and controls application, we would love to hear about it.

NeuroDimension has also used its leading edge neural network technology to develop numerous manufacturing and control applications with a variety of companies. If you need neural network consulting for your manufacturing and control application, please contact NeuroDimension.

Sample Applications

Locate common characteristics in large amounts of data (divide research populations).
Predict the relationship between multiple factors (changes to device settings).
Predict the progression of scientific data over time (probability of mechanical failure).
Identify characteristics in images or video feeds (traffic flow, machine status).
Group scientific data based on key characteristics.

Locate common characteristics in large amounts of data

Detecting common characteristics in large amounts of manufacturing/control data is a type of classification problem. Neural networks can be used to solve classification problems, typically through Multi-Layer Perceptron (MLP) and Support Vector Machines (SVM) type networks.

Examples of classification applications in manufacturing/control include dividing research populations or data into groups for further study. For example, data can be extracted from mechanical logs to determine the maintenance proficiency level of operators.

Sample Study: Improving plant operator maintenance proficiency

Using NeuroSolutions, this study successfully modeled machine breakdown, but revealed that the operator’s impact upon machine breakdown rates can be considerable. Specifically, an artificial intelligent classification model is proposed as a means of classifying plant operator maintenance proficiency into one of three bandings. These are good, average and poor. The results of such work will form the basis of new prescriptive guidelines, for incorporation into the new certificate of training achievement (CTA) scheme, available to inexperienced construction plant operators. An artificial intelligence approach for improving plant operator maintenance proficiency - David J. Edwards, Gary D. Holt, Barry Robinson Locate this paper on Google Scholar!

Our NeuroSolutions product is an excellent resource for classification applications. For an interactive example of classification in NeuroSolutions for Excel, download the free evaluation version and view the demo called “Testing Classifiers” in the Help menu.

Predict the relationship between multiple factors

Forecasting the relationship between multiple factors in manufacturing/control data is a type of function approximation problem. Neural networks can be used to solve function approximation problems, typically through Multi-Layer Perceptron (MLP), Radial Basis Function (RBF) and CANFIS (Co-Active Neuro-Fuzzy Inference System) type networks.

Examples of function approximation in manufacturing/control include predicting changes to device settings. For example, data from studies can potentially help predict milling strategy, for prediction of surface quality and for the optimization of technological parameters in milling.

Sample Study: Neural-Network-Based Numerical Control for Milling Machine

Using NeuroSolutions for Excel, this sample study highlights using neural networks to generate part-programs for milling, drilling and similar operations on machining centers, on the basis of 2D, 2.5D or 3D geometric models of prismatic parts, without operator intervention. The neural network consists of networks for prediction of milling strategy, for prediction of surface quality and for the optimization of technological parameters in milling. The device, which can be retrofitted to a CNC controller, can be trained from a set of typical parts and will then generate new NC part-programs. Neural-Network-Based Numerical Control for Milling Machine - Joze Balic Locate this paper on Google Scholar!

Our NeuroSolutions product is an excellent resource for function approximation applications. For an interactive example of function approximation in NeuroSolutions, download the free evaluation version of the software and view the demo called “Multi-Layer Perceptron, Basic” in the Help menu.

Predict the progression of scientific data over time

Forecasting the relationship between multiple factors in manufacturing/control data is a type of time-series prediction problem. Neural networks can be used to solve time-series problems, typically through Time-Lagged Recurrent (TLRN) type network.

Examples of time-series predictions in manufacturing/control include machine diagnosis or even controlling a device. For example, data from manufacturing/control studies can forecast driving patterns to support navigation.

Sample Study: Learning Driving Patterns to Support Navigation

Using NeuroSolutions, this sample study highlights the advantage of using a time delay network over a multi-layer Perceptron for predicting driving patterns. Using a Moving Average Method the total prediction error was 557.50% compared with a Multi-Layer Perceptron error of 58.66% and a time-series (TDNN) error of 41.3%. Learning Driving Patterns to Support Navigation - Dejan Mitrovic Locate this paper on Google Scholar!

Our NeuroSolutions product is an excellent resource for time-series prediction applications. For an interactive example of time-series prediction in NeuroSolutions, download the free evaluation version of the software and view the demo called “Time Lagged Recurrent Network” in the Help menu.

Identify characteristics in images or video

Identifying characters in images or video feeds in business is a type of image processing problem. Neural networks can be used to solve image processing problems, typically through Principal Component Analysis (PCA) type network.

Identifying characters in images or video feeds in manufacturing/control is a type of image processing problem. Neural networks can be used to solve image processing problems, typically through Principal Component Analysis (PCA) type network.

Examples of image processing in manufacturing/control include identifying mechanical or control problems in images. For example, image data from manufacturing/control studies can control a robot based on visual camera cues via neural networks.

Our NeuroSolutions product is an excellent resource for image processing applications. For an interactive example of image processing in NeuroSolutions, download the free evaluation version of the software and view the demo called “Linear Associator” in the Help menu.

Group scientific data based on key characteristics

Grouping of manufacturing/control data based on key characteristics is a type of clustering problem. Neural networks can be used to solve clustering problems, typically through Self-Organizing Map (SOM) type network.

Examples of clustering in manufacturing/control include the detection of key characteristics in manufacturing machines or control devices. For example, data from machinery can be grouped into common categories to determine the likelihood of a component failure in the near future.

Our NeuroSolutions product is an excellent resource for clustering applications. For an interactive example of clustering in NeuroSolutions, download the free evaluation version of the software and view the demo called “Unsupervised Learning” in the Help menu.