Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

A complete defect detection task aims to achieve the specific class and precise location of each defect in an image, which makes it still challenging for applying this task in practice. The defect detection is a composite task of classification and location, leading to related methods is often hard to take into account the accuracy of both. The implementation of defect detection depends on a special detection data set that contains expensive manual annotations. In this paper, we proposed a novel defect detection system based on deep learning and focused on a practical industrial application: steel plate defect inspection. In order to achieve strong classification ability, this system employs a baseline convolution neural network (CNN) to generate feature maps at each stage, and then the proposed multilevel feature fusion network (MFN) combines multiple hierarchical features into one feature, which can include more location details of defects. Based on these multilevel features, a region proposal network (RPN) is adopted to generate regions of interest (ROIs). For each ROI, a detector, consisting of a classifier and a bounding box regressor, produces the final detection results. Finally, we set up a defect detection data set NEU-DET for training and evaluating our method. On the NEU-DET, our method achieves 74.8/82.3 mAP with baseline networks ResNet34/50 by using 300 proposals. In addition, by using only 50 proposals, our method can detect at 20 ft/s on a single GPU and reach 92% of the above performance, hence the potential for real-time detection.

/pdf/an-end-to-end-steel-surface-defect-detection-approach-via-2kbhxkp2p9.pdf

An End-to-End Steel Surface Defect Detection Approach via Fusing Multiple Hierarchical Features

A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects

Steel is the material of choice for a large number and very diverse industrial applications. Surface qualities along with other properties are the most important quality parameters, particularly for flat-rolled steel products. Traditional manual surface inspection procedures are awfully inadequate to ensure guaranteed quality-free surface. To ensure stringent requirements of customers, automated vision-based steel surface inspection techniques have been found to be very effective and popular during the last two decades. Considering its importance, this paper attempts to make the first formal review of state-of-art of vision-based defect detection and classification of steel surfaces as they are produced from steel mills. It is observed that majority of research work has been undertaken for cold steel strip surfaces which is most sensitive to customers' requirements. Work on surface defect detection of hot strips and bars/rods has also shown signs of increase during the last 10 years. The review covers overall aspects of automatic steel surface defect detection and classification systems using vision-based techniques. Attentions have also been drawn to reported success rates along with issues related to real-time operational aspects.

https://link.springer.com/content/pdf/10.1186%2F1687-5281-2014-50.pdf

Review of vision-based steel surface inspection systems

Automated computer-vision-based defect detection has received much attention with the increasing surface quality assurance demands for the industrial manufacturing of flat steels. This article attempts to present a comprehensive survey on surface defect detection technologies by reviewing about 120 publications over the last two decades for three typical flat steel products of con-casting slabs and hot- and cold-rolled steel strips. According to the nature of algorithms as well as image features, the existing methodologies are categorized into four groups: statistical, spectral, model-based, and machine learning. These works are summarized in this review to enable easy referral to suitable methods for diverse application scenarios in steel mills. Realization recommendations and future research trends are also addressed at an abstract level.

/pdf/automated-visual-defect-detection-for-flat-steel-surface-a-3wjhcxn3aa.pdf

Automated Visual Defect Detection for Flat Steel Surface: A Survey

Automatic defect detection on hot-rolled steel surface is challenging owing to its localization on a large surface, variation in appearance, and their rare occurrences. It is difficult to detect these defects either by physics-based models or by small-sample statistics using a single threshold. As a result, this problem is focused to derive a set of good-quality defect descriptors from the surface images. These descriptors should discriminate the various surface defects when fed to suitable machine learning algorithms. This research work has evaluated the performance of a number of different wavelet feature sets, namely, Haar, Daubechies 2 (DB2), Daubechies 4 (DB4), biorthogonal spline, and multiwavelet in different decomposition levels derived from 32 × 32 contiguous (nonoverlapping) pixel blocks of steel surface images. We have developed an automated visual inspection system for an integrated steel plant to capture surface images in real time. It localizes defects employing kernel classifiers, such as support vector machine and recently proposed vector-valued regularized kernel function approximation. Test results on 1000 defect-free and 432 defective images comprising of 24 types of defect classes reveal that three-level Haar feature set is more promising to address this problem than the other wavelet feature sets as well as texture-based segmentation or thresholding technique of defect detection.

Automatic Defect Detection on Hot-Rolled Flat Steel Products

One of the critical impediment faced in hierarchical control in an process industry is unavailability of exact mathematical co-relations, which can precisely define the process behavior. These are primarily due to variable, complex and un-measurable factors and noises influencing the process behavior. However, such cases are most appropriate application areas of Expert Systems. In process industry, Expert Systems are one of the successful application areas of Artificial Intelligence, where expertise and knowledge of a Process Expert or a group of Experts are embedded as computer inference software and database. In a real time situation, these systems can take intelligent decisions as would have been taken by process Expert on a similar situation. Determination of exact Set Process Temperatures or thermal regime on different parts of Rolling Mill Furnaces like Annealing Furnace in a Steel Industry is an intriguing problem. However, this decision is very crucial as final mechanical and metallurgical quality of steel stock significantly depends on fixing and accurate control of these temperatures. But as a irony, no well defined mathematical co-relations are available, which can predict exact thermal regime to be followed to achieve desired quality and properties of steel coils / sheets under heating inside such furnaces. The aforesaid intriguing issue has been successfully resolved by development and implementation of Expert System guided heating control system through prediction and control of optimum furnace temperatures inside Annealing Furnaces at Cold Rolling Mill of Bokaro Steel Plant and Decarburization-Annealing Furnace at Silicon Steel Mill of Rourkela Steel Plant. In both the cases, concepts of hierarchical automation has been used, wherein Expert System comprising Level-II tier of automation predicts most appropriate thermal regime to obtain desired product quality for a given set of steel sheet. A seamlessly dovetailed PLC constitutes Level-I automation layer. PLC monitors and controls the plant as per advice from Expert System. Both the systems have enhanced plants efficiency by improving production, quality and energy conservation.

Application of close loop expert system for heating control of rolling mill furnaces in a steel plant

Conventional AC operated electric overhead travelling (EOT) cranes uses slip ring induction motors whose rotor windings are connected to a power resistance. Speed control is performed by changing the rotor resistance in 3 to 4 steps by power contactors. Reversing is performed by changing the phase sequence of the stator supply through line contactors. Braking is achieved by a plugging operation. A crane control system has been developed using a variable voltage variable frequency drive and a programmable controller which has the advantage of continuous speed control; reversing is achieved by changing the phase sequence through an inverter. The main advantages of thi system are precise positioning, energy saving and increased motor life. This paper focuses on the application of variable voltage variable frequency induction motor drives in crane applications.

AC operated EOT crane control with variable voltage variable frequency drive

The automatic visual inspection systems (AVIS) are being obvious now-a-days in modern manufacturing industries for quality control, ease of documentation and reduced labor cost. The automatic detection of hot rolled steel surface defects in a real process is challenging due to the localization of it on a large surface and its rare occurrences. In this work an effort has been made to extract a set of features that can effectively address the problem of defect detection on hot rolled steel surface by using machine learning algorithm. It is intended to extract two types of features, namely wavelet and contourlet features with two and three resolution levels separately, and then make a comparison of performance of classification accuracy using these features. Here it is proposed to use state-of-the art support vector machine (SVM) classifier as the machine learning algorithm for detecting the defect surface and normal (defects free) surface. Experimental results on 14 different types of steel surface defects show that ‘haar’ wavelet features with three decomposition levels performs better than two levels ‘haar’ feature set or two and three decomposition levels contourlet feature set.

Wavelet versus contourlet features for automatic defect detection on hot rolled steel sheet

Sinter making process in an integrated steel plant substantially depends on efficacious functioning of series of operations. Owing to their complex nature and frequent process fluctuations, a precision automation system is imperative in each of these operations. A state-of-the-art Programmable Automation Controller (PAC) based automation system has been developed and successfully implemented for operation and control of Sinter Machine # 3 at Bokaro Steel Plant of Steel Authority of India Limited, India. The new system renders a comprehensive process control and visualization system for entire Sinter Machine. The application of advanced process automation system has significantly improved the plant performance and reduced the energy consumption.

M. Gangadaran

Papers

Automatic Defect Detection on Hot-Rolled Flat Steel Products

Application of close loop expert system for heating control of rolling mill furnaces in a steel plant

AC operated EOT crane control with variable voltage variable frequency drive

Wavelet versus contourlet features for automatic defect detection on hot rolled steel sheet

Implementation of an Advanced Process Automation System for Improvement of Sinter Machine # 3 Operation at Bokaro Steel Plant