Towards Online Anomaly Detection in Steel Manufacturing Process

For the low-speed diesel engine monitoring with multi-sensor information on ship, the on-line anomaly detection as the fault symptom pre-warning is mainly considered in this paper. The stable operating condition is firstly identified by the ADF test. Then, the on-line anomaly detection with baseline deviation is modeled by the Auto associative Kernel Regression (AAKR) method, where the baseline is constructed by the proper memory matrix with stable operating process, and the anomaly is timely diagnosed using the model estimation deviation compared to the normal monitoring. Our results with presented AAKR model are verified by the studies of the real low-speed diesel engine monitoring case.

Anomalous behavior detection is an important component in many applications. Anomalies can represent problematic situations where early detection is critical to make situational assessments in the event of unexpected conditions. For many problems, the state of the art in machine learning is batch learning. However, online anomaly detection algorithms have emerged as an alternative which offer rapid access to useful insights with fewer computing capacity requirements. Ubiquitous and accelerated data streams have led to the development of several machine learning algorithms that favor adaptive learning. Real-time digital environments necessitate tackling specific data analysis challenges such as copious volumes of accelerated, infinite data streams and the phenomenon of concept drift. These Big Data challenges also represent real opportunities for improving a multitude of processes. In this paper, a novel thresholding approach for online anomaly detection based on the long short-term memory recurrent neural network encoder-decoder architecture is proposed. Comparative results in applying various advanced algorithms on 5 streaming datasets from the UCI repository and 3 synthetic datasets are discussed. All datasets contain anomaly ground truth information to evaluate the effectiveness of algorithms in detecting anomalous instances in streaming data.

Anomaly detection is a significant application of residential appliances load monitoring systems. As an essential prerequisite of load diagnosis services, anomaly detection is critical to energy saving and occupant comfort actualization. Notwithstanding, the investigation into diagnosis of household anomalous appliances has not been decently taken into consideration. This paper presents an extensive study about operation-time anomaly detection of household devices particularly, refrigerators, in terms of appliances candidate, by utilizing their energy consumption data. Energy as a quantitative property of electrical loads, is a reliable information for a robust diagnosis. Additionally, it is very practical since it is low-priced to measure and definite to interpret. Subsequently, an on-line anomaly detection approach is proposed to effectively determine the anomalous operation of the household appliances candidate. The proposed approach is capable of continuously monitoring energy consumption and providing dynamic information for anomaly detection algorithms. A machine learning-based technique is employed to construct efficient models of appliances normal behavior with application to operation-time anomaly detection. The performance of the suggested approach is evaluated through a set of diagnostic tests, by utilizing normal and anomalous data of targeted devices, measured by an acquisition system. In addition, a comparison analysis is provided in order to further examine the effectiveness of the developed mechanism by exploiting a public database. Moreover, this study elaborates sensible remarks on an effective management of anomaly detection and diagnosis decision phases, pivotal to correctly recognition of a faulty/abnormal operation. Indeed, through experimental results of case studies, this work assists in the development of a load monitoring and anomaly detection system with practical implementation.

The definitions of anomaly detection and big data were presented. Due to the sampling and storage burden of anomaly detection in big data, compressive sensing theory was introduced and used in anomaly detection algorithm. The anomaly detection criterion based on wavelet packet transform and statistic process control theory was deduced. The anomaly detection method was used for through wall human detection. The experiments for detecting human behind Brick wall based on UWB radar signal was carried out. The results showed that the proposed anomaly detection algorithm could effectively detect the existence of human being through compressed signals.KeywordsAnomaly detectionBig dataThrough wall human detectionCompressive sensing

Because the internet and computer networks are exposed to rapidly increasing number of serious security threats, efficient and effective anomaly detection techniques have become a necessity to secure the internet and computer networks. Traditional signature based anomaly detection techniques failed to detect polymorphic and new security threats. In this paper, we propose an online worm detection system based on relative entropy. The system effectively profiles network traffic features and then uses relative entropy to dynamically determine the traffic changes. It then applies adaptive filter to differentiate the traffic changes and determines whether the traffic is normal or contains worms. Our experimental results show that the proposed system is efficient for on-line anomaly detection, using traffic trace collected in high-speed links.

According to the present situation of lack of systemic analysis for manufacturing resources optimization operation for iron and steel enterprise in domestic and overseas, a resource input/output frame about steel and iron manufacturing unit was established to analyze the resource consumption situation, and the main line of steel green manufacturing resources was built, which is based on the theory and method of green manufacturing and the operation law of iron and steel enterprise. And manufacturing resources optimization operation strategies were put forward for iron and steel enterprises, considering the resource transformation and consumption from the whole steel product life cycle. The operation strategies can provide guidance ideas for the iron and steel enterprises the most efficient use of material resources and the least energy consumption in the steel manufacturing process.

Flow classification by application type is motivated by on-line anomaly detection, off-line network planning, and on-line enforcement of terms-of-use policies by public ISPs or by administrators of private-enterprise networks. Both signature matching and a variety of feature-based pattern recognition methods have been applied to address this problem. In this paper, we propose a TCP flow classifier that employs neither packet header information that is protocol-specific (including port numbers) nor packet-payload information. Techniques based on the former are readily evadable, while detailed yet scalable inspection of packet payloads is difficult to achieve, may violate privacy laws, and is defeated by data encryption. Our classifier is tested on two contemporary publicly available datasets recorded in similar networking contexts. We consider the often encountered scenario where ground-truth labels, necessary for supervised classifier training, are unavailable for a domain where flow classification needs to be applied. In this case, one must "port over" a classifier trained on one domain to make decisions on another. We address issues in reconciling differences in class definitions between the two domains. We also demonstrate by our results that domain differences in the class-conditional feature distributions, which will exist in practice, can lead to substantial losses in classification accuracy on the new domain. Finally, we also propose and evaluate a hypothesis testing approach to detect port spoofing by exploiting confusion matrix statistics.

The comprehensive influence on the overall integration of steel manufacturing process is discussed in this paper, which influences not only the target group of technique and economy, but also the process emission and environment. The evolution of steel manufacturing process for a long period is reviewed, which can be summarized as from simplicity to complication and then from complication to simplification. It is pointed out that the essence of steel manufacturing process is a production system which is combined mass state transformation, mass property control and mass flow control. It is a multi-dimensional mass-flow control system. In fact, the optimization of steel manufacturing process is the analysis-optimization of the collection of procedure's function, the harmony optimization of the collection of procedure's relations and restructuring optimization of collection of procedures in the process. Based on above theory, the linkage optimization of function-structure-efficiency for steel plants will be realized and the mode of steel plants will be improved. It is proposed that the social/economic role of steel plants should be positioned actively. The function of manufacturing process at the steel plants should be evolved from metallurgical function mainly to a multifunctional, which has both energy conversion and environmental treatment of social wastage. The steel plants may be an important part of the ecological industry zone in the future.

Introduction: This paper presents a novel approach for classifying different types of steel rods using a combination of pre-trained convolutional neural networks (CNNs) and fuzzy logic systems. We utilize VGG16, ResNet50, and InceptionV3 models to extract features from grayscale images of steel rods, which are then classified using Support Vector Machines (SVM). Furthermore, we incorporate a fuzzy logic system to improve the final classification accuracy by combining the individual accuracies of each CNN model. Experimental results demonstrate the effectiveness of our approach in achieving high classification accuracy compared to traditional methods. Objectives: This research presents a novel multi-model approach for steel rod classification utilizing three distinct fuzzy logic systems: Fuzzy Recurrent Neural Network (RNN), Fuzzy Convolutional Neural Network (CNN), and Fuzzy Neural Network. The proposed system addresses the critical challenge of accurate defect detection and classification in steel manufacturing processes. By combining these complementary approaches, we achieve enhanced feature extraction capabilities and improved classification accuracy. Experimental results demonstrate that our multi-model system achieves a classification accuracy of 97.8%, surpassing single-model approaches by an average of 8.2%. The system successfully identifies surface defects, structural anomalies, and dimensional variations with high precision, making it suitable for real-time industrial applications. Methods: This paper introduces a novel approach for the feature extraction and classification of steel rods by integrating multiple models and utilizing fuzzy logic systems. The methodology leverages pre-trained convolutional neural networks (CNNs) for extracting comprehensive feature representations from steel rod images. These extracted features are then combined and integrated using fuzzy logic to enhance classification accuracy and reliability. By addressing the limitations of traditional manual inspection methods and single-model approaches, this integrated multi-model system offers a robust solution for real-time industrial implementation. The proposed system aims to improve the efficiency and effectiveness of quality control processes in steel rod manufacturing, ensuring consistent and accurate classification even under varying conditions and complexities. This innovative approach paves the way for more advanced and adaptable automated inspection systems in the industry. Results: The paper aims to develop an integrated multi-model system that combines three distinct fuzzy logic approaches to enhance feature extraction capabilities through complementary methodologies. By improving the classification accuracy and reliability, the system addresses the limitations of existing methods. The goal is to create a robust and adaptable system that is suitable for real-time industrial implementation for steel rod analysis and classification. This comprehensive approach leverages the strengths of multiple models and fuzzy logic techniques, ensuring accurate and efficient classification processes, even under complex and varying conditions. The proposed multi model system is designed to meet the stringent quality control requirements of industrial applications, ultimately improving productivity and product quality through reliable automated inspection and classification for steel rod with accuracy of 97.80%, precision of 97.30% and recall 97.50%. Conclusions: This paper presents a novel approach for the classification of steel rods using a combination of pre-trained CNN models and fuzzy logic systems. The experimental results demonstrate the effectiveness of our method in achieving high classification accuracy. This research demonstrates the effectiveness of a multi-model fuzzy logic approach for steel rod classification. The system achieves significant improvements over single-model approaches while maintaining real-time processing capabilities. Our approach provides a foundation for further research and development in automated industrial image classification.

The present paper deals with the optimal planning for blending of coal of different grades for beneficiation of coal with a view to satisfy the requirements of the end users with desired specifications. The input specifications are known whereas aspiration levels of the characteristics washed coal have been specified. Beneficiation of coal refers to the production of wash coal from raw coal with the help of some suitable beneficiation/coal washing technologies. The processed coal is used by the different steel plants to serve their purpose during the manufacturing process of steel. The aim is to fix the level of the raw coal samples from different coal seams to be used/fed for the beneficiation to meet the desired target of the coal blending indicators, yield to maximum extent and to restrict the input cost of raw coal to be fed for beneficiation. The problem is considered as multi criteria decision making problem and solved using multi objective genetic algorithm. A case study from a regional coal company situated at Jharia coalfield, India has been made and solved using the proposed model.

Ferrous slag is the most abundant solid by-product generated from the steel manufacturing process, and a stable demand for ferrous slag is essential to ensure the stable production of steel. Therefore, various applications have been developed to maintain a stable demand for ferrous slag. Furthermore, continuous fundamental study and technological development are essential to find more value-added valorization and explore more advanced ways of use. It is inevitable to develop ideal slag valorization methods corresponding to new types of ferrous slag with a society-wide perspective to ensure the rapid decarbonization trend, which is an unprecedented experience in the steel industry. This article provides an overview of the progress and technological structure of ferrous slag valorization in Japan so far and also summarizes the research activities related to ferrous slag in recent years in the Iron and Steel Institute of Japan, which plays a central role in this field. Particularly, unique activities such as exploring environmentally friendly valorization methods using ferrous slag through collaboration between different industries such as agriculture and fisheries, and carbon fixation through vegetation promotion in coastal areas in Japan, harvesting blue carbon, are summarized. Based on the above, the future role of ferrous slag in establishing a sustainable society has been discussed. Graphical Abstract

Heat furnace is one of the most important parts in iron and steel industry which is one of the basic industries. The control of furnace quality indices has a direct impact on iron and steel qualities and energy consumptions in an iron and steel manufacturing process. Due to dramatic changes of exhaust gas in combustion, this multi-variable process becomes time-varying, and also has inherent nonlinearities, couplings among the variables, large inertias and time delays.Therefore, manual operations are still being widely used in quality indices control. In this paper, an optimization control method is proposed for the control of furnace quality indices. The optimization consists of a materials temperature calculation model, an optimization objective, an ideal materials heating model and a furnace heating model. Optimization algorithm consists of the maximum principle, the simulated annealing algorithm，the iterative algorithm and sensitive analysis.Finally, quality indices were controlled by lower layer loop control on-line.The proposed optimization control method has been successfully applied to some steel plants. The industrial applications show the effectiveness of the proposed method.

Carbon emissions from industrial sources are of major global concern, especially contributions from the steel manufacturing process which accounts for the majority of emissions. Typical blast furnace gases consist of CO2 (20‐25%), CO (20‐25%), H2 (3‐5%) and N2 (40‐50%) and trace amounts of other gases. It is demonstrated that gas mixtures with these compositions can be used at atmospheric pressure to grow carbon nanotubes (CNTs) by chemical vapor deposition (CVD) on to steel substrates, which act as catalysts for CNT growth. Computational modelling was used to investigate the CNT growth conditions inside the CVD chamber. The results show that industrial waste pollutant gases can be used to manufacture materials with significant commercial value, in this case CNTs.

Laser‐EMAT (ElectroMagnetic Acoustic Transducer) ultrasonics is a suitable technique for on‐line surface and internal defect detection in a steel mill. The system is intended to automatically inspect steel, at temperatures in excess of 700° C, as it moves through the steel manufacturing process. It is one of the few ultrasonic systems that could ever be used in the harsh operating environment of a steel mill due to its non‐contact nature. In the laboratory and pilot development stages the equipment can be optimised and designed to work under these harsh conditions. Before the technology can be used on hot, moving product in the steel plant, it is necessary to conduct experiments on moving steel at ambient temperatures, so that system optimisation is performed under more practical conditions. As such, the design of an automated trolley inspection system for inspecting a 1.6 m long, 110 mm square steel billet at room temperature will be discussed. The Laser‐EMAT system was later used to find a surface defect in the steel, as it moved at 800° C on a pilot scale rolling mill. B‐Scan data will be presented highlighting the presence of a surface defect on the steel moved both under laboratory and industrial conditions.

The detection of surface defects in the steel manufacturing process is a very important issue in terms of quality assurance and facility management. Recently, many studies have been conducted to improve the performance of detection by applying deep learning models. However, it is still difficult to detect surface defects because of class imbalance problem. In this study, we propose a deep learning model using object-level data augmentation method to improve the detection accuracy of steel sheet surface defect images with class imbalance. We demonstrated the usefulness and applicability of the proposed method by conducting various experiments using Severstal steel defect detection dataset. We applied various deep learning model architectures to the proposed method and proved that its performance was improved compared to the model using existing image-level data augmentation method. Further, the experimental results showed that the proposed method especially improves the defect detection performance of minor classes.