Vibration data-driven machine learning architecture for structural health monitoring of steel frame structures

A vibration data-based machine learning architecture is designed for structural health monitoring (SHM) of a steel plane frame structure. This architecture uses a Bag-of-Features algorithm that extracts the speeded-up robust features (SURF) from the time-frequency scalogram images of the registered vibration data. The discriminative image features are then quantised to a visual vocabulary using K-means clustering. Finally, a support vector machine (SVM) is trained to distinguish the undamaged and multiple damage cases of the frame structure based on the discriminative features. The potential of the machine learning architecture is tested for an unseen dataset that was not used in training as well as with some datasets from entirely new damages close to existing (i.e., trained) damage classes. The results are then compared with those obtained using three other combinations of features and learning algorithms—(i) histogram of oriented gradients (HOG) feature with SVM, (ii) SURF feature with k-nearest neighbours (KNN) and (iii) HOG feature with KNN. In order to examine the robustness of the approach, the study is further extended by considering environmental variabilities along with the localisation and quantification of damage. The experimental results show that the machine learning architecture can effectively classify the undamaged and different joint damage classes with high testing accuracy that indicates its SHM potential for such frame structures.     

基于机器学习的热导率预测模型研究

传统的理论研究、实验研究及计算仿真已无法满足科学家对新材料的探索与设计。数据驱动的机器学习算法对材料的筛选与性能预测有着推动作用。将机器学习算法应用到材料信息学,基于现有材料热导率数据集,建立机器学习热导率预测模型,通过交叉验证来对机器学习回归模型进行评估。利用机器学习算法建立描述符与热导率属性之间的映射模型,可用于大规模的材料筛选,从而指导实验研究。     

A support vector machine integrated system for the classification of operation anomalies in nuclear components and systems

A support vector machine (SVM) approach to the classification of transients in nuclear power plants is presented. SVM is a machine-learning algorithm that has been successfully used in pattern recognition for cluster analysis. In the present work, single- and multiclass SVM are combined into a hierarchical structure for distinguishing among transients in nuclear systems on the basis of measured data. An example of application of the approach is presented with respect to the classification of anomalies and malfunctions occurring in the feedwater system of a boiling water reactor. The data used in the example are provided by the HAMBO simulator of the Halden Reactor Project.     

Performance of Lung Cancer Prediction Methods Using Different Classification Algorithms

In 2018, 1.76 million people worldwide died of lung cancer. Most of these deaths are due to late diagnosis, and early-stage diagnosis significantly increases the likelihood of a successful treatment for lung cancer. Machine learning is a branch of artificial intelligence that allows computers to quickly identify patterns within complex and large datasets by learning from existing data. Machine-learning techniques have been improving rapidly and are increasingly used by medical professionals for the successful classification and diagnosis of early-stage disease. They are widely used in cancer diagnosis. In particular, machine learning has been used in the diagnosis of lung cancer due to the benefits it offers doctors and patients. In this context, we performed a study on machine-learning techniques to increase the classification accuracy of lung cancer with 32 × 56 sized numerical data from the Machine Learning Repository web site of the University of California, Irvine. In this study, the precision of the classification model was increased by the effective employment of pre-processing methods instead of direct use of classification algorithms. Nine datasets were derived with pre-processing methods and six machine-learning classification methods were used to achieve this improvement. The study results suggest that the accuracy of the k-nearest neighbors algorithm is superior to random forest, naïve Bayes, logistic regression, decision tree, and support vector machines. The performance of pre-processing methods was assessed on the lung cancer dataset. The most successful pre-processing methods were Z-score (83% accuracy) for normalization methods, principal component analysis (87% accuracy) for dimensionality reduction methods, and information gain (71% accuracy) for feature selection methods.     

Neuroimage‐based clinical prediction using machine learning tools

Classification of structural brain magnetic resonance (MR) images is a crucial task for many neurological phenotypes that machine learning tools are increasingly developed and applied to solve this problem in recent years. In this study binary classification of T1‐weighted structural brain MR images are performed using state‐of‐the‐art machine learning algorithms when there is no information about the clinical context or specifics of neuroimaging. Image derived features and clinical labels that are provided by the International Conference on Medical Image Computing and Computer‐Assisted Intervention 2014 machine learning challenge are used. These morphological summary features are obtained from four different datasets (each N > 70) with clinically relevant phenotypes and automatically extracted from the MR imaging scans using FreeSurfer, a freely distributed brain MR image processing software package. Widely used machine learning tools, namely; back‐propagation neural network, self‐organizing maps, support vector machines and k‐nearest neighbors are used as classifiers. Clinical prediction accuracy is obtained via cross‐validation on the training data (N = 150) and predictions are made on the test data (N = 100). Classification accuracy, the fraction of cases where prediction is accurate and area under the ROC curve are used as the performance metrics. Accuracy and area under curve metrics are used for tuning the training hyperparameters and the evaluation of the performance of the classifiers. Performed experiments revealed that support vector machines show a better success compared to the other methods on clinical predictions using summary morphological features in the absence of any information about the phenotype. Prediction accuracy would increase greatly if contextual information is integrated into the system. © 2017 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 27, 89–97, 2017     

Combination of probability approach and support vector machine towards machine health prognostics

This study presents a combined method of the probability approach and support vector machine (SVM) to predict failure degradation based on simulated and experimental failure bearing data. The failure rate as a degradation parameter is calculated using the Cox-proportional hazard model and the reliability theory based on simulated and experimental data. Kurtosis is used to show the bearing condition under specified operating conditions up to final failure occurrence. For simulated data, a failure degradation is calculated using the Cox model, where the baseline hazard is assumed having Weibull probability. In the case of experimental data, a reliability formula is employed to estimate the failure degradation of the bearing based on run-to-failure datasets. Both failure degradations are regarded as target vectors which indicate the bearing health to failure condition. Moreover, an SVM is employed as an artificial intelligence prognostics method and trained by kurtosis and the target vector to build the prediction model. The trained SVM is then utilized to predict the final failure time of individual bearing data. The result shows that the proposed method has the potential to be a machine health prognostics framework.     

Feature selection and fault‐severity classification–based machine health assessment methodology for point machine sliding‐chair degradation

In this paper, we propose an offline and online machine health assessment (MHA) methodology composed of feature extraction and selection, segmentation‐based fault severity evaluation, and classification steps. In the offline phase, the best representative feature of degradation is selected by a new filter‐based feature selection approach. The selected feature is further segmented by utilizing the bottom‐up time series segmentation to discriminate machine health states, ie, degradation levels. Then, the health state fault severity is extracted by a proposed segment evaluation approach based on within segment rate‐of‐change (RoC) and coefficient of variation (CV) statistics. To train supervised classifiers, a priori knowledge about the availability of the labeled data set is needed. To overcome this limitation, the health state fault‐severity information is used to label (eg, healthy, minor, medium, and severe) unlabeled raw condition monitoring (CM) data. In the online phase, the fault‐severity classification is carried out by kernel‐based support vector machine (SVM) classifier. Next to SVM, the k‐nearest neighbor (KNN) is also used in comparative analysis on the fault severity classification problem. Supervised classifiers are trained in the offline phase and tested in the online phase. Unlike to traditional supervised approaches, this proposed method does not require any a priori knowledge about the availability of the labeled data set. The proposed methodology is validated on infield point machine sliding‐chair degradation data to illustrate its effectiveness and applicability. The results show that the time series segmentation‐based failure severity detection and SVM‐based classification are promising.     

Crack detection of structures using modified extreme learning machine (MELM)

In this paper, crack detection and estimation method is presented in structures using modified extreme learning machine. For this purpose, extreme learning machine was modified using modified weights and biases. By using the first three frequencies and mode shapes as input, crack was detected as output. Performance of the proposed method was evaluated by using some numerical examples consisting of a simply supported beam, cantilever beam and fixed-simply supported beam. In addition, noise effect (3% noise level) on the measured frequencies and mode shapes have been investigated. In another work, a portal frame has been studied. The results indicated that the proposed method is effective and fast in crack detection and estimation of structures.     

A Fused Machine Learning Approach for Intrusion Detection System

The rapid growth in data generation and increased use of computer network devices has amplified the infrastructures of internet. The interconnectivity of networks has brought various complexities in maintaining network availability, consistency, and discretion. Machine learning based intrusion detection systems have become essential to monitor network traffic for malicious and illicit activities. An intrusion detection system controls the flow of network traffic with the help of computer systems. Various deep learning algorithms in intrusion detection systems have played a prominent role in identifying and analyzing intrusions in network traffic. For this purpose, when the network traffic encounters known or unknown intrusions in the network, a machine-learning framework is needed to identify and/or verify network intrusion. The Intrusion detection scheme empowered with a fused machine learning technique (IDS-FMLT) is proposed to detect intrusion in a heterogeneous network that consists of different source networks and to protect the network from malicious attacks. The proposed IDS-FMLT system model obtained 95.18% validation accuracy and a 4.82% miss rate in intrusion detection.     

An alliance of humans and machines for machine learning: Hybrid intelligent systems and their design principles

With the growing number of applications of artificial intelligence such as autonomous cars or smart industrial equipment, the inaccuracy of utilized machine learning algorithms could lead to catastrophic outcomes. Human-in-the-loop computing combines human and machine intelligence resulting in a hybrid intelligence of complementary strengths. Whereas machines are unbeatable in logic and computation speed, humans are contributing with their creative and dynamic minds. Hybrid intelligent systems are necessary to achieve high accuracy and reliability of machine learning algorithms. In a design science research project with a Swedish manufacturing company, this paper presents an application of human-in-the-loop computing to make operational processes more efficient. While conceptualizing a Smart Power Distribution for electric industrial equipment, this research presents a set of principles to design machine-learning algorithms for hybrid intelligence. From being AI-ready as an organization to clearly focusing on the customer benefits of a hybrid intelligent system, designers need to build and strengthen the trust in the human-AI relationship to make future applications successful and reliable. With the growing trends of technological advancements and incorporation of artificial intelligence in more and more applications, the alliance of humans and machines have become even more crucial.     

水声通信中的信道估计与机器学习交叉研究进展

近年来,以深度学习为代表的机器学习技术飞速发展,凭借其出色的学习能力,在复杂环境条件下的建模问题中展现出了独特的优势。当前,基于机器学习的水声通信技术研究方兴未艾,在信道估计及均衡、典型通信系统应用等方面取得了一定的进展,但是针对实际水声环境约束条件下的研究较少。为此,文章围绕信道估计这一水声通信关键技术,针对水声信道估计中存在的样本不足,标签标定困难以及水声环境时空变导致的源域、目标域失配等问题,讨论了水声信道估计与数据增强、无标签学习、少样本学习等模型和方法交叉研究的发展思路,并给出了初步的仿真和试验结果。文章是对水声通信中的信道估计与机器学习交叉领域研究重难点问题的初步探索,为水下各类平台自主智能化的通信技术发展提供了参考。     

基于ELM的可折支撑锁机构可靠性及其敏感度分析

 针对大多可靠性工程问题中机构极限状态函数为隐式的情况,提出了一种基于极限学习机（ELM）回归近似极限状态方程的可靠性及灵敏度分析的新方法.通过极限学习机与蒙特卡洛法相结合,利用极限学习机快速学习的能力,将复杂或隐式极限状态方程近似等价为显式极限状态方程,运用蒙特卡洛法计算出机构的失效概率,然后由高精度的显式极限状态方程进行各随机变量参数的灵敏度分析.该方法采用了基于单隐层前馈神经网络极限学习算法,因而在拟合非线性极限状态方程上表现优越,计算精度和效率高.最后以某型起落架中可折支撑锁机构为对象,进行了机构的可靠性及敏感度分析.结果表明：该方法具有高精度和高效率的优点,在工程应用上具有一定的价值．     

Big data and machine learning: A roadmap towards smart plants

Industry 4.0 aims to transform chemical and biochemical processes into intelligent systems via the integration of digital components with the actual physical units involved. This process can be thought of as addition of a central nervous system with a sensing and control monitoring of components and regulating the performance of the individual physical assets (processes, units, etc.) involved. Established technologies central to the digital integrating components are smart sensing, mobile communication, Internet of Things, modelling and simulation, advanced data processing, storage and analysis, advanced process control, artificial intelligence and machine learning, cloud computing, and virtual and augmented reality. An essential element to this transformation is the exploitation of large amounts of historical process data and large volumes of data generated in real-time by smart sensors widely used in industry. Exploitation of the information contained in these data requires the use of advanced machine learning and artificial intelligence technologies integrated with more traditional modelling techniques. The purpose of this paper is twofold: a) to present the state-of-the-art of the aforementioned technologies, and b) to present a strategic plan for their integration toward the goal of an autonomous smart plant capable of self-adaption and self-regulation for short- and long-term production management.     

A Comprehensive Review on Medical Diagnosis Using Machine Learning

The unavailability of sufficient information for proper diagnosis, incomplete or miscommunication between patient and the clinician, or among the healthcare professionals, delay or incorrect diagnosis, the fatigue of clinician, or even the high diagnostic complexity in limited time can lead to diagnostic errors. Diagnostic errors have adverse effects on the treatment of a patient. Unnecessary treatments increase the medical bills and deteriorate the health of a patient. Such diagnostic errors that harm the patient in various ways could be minimized using machine learning. Machine learning algorithms could be used to diagnose various diseases with high accuracy. The use of machine learning could assist the doctors in making decisions on time, and could also be used as a second opinion or supporting tool. This study aims to provide a comprehensive review of research articles published from the year 2015 to mid of the year 2020 that have used machine learning for diagnosis of various diseases. We present the various machine learning algorithms used over the years to diagnose various diseases. The results of this study show the distribution of machine learning methods by medical disciplines. Based on our review, we present future research directions that could be used to conduct further research.     

A data acquisition system for machine tool condition monitoring

A flexible, generically applicable and inexpensive data acquisition system (DAS), for machine tool condition monitoring, has been designed, constructed and installed as part of a European Union sponsored project. The DAS is more than just a data logger and an array of sensors. It also consists of a methodology for analysing data logging requirements and a relational database that supports this methodology. The database is held on a central ‘maintenance management’ computer. The monitoring to be carried out by the DAS is specified through this database, which contains detailed information about the DAS's facilities. This feature makes it simple to reconfigure the DAS to implement new monitoring requirements and to customize its operation to meet the needs of different machines. The information in the database is transformed into a look-up table that is read by the software that sets up and controls the data logging processes.     

A knowledge-centric CNC machine tool design and development process management framework

To cope with the increasingly competitive and demanding markets, CNC machine tool company needs a new form of development that focuses on two core competency factors: ‘process’ and ‘knowledge’. This study presents a knowledge-centric process management framework for the CNC machine tool design and development (D&D) with the integration of process and knowledge. Requirements for the framework are generated based primarily on the nature of the machine tool design practice. The proposed framework consists of process integration model, process simulation, process execution and knowledge objects management modules. Each of these modules is elaborated to support the knowledge-centric machine tool development process management. Finally, the prototype development is presented. Results of this study facilitate the knowledge integration in CNC machine tool D&D, and thus increase machine tool development capability, reduce development cycle time and cost, and ultimately speed up the effectiveness and ensure the excellent machine tool development.     

通用图灵机的计算机仿真设计

将图灵机转移函数δ(qi,aj)=(qk,al)编码为(i,Unicode(aj),k,Unicode(al)),并将此编码方案应用于所设计的通用图灵机模型.模型的存储装置由两个带组成:一个一维的单向带,用来存储输入数据ω;一个二维带,用来存储图灵机描述"M".在PC机上仿真了上述模型,控制器算法的时间复杂度为O(|K|2),优于传统编码方案的通用图灵机模型.     

A machine learning approach to yield management in semiconductor manufacturing

Yield improvement is one of the most important topics in semiconductor manufacturing. Traditional statistical methods are no longer feasible nor efficient, if possible, in analysing the vast amounts of data in a modern semiconductor manufacturing process. For instance, a typical wafer fabrication process has more than 1000 process parameters to record on a single wafer and one manufacturing plant may produce tens of thousands wafers a day. Traditional approaches have limits in extracting the full benefits of the data. Therefore, the manufacturing data is poorly exploited even in the most sophisticated processes. Now it is widely accepted that machine learning techniques can provide powerful tools for continuous quality improvement in a large and complex process such as semiconductor manufacturing. In this work, memory based reasoning (MBR) and neural network (NN) learning are combined for yield improvement and an integrated framework is proposed for a yield management system based on hybrid machine learning techniques. In this hybrid system of NN and MBR, the feature weight set which is calculated from the trained neural network plays the core role in connecting both learning strategies and the explanation on prediction can be given by obtaining and presenting the most similar examples from the case base. The proposed system has advantages in typical semiconductor manufacturing problems such as scalability to large datasets, high dimensions and adaptability to dynamic situations.