Failure mode classification and bearing capacity prediction for reinforced concrete columns based on ensemble machine learning algorithm

Failure mode (FM) and bearing capacity of reinforced concrete (RC) columns are key concerns in structural design and/or performance assessment procedures. The failure types, i.e., flexure, shear, or mix of the above two, will greatly affect the capacity and ductility of the structure. Meanwhile, the design methodologies for structures of different failure types will be totally different. Therefore, developing efficient and reliable methods to identify the FM and predict the corresponding capacity is of special importance for structural design/assessment management. In this paper, an intelligent approach is presented for FM classification and bearing capacity prediction of RC columns based on the ensemble machine learning techniques. The most typical ensemble learning method, adaptive boosting (AdaBoost) algorithm, is adopted for both classification and regression (prediction) problems. Totally 254 cyclic loading tests of RC columns are collected. The geometric dimensions, reinforcing details, material properties are set as the input variables, while the failure types (for classification problem) and peak capacity forces (for regression problem) are set as the output variables. The results indicate that the model generated by the AdaBoost learning algorithm has a very high accuracy for both FM classification (accuracy = 0.96) and capacity prediction (R² = 0.98). Different learning algorithms are also compared and the results show that ensemble learning (especially AdaBoost) has better performance than single learning. In addition, the bearing capacity predicted by the AdaBoost is also compared to that by the empirical formulas provided by the design codes, which shows an obvious superior of the proposed method. In summary, the machine learning technique, especially the ensemble learning, can provide an alternate to the conventional mechanics-driven models in structural design in this big data time.     

Mechanical behavior of aluminum foils as micro structural material under low velocity impact loading

 If many works consist in describing the static behavior of micro materials, not one concerns impact loading. Therefore, the proposed work aims to analyze the dynamic behavior of micro material items under low velocity impact loading, with an application for aluminum foils as micro structural material. The purpose of this experimental study is also to establish the feasibility and the performance of an impact testing machine for micro materials. In comparison of quasi-static reference curves, the structural responses of dynamically loading micro plates underline the specificity and so the necessity of impact tests. The material strength repartition exhibiting a few scattering data allows to validate the drop-weight set-up, confirms the differences statistically and authorizes some future investigation. Received: 22 August 2001/Accepted: 8 January 2002 The authors wish to acknowledge the contribution of both Prof. Y. Higo and Prof. K. Takashima of the Precision and Intelligence Laboratory (Tokyo Institute of Technology) and Toyotechnica Corporation for the realization of the micro indentation tests. This paper was presented at the conference of Micro System Technologies 2001 in March 2001.     

光伏板缺陷分类的原型网络改进

在光伏板缺陷分类领域中,传统的缺陷分类手段和新兴的机器学习方法都存在局限性,不足以满足光伏板缺陷分类需求,急需更可靠的解决方案.近些年来小样本学习以其能在有限量数据下快速学习并泛化到新任务的特点,逐渐在各领域兴起,给缺陷技术的优化带来新的思路.在这里,以典型的小样本学习方法——原型网络方法为基础,提出了基于改进的原型网络的光伏板缺陷分类方法.该方法调整了训练模式,通过改进模型主干网络和相似性度量标准来有效解决原型网络对复杂样本的特征嵌入能力较差和模型精度一般的问题,方法在经典的光伏板缺陷数据集进行了多次对比实验.结果表明:改进方法的实验耗时大大缩短,模型精度得到提高.     

Ensemble weighted extreme learning machine for imbalanced data classification based on differential evolution

Extreme learning machine for single-hidden-layer feedforward neural networks has been extensively applied in imbalanced data learning due to its fast learning capability. Ensemble approach can effectively improve the classification performance by combining several weak learners according to a certain rule. In this paper, a novel ensemble approach on weighted extreme learning machine for imbalanced data classification problem is proposed. The weight of each base learner in the ensemble is optimized by differential evolution algorithm. Experimental results on 12 datasets show that the proposed method could achieve more classification performance compared with the simple vote-based ensemble method and non-ensemble method.

     

Depression detection from sMRI and rs-fMRI images using machine learning

Major Depression Disorder (MDD) is a common mental disorder that negatively affects many people’s lives worldwide. Developing an automated method to find useful diagnostic biomarkers from brain imaging data would help clinicians to detect MDD in its early stages. Depression is known to be a brain connectivity disorder problem. In this paper, we present a brain connectivity-based machine learning (ML) workflow that utilizes similarity/dissimilarity of spatial cubes in brain MRI images as features for depression detection. The proposed workflow provides a unified framework applicable to both structural MRI images and resting-state functional MRI images. Several cube similarity measures have been explored, including Pearson or Spearman correlations, Minimum Distance Covariance, or inverse of Minimum Distance Covariance. Discriminative features from the cube similarity matrix are chosen with the Wilcoxon rank-sum test. The extracted features are fed into machine learning classifiers to train MDD prediction models. To address the challenge of data imbalance in MDD detection, oversampling is performed to balance the training data. The proposed workflow is evaluated through experiments on three independent public datasets, all imbalanced, of structural MRI and resting-state fMRI images with depression labels. Experimental results show good performance on all three datasets in terms of prediction accuracy, specificity, sensitivity, and area under the Receiver Operating Characteristic (ROC) curve. The use of features from both structured MRI and resting state functional MRI is also investigated.

     

Integrating preventive and predictive maintenance policies with system dynamics: A decision table approach

A decision table is a practical tool that helps systems planners to make operational decisions, especially when they are under stress. With the effect of recent trends, such as the use of machine learning, data mining, and reinforcement learning methods, the maintenance decision has been a dynamic issue depending on system conditions. An expert may execute the maintenance or wait for the next periodic maintenance due to lack of maintenance workers, tools or budget, resources, etc., although the intelligent method predicts a failure approaching. Even sometimes, he/she may ignore the current periodic maintenance. Our method allows making some changes in the maintenance plan systematically. It integrates the results of preventive and predictive maintenance policies, and as different from the literature, it allows ignoring some maintenance actions depending on the maintenance resource levels in a decision table. Such a strategy helps to allocate limited resources to maintenance actions reasonably. We conducted an extensive simulation study on a real-life dataset. The preventive maintenance period is determined using classical approaches such as Weibull analysis. A machine learning algorithm is utilized to predict the type of failure. We have analyzed the performance of the proposed decision table approach under a variety of scenarios and with different parameter settings. We also showed the effect of parameter settings and the marginal utility of each maintenance policy. In addition, the approach provides several choices for planners. As a result, the proposed approach improves the system’s sustainability compared to traditional policies.     

一种新的孪生大间隔分布机算法

为了提高孪生支持向量机的泛化能力,提出一种新的孪生大间隔分布机算法,以增加间隔分布对于训练模型的影响.理论研究表明,间隔分布对于模型的泛化性能有着非常重要的影响.该算法在标准孪生支持向量机优化目标函数上增加了间隔分布的影响,间隔分布通过一阶和二阶数据统计特征来体现.在标准数据集上的实验结果表明,所提出的算法比SVM、TWSVM、TBSVM算法的分类精确度更高.     

Tool wear monitoring and prognostics challenges: a comparison of connectionist methods toward an adaptive ensemble model

In a high speed milling operation the cutting tool acts as a backbone of machining process, which requires timely replacement to avoid loss of costly workpiece or machine downtime. To this aim, prognostics is applied for predicting tool wear and estimating its life span to replace the cutting tool before failure. However, the life span of cutting tools varies between minutes or hours, therefore time is critical for tool condition monitoring. Moreover, complex nature of manufacturing process requires models that can accurately predict tool degradation and provide confidence for decisions. In this context, a data-driven connectionist approach is proposed for tool condition monitoring application. In brief, an ensemble of Summation Wavelet-Extreme Learning Machine models is proposed with incremental learning scheme. The proposed approach is validated on cutting force measurements data from Computer Numerical Control machine. Results clearly show the significance of our proposition.     

AK-SYSi: an improved adaptive Kriging model for system reliability analysis with multiple failure modes by a refined U learning function

Due to multiple implicit limit state functions needed to be surrogated, adaptive Kriging model for system reliability analysis with multiple failure modes meets a big challenge in accuracy and efficiency. In order to improve the accuracy of adaptive Kriging meta-model in system reliability analysis, this paper mainly proposes an improved AK-SYS by using a refined U learning function. The improved AK-SYS updates the Kriging meta-model from the most easily identifiable failure mode among the multiple failure modes, and this strategy can avoid identifying the minimum mode or the maximum mode by the initial and the in-process Kriging meta-models and eliminate the corresponding inaccuracy propagating to the final result. By analyzing three case studies, the effectiveness and the accuracy of the proposed refined U learning function are verified.

     

Anomaly detection in the context of long-term cloud resource usage planning

This paper describes a new approach to automatic long-term cloud resource usage planning with a novel hybrid anomaly detection mechanism. It analyzes existing anomaly detection solutions, possible improvements and the impact on the accuracy of resource usage planning. The proposed anomaly detection solution is an important part of the research, since it allows greater accuracy to be achieved in the long term. The proposed approach dynamically adjusts reservation plans in order to reduce the unnecessary load on resources and prevent the cloud from running out of them. The predictions are based on cloud analysis conducted using machine learning algorithms, which made it possible to reduce costs by about 50%. The solution was evaluated on real-life data from over 1700 virtual machines.

     

Reliability-based design optimization of composite stiffened panels in post-buckling regime

This paper focuses on Deterministic and Reliability Based Design Optimization (DO and RBDO) of composite stiffened panels considering post-buckling regime and progressive failure analysis. The ultimate load that a post-buckled panel can hold is to be maximised by changing the stacking sequence of both skin and stringers composite layups. The RBDO problem looks for a design that collapses beyond the shortening of failure obtained in the DO phase with a target reliability while considering uncertainty in the elastic properties of the composite material. The RBDO algorithm proposed is decoupled and hence separates the Reliability Analysis (RA) from the deterministic optimization. The main code to drive both the DO and RBDO approaches is written in MATLAB and employs Genetic Algorithms (GA) to solve the DO loops because discrete design variables and highly nonlinear response functions are expected. The code is linked with Abaqus to perform parallel explicit nonlinear finite element analyses in order to obtain the structural responses at each generation. The RA is solved through an inverse Most Probable failure Point (MPP) search algorithm that benefits from a Polynomial Chaos Expansion with Latin Hypercube Sampling (PCE-LHS) metamodel when the structural responses are required. The results led to small reductions in the maximum load that the panels can bear but otherwise assure that they will collapse beyond the shortening of failure imposed with a high reliability.

     

Calling communities analysis and identification using machine learning techniques

The analysis of social communities related logs has recently received considerable attention for its importance in shedding light on social concerns by identifying different groups, and hence helps in resolving issues like predicting terrorist groups. In the customer analysis domain, identifying calling communities can be used for determining a particular customer’s value according to the general pattern behavior of the community that the customer belongs to; this helps the effective targeted marketing design, which is significantly important for increasing profitability. In telecommunication industry, machine learning techniques have been applied to the Call Detail Record (CDR) for predicting customer behavior such as churn prediction. In this paper, we pursue identifying the calling communities and demonstrate how cluster analysis can be used to effectively identify communities using information derived from the CDR data. We use the information extracted from the cluster analysis to identify customer calling patterns. Customers calling patterns are then given to a classification algorithm to generate a classifier model for predicting the calling communities of a customer. We apply different machine learning techniques to build classifier models and compare them in terms of classification accuracy and computational performance. The reported test results demonstrate the applicability and effectiveness of the proposed approach.     

Learning to Generate Posters of Scientific Papers by Probabilistic Graphical Models

Researchers often summarize their work in the form of scientific posters. Posters provide a coherent and efficient way to convey core ideas expressed in scientific papers. Generating a good scientific poster, however, is a complex and time-consuming cognitive task, since such posters need to be readable, informative, and visually aesthetic. In this paper, for the first time, we study the challenging problem of learning to generate posters from scientific papers. To this end, a data-driven framework, which utilizes graphical models, is proposed. Specifically, given content to display, the key elements of a good poster, including attributes of each panel and arrangements of graphical elements, are learned and inferred from data. During the inference stage, the maximum a posterior (MAP) estimation framework is employed to incorporate some design principles. In order to bridge the gap between panel attributes and the composition within each panel, we also propose a recursive page splitting algorithm to generate the panel layout for a poster. To learn and validate our model, we collect and release a new benchmark dataset, called NJU-Fudan Paper-Poster dataset, which consists of scientific papers and corresponding posters with exhaustively labelled panels and attributes. Qualitative and quantitative results indicate the effectiveness of our approach.

     

Multi-kernel optimized relevance vector machine for probabilistic prediction of concrete dam displacement

The observation data of dam displacement can reflect the dam’s actual service behavior intuitively. Therefore, the establishment of a precise data-driven model to realize accurate and reliable safety monitoring of dam deformation is necessary. This study proposes a novel probabilistic prediction approach for concrete dam displacement based on optimized relevance vector machine (ORVM). A practical optimization framework for parameters estimation using the parallel Jaya algorithm (PJA) is developed, and various simple kernel/multi-kernel functions of relevance vector machine (RVM) are tested to obtain the optimal selection. The proposed model is tested on radial displacement measurements of a concrete arch dam to mine the effect of hydrostatic, seasonal and irreversible time components on dam deformation. Four algorithms, including support vector regression (SVR), radial basis function neural network (RBF-NN), extreme learning machine (ELM) and the HST-based multiple linear regression (HST-MLR), are used for comparison with the ORVM model. The simulation results demonstrate that the proposed multi-kernel ORVM model has the best performance for predicting the displacement out of range of the used measurements dataset. Meanwhile, the ORVM model has the advantages of probabilistic output and can provide reasonable confidence interval (CI) for dam safety monitoring. This study lays the foundation for the application of RVM in the field of dam health monitoring.

     

Physics-based machine learning method and the application to energy consumption prediction in tunneling construction

Representing causality in machine learning to predict control parameters is state-of-the-art research in intelligent control. This study presents a physics-based machine learning method providing a prediction model that guarantees enhanced interpretability conforming to physical laws. The proposed approach encodes physical knowledge as mapping relationships between variables in engineering dataset into the learning procedure through dimensional analysis. This derives causal relationships between the control parameter and its influencing factors. The proposed machine learning method's objective function is further improved by the penalty term in the regularization strategy. Verifications on the energy consumption prediction of tunnel boring machine prove that, the established model accords with basic principles in this field. Moreover, the proposed approach traces the impact of three major factors (structure, operation, and geology) along the construction section, offering each component's contribution rates to energy consumption. Compared with several commonly used machine learning algorithms, the proposed method reduces the need for large amounts of training data and demonstrates higher accuracy. The results indicate that the revealed causality and enhanced prediction performance of the proposed method advance the applicability of machine learning methods to intelligent control during construction.     

Independent component analysis-based defect detection in patterned liquid crystal display surfaces

In this paper, we propose a machine vision approach for automatic detection of micro defects in periodically patterned surfaces and, especially, aim at thin film transistor liquid crystal display (TFT-LCD) panels. The proposed method is based on an image reconstruction scheme using independent component analysis (ICA). ICA is first applied to a faultless training image to determine the de-mixing matrix and the corresponding independent components (ICs). The ICs representing the global structure of the training image are then identified and the associated row vectors of those ICs in the de-mixing matrix are replaced with a de-mixing row representing the least structured region of the training image. The reformed de-mixing matrix is then used to reconstruct the TFT-LCD image under inspection. The resulting image can effectively remove the global structural pattern and preserve only local anomalies. A number of micro defects in different TFT-LCD panel surfaces are evaluated with the proposed method. The experiments show that the proposed method can well detect various ill-defined defects in periodically patterned surfaces.     

Artificial intelligence-enhanced seismic response prediction of reinforced concrete frames

Existing physics-based modeling approaches do not have a good compromise between performance and computational efficiency in predicting the seismic response of reinforced concrete (RC) frames, where high-fidelity models (e.g., fiber-based modeling method) have reasonable predictive performance but are computationally demanding, while more simplified models (e.g., shear building model) are the opposite. This paper proposes a novel artificial intelligence (AI)-enhanced computational method for seismic response prediction of RC frames which can remedy these problems. The proposed AI-enhanced method incorporates an AI technique with a shear building model, where the AI technique can directly utilize the real-world experimental data of RC columns to determine the lateral stiffness of each column in the target RC frame while the structural stiffness matrix is efficiently formulated via the shear building model. Therefore, this scheme can enhance prediction accuracy due to the use of real-world data while maintaining high computational efficiency due to the incorporation of the shear building model. Two data-driven seismic response solvers are developed to implement the proposed approach based on a database including 272 RC column specimens. Numerical results demonstrate that compared to the experimental data, the proposed method outperforms the fiber-based modeling approach in both prediction capability and computational efficiency and is a promising tool for accurate and efficient seismic response prediction of structural systems.     

A face detection ensemble to monitor the adoption of face masks inside the public transportation during the COVID-19 pandemic

The designing of ensembles is widely adopted when single machine learning methods fail to obtain satisfactory performances by analyzing complex data characterized by being imbalanced, high-dimensional, and noisy. Such a failure is a well-known statistical challenge when the learning algorithm searches for a model in a large space of hypotheses and the data do not significantly represent the problem, thus not inducing it from a space of admissible functions towards the best global model. We have addressed this issue in a real-world application, whose main objective was to identify whether users were wearing masks inside public transportation during the COVID-19 pandemic. Several studies have already pointed that face masks are an important and efficient non-pharmacological strategy to reduce the virus spread. In this sense, we designed an approach using Convolutional Neural Networks (CNN) to track the adoption of masks in different transportation lines, regions, days, and time. Aiming at reaching this goal, we propose an ensemble of face detectors and a CNN architecture, called MaskNet, to analyze all public-transport passengers and provide valuable information to policymakers, which are able to dedicate efforts to more effective advertisements and awareness work. In practice, our approach is running in a real scenario in Salvador (Brazil).

     

Predicting Code Smells and Analysis of Predictions: Using Machine Learning Techniques and Software Metrics

Code smell detection is essential to improve software quality, enhancing software maintainability, and decrease the risk of faults and failures in the software system. In this paper, we proposed a code smell prediction approach based on machine learning techniques and software metrics. The local interpretable model-agnostic explanations (LIME) algorithm was further used to explain the machine learning model’s predictions and interpretability. The datasets obtained from Fontana et al. were reformed and used to build binary-label and multi-label datasets. The results of 10-fold cross-validation show that the performance of tree-based algorithms (mainly Random Forest) is higher compared with kernel-based and network-based algorithms. The genetic algorithm based feature selection methods enhance the accuracy of these machine learning algorithms by selecting the most relevant features in each dataset. Moreover, the parameter optimization techniques based on the grid search algorithm significantly enhance the accuracy of all these algorithms. Finally, machine learning techniques have high potential in predicting the code smells, which contribute to detect these smells and enhance the software’s quality.