The Cambridge Structural Database (CSD): Current Activities and Future Plans

This paper reviews the search and analysis software packages QUEST3D and VISTA, also the database-building program PreQuest. The relationship between the CSD and the Protein Data Bank is discussed and development plans are outlined.     

Recognition of machining features - a hybrid approach

This paper describes a hybrid system which endeavours to recognize machining features automatically from a boundary representation (b-rep)-based solid modeller. The graph-based approach and the volume approach are adopted in consecutive stages in a prototype feature recognition system to combine the positive aspects of both strategies. The graph-based approach is based on feature edge sequence (FES) graph, a new graph structure introduced in this system. The FES graph approach is used to extract primitive features from the three-dimensional solid model; and the volume decomposition approach is incorporated to generate multiple interpretations of the feature sets. In addition, a neural network (NN)-based technique is used to tackle the problem of nonorthogonal and arbitrary features. Using the hybrid system, a workpiece designed in b-rep solid modeller will be interpreted and represented by a set of primitive features attached with significant manufacturing parameters, including multiple interpretations, tool directions and machining sequences, etc. The overall hybrid system is able to transform a pure geometric model into a machining feature-based model which is directly applicable for downstream manufacturing applications.     

Durability design of reinforced concrete structures: a comparison of the use of durability indexes in the deemed-to-satisfy approach and the full-probabilistic approach

To show the application of the chloride conductivity index test in service life prediction (SLP) using both the deemed-to-satisfy and probabilistic approaches to performance-based durability design. It is desirable to adopt a performance-based approach with respect to durability design of reinforced concrete (RC) structures. This is based on the perception that the durability of RC is achieved when the limiting value from an established test method is met. In South Africa, the durability index (DI) approach has been developed, which permits performance-based specifications for durability of RC. This approach involves the application of a test method together with a SLP model. This integrated approach links material properties directly with the expected service life of RC structures and environmental conditions. Two DIs are relevant to degradation processes in RC: the chloride conductivity index which is related to chloride ingress, and the oxygen permeability index related to carbonation. The study presented here focuses on the application of the chloride conductivity index as the main input parameter of a SLP model concerned with chloride-induced reinforcement corrosion. The methodology and output of the SLP model as applied in the deemed-to-satisfy approach are compared with those of the probabilistic approach. Both approaches are exemplified using a concrete pier cast in situ in a marine environment. The performance-based durability specifications from the deemed-to-satisfy approach are found to be more conservative compared to those of the probabilistic approach.     

旋转机械升降速过程的双谱-FHMM识别方法

结合双谱和因子Markov模型，提出了一种基于双谱的特征提取建立机组各状态相应的因子隐Markov模型状态识别法，并成功地应用到旋转机械升降速过程的故障诊断中，同时还与基于双谱的特征提取的HMM状态识别法进行了比较，实验结果表明该方法是有效的。     

Multiatlas‐based segmentation of female pelvic organs: Application for computer‐aided diagnosis of cervical cancer

Atlas‐based segmentation is a high level segmentation technique which has become a standard paradigm for exploiting prior knowledge in image segmentation. Recent multiatlas‐based methods have provided greatly accurate segmentations of different parts of the human body by propagating manual delineations from multiple atlases in a data set to a query subject and fusing them. The female pelvic region is known to be of high variability which makes the segmentation task difficult. We propose, here, an approach for the segmentation of magnetic resonance imaging (MRI) called multiatlas‐based segmentation using online machine learning (OML). The proposed approach allows separating regions which may be affected by cervical cancer in a female pelvic MRI. The suggested approach is based on an online learning method for the construction of the dataset of atlases. The experiments demonstrate the higher accuracy of the suggested approach compared to a segmentation technique based on a fixed dataset of atlases and single‐atlas‐based segmentation technique.     

Collocation-based stochastic finite element analysis for random field problems

A stochastic response surface method (SRSM) which has been previously proposed for problems dealing only with random variables is extended in this paper for problems in which physical properties exhibit spatial random variation and may be modeled as random fields. The formalism of the extended SRSM is similar to the spectral stochastic finite element method (SSFEM) in the sense that both of them utilize Karhunen–Loeve (K–L) expansion to represent the input, and polynomial chaos expansion to represent the output. However, the coefficients in the polynomial chaos expansion are calculated using a probabilistic collocation approach in SRSM. This strategy helps us to decouple the finite element and stochastic computations, and the finite element code can be treated as a black box, as in the case of a commercial code. The collocation-based SRSM approach is compared in this paper with an existing analytical SSFEM approach, which uses a Galerkin-based weighted residual formulation, and with a black-box SSFEM approach, which uses Latin Hypercube sampling for the design of experiments. Numerical examples are used to illustrate the features of the extended SRSM and to compare its efficiency and accuracy with the existing analytical and black-box versions of SSFEM.     

Stability analysis of autonomously controlled production networks

In this paper we present a stability analysis of autonomously controlled production networks from mathematical and engineering points of view. Roughly speaking stability of a system means that the defined state of the system remains bounded over time. The dynamics of a production network are modelled by differential equations (macroscopic approach) and discrete event simulation (microscopic approach), respectively. Both approaches are used to perform a stability analysis. As a result of the stability analysis of the macroscopic approach we calculate parameters, which guarantee stability of the network for arbitrary inputs. These results are refined for a certain (varying) input using the microscopic approach, where we derive the smallest maximal production rates of the plants for which stability of the overall system can be guaranteed. Furthermore, the microscopic approach includes two different autonomous control methods: the queue length estimator (QLE) and the pheromone based (PHE) method. These methods allow additional autonomous decision making on the shop floor level. The approach presented in this paper is to calculate stability conditions by mathematical systems theory to guarantee stability for production networks, to identify a stability region and to refine this region by simulations.     

Multi-Layer Fog-Cloud Architecture for Optimizing the Placement of IoT Applications in Smart Cities

In the smart city paradigm, the deployment of Internet of Things (IoT) services and solutions requires extensive communication and computing resources to place and process IoT applications in real time, which consumes a lot of energy and increases operational costs. Usually, IoT applications are placed in the cloud to provide high-quality services and scalable resources. However, the existing cloud-based approach should consider the above constraints to efficiently place and process IoT applications. In this paper, an efficient optimization approach for placing IoT applications in a multi-layer fog-cloud environment is proposed using a mathematical model (Mixed-Integer Linear Programming (MILP)). This approach takes into account IoT application requirements, available resource capacities, and geographical locations of servers, which would help optimize IoT application placement decisions, considering multiple objectives such as data transmission, power consumption, and cost. Simulation experiments were conducted with various IoT applications (e.g., augmented reality, infotainment, healthcare, and compute-intensive) to simulate realistic scenarios. The results showed that the proposed approach outperformed the existing cloud-based approach in terms of reducing data transmission by 64% and the associated processing and networking power consumption costs by up to 78%. Finally, a heuristic approach was developed to validate and imitate the presented approach. It showed comparable outcomes to the proposed model, with the gap between them reach to a maximum of 5.4% of the total power consumption.     

Analytical evaluation and application of the singularities in boundary element method

In this paper, two alternative approaches to the boundary element method (BEM) are investigated; namely, the contour approach method and the direct approach method. A detailed comparison of these methods is made by evaluating the accuracy of singular boundary integrals. A complete and comprehensive exposition of the derivation leads to the correct implementation. This is in contrast to conventional numerical integration methods, which suffer from the numerical boundary layer. Singularities which are mathematical artifacts are shown to vanish when the contour approach and the direct approach methods are applied. Singularities which arise from the physics are dealt with by way of a complex mapping method in the BEM. The results of seven benchmark problems which are supportive of these conclusions are presented at the end of this article.     

Identification of Failure Mechanisms to Enhance Prognostic Outcomes

Predicting the reliability of a system in its actual life cycle conditions and estimating its time to failure is helpful in decision making to mitigate system risks. There are three approaches to prognostics: the physics-of-failure approach, the data-driven approach, and the fusion approach. A key requirement in all these approaches is the identification of the appropriate parameter(s) to monitor the collection of the data that can be employed to assess impending failure. This article presents the physics-of-failure approach, which uses failure modes, mechanisms, and effects analysis (FMMEA) to enhance prognostics planning and implementation. This article also presents the fusion approach to prognostics and the applicability of FMMEA to this approach. As an example, a case of generating FMMEA information, and using that to identify appropriate parameters to monitor, is presented.     

A new directed graph approach for automated setup planning in CAPP

The task of setup planning is to determine the number and sequence of setups and the machining features or operations in each setup. Now there are three main methods for setup planning, i.e., the knowledge-based approach, the graph-based approach and the intelligence algorithm-based approach. In the knowledge-based and graph-based approaches reported in the literature, the main problem is that there is no guarantee that all precedence cycles between setups can be avoided during setup formation. The methods to break precedence cycles between setups are to split one setup into smaller setups. However, the implementation of this method is difficult and complex. In the intelligence algorithm-based approach, the method to handle the precedence constraints is a penalty strategy, which does not reflect the influence of precedence constraints on setup plans explicitly. To deal with the above deficiencies, a new directed graph approach is proposed to describe precedence constraints explicitly, which consists of three parts: (1) a setup precedence graph (SPG) to describe precedence constraints between setups. During the generation of the SPG, the minimal number of tolerance violations is guaranteed preferentially by the vertex clusters algorithm for serial vertices and the minimal number of setups is achieved by using variants of the breadth-first search. Precedence cycles between setups are avoided by checking whether two serial vertex clusters can generate a cycle; (2) operation sequencing to minimise tool changes in a setup; and (3) setup sequencing to generate optimal setup plans, which could be implemented by a topological sort. The new directed graph approach will generate many optimal or near-optimal setup plans and provide more flexibility required by different job shops. An example is illustrated to demonstrate the effect of the proposed approach.     

Setup planning using Hopfield net and simulated annealing

This paper reports a new approach to setup planning of prismatic parts using Hopfield neural net coupled with simulated annealing. The approach deals with setup planning in two stages, i.e.: (1) sequence all the features of a workpiece according to geometric and technological constraints; and (2) identify setups from the sequenced features. In the first stage, the task of feature sequencing is converted to a constraint optimization problem (COP) which is similar to the travelling salesman problem (TSP). The setup time due to setup and tool changes is incorporated into the 'distance' between features, while the precedence and critical tolerance relationships between features are treated as constraints. The Hopfield neural net approach for TSP, i.e. energy function, is adopted to model the COP mathematically where the constraints are attached as additional penalty functions. Simulated annealing is then used to search for the minimum energy state of the net while avoiding the local minima. The feature sequence obtained aims at minimizing the number of setups and tool changes while ensuring little or no violation of feature precedence relationship, thus keeping critical tolerance violation to a minimum. In the second stage, setups are generated from the sequenced features using a vector intersection approach based on common tool approach directions. A case study is presented to demonstrate the effectiveness of this approach. A comparison study between this approach and an existing integer programming setup planning system is also given which indicates the superior efficiency of the proposed approach when dealing with problems with large number of features.     

English to Tamil machine translation system using universal networking language

This paper proposes English to Tamil machine translation system, using the universal networking language (UNL) as the intermediate representation. The UNL approach is a hybrid approach of the rule and knowledge-based approaches to machine translation. UNL is a declarative formal language, specifically designed to represent semantic data extracted from a natural language text. The input English sentence is converted to UNL (enconversion), which is then converted to a Tamil sentence (deconversion) by ensuring that the meaning of the input sentence is preserved. The representation of UNL was modified to suit the translation process. A new sentence formation algorithm was also proposed to rearrange the translated Tamil words to sentences. The translation system was evaluated using bilingual evaluation understudy (BLEU) score. A BLEU score of 0.581 was achieved, which is an indication that most of the information in the input sentence is retained in the translated sentence. The scores obtained using the UNL based approach were compared with existing approaches to translation, and it can be concluded that the UNL is a more suited approach to machine translation.     

A non-iterative approach for the modelling of quasi-brittle materials

Due to the softening behaviour of quasi-brittle materials, in particular the localisation of initially diffused cracking, convergence problems are often found using an iterative procedure, such as the Newton?CRaphson method. This is why a new non-iterative procedure is adopted in this paper, which is inspired by the sequentially linear approach(SLA) (Rots et?al. in Eng Fract Mech 75(3?C4):590?C614, 2008). However, several important differences between the present approach and the SLA are presented. In the present model, multi-linear material laws are adopted such that non-linearities occur only due to changes in loading/unloading states. An incremental solution is obtained until non-convergence occurs, upon which a secant approach is used in a corresponding step. The update of the stiffness in the secant approach is based on information obtained from the previous incremental solution. This method is applied to: (i) softening materials, within the scope of the discrete crack approach, and to (ii) hardening materials. As a consequence, conversely to the smeared crack approach adopted in the SLA, no mesh size sensitivity problems are obtained and there is no need to adjust material parameters. Several numerical examples are shown in order to illustrate the proposed formulation.     

Emotion recognition using eigenvalues and Levenberg–Marquardt algorithm-based classifier

In this paper, a simple and computationally efficient approach is proposed for person independent facial emotion recognition. The proposed approach is based on the significant features of an image, i.e., the collection of few largest eigenvalues (LE). Further, a Levenberg–Marquardt algorithm-based neural network (LMNN) is applied for multiclass emotions classification. This leads to a new facial emotion recognition approach (LE-LMNN) which is systematically examined on JAFFE and Cohn–Kanade databases. Experimental results illustrate that the LE-LMNN approach is effective and computationally efficient for facial emotion recognition. The robustness of the proposed approach is also tested on low-resolution facial emotion images. The performance of the proposed approach is found to be superior as compared to the various existing methods.     

A cutting plane approach for the single-product assembly system design problem

This paper evaluates a new branch-and-cut approach, establishing a computational benchmark for the single-product, assembly system design (SPASD) problem. Our approach, which includes a heuristic, preprocessing, and two cutgenerating methods, outperformed OSL in solving a set of 102 instances of the SPASD problem. The approach is robust; test problems show that it can be applied to variations of the generic SPASD problem that we encountered in industry.     

Robust design of asynchronous flexible assembly systems

In this paper, we propose a new analytical approach for designing asynchronous flexible assembly systems (AFAS). Our approach is based on the robust design methodology, which aims at studying and reducing the effect of uncontrollable factors in the process of identifying the most appropriate configuration for an AFAS. The traditional approach in designing AFAS is to pre-fix a set of the design parameters, e.g. workstation jam rates and jam clear times. We attempt to remedy this shortcoming of the prevailing studies by developing an AFAS design optimization methodology that ensures robustness of the final system design with respect to possible variations in the uncontrollable factors. We report on our analyses of four families of AFAS designs, which reveal the effectiveness of our approach.     

Hybrid capacity modeling for alternative machine types in linear programming production planning

Processing by alternative machines is very common in today's manufacturing environment, especially in the semiconductor industry. Leachman and Carmon (1992) have presented a novel approach to model alternative machine capacitated problems for Linear Programming (LP) production planning. Their approach makes possible the modeling of complex processes with re-entry into alternative machines in large scale LP production planning. However, there are difficulties in using their approach in industrial applications. In order to use their approach, a uniform assumption must be satisfied. But in many industrial applications, this assumption cannot be satisfied. In addition, their approach creates new alternative machine sets by performing union operations on existing alternative machine sets with common machine types. This will increase the number of capacity constraints, which may increase the solution time of the LP formulation. This study compares their approach and the partition approach outlined herein in terms of CPU times used. Finally, this study proposes a hybrid capacity modeling approach that is more suitable for industrial applications.     

A stress-influence-function with adaptive strength feature approach for stress constrained continuum topology optimization via small-loop sequential strategy

Recently, the stress-influence-function (SIF) approach is presented for stress constrained continuum topology optimization. The SIF approach provides an alternative for continuum topology optimization with stress constraints. However, the SIF approach is not good at controlling the maximum stress of the elements compared to the conventional approach. In the study, the stress-influence-function with adaptive strength feature (SIF-ASF) approach via small-loop sequential strategy is proposed to achieve better control on the maximum elemental stress. First, the stress constrained continuum topology optimization formulation is given and the SIF approach is briefly introduced. Then the SIF-ASF approach is proposed for stress constrained continuum topology optimization, in which the strength feature in the stress influence function is adjusted in each iterative step of the optimization process. The adjoint-vector based sensitivity analysis to the design variables is further discussed. Three numerical examples are given to illustrate the applicability and validity of the proposed SIF-ASF approach. It is shown that the proposed SIF-ASF approach can achieve better control on the maximum elemental stress than the SIF approach. Moreover, the proposed SIF-ASF approach may obtain a lighter structure than the conventional approach.     

Transfer Learning for Chest X-rays Diagnosis Using Dipper ThroatedAlgorithm

Most children and elderly people worldwide die from pneumonia, which is a contagious illness that causes lung ulcers. For diagnosing pneumonia from chest X-ray images, many deep learning models have been put forth. The goal of this research is to develop an effective and strong approach for detecting and categorizing pneumonia cases. By varying the deep learning approach, three pre-trained models, GoogLeNet, ResNet18, and DenseNet121, are employed in this research to extract the main features of pneumonia and normal cases. In addition, the binary dipper throated optimization (DTO) algorithm is utilized to select the most significant features, which are then fed to the K-nearest neighbor (KNN) classifier for getting the final classification decision. To guarantee the best performance of KNN, its main parameter (K) is optimized using the continuous DTO algorithm. To test the proposed approach, six evaluation metrics were employed namely, positive and negative predictive values, accuracy, specificity, sensitivity, and F1-score. Moreover, the proposed approach is compared with other traditional approaches, and the findings confirmed the superiority of the proposed approach in terms of all the evaluation metrics. The minimum accuracy achieved by the proposed approach is (98.5%), and the maximum accuracy is (99.8%) when different test cases are included in the evaluation experiments.