In this work a new data-driven compression approach is presented. The compression algorithm is an autoencoder trained with an improved On-line sequential Extreme Learning Machine (OS-ELM). First, a dynamic adaptation of the training algorithm towards the newly coming data is achieved by integrating an updated selection strategy (USS) and dynamic forgetting function (DDF). Second, Singular Value Decomposition (SVD) is involved to enhance hidden layer representation via sparse mapping. This new developed autoencoder (ASOS- AE) is compared with the ordinary OS-ELM autoencoder (OS-AE) and proved its accuracy in CMAPSS dataset (Commercial Modular Aero-Propulsion System Simulation). The C-MAPSS software has revisions in civil and military applications. In the present work we used the military version of its applications.

Nowadays, successful and innovative product development is highly correlated with the company’s success and reason for existence. A development process is a major factor influencing cost, timing and quality of product development. It requires additional attention to decisions made about programme, budget, technical and market risks. In this paper a product development process model is proposed in an innovation context and strategy framework of design process and project management. The process modelling is complex network theory based, to improve characterization analysis for product development process modelling. Required concepts for complex process are established to build product development mathematical model, and provide an overview of key definitions and complex networks advanced tools. Finally, a case study for an Algerian electric generator company is carried out to prove the practicality of the proposed model.

In this paper, a new length changeable extreme learning machine is proposed. The aim of the proposed method is to improve the learning performances of a Single hidden layer feedforward neural network (SLFN) under rich dynamic imbalanced data. Particle Swarm Optimization (PSO) is involved for hyper-parameters tuning and updating during incremental learning. The algorithm is evaluated using a subset from C-MAPSS (Commercial Modular Aero-Propulsion System Simulation) dataset of gas turbine engine and compared to its derivatives. The results prove that the new algorithm has a better learning attitude. The toolbox that contains the developed algorithms of this comparative study is publicly available.

The existing literature on process scheduling issues have either ignored installation times or assumed that installation times on all machines is free by association with the task sequence. This working arrangement addresses hybrid flow shop scheduling issues under which there are sequence-dependent configuration times referred to as HFS with SDST. This family of production systems are common in industries such as biological printed circuit boards, metallurgy and vehicles and automobiles making. Due to the increasing complexity of industrialized sectors, simple planning systems have failed to create a realistic industrial scheduling. Therefore, a hybrid multi-agent and immune algorithm can be used as an alternative approach to solve complex problems and produce an efficient industrial schedule in a timely manner. We propose in this paper a multi-agent and immune hybrid algorithms for scheduling HFS with SDST. The findings of this paper suggest that the proposed algorithm outperforms some of the existing ones including PSO (particle swarm optimization), GA (Genetic Algorithm), LSA (Local Search Algorithm) and NEHH (Nawaz Enscore and Ham).

The existing literature on process scheduling issues have either ignored installation times or assumed that installation times on all machines is free by association with the task sequence. This working arrangement addresses hybrid flow shop scheduling issues under which there are sequence-dependent configuration times referred to as HFS with SDST. This family of production systems are common in industries such as biological printed circuit boards, metallurgy and vehicles and automobiles making. Due to the increasing complexity of industrialized sectors, simple planning systems have failed to create a realistic industrial scheduling. Therefore, a hybrid multi-agent and immune algorithm can be used as an alternative approach to solve complex problems and produce an efficient industrial schedule in a timely manner. We propose in this paper a multi-agent and immune hybrid algorithms for scheduling HFS with SDST. The findings of this paper suggest that the proposed algorithm outperforms some of the existing ones including PSO (particle swarm optimization), GA (Genetic Algorithm), LSA (Local Search Algorithm) and NEHH (Nawaz Enscore and Ham).

In this paper, we propose new fusion and selection approaches to accurately predict the remaining useful life. The fusion scheme is built upon the combination of outcomes delivered by an ensemble of Gaussian process regression models. Each regressor is characterized by its own covariance function and initial hyperparameters. In this context, we adopt the induced ordered weighted averaging as a fusion tool to achieve such combination. Two additional fusion techniques based on the simple averaging and the ordered weighted averaging operators besides a selection approach are implemented. The differences between adjacent elements of the raw data are used for training instead of the original values. Experimental results conducted on lithium-ion battery data report a significant improvement in the obtained results. This work may provide some insights regarding the development of efficient intelligent fusion alternatives for further prognostic advances.

This paper investigates the use of the Particle Swarm Optimization (PSO) algorithm to quantify the effect of RUL uncertainty on predictive maintenance planning. The prediction of RUL is influenced by many sources of uncertainty, and it is required to quantify their combined impact by incorporating the RUL uncertainty in the optimization process to minimize the total maintenance cost. In this work, predictive maintenance of a multi-functional single machine problem is adopted to study the impact of RUL uncertainty on maintenance planning. Therefore, the PSO algorithm is integrated with a random sampling-based strategy to select a sequence that performs better for different values of RUL associated with different jobs. Through a numerical example, results show the importance of optimizing maintenance actions under the consideration of RUL randomness.

This work presents the prediction of the rate of progression in oil drilling based on random forest algorithm, which is part of the family of ensemble machine learning. The ROP parameter plays a very important role in oil drilling, which has a great impact on drilling costs, and its prediction allows drilling engineers to choose the best combination of input parameters for better progress in drilling operations. To resolve this problem, several works have been realized with the different modeling techniques as machine learning: RNAs, Bayesian networks, SVM etc. The random forest algorithm chosen for our model is better than the other MLS techniques. in speed or precision, following what we found in the literature and tests done with the open source machine learning tool on historical oil drilling logs from fields of Hassi Terfa located in southern Algeria.

In this work a new data-driven approach for Remaining Useful Life estimation of aircraft engines is developed. The proposed approach is a regularized Single Hidden Layer Feedforward Neural network (SLFN) with incremental constructive enhancements. The training rules of this algorithm are inspired form different Extreme Learning Machine (ELM) variants. Particle Swarm Optimization (PSO) algorithm is integrated to enhance tracking ability of the best regularization parameter to reduce the norm of the tuned weights. The proposed approach is evaluated using C-MAPSS (Commercial Modular Aero-Propulsion System Simulation) dataset and compared to its other derivatives and proved its accuracy. C-MAPSS software has revisions in military and civil applications. In this paper, the military version of its application is the used one.

The main objective of this works is to study and improve the performances of the Single hidden Layer Feedforward Neural network (SLFN) for the application of Remaining Useful Life (RUL) prediction of aircraft engines. The most common problems in SLFNs based old training algorithms such as backpropagation are time consuming, over-fitting and the appropriate network architecture identification. In this paper a new incremental constructive learning algorithm based on Extreme Learning Machine algorithm is proposed for founding the appropriate architecture of a neural network under less computational costs. The aim of the proposed training approach is to study its maximum capabilities during RUL prediction by reducing over-fitting and human intervention. The performances of the proposed approach which are evaluated on C-MAPPS dataset and compared with its original variant from the literature. Experimental results proved that the new algorithm outperforms the old one in many metrics evaluations.

This article showcases the adaptability of existing mobility devices for the Algerian disabled population. It aims to develop a behavior model of disabled Algerian persons through (1) development of a theoretical model based on literature review and (2) improvement of this model by using local collected data from our developed questionnaire.

In this paper, we propose an algorithm for classification based on extreme learning machine, named TS-ELM (Two feature Spaces Extreme learning Machine). It is a hybridization of two distinct feature mapping of SLFNs (Single hidden layer feedforward neural network). Both are realized based on ELM theories. The first feature space resulted from a random kernel distributions of a randomly connected input samples, that inspired initially from conventional random connected neural network and it is also included in ELM theories. The second feature space that gives the training or testing samples is the result of a random probability distribution of fully connected samples taken from the first feature space, and adjusted with their own weight and threshold parameters. This algorithm was applied on three datasets of multiclass and binary classification, and the results shows that it has strong classification capabilities and universal approximation as well. The mechanisms of the algorithm and universal approximation are discussed in this paper.