Searching for the (near) optimal subset of features is a challenging problem in the process of feature selection (FS). In the literature, Swarm Intelligence (SI) algorithms show superior performance in solving this problem. This motivated our attempts to test the performance of the newly proposed Salp Swarm Algorithm (SSA) in this area. As such, two new wrapper FS approaches that use SSA as the search strategy are proposed. In the first approach, eight transfer functions are employed to convert the continuous version of SSA to binary. In the second approach, the crossover operator is used in addition to the transfer functions to replace the average operator and enhance the exploratory behavior of the algorithm. The proposed approaches are benchmarked on 22 well-known UCI datasets and the results are compared with 5 FS methods: Binary Grey Wolf Optimizer (BGWO), Binary Gravitational Search Algorithms (BGSA), Binary Bat Algorithm (BBA), Binary Particle Swarm Optimization (BPSO), and Genetic Algorithm (GA). The paper also considers an extensive study of the parameter setting for the proposed technique. From the results, it is observed that the proposed approach significantly outperforms others on around 90% of the datasets.

/pdf/an-efficient-binary-salp-swarm-algorithm-with-crossover-9kyl7dt8j9.pdf

An efficient binary Salp Swarm Algorithm with crossover scheme for feature selection problems

The new evolution of the production and industrial process called Industry 4.0, and its related technologies such as the Internet of Things, big data analytics, and cyber–physical systems, among others, still have an unknown potential impact on sustainability and the environment. In this paper, we conduct a literature-based analysis to discuss the sustainability impact and challenges of Industry 4.0 from four different scenarios: deployment, operation and technologies, integration and compliance with the sustainable development goals, and long-run scenarios. From these scenarios, our analysis resulted in positive or negative impacts related to the basic production inputs and outputs flows: raw material, energy and information consumption and product and waste disposal. As the main results, we identified both positive and negative expected impacts, with some predominance of positives that can be considered positive secondary effects derived from Industry 4.0 activities. However, only through integrating Industry 4.0 with the sustainable development goals in an eco-innovation platform, can it really ensure environmental performance. It is expected that this work can contribute to helping stakeholders, practitioners and governments to advance solutions to deal with the outcomes emerging through the massive adoption of those technologies, as well as supporting the expected positive impacts through policies and financial initiatives.

https://www.mdpi.com/2071-1050/10/10/3740/pdf

Industry 4.0 and Sustainability Implications: A Scenario-Based Analysis of the Impacts and Challenges

Predictive maintenance in the Industry 4.0: A systematic literature review

Shipbuilding companies are upgrading their inner workings in order to create Shipyards 4.0, where the principles of Industry 4.0 are paving the way to further digitalized and optimized processes in an integrated network. Among the different Industry 4.0 technologies, this paper focuses on augmented reality, whose application in the industrial field has led to the concept of industrial augmented reality (IAR). This paper first describes the basics of IAR and then carries out a thorough analysis of the latest IAR systems for industrial and shipbuilding applications. Then, in order to build a practical IAR system for shipyard workers, the main hardware and software solutions are compared. Finally, as a conclusion after reviewing all the aspects related to IAR for shipbuilding, it proposed an IAR system architecture that combines cloudlets and fog computing, which reduce latency response and accelerate rendering tasks while offloading compute intensive tasks from the cloud.

A Review on Industrial Augmented Reality Systems for the Industry 4.0 Shipyard

Industry 4.0 (I4.0) encompasses a plethora of digital technologies effecting on manufacturing enterprises. Most research on this topic examines the effects in the smart factory domain, focusing on ...

The applications of Industry 4.0 technologies in manufacturing context: a systematic literature review

Industry 4.0 can make a factory smart by applying intelligent information processing approaches, communication systems, future-oriented techniques, and more. However, the high complexity, automation, and flexibility of an intelligent factory bring new challenges to reliability and safety. Industrial big data generated by multisource sensors, intercommunication within the system and external-related information, and so on, might provide new solutions for predictive maintenance to improve system reliability. This paper puts forth attributes of industrial big data processing and actively explores industrial big data processing-based predictive maintenance. A novel framework is proposed for structuring multisource heterogeneous information, characterizing structured data with consideration of the spatiotemporal property, and modeling invisible factors, which would make the production process transparent and eventually implement predictive maintenance on facilities and energy saving in the industry 4.0 era. The effectiveness of the proposed scheme was verified by analyzing multisource heterogeneous industrial data for the remaining life prediction of key components of machining equipment.

Industrial Big Data in an Industry 4.0 Environment: Challenges, Schemes, and Applications for Predictive Maintenance

In this paper, a big-data-driven based intelligent prognostics strategy is proposed to deal with industrial big data generated in the process of intelligent manufacturing, which is an inevitable trend in the industry 4.0 environment. The developed scheme demonstrated the important issues for the intelligent prognostics methodology, including pre-processing methods for industrial big data, association analysis based feature processing, and deep learning based prognostics model, spark platform based parallel computing, etc. The proposed methodology and technical system will provide important referential value for the construction of big-data-driven machine prognostics system in industry 4.0 environment.

Yue Meng

Papers

Industrial Big Data in an Industry 4.0 Environment: Challenges, Schemes, and Applications for Predictive Maintenance

Big-data-driven based intelligent prognostics scheme in industry 4.0 environment

Dynamic Genetic Algorithm-based Feature Selection Scheme for Machine Health Prognostics

Shaft Orbit Feature Based Rotator Early Unbalance Fault Identification

Integrated optimization for design and operation of turbomachinery in a solar-based Brayton cycle based on deep learning techniques