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

Purpose – The purpose of this paper is to discuss how tacit and explicit knowledge determine grey knowledge and how these are stimulated through interactions within networks, forming the grey hybrid intelligent systems (HISs). The feedback processes and mechanisms between internal and external knowledge determine the apparition of grey knowledge into an intelligent system (IS). The extension of ISs is determined by the ubiquity of the internet but, in our framework, the grey knowledge flows assure the viability and effectiveness of these systems. Design/methodology/approach – Some characteristics of the Hybrid Intelligent Knowledge Systems are put forward along with a series of models of hybrid computational intelligence architectures. More, relevant examples from the literature related to the hybrid systems architectures are presented, underlying their main advantages and disadvantages. Findings – Due to the lack of a common framework it remains often difficult to compare the various HISs conceptually and evaluate their performance comparatively. Different applications in different areas are needed for establishing the best combinations between models that are designed using grey, fuzzy, neural network, genetic, evolutionist and other methods. But all these systems are knowledge dependent, the main flow that is used in all parts of every kind of system being the knowledge. Grey knowledge is an important part of the real systems and the study of its proprieties using the methods and techniques of grey system theory remains an important direction of the researches. Originality/value – The paper discusses the differences among the three types of knowledge and how they and the grey systems theory can be used in different hybrid architectures.

Download Full-text

Comparison of machine learning models based on time domain and frequency domain features for faults diagnosis in rotating machines

MATEC Web of Conferences ◽

10.1051/matecconf/201821117009 ◽

2018 ◽

Vol 211 ◽

pp. 17009

Author(s):

Natalia Espinoza Sepulveda ◽

Jyoti Sinha

Keyword(s):

Machine Learning ◽

Frequency Domain ◽

Time Domain ◽

Intelligent Systems ◽

Learning Models ◽

Machine Vibration ◽

Vibration Data ◽

Machine Learning Model ◽

The Time Domain ◽

Machine Learning Models

The development of technologies for the maintenance industry has taken an important role to meet the demanding challenges. One of the important challenges is to predict the defects, if any, in machines as early as possible to manage the machines downtime. The vibration-based condition monitoring (VCM) is well-known for this purpose but requires the human experience and expertise. The machine learning models using the intelligent systems and pattern recognition seem to be the future avenue for machine fault detection without the human expertise. Several such studies are published in the literature. This paper is also on the machine learning model for the different machine faults classification and detection. Here the time domain and frequency domain features derived from the measured machine vibration data are used separated in the development of the machine learning models using the artificial neutral network method. The effectiveness of both the time and frequency domain features based models are compared when they are applied to an experimental rig. The paper presents the proposed machine learning models and their performance in terms of the observations and results.

Download Full-text