AHI: a hybrid machine learning model for complex industrial information systems

A summary of the numerous hybrid machine learning (HML) patterns is provided in this paper, which covers the complete ML lifecycle from model construction to data preparation to training to deployment to ongoing management. As a resource for the primary decision and control of production systems, industrial information systems (IIS) is a major research field in industrial systems management. Industrial and manufacturing methods are being inundated with massive amounts of data due to the increasing use of industrial information systems (IIS). Data management in networked industrial systems is examined in this paper. We recommend hybrid machine learning (HML) patterns for these customers as a stop-gap measure on the road to the cloud. To overcome the missing data problem, we propose using hybrid machine learning (HML) to solve this issue. This challenge has been given a more comprehensive range of possible solutions thanks to advances in machine learning technology. Here, a complex industrial information system based on a hybrid machine learning model (CIIS-HMLM) is proposed to address recovering the sensor's lost data that failed. Nonlinear data modeling using an intelligent algorithm is discussed in detail. In addition, this presents a method for processing data to ensure uninterrupted service for consumers using HML. We classify many research difficulties related to the effective design and proper implementation of CIIS-HMLM. As a wrap-up, we provide a few ideas for further research on this topic.