Non-Invasive integration of Legacy OT and IT Information Systems

By Hubert Yoshida posted 02-24-2021 23:49

We are now in the fourth industrial revolution, or Industry 4.0. This revolution is brought about by the transition to smart factories which are informed by collecting more OT (Operation Technology) data from the factory floor and combining it with IT (Information Technology) data from enterprise information and analytic systems. This combination of OT and IT enables increased automation, efficiency, productivity, and business agility. 
Industry 4.0.jpg

The Internet of Things (IoT) is a key component of smart factories. Machines on the factory floor are equipped with sensors that feature an IP address that allows the machines to connect with other web-enabled devices. This connectivity makes it possible for large amounts of valuable data to be collected, analyzed and exchanged. The advent of Internet of Things (IoT) has seen fundamental changes in data acquisition, storage and analysis to create new value in multiple verticals such as manufacturing, energy, oil, gas, transportation and so on. IoT in conjunction with machine learning and AI has the potential of transforming society and improving human life.

The prior, or third industrial revolution began in the middle of the 20th century and added computers, advanced telecommunications and data analysis to manufacturing processes. The digitization of factories began by embedding programmable logic controllers (PLCs) into machinery to help automate some processes and collect and share data. Unfortunately, these OT controller protocols and networks were not the same as IT protocols and networks. Legacy OT protocols for data acquisition were designed for in-situ data visualization and manual recording. Because they were located in a local factory, they lacked the security mechanisms that would be required for connection on an enterprise network for data acquisition. There is the risk of infecting the OT/IT network with a virus such as Stuxnet

This legacy of Industry 3.0 computers, telecommunications., and data analysis poses a challenge to the integration of OT and IT data for Industry 4.0. Having access to OT data in an IT database is a pre-requisite for building a successful AI or “smart” solution for Industry 4.0. AI and machine learning allow manufacturing companies to take full advantage of the volume of information generated not just on the factory floor, but across their business units, and even from partners and third-party sources. AI and machine learning can create insights providing visibility, predictability and automation of operations and business processes. 

Converting legacy data acquisition to smart IoT devices or reprogramming PLCs can be disruptive, expensive, and time consuming. Hitachi is addressing this with non-invasive data extraction methods that do not need physical connection to the existing OT networks. These methods ensure that the reliability, availability and safety constraints of the OT networks are respected while, the OT data are connected to an AI engine. This non-invasive data extraction solution is based on video analytics.

The first step of this solution uses a video camera to capture images of the digital display units attached to the Programmable Logic Controller (PLC) that controls the OT assets. It then runs an edge analytics algorithm at a connected IoT gateway to automatically extract and store the values being displayed on the screen. The high-level overview of this solution is shown in the figure below, where the camera, gateway and analytics engine are connected to an IT network which is separate from the OT network which connects PLCs and SCADA (Supervisory Control and Data Acquisition) server. Since, there is no need to connect the two networks, this solution is non-invasive.
Non Invasive.jpg

This solution uses Optical Character Recognition (OCR) to interpret the digits on the screen. However, simply using an OCR algorithm doesn’t guarantee a reliable solution due to the complexity and variability in digital display units found in factories. The solution augments the OCR algorithm with additional modules for image preprocessing, and edge analytics module in the IoT gateway for OCR analysis, and an analytics module which calculates the confidence level of the OCR result. This is stored in the IoT gateway along with the OCR result and is used as an additional input to a subsequent analytics application that uses the data. The details of the implementation is contained in this report Non-Invasive Data Extraction from Machine Display Units Using Video Analytics which was published in World Academy of Science - International Journal of Computer and Information Engineering 2019, 13(7), 427 – 432.

This is a picture of the type of data that can be captured and extracted for analysis by an analytics engine:


In summary, this is a solution to automatically extract information (meta-data and variable time series data values) from digital displays found in many environments such as factories. The extraction is non-invasive and thus, is very easy to deploy and possess no security risks associated with traditional methods of data extraction which require connection to the machine. Hitachi has tested this solution with realistic PLC display units used in manufacturing, under various real-world environment conditions and obtained reasonably good performance.

1 view