Industrial AI

Industrial AI
Building Next Generation Autonomous Operations

Watch introduction video Download eBook

Yokogawa AI Vison

Yokogawa creates a new normal with customers to open up tomorrow's opportunities
Perceive the present Predict the future and Optimize Operations

Are you sure you have the data you need?

Are you using your data in the right way to meet your objectives?

Most end-users imagine what could be, but lack the means to meet their objectives. This usually leads to a lot of worries & frustrations.

Yokogawa AI Value Proposition

Maximize operational efficiency and performance via a unified data fabric
Create actionable intelligence that is readily usable by process experts
Identify and resolve operational pain points by comparing customer words with the data
Leverage operational knowledge through connected factory nerve centers

What are the strengths of Yokogawa's AI applications?

Based on the message of our vision for the future of AI, " Perceive the present, Predict the future, and Optimize operations," Yokogawa is promoting the use of AI in a wide range of fields to solve customer's problems. To further drive innovation in industrial AI, Yokogawa has initiated the AI Center of Excellence (CoE). Four key members of the AI CoE talk about how Yokogawa is utilizing AI from their respective perspectives. Please take a look at the interesting videos.


AI Priorities Explained

Evolving megatrends have led to challenges in the business environment for many industrial and energy firms.
Yokogawa has identified key priority areas where Industrial AI can help firms navigate these business challenges and improve business outcomes.

AI Priorities Explained
AI Priorities Explained Image

Design optimization

Improve the yield and efficiency of an industrial plant by using AI to optimize the design of facility layout

Operation optimization

Reduce energy usage, manufacturing costs by using AI to monitor, control and extract peak performance levels from assets and labor

Trouble loss minimization

Reduce losses in production by quickly detecting and/or proactively predicting damage to equipment

Supply chain efficiency

Reduce costs and time to market by monitoring and managing the movement and storage of raw materials and finished goods

Quality stabilization

Monitor raw material quality, manufacturing machinery, labor practices to understand their impact on the quality of output

Advanced operations

Analyze best practices of high performing plant operations and use insights to provide live digital support to all operators across the firm

Digital infrastructure upgrade

Integrating manufacturing OT systems with networked IT hardware and software while minimizing cybersecurity risks


Case Studies

Unplanned Asset Downtime PreventionUnplanned Asset Downtime Prevention

Unplanned Asset Downtime Prevention

Along with Condition Based Maintenance, Predictive Maintenance is required to detect early signs of equipment failure or abnormality and performs maintenance more quickly and efficiently by integrating AI and IoT technologies.

Learn about our AI Analysis software and Sushi sensor here
Learn about our Industrial AI Platform here

Production Process & Quality Stabilization

Production Process & Quality Stabilization

In the analysis of complex continuous processes involving huge amounts of process data, the addition of evaluation models using AI and machine learning can detect signs of deviation from the required quality and take measures to prevent.

Learn about Process Data Analytics, click here for Mitsubishi Gas Chemical and here for Sumitomo Seika Chemicals
Learn about Osaka Gas Chemical case study of Digital Plant Operational Intelligence here

Visualization of Implicit Operations & Know-how

Visualization of Implicit Operations & Know-how

As production plants seek to achieve optimal operating conditions, maintain consistency across various process variables and share best-practices across facilities, but machine learning is a technology that helps plant production effectively gain insights from control system data.

Learn about our Operating Procedure Analysis here and click here to see the informative white paper here
Learn about our Alarm Behavior Analysis here

Advanced Characterization of Live Cells

Advanced Characterization of Live Cells

In High Content Analysis (HCA), which is widely used in cell-based screening evaluation, deep learning capabilities are ideal for data analysis in the areas of cell recognition, counts, classification, and calculation.

Learn about our High Content Analysis Software - CellPathfinder here

Future Prediction Accelerated by Embeded AI Capabilities

Future Prediction Accelerated by Embeded AI Capabilities

Solutions that incorporate AI into paperless recorders can use acquired data to predict future data, draw future waveforms alongside the real-time performance of the plant.

Learn about our Smart Data Acquisition Solution here

Source: Frost & Sullivan estimates based on industry reports
Definition of Industrial AI Image
Definition of Industrial AI

Artificial Intelligence

An umbrella term for computing techniques that allow machines to replicate the cognitive aspects of the human brain – becoming capable of perception, logic and learning

Machine Learning

A subset of AI that leverages algorithms which learn from data without being explicitly programmed – unlike classic (or symbolic) AI techniques
Machine learning has become mainstream in recent years as the big data revolution produced large amounts of data to learn from

Deep Learning

A subset of machine learning in which multi-layered neural networks are used to build algorithms that learn from vast sets of data
Developments in GPU (Graphics Processing Units) technologies have allowed the efficient creation of additional layers in natural networks (going “deeper”) accelerating the adaption of deep learning techniques



Why is AI gaining momentum in recent years?

Ready to take the next step forward in your digitalization journey?

Contact Us