To define industrial AI, we must first define AI itself. Although the field of artificial intelligence has existed for over half a century, it has no clear and all-encompassing definition. Further, the lines between AI and adjacent fields like machine learning, big data, predictive analytics, and IOT are often blurred, as are the lines between AI and subfields like deep neural networks and cognitive computing.
Recommended ITech News: SpotX Expands Privacy-Compliant Audience Data Technology for CTV
- What is Industrial AI?
For our purposes, artificial intelligence(AI) refers to those computer science techniques and technologies that allow the software to exhibit ‘smarts’—in other words, to do things that seem human-like. This can include things like making decisions, recognizing objects, or understanding speech. It really is a very broad term.
- What is MI?
Strictly speaking, machine learning (ML) is a subset of AI. ML refers to a set of techniques that allow us to create AI software by training that software with data) to display some desired intelligent behavior. This is as opposed to, for example, explicitly programming our software with a bunch of rules to generate our desired behavior—and it’s a very powerful concept.
It is for this reason that, while machine learning is only one way to build an artificially intelligent system, for all practical purposes ML and AI are used interchangeably today. All the interesting activity in AI is in machine learning.
Due to the physical nature of the systems and processes to which they relate, industrial AI systems share similar characteristics and constraints. For example, the fact that industrial AI ultimately relates to the physical systems of an enterprise tends to mean that access to training and test data is more difficult; the reliance on subject matter expertise is larger; the AI models themselves are harder to develop, train, and test; and the costs associated with their failure are greater. In other words, the stakes are higher.
The specific benefits of such artificial intelligence systems in industrial environments are many. At a high level, they include:
Recommended ITech News: Netenrich Appoints Security Leader Christopher Morales as Chief Information Security Officer
- Enhanced, and predictive, situational awareness:
By allowing enterprises to model complex industrial systems, industrial AI allows enterprises to increase quality, reduce downtime, avoid stock-outs, reduce risk, and more.
- Better planning and decision-making:
Helping enterprises assess the effectiveness of different policies in dynamic, unpredictable environments, industrial AI helps enterprises increase process efficiency, improve asset utilization, increase yields, and optimize the design and management of complex systems.
- Greater efficiency & productivity:
Industrial AI lets enterprises enhance the results they achieve through automation, resulting in increased production, increased product quality, lower labor costs, reduced errors and rework lower material consumption and less waste.
- Industrial AI Use Case Examples
- Quality control:
A common manufacturing use case for AI is for machines to visually inspect items on a production line. Using AI allows quality control to be automated, and ensures that all final product is inspected, allowing fewer defects to reach customers compared to traditional statistical sampling methods. In addition to ensuring that products are free of imperfections, AI-based visual inspection systems can validate many products attributes including geometry and tolerances, surface finish, product classification, packaging, color & texture.
- Fault detection & isolation:
In regulated manufacturing environments, ensuring process compliance can be expensive and time-consuming. In many such scenarios, lives are at stake—as can be the case in the food, chemical, and energy industries. By monitoring a variety of system operational factors, AI can be used in the detection, prediction, and diagnosis of undesirable operating conditions in industrial systems. By accelerating or replacing unreliable and time-consuming human analysis, automated process surveillance helps prevent or minimize system downtime and the persistence of hazardous conditions.
Recommended ITech News: Adstream Uses Exasol to Power Industry Consumer Behavior Dashboards
- Inventory monitoring:
AI powers a wide variety of inventory management and supply chain use cases, allowing enterprises to avoid costly stock-outs. Hardware retailer Lowe’s is currently testing the LoweBot, an autonomous mobile robot operating in stores in the San Francisco Bay Area. In addition to its customer service tasks, the LoweBot uses an on-board computer vision system to detect misplaced and out-of-stock inventory on store shelves.18 similar systems are being deployed in warehouses, with several startups experimenting with drone-based approaches.
- Supply chain risk management:
Effective management of a complex, global supply chain demands the ability to identify and mitigate potential disruptions before they cause delays or shortages. AI can be used to predict supply disturbances before they happen, providing early warning for enterprise supply chains based on potential disruptors sourced from global news, event and weather feed.
- Process planning:
Many industrial scenarios involve complex sequences of work whose ordering can significantly impact factors such as cost, time, quality, labor input, materials input, tool life, and waste. A simple and well-studied example is the sequence of operations required to create a machined part or die using Computer Numeric Control (CNC) machines. A given part is made up of a sequence of operations such as cuts. Each cut is made using a specific tool,of which there are many, but only a few can be loaded on the machine at the same time. A variety of different optimization problems arise from this scenario, including set-up planning, operation selection and sequencing, machine and tool selection, and tool path sequencing. Each of these has been solved with a variety of machine learning techniques including genetic algorithms and neural networks.
Recommended ITech News: Atos and RingCentral Announce ‘Unify Video by RingCentral’ in Europe
- Job shop scheduling:
The job shop scheduling problem, a specific type of process planning problem, models the allocation of jobs of varying processing times to a set of machines with varying processing power. Job shop scheduling provides a well-studied if idealized, a model for many common industrial scenarios. Many different types of problems can be modeled using the general job shop scheduling approach and AI, including the famous “traveling salesperson problem,” which seeks to optimize the routing of a salesperson traveling to a list of cities given the distances between each city pair. These problems have been historically solved using operations research methods such as combinatorial optimization, but lend themselves to learning approaches that can more easily adapt to changes in their environment.
- Yield management:
In manufacturing, the yield of a given process can mean the difference between profitable and unprofitable products. For example, in semiconductor manufacturing, in the face of increasingly complex manufacturing processes, with many hundreds of process parameters coming into play in the production of a single wafer, traditional techniques for estimating and optimizing yields have become untenable. Machine learning allows manufacturers to fully utilize available data to continually improve process quality and increase yields.
- Industrial MI Use Case Examples
To wrap up, here is how machine learning can break into modern-day factories and add some intelligence to our machines.
- Vision:
By quickly and robustly recognize and monitor objects under various conditions without complex and specific fine-tuning procedures.
- Maintenance:
By learning how machine variables normally behave, predict their future state, and warn of possible faults before damages happen.
- Optimization:
By improving existing control parameters and maximize the outcome, efficiency, or productivity of a machine.
- Control:
By discovering entire new control strategies for processes that we are currently not able to master.
Recommended ITech News: Virsec Security Platform Adds Runtime Container Workload Protection from the Inside
