In a recent manufacturing industry insights survey on artificial intelligence (AI), 44 percent of respondents from the automotive and manufacturing sectors classified AI as “highly important” to the manufacturing function in the next five years, while almost half—49 percent—said it was “absolutely critical to success.”
Critical sounds impressive. Yet, in many cases, AI is hard to comprehend for manufacturers, as the technology industry has painted it with such a wide brush that few actually understand how it becomes instantiated—beyond some omnipotent source delivering better business results.
Manufacturers may actually view AI as highly complex and expensive, requiring end-to-end systems throughout their whole company to work properly, and this translates to a costly overhaul of their entire IT/OT operation. The reality is, AI is much more focused and achievable. AI can work on factory floors with minimal construction and get connected to machines via the Industrial Internet of Things (IIoT).
The first thing OEMs need to understand when it comes to implementations of AI is the type of use case to zero in on. The majority of edge machines on the manufacturing floor are being retooled to send data through wireless sensors as part of IoT. That data then feeds into software suites for “crunching.” The data feeding process becomes an ongoing one to create an ever-expanding web of data. All this data can be stored in the cloud to harvest insights, making AI-driven models possible.
Here are three use cases that can help erase doubts manufacturers have about the power of AI:
1. Machine Uptime
A consumer goods packaging lines runs 24×7, producing millions of cartons of varied sizes to package differing consumer products. It is crucial to keep producing them without any breakdown or any quality issues. Speed and quality are of highest importance. Manual monitoring is error-prone, costly and inefficient.
Data gathered through an IIoT system provides 24/7 real-time insight about production-line throughput and equipment failure through tailored visualization and alerts. (AI can eventually help you make sense of the troves of data you’ll gather.) This data is processed on an edge gateway for quick identification of anomalies and for sending instant alerts. The larger data is aggregated in a cloud-based IoT platform for further predictive analytics and defined behavior- and rules-based models. The system would provide a custom dashboard and reports with machine idle time, breakdown reason codes, and overall OEE data. This way, management is better equipped to plan the operations to avoid machine idle time and to apply predictive maintenance.
2. Cost Optimization
A US-based sensor manufacturer, SpectraSymbol, has been producing one of the best linear sensors and potentiometers in the industry, addressing the energy market. As a process, across remote oil wells, when oil and water are being pumped into tanks, the level of oil and water needs to be measured. Concerning this oil-drilling operation, the company had an express need for continued cost optimization by leveraging IIoT data to more economically extend the useful lives of marginal oil wells, aka “stripper wells.” Given the oil production volumes are not high, the greatest issue is that the wells don’t produce enough oil to be worth uniform investments in data sensors, and the cost model had to be reduced for them. The wells are also remotely located, adding to the cost and time challenges. Installation costs of sensors at these wells are also extremely high, adding 60 percent to the cost. For smaller operations and more remote end-of-life wells, fast ROI was of the essence to justify IoT implementation.
An IIoT software platform for storing and processing all machine data was put into place for SpectaSymbol’s multiple oil wells. It created a “data lake” where pertinent data is stored in the cloud. The data being analyzed with AI-driven machine learning has been the enabler for a business-focused, custom application expressly designed for assessing well performance, and condition monitoring through AI analytics. As a result, specific reports are available to all stakeholders, and stripper wells are optimized for uptime and performance.
3. Improved Predictive Quality
A chemical company, SRF, wanted to improve their productivity and manufacturing operations through IoT-enabled digital transformation. To achieve this, SRF had to connect critical processes in the manufacturing of their packaging films and technical textiles. The objectives were to improve quality by analyzing parameters critical to the manufacturing process, improve their fuel consumption, and implement a reduction in power consumption, in addition to reducing any line breakages. SRF’s plant productivity could be improved by predicting stoppages using condition monitoring. The resulting “data lake” created from input via the manufacturing process was integrated with SRF’s ERP to close the loop on the entire manufacturing value chain.
AI was central to the project, as machine learning techniques were utilized to support a set of flexible, multivariate statistical analysis. Specifically, real-time machine data was used as a feedback loop to more accurately define the optimum settings of the machine to ensure product quality and machine reliability. The result was SRF’s ability to monitor and analyze parameters that are critical to machine health, and to optimize machine downtime by predicting failure before it occurs.
Start with an Attainable Experiment or Pilot
When it comes to thinking about how exactly AI improves manufacturing intelligence, the key is to start with an attainable direction, as presented in the three use cases here. Whether you are looking to achieve machine uptime, to minimize costs, or to increase operational efficiencies, machine learning through cloud-hosted data can have an important role to play.
Written by Vinay Nathan, founder and CEO, Altizon Systems.