Human-centric cognitive tool for machine health assessment toward Zero Defect Manufacturing

Industry 4.0
Share on facebook
Share on linkedin
Share on twitter
Share on pinterest
Share on email

The radical innovation relies on the sharp break of traditional quality control methods, by a conjunctive engineering approach supported on human-centric approach and hybridization of traditional and machine learning strategies to tackle current technical bottlenecks with a significant change, transforming WS lifecycle health assessment market.

Xymbot Digital Solutions S.L. (Xymbot) in collaboration with Centre of Automation and Robotics (CAR-CSIC) is hybridizing advance artificial intelligence techniques with cognitive-based smart recommendation systems to address zero defect challenges on assets. ZeroCog tool is focused on data-driven human-centric strategy and cognitive quality control loops, integrating and fusing data from humans and workstations health lifecycle by means of artificial intelligence for zero-defect manufacturing SMEs.

ZeroCog tool is supported in four main pillars: simple data pre-processing and conditioning, simple and powerful model-based condition-based monitoring (CbM), adaptive threshold stage and data-driven smart recommendations in a closed-loop reliable assessment for WS-lifecycle monitoring and updating. The combination of supervised and unsupervised machine learning algorithms with automatic tuning parametrization for zero defect manufacturing and the focus on human-centric approach are also important innovation and novelty aspects.

The target is to lead the uptake of data-driven human-centric and artificial cognitive quality control loops integrating and fusing data from human decisions and workstations (WS) health lifecycle by using artificial intelligence and stats towards zero-defect strategies. In this context, the objective is to develop and deploy a zero defect tool to estimate the health index of any WS, with a progress in the technical state-of-the-art in the following four key aspects: a condition-based monitoring module (current WS health), a data-driven smart recommendation (proactive actions), human-centered decision-making (data-driven from/to human knowledge transfer) and a closed-loop reliability assessment evaluation for continuous WS health lifecycle monitoring (health quality before/after recommendation). The diagram of ZeroCog approach is shown in the following figure.

zerocog
ZeroCog Workstation health lifecycle monitoring

The key of the expected outcome is the integration of human expertise, verbalization and feedback in decision-making and smart recommendation procedures. This human-centric approach is supported in twofold: (1) the consensus-based approach for carrying out interventions given by artificial cognitive systems and (2) recording, storing and feeding back to the unsupervised learning method the operator/technologist interventions. The outcome of this project is the ZeroCog tool as a service to estimate the health index of workstations with a novel solution for zero defect manufacturing.

KPIs and expected impacts:

  • +30% workstation breakdown reduction,
  • -30% reduction of ramp-up time,
  • Achieve 90% OEE for workstation and assembly line,
  • Zero unemployment impact,
  • +20% quality of working and employment sustainability,
  • -10% waste reduction due to early health assessments,
  • +15% increased productivity thanks to enforcing health assessment.

From the business point of view, Xymbot ambition is to offer new methods and services that facilitate manufacturing companies to adopt smart ZDM strategies by means of human-centric decision-making actions based on smart recommendations to improve product quality and shortening the time-to-market with early and reliable WS health assessment. ZeroCog is mainly focused on manufacturing SMEs with a digitization strategy and interested in investing in digital technology to accelerate their current business model, or looking for a business partner to execute that objective/strategy are also relevant. Priority will give to SMEs with sensor data and/or historical datasets about events and failures collected from the workstations.

In addition, the service adopts standard DevOps principles for easy integration in other European initiatives in this field:

  • Digital tool/service offered in AIR4S Digital Innovation Hub (DIH) with a potential market of more than 400 potential interested companies only in Spain according to SERCOBE industrial association.
  • KITT4SME platform/approach (kitt4sme.eu), available in RAMP and therefore available to be commercially exploited in other DIHs and industrial ecosystems.

Finally, the high potential relies on the high demand of this low cost, easy customizable and deployable solution for manufacturing SMEs fostering exploitation of own know-how by putting the operator-in-the-loop, analyzing tool sustainability in the zero-defect as a service marketplace on the basis of a time-to-market tailored business plan.

In future posts, we will be continue writing about technology and business trends for enterprises. The objective of this blog is to provide a personal vision of how digital transformation trends will be impacting in our daily activities, businesses and lifestyle.

By Fernando Castañolinkedin2, Rodolfo Haber twitterlinkedin2, Alberto Villalonga twitterlinkedin2and Gerardo Beruvides twitterlinkedin2

Xymbot’s experts on Industry 4.0, Smart-Maintenance, Process Optimization, Machine Learning, AI engineering and Cloud-based solutions for industrial applications.

Leave a Reply

Your email address will not be published. Required fields are marked *

en_GBEnglish (UK)

Subscribe to Stay Up to Date

We would like to retain some of the information gathered from you (it will be stored on a password protected hard drive), for the purposes of keeping in touch and updating you with relevant information. This information will never be shared with a 3rd party without your direct consent. By clicking ‘Sign Up’ you understand and agree with us retaining this information to contact you.