AI technology could identify manufacturing Defects.

Fujitsu | March 31, 2021

AI technology could identify manufacturing Defects.
Products are routinely examined for abnormalities, flaws, or manufacturing errors as part of the production process. Now, modern AI technology developed by the Japanese company Fujitsu has the potential to significantly reduce the number of working hours needed for this procedure.

Fujitsu Laboratories, a research center within the multinational ICT group, has developed an AI technology for image inspection that helps for the highly detailed identification of a wide range of external defects on manufactured goods.

The technology employs an AI model trained on photographs of goods with artificial abnormalities, eliminating the need to prepare training data from live images of faulty products pulled from a manufacturing line's inspection procedure.

The problem in training AI to execute quality management tasks is that models are often trained using weighted and summed indices for individual characteristics. This will make it difficult to construct a model that thoroughly comprehends all of the features that must be examined.

Fujitsu has created a system for training an AI model that allows a normal image with several irregularities such as form, scale, and color to be recovered by artificially applying the virtual defects to a normal image prepared for training.

According to the company, this technology achieved more than 98 percent in an AUROC ranking, which is an assessment metric used to evaluate classification model performance.

The score was obtained in a category of items of typical appearance differences, such as carpets with varying fur patterns and colors on an individual basis, and printed circuit boards with different wiring shapes on different components.

Fujitsu has validated the technology's usefulness in a real-world environment at Fujitsu Interconnect Technologies' Nagano factory, which produces electronic equipment. The AI, according to the firm, reduced the number of hours needed for inspecting printed circuit boards by 25%.

In recent years, the manufacturing industry has been a significant target for digitalization. An €11 million European initiative to use machine learning to improve processes and achieve zero-defect manufacturing was announced last week.

Fujitsu's AI advances have also been applied in other fields. Earlier this month, the company unveiled specifics of a facial recognition system that uses an AI model to track subtle variations in muscle expressions in a person's facial expression to measure how focused someone is in online classes and meetings.


We all know that shipbuilding is a cyclical industry. The volatile nature of the markets for its raw materials and finished products makes shipbuilding a particularly challenging business. In a cycle where there is pressure on capacity and fewer new-builds, shipyards must become more efficient at ship production.


We all know that shipbuilding is a cyclical industry. The volatile nature of the markets for its raw materials and finished products makes shipbuilding a particularly challenging business. In a cycle where there is pressure on capacity and fewer new-builds, shipyards must become more efficient at ship production.

Related News


Aizon Introduces a Pharmaceutical Manufacturing Predictive Maintenance Solution

Aizon | January 25, 2022

On January 24, Aizon announced the introduction of its new asset tracking tool for the pharmaceutical and biotech industries. Aizon Asset Health is built on Aizon's GxP-compliant AI SaaS Platform. It performs intelligent historical maintenance analysis, continuously monitors the condition of critical assets in real-time, identifies potential problems, and provides actionable maintenance recommendations to keep equipment operating at peak performance. This data-driven approach to maintenance lowers maintenance costs, minimizes unexpected downtime, and maximizes product output, thus maximizing the potential of Smart Pharma Manufacturing. Maintaining manufacturing equipment in good operating order may be costly and inefficient. A schedule-based approach to maintenance frequently results in the wasteful repair or replacement of equipment that is still operating in acceptable conditions or the catastrophic failure of equipment owing to undiscovered faults. This might result in production interruptions, product rejection, and a longer time to market, and product compromise. That is, guaranteeing that any operation is executed correctly the first time and every time. Combining sophisticated analytics and multivariate analysis with artificial intelligence, the Aizon Asset Health program improves unexpected downtime reduction beyond today's industry standard, eventually lowering maintenance costs while increasing asset dependability and performance. "Pharmaceutical manufacturers and biotech companies are under tremendous pressure to maximize their return on investment and to reduce unplanned downtime. However, the traditional schedule-based maintenance approach tends to fall short in terms of gaining control of downtime and the high costs associated with replacing equipment in an effort to achieve better performance, Our Asset Health application enables our customers to harness the power of their equipment and environmental data to slash maintenance costs, optimize equipment performance, enhance product output, and improve product quality." -John Vitalie, CEO, Aizon Monitoring Intelligent, Real-Time Assets Across Equipment and Facilities The Aizon Asset Health application enables pharmaceutical and biotech organizations to employ predictive analytics to monitor their assets' health and receive advanced warnings on their problems based on the solution's prescriptive and conditional data-driven insights. These actionable insights enable operators and maintenance teams to respond and intervene in real-time, ensuring the continued operation of manufacturing lines. In addition, asset Health is a cloud-native application that can be expanded across various sites and regions and maintains a history and condition of every piece of equipment. This enables pharmaceutical and biotechnology organizations to assure total asset integrity, maintain ideal facility conditions (such as temperature, humidity, and vibration), forecast the projected life of equipment, and track the energy utilized by an asset and its CO2 emissions. Furthermore, this vital information is aggregated on a single dashboard tailored to meet every firm's particular asset care requirements. "Demands for pharmaceutical manufacturing have never been higher. The Aizon Asset Health application helps manufacturers prevent unplanned downtime and maximize product quality and yield Aizon Asset Health taps into real-time sensor data, consolidates it, and leverages AI to generate alarms and/or actionable insights to optimize asset performance. It’s a game changer for the industry. " -Andy Alasso, SVP Product, Aizon.

Read More

Essentium Announces a Distribution Partnership with Hephzibah to Advance Additive Manufacturing in South Korea

Essentium, Inc., Hephzibah | July 13, 2020

Essentium, Inc., a leading innovator of industrial additive manufacturing (AM) solutions, today announced a distribution partnership with Hephzibah, prominent South Korean 3D printing specialist, to advance additive manufacturing in South Korea. The combination of Hephzibah’s best-in-class service, customer support, and use-case specific expertise, together with the ground-breaking speed and economics of the Essentium High Speed Extrusion (HSETM) 3D Printing Platform will help resolve many of the historic barriers to widespread adoption of industrial-scale AM and to advance additive manufacturing in South Korean market. Manufacturing firms in South Korea recognize that adding 3D printing to their factory floors could save billions in production costs. However, they face significant obstacles to using 3D printing for large-scale production, such as the strength of parts, speed and scale of production, and economics. The Essentium and Hephzibah partnership will deliver AM solutions, based on open ecosystems, that produce parts with the strength, speed, and scale customarily associated with injection-moulding and with vastly improved economics.

Read More

Moderna Collabs with ROVI for Large Scale Fill-Finish Manufacturing of Its COVID-19 Vaccine Candidate

Moderna, ROVI | July 10, 2020

Moderna, Inc., a clinical stage biotechnology company pioneering messenger RNA (mRNA) therapeutics and vaccines to create a new generation of transformative medicines, and Laboratorios Farmacéuticos Rovi, S.A. (BME: ROVI), a pan-European pharmaceutical company specializing and engaging in the research, development, contract manufacturing and marketing of small molecules and biological specialties, today announced a collaboration for large-scale, commercial fill-finish manufacturing of Moderna’s mRNA vaccine candidate against COVID-19 (mRNA-1273) at ROVI’s facility in Madrid, Spain. As part of the agreement, ROVI will provide vial filling and packaging capacity by procuring a new production line and equipment for compounding, filling, automatic visual inspection and labeling to support production of hundreds of millions of doses of the vaccine candidate intended in principle to supply markets outside of the U.S. starting in early 2021. ROVI will also hire additional staffing required to support manufacturing operations and production.

Read More