C3 IoT Case Studies Improving Uptime and Asset Reliability with AI in Biomanufacturing

	Improving Uptime and Asset Reliability with AI in Biomanufacturing C3 IoT

Improving Uptime and Asset Reliability with AI in Biomanufacturing

C3 IoT

Technology Category	Analytics & Modeling - Machine Learning Application Infrastructure & Middleware - Event-Driven Application
Applicable Industries	Education Equipment & Machinery
Use Cases	Predictive Maintenance Time Sensitive Networking
Services	Data Science Services System Integration
Challenge	Centrifuges, critical assets in the upstream stage of the biomanufacturing process, were experiencing unplanned failures that halted operations and caused significant revenue loss for a biotechnology company. The existing rules-based monitoring systems were producing an overwhelming number of false and inadequate alerts, with an average of 60 alerts a month. However, these alerts only captured 13% of actual failures and 71% of them were false alarms. The system also provided an average of only 45 minutes of lead time before a shutdown, leaving operators with a narrow window for preventative actions. The existing system was unable to flexibly incorporate new data sources or adjust preset sensor thresholds to improve the accuracy or comprehensiveness of alerts. The company needed an AI-led approach that could integrate all relevant data sources and apply advanced machine learning techniques to improve the recall and precision of failure predictions. Read More
About Customer	The customer is a biotechnology company with over $60 billion in annual revenue. The company serves more than 15 million patients worldwide and operates over 10 manufacturing sites. The company's operations heavily rely on centrifuges in the upstream stage of the biomanufacturing process. Unplanned centrifuge failures can halt operations and cause the company to miss a production slot entirely, reducing run rates and the number of batches produced. This can result in product being discarded from centrifuges, leading to millions in lost revenue. Read More
Customer Name	Not disclosed Read More
Solution	The biotechnology company chose C3 AI Reliability to implement an AI-driven approach to centrifuge monitoring. Over 12 weeks, the C3 AI team worked with subject matter experts at the company to configure the application to surface predictive and prescriptive insights for 3 centrifuges. The team ingested and unified over 6 years of historical data from 6 disparate systems, including batch reports, work orders, system alerts, sensor data, and deviation reports, to create a unified data model. Advanced machine learning techniques were applied to the unified data model, with over 500 ML model configurations tested to identify the optimal models for predicting centrifuge failures. The C3 AI Reliability user interface was configured to surface AI-based alerts and prescriptive insights, with user-friendly dashboards providing high-level site and asset KPIs, prioritized AI alerts, and details for risk investigation and mitigation. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Machine Learning

Application Infrastructure & Middleware - Event-Driven Application

Applicable Industries

Education

Equipment & Machinery

Use Cases

Predictive Maintenance

Time Sensitive Networking

Services

Data Science Services

System Integration

Challenge

Centrifuges, critical assets in the upstream stage of the biomanufacturing process, were experiencing unplanned failures that halted operations and caused significant revenue loss for a biotechnology company. The existing rules-based monitoring systems were producing an overwhelming number of false and inadequate alerts, with an average of 60 alerts a month. However, these alerts only captured 13% of actual failures and 71% of them were false alarms. The system also provided an average of only 45 minutes of lead time before a shutdown, leaving operators with a narrow window for preventative actions. The existing system was unable to flexibly incorporate new data sources or adjust preset sensor thresholds to improve the accuracy or comprehensiveness of alerts. The company needed an AI-led approach that could integrate all relevant data sources and apply advanced machine learning techniques to improve the recall and precision of failure predictions.

About Customer

The customer is a biotechnology company with over $60 billion in annual revenue. The company serves more than 15 million patients worldwide and operates over 10 manufacturing sites. The company's operations heavily rely on centrifuges in the upstream stage of the biomanufacturing process. Unplanned centrifuge failures can halt operations and cause the company to miss a production slot entirely, reducing run rates and the number of batches produced. This can result in product being discarded from centrifuges, leading to millions in lost revenue.

Customer Name

Not disclosed

Solution

The biotechnology company chose C3 AI Reliability to implement an AI-driven approach to centrifuge monitoring. Over 12 weeks, the C3 AI team worked with subject matter experts at the company to configure the application to surface predictive and prescriptive insights for 3 centrifuges. The team ingested and unified over 6 years of historical data from 6 disparate systems, including batch reports, work orders, system alerts, sensor data, and deviation reports, to create a unified data model. Advanced machine learning techniques were applied to the unified data model, with over 500 ML model configurations tested to identify the optimal models for predicting centrifuge failures. The C3 AI Reliability user interface was configured to surface AI-based alerts and prescriptive insights, with user-friendly dashboards providing high-level site and asset KPIs, prioritized AI alerts, and details for risk investigation and mitigation.

Impact #1	The implementation of the C3 AI Reliability application significantly improved the company's ability to predict and prevent centrifuge failures. The AI-driven approach allowed for the integration of all relevant data sources and the application of advanced machine learning techniques to improve the recall and precision of failure predictions. The user-friendly dashboards provided high-level site and asset KPIs, prioritized AI alerts, and details for risk investigation and mitigation. This not only reduced the number of false alarms but also increased the lead time for preventative actions, thereby reducing the risk of unplanned shutdowns and potential revenue loss.

Impact #1

The implementation of the C3 AI Reliability application significantly improved the company's ability to predict and prevent centrifuge failures. The AI-driven approach allowed for the integration of all relevant data sources and the application of advanced machine learning techniques to improve the recall and precision of failure predictions. The user-friendly dashboards provided high-level site and asset KPIs, prioritized AI alerts, and details for risk investigation and mitigation. This not only reduced the number of false alarms but also increased the lead time for preventative actions, thereby reducing the risk of unplanned shutdowns and potential revenue loss.

Benefit #1	Reduced the number of alarms generated by 80%, from 60 to 10 alerts per month
Benefit #2	Improved the number of impending failures predicted by 80%, from 13% to 93%
Benefit #3	Increased lead time by 48x, from 45 minutes to more than 2 days

Benefit #1

Reduced the number of alarms generated by 80%, from 60 to 10 alerts per month

Benefit #2

Improved the number of impending failures predicted by 80%, from 13% to 93%

Benefit #3

Increased lead time by 48x, from 45 minutes to more than 2 days

Download PDF Version

Overview

Improving Uptime and Asset Reliability with AI in Biomanufacturing

Operational Impact

Quantitative Benefit