Leveraging analytics to save millions for specialty chemical production

Producing anything on a global scale requires utmost optimization. Capacity management, workforce planning, downtime and maintenance planning – the list is endless. And what drives it all? Data and Analytics. Predictive and Prescriptive analytics in manufacturing sector can help optimize time and costs – two most important variables in production.

A leading chemical manufacturer needed an accurate and agile solution to predict optimal machine performance. They wanted to tackle unscheduled downtime to avoid losses and their existing IT infrastructure was inefficient in these predictions.

The client needed advice on what technology to use and a partner to evaluate different AI platforms and cloud providers to meet their business requirements.

The Solution

Ascendion designed an IOT solution to capture plant and machine data from factories, transform the data, and store it in Microsoft Azure Data Lake (ADL). Our engineers defined the data architecture, the setup, and analytical services for real-time sensor data ingestion, processing, anomaly detection, regression prediction, and visualization.

Sub-assemblies in a manufacturing unit are crucial to the entire process. These are beneficial in cost and quality control as they help break down the manufacturing process into simple, efficient tasks.

Ascendion experts had to engineer accurate failure predictions to maintain an optimal inventory and ensure minimal downtime during production.

We used Ascendion AVA, an integrated, intelligent engineering platform, to seamlessly load data from 80,000 sensors in one factory into the ADL. The solution helped transform data, covering over 25 use cases for the data science and analytics team to consume.

The Results:

Ascendion developed the AI/ML platform infrastructure and constructed an implementation roadmap for the client. The data architecture and management strategies used resulted in an increased lifespan of the equipment by 6 to 8 months and many other successful results:

• $4-5 Million savings due to the increased machine lifespan
• $30,000-50,000 savings per month due to improved utilization of raw materials
• $50,000-100,000 loss prevention from production unit downtime
• $12-15 Million predicted savings for each of the 25 planned business use cases

The production helped to predict downtime or failures and manufacturing process issues while also providing proactive maintenance leading to higher quality, faster time-to-market, and optimized costs.