Blog
Part V – Final conclusions
Artificial Intelligence in Laboratory Practice - Part V
Scenario 4: Calculation of process capability indices
Understanding the capability and performance of a process is essential for maintaining high-quality standards in manufacturing. For example, Cpk focuses on short-term variations, while Ppk is used for long-term process variations. This scenario shows how AI can help evaluate quality metrics to identify the most suitable supplier.
The Problem
Traditional manual methods of calculating process capability indices can be time-consuming and prone to error, making it difficult to accurately assess which supplier offers the best quality.
The Solution
Using the AI-powered digital assistant, labs can quickly calculate and analyze key statistical metrics in quality management, such as Process Capability (Cp and Cpk) and Process Performance (Pp and Ppk). These metrics assess the ability of a process to produce consistent output within defined specifications.
Process Capability (Cp and Cpk) and Process Performance (Pp and Ppk) are key statistical metrics in quality management that assess the ability of a process to produce a consistent output within defined specifications. In this scenario, the AI assistant was used to determine these values quickly and efficiently to evaluate which supplier had the best quality.
The initial prompt produces a table with the calculated process capability values (Cp, Cpk, Pp, Ppk) for the viscosity data with the specification limits (USL = 4 and LSL = 2). These values are derived from the provided data sets within the new limits. The prompts can then be expanded further to analyze this data within the newly defined limits to see which supplier (A,B, or C) has the best process from a statistical perspective. From the three different suppliers, the prompt showed that Viscosity A has the best overall process capability due to its higher Cp and Cpk values alongside Pp and Ppk that are comparable to the other samples. The prompt shows that sample A has the best short-term and long-term potential and should be chosen as the material for the processing company’s polymer blends.
The scenario shows that the digital assistant can easily calculate quality metrics for all suppliers at any time based on various desired laboratory data. This ensures that materials meet required standards and enables early detection of defects, which improves product quality and supplier evaluation. With continuous monitoring, quality variations can be detected immediately and the production process optimized, resulting in a reliable supply chain and long-term cost savings. This ensures consistent product quality and increases customer satisfaction. AI can help both the lab and the business to operate more efficiently, to produce higher quality products, and to make data-driven decisions at the lab level and beyond.
Summary
The case study showed that a fully integrated and AI-powered data management solution saves time, resources, and extracts the maximum amount of insights out of complex datasets. The ability to connect various analysis instruments and process all the data as a single data set means that materials can be analyzed more quickly and with a much higher degree of accuracy. Beyond this, the AI-powered digital assistant can analyze the data based on simple prompts to showcase trends within the data and visualize different properties of materials across batches. All this information is easily accessible and can be supplied to third parties if there is an issue with a supplied material, but most importantly, the digital lab assistant gives power to polymer manufacturers and processors to make more informed decisions about which materials they use in their products to ensure a consistent high quality.
To read the complete case study, please check out the download below that covers all 4 scenarios.
AI in Laboratory Practice
Everyone is talking about artificial intelligence (AI). In this case study however, we show how AI can be used in the lab on a practical level.
Learn more in this case study:
- How AI-based solutions can integrate fragmented laboratory data into a cohesive system
- What AI can do in your lab to improve efficiency and to exploit all data
- Practical examples of how AI can streamline data analysis
- The benefits of an AI-powered data management platform in transforming laboratory operations, reducing errors, and saving time.
Download the case study now and discover what AI can do in your laboratory.