Marketing
-
Posts
474 -
Joined
-
Last visited
Never
Content Type
Profiles
Forums
Events
Library
Downloads
Gallery
Posts posted by Marketing
-
-
In the process industries, manufacturing requirements for an individual company can vary significantly over time due to lengthy research and development timelines and differences in market demand compared to forecasts. In pharmaceuticals, for example, companies may not have the capital or desire to invest in and build a manufacturing plant for their products as their expertise lies in research and development. Whether a smaller biotech or a large-scale producer, they must also contend with patent expirations on their most profitable drugs. These uncertainties for both big and small pharma have led to a significant increase in outsourcing of clinical and commercial manufacturing to contract manufacturing organizations or CMOs. While the pharmaceutical industry has seen a dramatic increase of projects being outsourced in recent years, contract manufacturing is also prevalent in many other industries including food and beverage, semiconductors, and upstream oil and gas.
-
In the process industries, manufacturing requirements for an individual company can vary significantly over time due to lengthy research and development timelines and differences in market demand compared to forecasts. In pharmaceuticals, for example, companies may not have the capital or desire to invest in and build a manufacturing plant for their products as their expertise lies in research and development. Whether a smaller biotech or a large-scale producer, they must also contend with patent expirations on their most profitable drugs. These uncertainties for both big and small pharma have led to a significant increase in outsourcing of clinical and commercial manufacturing to contract manufacturing organizations or CMOs. While the pharmaceutical industry has seen a dramatic increase of projects being outsourced in recent years, contract manufacturing is also prevalent in many other industries including food and beverage, semiconductors, and upstream oil and gas.
-
Dr. Margret Bauer is the Professor of Automation in the Faculty of Life Sciences at HAW Hamburg University in Germany, and she’s an expert in data-driven process monitoring. And Seeq is a leader in advanced analytics for manufacturing and is the analytics provider of choice for many leading companies in the oil & gas, pharmaceutical, chemical, and other process manufacturing sectors. Recently, Dr. Bauer and Seeq combined efforts to provide graduate students at Hamburg University of Applied Sciences with a hands-on experience in the critical skills of analytics in process manufacturing.
-
Depending on the type of problem a subject matter expert (SME) is trying to solve, there are countless different ways they can monitor for changes in process data. As simple as it seems to look at data and identify a change in the way it is behaving, this methodology is not always straightforward due to the lack of advanced analytics capabilities in the engineering toolbox.
-
Depending on the type of problem a subject matter expert (SME) is trying to solve, there are countless different ways they can monitor for changes in process data. As simple as it seems to look at data and identify a change in the way it is behaving, this methodology is not always straightforward due to the lack of advanced analytics capabilities in the engineering toolbox.
-
If 2020 has proven anything, it is that agility and resilience are imperatives for process manufacturers. Demands on technology infrastructure, a critical enabler for business continuity, along with demands for data-driven operational decisions, are increasing rapidly. Add to this the expanding number of team members working from home, and you have a situation where the ability of IT organizations to support operational needs is being pushed to the limits of both capacity and capability.
-
Lately, there’s been a lot of talk about data cleansing. But is it possible to clean your data too much? What does that even mean? Many engineers don’t even realize that they are cleaning their data and are just doing so because they are forced to by whatever tool they are using (i.e. to comply with Excel’s limit of 1,048,576 rows or because they are just used to seeing their data in a certain way).
-
William Shakespeare once wrote, “...the readiness is all.” I think he was onto something...
-
Many manufacturers today list sustainability as one of their main corporate objectives. These companies understand that “going green” is more than just a trendy catchphrase—they realize that optimizing their processes to reduce energy consumption and waste gives them a significant competitive advantage.
-
-
Many upstream, midstream and downstream oil and gas customers use Seeq to gain faster insights, improve outcomes, and cut costs by enabling engineers to rapidly search, cleanse, investigate, and monitor the time-series data generated by their plants and assets.
-
The landscape of labor has evolved due to innovations in connectivity and mobile devices. This has lead to the mobilization of individual workers and globalization of organizations as distributed work has transformed into a practical arrangement.
-
Process manufacturing data is complex. The time series aspect of this data creates challenges. From differences in data sampling rates to inconsistent or custom units to data storage across multiple systems, process data can be difficult enough just to collate and align for modeling. While our engineering training drills into our head that we should always document our assumptions, we often focus solely on the assumptions of the model itself, such as what regression method we used, what training data set we used, or how the model only applies within a certain range of input values. We often overlook some of the key assumptions that went into the data preparation. These assumptions can be critical in deploying a model with high confidence as to which variables are critical process parameters (CPPs) versus a model with just a decent representation of the data set or moderate r-squared value.
-
I want to share our perspective on coronavirus and recent market fluctuations, and on how Seeq will ensure the sustainability, efficiency, and optimization efforts of our customers continue unabated.
-
-
-
Seeq continues to expand in deployments and user counts across process manufacturing verticals. These expansions are built on the successful insights achieved by customers using Seeq for predictive, diagnostic, and descriptive analytics. In particular, customers recognize Seeq’s unique understanding of, and features for, working with time series data.
-
End User License Agreement (EULA) admin Tue, 10/29/2019 - 14:03
-
End User License Agreement (EULA) admin Tue, 10/29/2019 - 14:03
-
-
Harnessing the Power of Machine Learning is More Accessible than You Think michellemay Fri, 10/04/2019 - 11:29
-
Effective Pharmaceutical Technical Transfer with Advanced Analytics michellemay Fri, 10/04/2019 - 11:29
-
Leveraging Seeq Functionality to Facilitate Remote Work michellemay Fri, 10/04/2019 - 11:29
-
Categorization & Reporting of Performance Losses Using Seeq - Cloned michellemay Fri, 10/04/2019 - 11:29
Batch Quality Prediction
in Resources
Posted
Challenge
Quality is the most critical metric in pharmaceutical manufacturing—after all, nothing is more important than protecting patient health. Drug companies need to test each batch to ensure it meets quality standards.
However, predicting the quality of a batch has traditionally been a challenge for drug manufacturers. The usual process is to take samples while a process is running and send it to the lab for analysis. But waiting for lab results adds time—often several hours—to the process. Inadequate lab results can require time consuming changes or expensive reworks if it is even possible to recover the batch. If the batch does not meet the quality requirements, the manufacturer can lose anywhere from hundreds of thousands to millions of dollars for a lost batch.
A large molecule pharmaceutical manufacturer was struggling to predict batch quality results in near real-time. Delayed lab results made it difficult for the company to optimize process inputs to control the batch yield. The company’s process inputs were set without optimizing the process, resulting in the potential of wasted energy and raw materials or reduced product quality and yield. The company needed a better way to predict batch quality, enabling process optimization.
Solution
Using Seeq, the scientists built a model of process quality based on data from the OSIsoft PI data historian. The team uses the model to predict the quality of during in progress batches, enabling modifications during production before a batch needs to be scrapped for a quality issue.
This analysis uses typical process measurements such as the reactor temperature, volume, and concentration as process parameters for controlling yield. The raw data is filtered to the desired operation of interest, the reactor heating portion of the process. A predictive model for yield is then generated based on statistically significant process parameters. The model was deployed online to detect abnormal batches.
Results
Instead of waiting for quality tests to come back from the lab, the manufacturer has potentially saved millions of dollars by gaining the ability to rapidly identify and analyze root cause analysis of abnormal batches via modeling. It can reduce the number of out-of-specification batches by adjusting process parameters during the batch. The company also saved on the reduction of wasted energy and materials.
Developing and deploying an online predictive model of the product quality and yield can aid in fault detection and enable rapid root cause analysis, helping to ensure quality standards are maintained with every batch.
View the full article