Automated Data Analysis
with PYTHIA Insights
Companies accumulate large amounts of process data with potentially massive value for their efficiency. But how to access that value and act on that data? Until now, this required time-consuming data project work. Now it can be done fast, easy, and fully automated.
Processes are getting more complicated, and data pools bigger. However, companies’ requirements remain the same: Improve productivity, maximize throughput, eliminate failures, identify flaws, assure quality, identify root causes, etc.
They can achieve these goals by continuously transforming data into insights and a good basis for decision making. PYTHIA Insights makes this process so quick and straightforward that they can easily include this transformation in everyday working life.
PYTHIA Insights enables domain experts, operators, and decision-makers to entirely focus on asking the right questions out of their domain context like Why does this happen…? What are the differences between…? How are these related…? Can this be predicted from…? How strongly is this influenced by…?
PYTHIA Insights is the first step to gain deeper process insights and increase efficiency. Cutting-edge data analytics technology allows you to ask questions to your data out of your domain context and get the answer fully automated. It performs a fully automated data analysis on those questions and presents the response as an easy to understand analytics report.
How it works
First, you provide the unfiltered, raw data of your processes (time-series data or tabular data, can be up to 1 TB). An in advance exclusion of individual signals or parts of the data is neither necessary nor recommended. You then define your question based on one of three different directions:
PYTHIA performs an automated data analysis and creates an analytics report regarding the question asked.
quality Assurance – error detection – root cause indicators – WASTE reduction
During the continuous process of papermaking, paper quality is a critical process parameter. Unfortunately, this parameter can not be measured directly because it has to be determined in the lab. Since it takes about one hour from sampling to the result, the operator is flying blind, so to speak, until the next lab value is available.
Since the whole process is accompanied by thousands of more parameters and online measurements, the question arises if the paper quality can be derived indirectly. This can be tested with PYTHIA Insights.
Paper breaks during the continuous process of industrial paper manufacturing are hard to control. These breaks can occur at any time without any warning. The sheet or paper web breaks inside the machine. Subsequently, there are various cleaning and retreading steps required before production can be continued. Sheet breaks have a significant negative impact on a paper machine’s productivity.
With PYTHIA Insights, the root cause indicators can be identified and classified, helping process experts to better understand this disruption.
Gear boxes are produced in a discrete manufacturing process. In the end, the slippage time is determined for each gearbox to check if it is within the tolerance. Is it possible to identify bad gearboxes earlier in the process?
To determine this, you can address the following questions with PYTHIA insights: Which characteristics distinguish the particularly good/bad from the average? Can the quality be predicted in an early stage?
A once in a long-time bad event occurred that never happened within the available historical data. When did the system’s condition deteriorate unnoticed so that this event could occur and which signals were responsible? Can this be prevented next time?
In a manufacturing plant, certain goods are produced in a discrete manufacturing process. The times and durations required for each piece’s production steps are recorded, including machines, tools, materials, and more. KPIs are available for each produced piece.
Are there combinations of shift, material, machines, etc. that are sometimes significantly worse than they should be compared to others? Are there anomalies in shifts, weekdays, material deliveries, etc.?
Products are being produced in a discrete manufacturing line. Process- and operational data of this production are collected and stored. After production, for each component, a KPI can be calculated, for example the quality.
Now you want to know which characteristics distinguish the particularly good/bad components from the average ones. This helps to find the reasons for outliers, detect them earlier in the process, and improve overall quality.
The dead oil viscosity is a critical process parameter that heavily depends on the type of oil. Even slight differences in composition can dramatically impact the viscosity, making it almost impossible to address this issue with classical black oil correlations.
Can the viscosity be predicted based on other available parameters?
These are only a few examples of PYTHIA Insights applications. In fact, the potential industrial applications are countless.
PYTHIA Insights is in no way restricted to the presented applications. In fact, it can be used analogously in many industrial applications. If you are wondering whether it can be used in your particular case as well, focus on the following criteria:
If your process environment matches those criteria, there is a good chance that PYTHIA Insights can bring you closer to your goals.