Protect yourself against regularly occurring process disruptions and equipment breaks. Let aivis find dangerous dynamics in your process and create models that recognize them and issue specific warnings in time so that suitable countermeasures can be applied.
Process disruptions and breakdowns are not only very costly, they lower productivity significantly, pollute the environment and can even be dangerous to people. But avoiding those disruptions is not always easy, especially in complex processes with thousands of sensors. Where human comprehension reaches its limits, aivis takes over and autonomously figures out critical dynamics leading to the disruptions and creates a model to prevent them in time.
How to avoid process disruptions with aivis
Avoiding process disruptions with aivis is incredibly easy. You will be astonished about the quality of information aivis reveals from just using automated machine learning on your raw data.
Historical time-series data
Step 1: Defining the disruption
aivis requires two things to analyze a specific process disruption: First, the raw, uncleaned, unfiltered, and unsynchronized historical time-series data of the process. Second, an expression like “Signal_5 is 1”, that determines when the disruption was present.
Step 2: Automated analysis
aivis then fully automated searches the data for all critical signal dynamics (segments) that have led to the disruption in the past and creates an event analysis report. Usually, aivis finds multiple independent segments, some of which are already known and others so far unknown.
Automated machine learning
Event analysis report
Step 3: Defining counter-measures
The report reveals the signals from which process engineers can draw the most evident conclusions about the underlying problem for each segment. It also shows how those signals differ from normal behavior during a conspicuous period. This helps the process experts develop an understanding and determine suitable counter-measures for each segment.
Step 4: Deploying the model
When creating the report, aivis simultaneously creates a model as an independent, lightweight software module that recognizes when one of the found segments is present. Once deployed and fed with the process’s live data stream, the operator is warned in time about each segment to apply suitable countermeasures and avoid the disruption.
Model guarding the process
PREDICTIVE MAINTENANCE – PREDICTIVE INTERVENTION – QUALITY ASSURANCE – PRESCRIPTIVE MAINTENANCE
Check out this selection of application examples, where aivis has already successfully been applied in the past. Since aivis is industry-agnostic, it can be applied to countless other scenarios as well.
Pulp & Paper
Goal: Preventing paper breaks
Process interruptions in the continuous process of industrial paper manufacturing are called ‘sheet breaks’. 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 to take before production continues. Sheet breaks have a significant negative impact on a paper machine’s productivity.
Due to the high complexity of the process, which is monitored by several thousand sensors, even experienced paper engineers have only limited knowledge of when countermeasure must be initiated to avoid paper breaks, resulting in significantly lowered productivity.
After about one hour of computing time, aivis had completed an event analysis report and an associated model based on various found segments, many of which were yet unknown to the paper engineers as causative for paper breaks.
The new insights in combination with the model helped the engineers to lower the number of paper breaks significantly.
Goal: Preventing strip breaks
The breakage of strip steel during rolling is a disruptive event that can be very costly. Besides loosing some of the product, it is dangerous to people and can damage the equipment. Thus, avoiding strip breaks is of vital importance.
Due to the high complexity of the process, which is monitored by several thousand sensors, even experienced operators have only limited knowledge of when countermeasure must be initiated to avoid strip breaks, resulting in significantly lowered productivity.
aivis created a live guard that monitors the current process and warns the operator if a dangerous process state occurs and suggests suitable countermeasures. This decreases the number of breaks dramatically which boosts productivity and raises safety.