Increased availability and avoidance of downtimes through analyses and forecasts during operation

Condition monitoring systems make it possible to continuously and reliably monitor the technical “health and operating status” of plants, systems or buildings. The aim is to ensure production start-up, monitor production during operation and prevent downtime, e.g. due to component wear, by means of condition-based maintenance and by analysing faults and causes or by using predictions as a basis for decisions on measures to be taken. 

The problem today: Sources and indicators of wear and tear are often only identified retrospectively, when the downtimes are already unavoidable and the costs have already been incurred.

Increased availability and avoidance of downtimes through analyses and forecasts during operation

Condition monitoring systems make it possible to continuously and reliably monitor the technical “health and operating status” of plants, systems or buildings. The aim is to ensure production start-up, monitor production during operation and prevent downtime, e.g. due to component wear, by means of condition-based maintenance and by analysing faults and causes or by using predictions as a basis for decisions on measures to be taken. 

The problem today: Sources and indicators of wear and tear are often only identified retrospectively, when the downtimes are already unavoidable and the costs have already been incurred.

ASCon combines Digital Twin Technology with Predictive Analytics

With the Condition Monitoring Assistant you can continuously monitor and analyze the essential process parameters in the context of your overall system – and thus anticipate potential problems before they occur. The Digital Twin enables companies to make data-driven, AI-supported predictive analyses of plant-related parameter limits and supports the user in diagnosis and decision-making.

Collect
Data

Signals, parameters and information are recorded in a holistic data context and form a “smart” database.

Analyze
Data

Analysis of live and historical data from machines, sensors, ERP, MES, APS and maintenance systems to detect patterns.

Identify
risks

Prediction of failure risk by monitoring process, product, and resource conditions that previously led to failure.

Alert
Teams

Notification of plant managers, operators and maintenance staff of potential anomalies with appropriate lead time.

Condition Monitoring

  • Visual representation of the overall plant status in context (environment, product, plant, process) with parameter monitoring
  • Display of connected system parameters including the respective standard value ranges
  • Determination of parameter anomalies, which e.g. lead to a plant shutdown
  • Application of different AI analyses, e.g. early detection of creeping deviations
  • Recommendation for corrective action

Connection of resource, product, process and environment

Using the data-based approach of the Digital Twin, all relevant parameters, sensors and environmental data are first recorded and standardized in a semantic model. In addition to online data acquisition from existing IT systems, offline data sources are also relevant, such as maintenance messages from downstream processes. Condition Monitoring systems work with sensors that typically record measured variables such as temperature, speed, levels, oscillations, vibrations and other values. For a comprehensive analysis, it may therefore be necessary to first equip the existing assets in the factory/building with suitable sensor technology that can provide information about the condition of a machine or component – keyword: retrofit. All data is finally networked, standardized and harmonized in the Digital Twin and then made available to users for data storage, analysis functions and for decision preparation or visualization.

Digital Twin: Starting point for innovative Predictive Maintenance solutions

Digitalisation (e.g. retrofitting) and the use of Digital Twin technology create the conditions for Predictive Maintenance. Maintenance processes clearly benefit from the concept of the Digital Twin: Conditions and operating parameters are persisted in the Digital File over a long period of time and are thus available in a historical form for maintenance-related decisions.

Condition Monitoring in the Digital Twin is the entry point for further expansion stages towards intelligent maintenance with Predictive Maintenance and Smart Data Analytics.

Do you have questions or are you interested in a product demonstration?

 

Your contact person

Tilo Geisel
Tech Sales Manager

Contact us