Yazzoom offers three very different solutions for condition-based maintenance (also know as predictive maintenance).
All three focus on indicators of future equipment failure or performance deterioration. These indicators are derived from available measurements using mathematical computations and models, e.g. normalized energy efficiency or predictive models.
All three focus on indicators of future equipment failure or performance deterioration. These indicators are derived from available measurements using mathematical computations and models, e.g. normalized energy efficiency or predictive models.
|
YASENSE & YASENSE Excel - Predictive models and asset performance KPIsYASENSE uses computer models that estimates hard to measure variables based on available other variables. This model can be “white box” (based on mathematical theory, aka first principles models), “black box” (learned from historical data using machine learning algorithms) or “grey box” (a mixture of the two).
|
Yazzoom develops, based on data analytics, models that enable condition-based maintenance by giving feedback on system or component performance, or even product quality.
For existing models or when the model is relatively simple (a KPI like normalized energy efficiency of pumps, mixers,…; heat exchanger efficiency etc.), YASENSE Excel enables robust deployment of models described in standard spreadsheets, allowing non-experts to maintain them.
For existing models or when the model is relatively simple (a KPI like normalized energy efficiency of pumps, mixers,…; heat exchanger efficiency etc.), YASENSE Excel enables robust deployment of models described in standard spreadsheets, allowing non-experts to maintain them.
|
YANOMALY - Anomaly Detection for Machine Data & Log FilesAn Artificial Intelligence solution for detection of anomalies in the "big data" coming from industrial equipment and assets, Yanomaly uses advanced machine learning techniques to learn machine's normal working conditions and processes based on the data they generate (multivariate sensor time-series data, log files from subsystems and more)
|
Able to take into account context (whether the equipment is starting up or powering down, is performing a specific task,...) and detect abnormal events, values or patterns indicative of technical issues, Yanomaly enables automatic monitoring of complex assets.
|
PiControl APROMON - Control Loop Performance MonitoringApromon watches the performance of any number of PID control loops in a plant using rules based on process control expertise, allowing the early detection of PID tuning, infrastructure/project and maintenance needs. In reports or alarms, it categorizes, gives useful diagnostic information and helps prioritize work.
|
Simple to install and use, it's a practical tool that focuses on the essential most valuable aspects of control loop performance monitoring: helping you focus on the loops that need attention, identify control problems and restore control quality.
