/ AI services for better performance
/ Our Features
- Performance monitoring
- Anomaly detection
- Data insights
- Event management
- Dashboard
- Training
- Visualized real-time data
- Using physic based models to detect changes
- Combination of operator & machinery feedback
- Annotation & aggregation on events
- AI events & various plots
- Model fitting on real-time or historic data
/ More than just energy management
Our energy management enables to track not only energy consumption but also enables the deep details about the main consumers and usages within the industrial plant.
With the ability to locate the most energy consuming parts of a machine, operators are gaining high accuracy and deep machinery insights empowering better decision-making for the setup and the operation of the machinery. The AI algorithm will not help to detect and uncover efficiency potentials, but also give recommendation on what to do next.
Technical features
- Cloud or on-premise
- Data integration into OsiSoft, SAP, ABB etc.
- Notifications via e-mail or MS Teams
- Data connectivity via OPC UA or other secured systems
- Requirements data sheets, P&IDs
AI Event Dashboard
Manage your events
The event combines machinery & operator feedback and will give recommendations on what to do next.
- Annotate & label events
- AI learns from operator feedback
- Receive event notifications
Digital twin
Simulate your plant
With our process model, you can understand the dynamical behavior and correlations within the plant
- Physical based models
- Calculating of soft sensors
- P&ID view of equipment
Edge box
IoT enabled Vibration Monitoring
With our vibration analysis & our cost-effective edge device you gain more insights about your machinery.
- Preprocessing of data
- Connect sensors & PLCs without IoT
- Flexible & cost-effective hardware
Dive deeper into our technology
- Model fitting
- Edge Analytics
- Evolutionary Algorithms
- Anomaly Detection using First Principle Models
- Vibration analysis
Data of the process
Industrial Analytics Thermodynamic Process Models are designed to be fitted without geometric data from the equipment, instead it uses measured data of the process.
Thermodynamic & Rotordynamic Process Models
A key necessity are the gas properties that are taken from an efficient implementation of the NIST REFPROP model. They provide additional insights of the monitored equipment and feature reasonable extrapolation into regions where the model is not trained.
Industrial Analytics Thermodynamic Process Models are designed to be fitted without geometric data from the equipment, instead it uses measured data of the process.
Thermodynamic & Rotordynamic Process Models
A key necessity are the gas properties that are taken from an efficient implementation of the NIST REFPROP model. They provide additional insights of the monitored equipment and feature reasonable extrapolation into regions where the model is not trained.
Signal Analysis software
The signal analysis software is developed by Industrial Analytics. It is possible to extract features relative to the rotational speed of the machine and a broad representation of the spectrum.
Transmitting the data
The data rates are reduced using a highly effective data compression algorithm. The data is transmitted via secure standard protocols like OPC-UA or can be fed directly into a PI System by OSIsoft Message Format. It is possible to use wired or Wi-Fi connections.
The signal analysis software is developed by Industrial Analytics. It is possible to extract features relative to the rotational speed of the machine and a broad representation of the spectrum.
Transmitting the data
The data rates are reduced using a highly effective data compression algorithm. The data is transmitted via secure standard protocols like OPC-UA or can be fed directly into a PI System by OSIsoft Message Format. It is possible to use wired or Wi-Fi connections.
Maximizing evidence results while minimizing uncertainties
Explainable AI models give not only the best answer, but obtain statistical information on the accuracy. The anomaly detection uses ensemble learning with training of multiple models. The results are a better estimation of expected value. This expected value is compared with the actual measured value.
Maximizing extrapolation capabilities while minimizing uncertainties
Industrial Analytics uses a reliable way to estimate the uncertainty of the model and the data. Maximizing Bayesian model evidence results in maximizing extrapolation capabilities while minimizing uncertainties. Generation of indicative events is based on hypothesis testing, which uses a quantifying effect size and probability of the errors and an automatic adjustment of the evaluation period.
Explainable AI models give not only the best answer, but obtain statistical information on the accuracy. The anomaly detection uses ensemble learning with training of multiple models. The results are a better estimation of expected value. This expected value is compared with the actual measured value.
Maximizing extrapolation capabilities while minimizing uncertainties
Industrial Analytics uses a reliable way to estimate the uncertainty of the model and the data. Maximizing Bayesian model evidence results in maximizing extrapolation capabilities while minimizing uncertainties. Generation of indicative events is based on hypothesis testing, which uses a quantifying effect size and probability of the errors and an automatic adjustment of the evaluation period.
Detection of changes without witnessing faults
The general monitoring strategy is to detect changes of the equipment relative to a state that is defined healthy. With this strategy, it is possible to monitor equipment without witnessing faults.
Accessible useful data
In many cases, the accessible, useful data do not have enough faults to use classic predictive maintenance strategies that rely on a degradation model.
Pretrained models
We use already trained models for certain physical assets, such a steam turbines or turbo compressors. So our customers don’t need extra data scientists for the fitting.
The general monitoring strategy is to detect changes of the equipment relative to a state that is defined healthy. With this strategy, it is possible to monitor equipment without witnessing faults.
Accessible useful data
In many cases, the accessible, useful data do not have enough faults to use classic predictive maintenance strategies that rely on a degradation model.
Pretrained models
We use already trained models for certain physical assets, such a steam turbines or turbo compressors. So our customers don’t need extra data scientists for the fitting.
Vibration signatures as sensors for machinery health
Vibration signatures are the most sensitive indicator for machinery health. Any defects are typically first indicated by a change of the vibration spectrum.
Cost-effective edge device
Industrial Analytics has engineered a cost-effective edge device which is built from industrial approved components. It is possible to use accelerometers or typical displacement sensors for shafts vibration. Other additional sensors can be added to the highly modular system.
Vibration signatures are the most sensitive indicator for machinery health. Any defects are typically first indicated by a change of the vibration spectrum.
Cost-effective edge device
Industrial Analytics has engineered a cost-effective edge device which is built from industrial approved components. It is possible to use accelerometers or typical displacement sensors for shafts vibration. Other additional sensors can be added to the highly modular system.
/ Onboarding
Equipment data
With provided P&ID and equipment data sheets by the client, we can start a project. Additional data like maintenance documentation, sensor data like vibration etc., help us provide better results
Data modelling & AI training
We will start to train the model and set the sensor data to their related functions. The result is process data model that is visualized. We initial train the model and provide consistency checks.
Deployment
We will integrate our solution into your existing IT infrastructure. We are experts on edge computing solutions and integration in the industry standard environments like OSIsoft PI, ABB, Siemens or other.
/ What's in for you?
We are experts in engineering and data science. We want our clients to understand their machinery better and optimized their production.
Reduction of unplanned downtime
Support of operator activities
Saving on maintenance costs
/ What our clients say
/ Get more insights with our White papers
/ Prescriptive Maintenance in Power Plants
What are the benefits of IoT enabled vibration analysis in a power plant & how to implement it?
/ Retrofitting in a Wastewater Plant
Learn more about how vibration analysis can be retrofitted and extend your machinery lifetime.
/ Prescriptive Maintenance in Refineries
Adding value with vibration analysis in a complex refinery.
/ Benefits of collaboration with startups
If you want to boost your corporate innovation, this one is for you!
