When explaining what ifm’s moneo solution can provide to a factory or plant, Freddie Coertze says it can be likened to how a smart watch on your wrist works.
“The moneo DataScience toolbox uses historical data, sensor data, and inputted process parameters to diagnose problems, detect anomalies and predict potential issues – just as a smart watch might give you an indication of your health through the monitoring of different physical attributes and the information you feed into it, ” explains the ifm Australia National IoT Business Manager. “This intelligent toolbox is designed to provide a holistic view of asset health and enhances an engineer’s predictive maintenance program and workflow.”
“It is a self-service platform and the algorithimic method of the SmartLimitWatcher is trained to measure and compare data against predicted target values,” he says. “It’s comparable to having an in-house doctor that monitors the health and performance of your assets on an ongoing basis, providing suggestions for improvement to prevent deterioration and lengthen the asset life.”
Just as a doctor relies on a patient’s medical history in addition to information a patient will provide as to what’s ‘good’ , the moneo DataScience Toolbox is essentially taught what is ‘good behaviour’ for an asset.
“It then enables automatic and early anomaly detection, giving users the ability to react quickly to deviations within the production process,” says Freddie. “In other words, you’re not relying solely on historical data to make decisions, and can be proactive about asset management, meaning equipment hasn’t already started to fail by the time you intervene.”
Named after the latin meaning ‘to warn or advise’, moneo is a solution that can be scaled according to a business’s needs – whether that’s a standalone asset or an entire plant, meaning it is suited to a wide range of applications.
Key benefits of the moneo DataScience Toolbox include:
- Self-service, easy to use: No data science expertise required. Provides a simple five-step wizard for users to set up. Data preparation and quality checks are automated.
- Smart: Draws on best-fit artificial intelligence mathematical model to automate learning and verification of monitoring accuracy.
- Reliable: Uses real-time condition-based monitoring and historic data to measure performance against target variables.
- Customised: Alarms and warnings are tailored to individual preference, including the sensitivity to anomaly detection.
Coertze also points out that implementation of the moneo DataScience Toolbox is cost-effective compared to an engineer attempting to run a data science project on their own.
“It’s worth doing the comparison to see the value that moneo can provide to a business. Because it is self-service, you’re excluding the need for data scientist expertise which can cost upwards of $20,000. It’s fast, it’s scalable, it provides an excellent price-to-performance ratio, and it can be integrated with existing systems,” he concludes.