Predictive analytics reduce downtime
July 2017, IT in Manufacturing
Rockwell Automation has combined professional services, powerful machine-learning algorithms and predictive analytics software to offer predictive and prescriptive maintenance. With these new capabilities, industrial operators can predict maintenance needs and perform the necessary repairs before failure occurs. This allows manufacturers to avoid costly downtime and improve productivity.
Predictive maintenance is the latest offering in the expanded Information Solutions portfolio from Rockwell Automation, helping manufacturers solve the issues that arise in their facility. The solutions can also scale to your business and manufacturing process by leveraging Rockwell Automation implementation, cloud monitoring and on-site response services.
“Unscheduled downtime is one of our customers’ top threats to maximising revenue,” said Christo Buys, business manager for control systems, Rockwell Automation sub-Saharan Africa. “Machines equipped with predictive and prescriptive analytics capabilities can help manufacturers avoid this critical risk through improved maintenance. These machines directly ask the maintenance department for assistance – but only when assistance is necessary. This helps our customers improve equipment uptime while lowering maintenance costs.”
Predictive maintenance solutions delivered by Rockwell Automation help inform operators how and why a machine is degrading, and then prescribe the best corrective course of action. This allows operators to conduct necessary, specific maintenance rather than reacting to machine failures or wasting time on undue repairs. The software integrates with FactoryTalk Historian software from Rockwell Automation and an industrial asset-management system.
The predictive maintenance software learns patterns that precede the downtime events identified in your maintenance history, and then trains agents to recognise those same patterns in the future. As new data is generated, machine-learning agents offer around-the-clock tracking of all live sensor data, looking for the patterns identified. Additionally, agents can watch for atypical patterns that may represent new failure modes to be investigated.
Prescriptive alerts can be put into action through convenient email and text alerts, a web application, or integration with computerised maintenance management systems. The predictive maintenance software also includes a work-order capability, which operators can use to manage alerts in the absence of an existing system.
Rockwell Automation provides integration services to deploy the predictive maintenance software on the premises, via the cloud or as a hybrid of both. Remote monitoring services can monitor the solution, prescribe critical preventive maintenance tasks, modify predictive algorithms as new failure modes are detected, and even provide on-site response to perform maintenance tasks. This allows industrial companies to realise the benefits of predictive maintenance without training staff to support the technology.
For more information contact Christo Buys, Rockwell Automation, +27 (0)11 654 9700, email@example.com, www.rockwellautomation.co.za