Industrial companies are constantly looking to improve production efficiency to reduce costs and increase margins. They rely on their assets to be efficient thereby looking to improve availability, up-time and operations of their machines and equipment. In a challenging global market, being able to do more with less – with speed and scalability – is crucial to succeed. If up-times between 90-95% were acceptable previously, we are now looking at companies aiming at up-times of 99% to be able to keep up with the competition.
To meet the high expectations on up-time, improving efficiency of service operations is essential. Industry 4.0 is driving the digitalization of manufacturing and revolutionizing digital maintenance. Connecting the machinery with the help of industrial IoT sensors, we are now able to collect real-time data throughout the whole production, and by applying advanced algorithms understand the equipment health so that anomalies can be detected, and corrective measures be taken in time. As data is collected and analysed, it is also visualized and enables monitoring of a whole, or several, factories remotely.
Preventive maintenance can be divided into two parts – predetermined and condition-based. While the pre-determined is based on normal service cycles, the condition-based maintenance is due to unexpected events. An event caused by e.g., a malfunctioning machinery part, can lead to catastrophic failures and complete production stop. The costs connected to fixing the failure are several including production waste, reduced productivity, overtime, more expensive spare parts, and extra freight costs to ship the spare parts.
By equipping the machinery with sensors, real-time data can be collected and analysed to detect anomalies triggering corrective service actions in time to prevent unexpected production stops. By using voice, corrective commands or requests for additional information can be asked remotely to be able to make quick adjustments or gather more intelligence without having to access the machinery systems.
Empowering the service operator to have access to real-time data and by voice being able to further gather intelligence and take actions, preventive actions can be taken quicker. As this can be done remotely, a single service operator is able to work more efficiently and serve a larger part of the production.
By applying machine learning, the predetermined service cycles can also be optimized to match the specific needs of the production line, rather than having to adjust to a predetermined general schedule.
Working with digital and smart preventive maintenance will minimize planned and unplanned downtime, predict equipment performance over time, reduce the cost and effort of people management and can lower your maintenance cost by up to 40%.
By applying advanced analytics, preventive maintenance can be scheduled, ensuring spare parts are available, the problem diagnosed, and the service operator being scheduled to work when production is affected the least. The results are increased operator efficiency, increased first time fix rate, less unscheduled down-time and faster on-site service.
Azure Percept is a platform of hardware and services that simplifies use of Azure AI technologies on the edge. The development kit comes with Azure Percept Vision, an intelligent camera, and it can be extended with Azure Percept Audio, a linear microphone array. With use of the Azure Percept Audio your kit will have speech AI capabilities enabling you to use voice commands, keyword spotting, and far field speech.
Information about Azure Percept development kit can be found here. Azure Percept Studio, which allows you to connect, build, customise and manage your Azure Percept edge solutions is described here. Azure Percept devices come with built-in security on every device and information about it can be found here. Azure Percept library of AI models is available here.