Beyond Technology; Focus More on the Processes & Organisational Changes
ADI has a complete systems-level solution to provide the technology and insight to create new, high-value, predictive maintenance service offerings for deployed equipment.
TS Shankar, Sales Director, Analog Devices India during an interaction with Nitisha elaborates on predictive maintenance in automation. Sharing the company’s leadership in this segment, the veteran shares about the company’s latest product ADI OtoSense – an AI-powered platform which includes turnkey hardware and software solution. During the candid chat, he significantly foresees the trends shaping predictive maintenance and the impact of machine learning and IIoT shaping PdM and defines the buzzword Predictive Maintenance 4.0. Below are the edited excerpts from the interview;
Please highlight the value of predictive maintenance in automation.
Predictive maintenance (PdM) involves a combination of Condition-based Monitoring (CBM), machine learning and analytics to predict machine or asset failures. Given that unscheduled downtime can account for about a quarter of the total manufacturing costs, predictive maintenance has the potential to unlock significant savings and productivity. The increased use of data corresponds to increasing levels of maturity, which leads to improved maintenance performance. Maintenance personnel can make better-informed decisions that lead to increased reliability, higher uptime, fewer accidents and failures, and lower costs.
When monitoring the health of a machine, it is critical to select the most suitable sensors to ensure faults can be detected, diagnosed, and even predicted. Due to advances in AI and the increase in data points, sophisticated analytics are becoming increasingly important and make up a larger share of the overall predictive maintenance budget (IoT Analytics). With IIoT and machine learning, what is now often called predictive maintenance is in fact a more advanced stage of PdM, with more data sources. Thus, predictive maintenance offers several business advantages compared to traditional, reactive and preventive models. These include better asset utilisation and OEE, (Overall Equipment Effectiveness) avoidance of unscheduled downtime and optimal planning of maintenance activities.
Please highlight the latest trends in predictive maintenance.
Manufacturers look to increase throughput and asset utilisation by reducing maintenance costs and asset downtime. Real-time, continuous, condition-based monitoring and predictive maintenance solutions are increasing in importance.
Thermography – Thermographic analysis is a non-destructive testing technique, which uses an infrared scanner to detect the wear and corrosion of equipment that is not visible to the naked eye. Manufacturers who regularly perform infrared PDM check on the temperature of their equipment will save money on reactive maintenance and equipment repair costs. Also, manufacturers can manage their equipment lifecycle by monitoring the condition over time and identifying abnormal readings that require further inspection.
Plug & Play – Many manufacturers rely on older equipment to run critical application processes. However, the machines are not equipped with connectivity to send real-time data. Plug and Play (PNP) devices allow manufacturers to connect legacy machines without costly machinery replacement.
PdM-as-a-Service – It provides value from day one, detecting the early warning signs of equipment failure to schedule maintenance. It gives OEMs a unique advantage when it comes to predictive analytics, as they can build models from customer data and provide personalised insights and equipment-specific maintenance goals.
What are the challenges and scope of Implementing CBM?
Despite the abundance of technical know-how, companies still struggle to effectively implement CBM (Condition-based Monitoring) in practice. It is due to the complexity of real-life systems currently available, compared to the simplified systems in use earlier or the lack of required technical skills. The lack of product failure data in the field makes development of robust diagnostics and forecasts difficult. Furthermore, these challenges exist for comprehensive CBM implementation at all technical levels, from data collection to decision support through data analysis. When businesses are opting for digital-front strategies, then there is a need to look beyond technology and focus more on the processes and organisational changes required for successful CBM implementation. The biggest challenge of industrial AI (including CBM) is not the lack of appropriate technology, but how to create real value by combining technologies in a resource-efficient and collaborative manner. Successful implementation can only take place and be sustained within organisations that are capable of change, fostering a digital culture and developing and attracting the right capabilities.
What is Predictive Maintenance 4.0?
Predictive maintenance is one small part of the broad concept of digitalisation, or ‘Industry 4.0.’ It refers to the ability to monitor a machine or machine component and avoid unplanned downtime by foreseeing machine failure and allowing the opportunity to take preventive action. Since plant downtime can incur monetary losses due to lost output, an investment in predictive maintenance technology is a logical step.
While getting the technology to work may be central to PdM 4.0, the scope of its implementation is far broader. Companies should also pay attention to the organisational dimensions and ensure the project management and change management skills required for a successful PdM 4.0 implementation.
Implementing PdM 4.0 should not be viewed as a strictly technological challenge. Obviously, strong project management skills are needed to get PdM 4.0 ‘up and running’ in the first place. However, to reap the rewards of PdM 4.0 in the longer term, companies will also have to create an organisational support structure.
Is there any flagship offering you wish to highlight?
ADI has a complete systems-level solution to provide the technology and insight to create new, high-value, predictive maintenance service offerings for deployed equipment. Our flagship product, ADI OtoSense™ is an AI-powered platform, which includes turnkey hardware and software solution. It senses and interprets any sound, vibration, pressure, current or temperature for continuous, condition monitoring and on-demand diagnostics. It provides diagnosis and severity-level insight into nine different fault types and sets out recommended actions to correct any of these faults before failure occurs. These insights enable machinists to forecast maintenance cycles and avoid costly unplanned downtime.
