Reply is the place to meet an incredible variety of enthusiastic, passionate, ideas-driven people, who want to make a difference and an impact.Would you like to know more?
As part of the digital transformation process that is consolidating the role of Industrie 4.0 within production systems, the self-aware factory represents a natural evolution of current trends. The development of this new type of factory is based on a distributed intelligence model more closely aligned to the production line, on advanced sensors and on the most sophisticated data analysis and Machine Learning techniques available.
The latest developments facilitate the integration of latest generation sensors into existing equipment, using data supplied by means of production. This combination makes it possible to test the system in order to predict eventual failures and outages, reducing machine downtime, together with energy and materials consumption.
Reply supports its customers to exploit the potential of predictive maintenance providing end-to-end solutions, from the design of ad-hoc sensors to the integration with existing systems and specialised algorithms in function of the specific production sectors (Automotive, Machine Tools, Consumer goods).
Reply uses design thinking techniques to evaluate the available information and the necessary elements to develop a predictive maintenance system, relying on a structured approach.In this process, the main challenge is the definition of evaluation criteria for the return on investment and potential security threats.
Reply offers consulting as well as hardware and software design applied to the Industrial IoT realm, data analysis, algorithms and applications for each manufacturing sector, thanks to a team of experts capable of providing customers with a targeted technical support, based on specific expertise.Regardless of the degree of automation within the existing processes, the innovative solutions proposed by Reply guide the customer and facilitate the digital transformation process.
Implementing sensors on existing machines or designing installations that are truer to the concept of a self-aware factory is not just for large companies: SMEs can also derive significant benefits in terms of efficiency and process optimisation.Industrial businesses of various sizes are in fact collaborating with Reply to help establish a connection between existing data and new sensors, so that intelligent agents such as machine learning algorithms can extract information from that data and create added value in terms of improved security and energy savings.
Reply operates on a proprietary platform and commercial modules, supported by strong partnerships with leading market players (Amazon, Microsoft, Google, SAP) and specific vertical service providers (GE Predix, Thingworx).The company operates independently in relation to specific technologies or service providers, in order to avoid vendor lock-in and to be able to best adapt to the specific needs of customers and existing systems. At the same time, however, the solutions offered are built on standard modules, both on Cloud PaaS or Open Source platforms, with specific expertise in relation to the field of application.
The project, with the support of technology partners including the Politecnico di Milano, the Fondazione Bruno Kessler di Trento and ST Microelectronics, aims to demonstrate that predictive maintenance does not necessitate costly investments. The innovative ALMeS sensors solution relies on standard optical fibre, low cost microcontrollers and a machine learning software that can help reduce maintenance costs by 25-35%, eliminating 70% of outages and promoting a 25% increase in productivity.
Reply has been operating as a technology incubator for some of the most innovative start-ups in the IoT realm for a number of years. Several Group companies specialise in predictive maintenance. Senseye, for example, focuses on downtime and optimising machine OEE (Overall Equipment Effectiveness) within a facility. The Cloud Solution relies heavily on current and historical data so does not have high initial costs, facilitating a 30-50% reduction in downtime. We Predict, on the other hand, offers predictive analytics solutions in the automotive sector, concentrating on warranty cost savings with reductions of 8-15%.