or data volume but also to the variety and speed of data (veracity and value of data are also relevant). Let us not forget that information is useful if it is known how to interpret it. The underlying idea of making use

of Big Data Analytics is to evolve from the SPC (statistical process control) to the PPC (prescriptive process control). The existing data are used to create a learning model for the machine (process or system). The model is capable to predict product quality vs a certain combination of data set for input, ambient and process parameters (allowing the experimental simulation – see digital twin model data based). As per the above implementation

(machine learning), prescriptive techniques will allow a full process automation of the process cycle acting on the specific parameters to ensure the quality in a sustained manner. Thus, the predictive model acts as prescriber. Effective implementation


process control based on big data analytics shall bring a major step function change in reducing variability to the Investment Casting Industry.

Digitized Inspection Investment Casting industry is very

intensive in parts inspection,

specifically for those components associated to the High Added Value market segment.

Dimensional accuracy and free from internal defects are routine inspections to be carried out on full series production. The incorporation of technologies such as 3D optical measurement and digital radiography (DR) are impacting in a very effective way

reducing inspection

production lines and the automation of

proper Hw and Sw, such inspection.

The time and

improving inspection accuracy. The challenge relies with the integration of

within the effective

organization of the inspection records database is another element of added value derived from this implementation.

Predictive Maintenance PdM 4.0 Maintenance of equipment ensuring high rates of availability is a funda- mental aspect for any manufacturing

16 ❘ November 2019 ®

facility. Let us not forget that the third factor associated to the OEE (Over- all Equipment Effectiveness) is related with equipment availability. Maintenance has been evolving

significantly during the last years from basic repair corrective actions and visual inspections to the incorporation of monitoring instrumentation, and real time monitoring based on sensors incorporated to the equipment. As mentioned above, Industry 4.0 represents for Maintenance a step forward to the so called PdM 4.0. Again, Big data analytics based on sensors monitoring different variables within the different equipment can provide not only predictive failure identification but prescriptive actions to reduce or avoid it and, in any case, an effective Maintenance prescription for action.

An improvement in Maintenance

effectiveness will maximize the OEE and shall be reducing OPEX and CAPEX supporting a gain in competitiveness for the company.

Supply Chain, Management and Decision Taking The digital transformation shall be supporting a new approach and solutions to the way Supply Chain has been managed or the use of information by management in decision taking. If we take just for instance the way the demand is varying nowadays where most of the forecast facilitated by customers depart from reality, the organizations must look for internal solutions to cope with this fact. Conventional MRP are no longer valid and again solutions based on Big Data Analytics such as DDMRP can learn from data to provide the definition of the Material Resource Planning to cope with true demand. The effectiveness derived in terms of minimizing the use of resources is of paramount importance for any company. ERPs

have been providing to

management with information in different stages in accordance with the advance degree of information use of the organization. From “What happened” (based on different reports), to “Why did it happen?” (based on

certain analysis), to “What is happening now?” (based on real time dashboards). Next step that digital transformation is bringing along should be the capability to answer questions like: • “What is likely to happen?” (predictive analysis)

• “What should we do?” (prescriptive analysis)

Integration with ERP of Big Data Analytics and business model learning shall result in putting forward also for the

Management discipline scenario decision taking. Customer Relationship

As in the other axes explored in this article, the digital transformation is bound to produce an integral redefinition in the Customer relation and business model orientation, not only in the way the information is being shared, but affecting to understanding and measuring what represents value for the customer and orienting actions to maximize it, their market needs and personalization required based on what is being learned from the demand, the predicted design solutions based on monitoring of Customer experience and product life cycle. This integration with the Customer again based on Big Data Analytics represents an open scenario which as mentioned shall redefine the way we understand the customer relationships nowadays and the whole of the commercial approach in the future. EICF is very conscious of how

challenging and at the same time attractive represents this digital transformation for the Investment casting industry. Digital transformation in which we are already immersed and which at the same time is bound to provide solutions and scenarios that we could only limited be envisaged. In order to provide some guidance and indication about it, the 30th EICF International Conference & Exhibition to be held in Bregenz (Austria) next 10 to 13 of May 2020 is tackling the subject with the Conference theme “Driving the Digital Transformation into Investment Casting”.

a new of reduced uncertainty for

Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32