BUSINESS INTELLIGENCE INDUSTRY 4.0

R&D of descriptive, predictive and prescriptive analytics models for Business Intelligence.

BUSINESS INTELLIGENCE INDUSTRY 4.0

R&D of descriptive, predictive and prescriptive analytics models for Business Intelligence.

PROJECT DATA

Customer: HS Systems
Category: Research and development
Start: 05/2018 – End: 12/2018

PROJECT DATA

Customer: HS Systems
Category: Research and development
Start: 05/2018 – End: 12/2018

RESULTS

-
0
%

Production waste

-
0
%

Energy costs

-
0
%

Complaint rate

OBJECTIVES

Reduction of operational expediture / Reduction of waste / Minimization of plant downtime / Maximization of profit
The goal of the project was to develop descriptive, predictive and prescriptive analytics models for Business Intelligence in order to improve energy efficiency and predictive maintenance of industrial machinery from an Industry 4.0 perspective.
Specifically, one of the main purposes was to minimize the use of purposedly built systems, ensuring compatibility with existing infrastructures, creating interfaces that were proven suitable for different types of users, building a plant history database, in order to predict future trends. The project also focused on the improvement of workforce efficiency by avoiding inoperativeness, minimizing the waste of hardware and computational resources, ensuring maximum safety and service personalization, through decision support.

SOLUTIONS

Forecast Algorithms for energy consumption and system failures / Decision support for operational planning
With BI_I4.0 we developed descriptive and predictive analytics algorithms, for energy efficiency and predictive maintenance.

The developed solution uses machine learning processes. By automatically retrieving data over time from on-site sensors it allows to intuitively and inductively elaborate future forecasts. Energy efficiency has been achieved thanks to the possibility of forecasting and processing energy consumption data, in order to understand where to work on and optimize the levels of consumption.
In the field of prescriptive analytics, our decision support system dynamically adapts to the available data, selecting the most appropriate forecasting model based on user-specified criteria.

SOLUTIONS

Forecast Algorithms for energy consumption and system failures / Decision support for operational planning
With BI_I4.0 we have developed descriptive and predictive analytics algorithms, for energy efficiency and predictive maintenance.

The developed solution uses machine learning processes. By automatically retrieving data over time from on-site sensors it allows to intuitively and inductively elaborate future forecasts. Energy efficiency has been achieved thanks to the possibility of forecasting and processing energy consumption data, in order to understand where to work on and optimize the levels of consumption.
In the field of prescriptive analytics, our decision support system dynamically adapts to the available data, selecting the most appropriate forecasting model based on user-specified criteria.

MORE IN DEPTH

Specifically, Business Intelligence Industry 4.0 aims:

  • to minimize the use of purposedly built systems, ensuring compatibility with existing infrastructures;
  • to create interfaces suitable for different types of users;
  • to build a plant history database, in order to predict future trends;
  • to improve the efficiency of the workforce and to avoid inoperativeness;
  • to minimize the waste of hardware and computational resources, ensuring maximum safety;
  • to customize the service, providing decision support.

With Business Intelligence Industry 4.0 (called BI_I4.0) Idea75 developed descriptive and predictive analytics algorithms, for energy efficiency and predictive maintenance.

The solution developed uses machine learning processes, automatically gathering information over time thanks to adaptive algorithms that have the ability to process large amounts of data coming from on-site sensors (for example energy consumption data: electricity, water, gas). They learn from them and are able to intuitively and inductively elaborate future predictions.

By interweaving computational, statistical and mathematical analysis, the implemented energy efficiency function is able to predict the energy consumption of a given plant, for a specific time and in a given production activity.

The forecast data, once processed, work as fundamental information to understand where to work on to optimize consumption and improve energy efficiency, analyzing the Key Performance Indicators (KPI).

In the field of prescriptive analytics, Idea75 developed a decision support system (DSS) that dynamically adapts to the available data, selecting the most appropriate forecasting model based on criteria specified by the user.

With Business Intelligence Industry 4.0 (called BI_I4.0) Idea75 developed descriptive and predictive analytics algorithms, for energy efficiency and predictive maintenance.

The solution developed uses machine learning processes, automatically gathering information over time thanks to adaptive algorithms that have the ability to process large amounts of data coming from on-site sensors (for example energy consumption data: electricity, water, gas). They learn from them and are able to intuitively and inductively elaborate future predictions.

By interweaving computational, statistical and mathematical analysis, the implemented energy efficiency function is able to predict the energy consumption of a given plant, for a specific time and in a given production activity.

The forecast data, once processed, work as fundamental information to understand where to work on to optimize consumption and improve energy efficiency, analyzing the Key Performance Indicators (KPI).

In the field of prescriptive analytics, Idea75 developed a decision support system (DSS) that dynamically adapts to the available data, selecting the most appropriate forecasting model based on criteria specified by the user.

For the validation of BI_I4.0 two machines with high energy consumption used in the milling process were taken in consideration; each of these has production constraints (batch size, processing times, storage times, etc.).
Production planning based on the forecast of consumption and faults was carried out through the analysis and monitoring of different categories of KPIs:

  • programming / production;
  • resource management;
  • maintenance;
  • product quality.

In addition, out of samples indicators were evaluated for six different prediction models and for the different optimization methods used.
The implemented decision support system dynamically adapts to the available data, selecting the most appropriate forecast model based on criteria specified by the user (accuracy criterion or variability criterion).
With its technological and innovative solutions, BI_I4.0 managed to obtain the reduction of:

  • production waste by 20%;
  • energy costs by 15%;
  • final customer complaint rate by 5%.

DSS: selection criteria for the most appropriate forecasting model

Comparison of optimization methods used

STAKEHOLDERS & CREDITS

PARTNER

H.S. Systems offers business management software, analytics and cloud services to help organizations improve performance and apply digital technologies to break traditional thinking and enable new business models.
www.hssystems.it

PROJECT KEYWORDS