Data paradise factory floor: get more out of your machine and production information
Publicado às 25 de setembro de 2020 em AI
Strategic Data Science is an essential pillar of every Industry 4.0 scenario. A four-step data mining approach based on CRISP-DM supports successful projects.
Whenever "Big Data" is mentioned, most people first think of social media or the analysis of customer behaviour in online commerce. Think again: Strategic data analysis is also gaining momentum in the production environment. Frost & Sullivan believes that data analysis in the industrial sector has immense potential. The experts found out that production efficiency could be increased by about ten percent, operating costs could be reduced by almost 20 percent and maintenance costs could be minimized by 50 percent when focusing more on working with the data that’s already there in the production process. The problem though: Data can be collected and stored in factories relatively easily. However, little happens after that, and important insights that are hidden in the available information are lost. In addition, there is often a lack of budget and personnel to devote to this task. But those who overcome these hurdles and focus on Industrial Data Science will soon gain new insights. They transform their production environment into a data paradise.
Data Science project approach: preparation, analysis and application development, evaluation and maintenance
Industrial Data Science is quite a new discipline. That’s why, there is (still) no generally valid approach that is suitable for every company. Every solution and application require customized data analysis and modelling to achieve the best possible result. However, a standard approach is useful. The CRISP-DM model, (Cross-Industry Standard Process for Data Mining) is the most commonly adapted basis. OMRON simplified and tailored CRISP-DM into a new approach. The four steps of this approach are preparation, analysis and application development, evaluation and maintenance.
Phase 1: Preparation
The preparation phase is the most important phase. A data science project will never be successful if the goal is unclear. Therefore, in this first important step, all participants and area experts first deal with the problem or the specific requirement in order to arrive at a clearly defined project goal. They analyse the machine and/or the production process in detail in order to get an overview of which data is already available and which still needs to be collected. In this process, an initial data set can be collected and analysed as a kind of feasibility study. At the end of the preparation phase, a report is produced that provides insights into the expected generated value and a realistic ROI.
Phase 2: Analysis and application development
In the following, the data is collected over a longer period of time in order to obtain a representative picture of the machine and process behaviour. Depending on the project objective, a data pipeline contains the following stages:
Data collection: Data is collected from various sources – from raw sensor data to information from MES systems.
Data pre-processing: The collected data is prepared for the analysis step, transformed, merged and cleaned up.
Data analytics: The developed analysis algorithms and machine learning models are applied.
Application: The results and conclusions of the data analysis are made available. Examples are visualizations, tailored to the situation, target group or as feedback to the machine.
The necessary machine learning models can be trained and validated together with the other data processing steps. If the validation is successful, an application can be developed based on the described data pipeline, which can be easily implemented and executed.
Phase 3: Evaluation
The application is used in the production environment, performance and business results are evaluated. If the performance does not meet expectations, the previous project phases are rerun again.
Phase 4: Service and Maintenance
Production processes change and machine behaviour is also subject to constant change over time. Reasons for this can be updates or wear and tear. Therefore, a regular revalidation of the solution is necessary to ensure that the solution works realistically and retains its value. In addition, the amount of data available is also growing, and often better models can be developed. As a result, existing (machine learning) models need to be reviewed regularly.
Practical example SMT line
A data-driven solution does not always have to include fancy machine learning models or artificial intelligence. Sometimes effective data processing and providing the right information at the right time in the right way can be enough. An illustrative example of such a data science project can be found in the current white paper "Data Science Services by OMRON – How to get the full value from your factory floor data", which is available for free download. The project was carried out at the OMRON Manufacturing of the Netherlands (OMN) factory on surface-mount technology (SMT) lines where electronic components are mounted and soldered onto printed circuit boards (PCBs).
Only the most commonly used solutions develop their full potential
Developing the potential of Big Data in your own production environment is not easy, but it is worth it. It's not enough just to collect data and build a few graphs. It's about filtering out production-relevant information from the data and presenting it to the right audience in the right way. The key is to transform data into useful information. This must be done in close cooperation between data scientists and experts in the production process. Only then can a solution be developed that is popular, often used and generates long-term value.
For more information on how to benefit from the full value of industry data, see the latest OMRON white paper: