The company is market leader for polishing products to the semiconductor industry and have multiple production plants around the globe. As market requirements, for example with the EUV evolution in the semiconductor industry, keep on increasing and time to market is essential, analytics and supply chain have been identified as the key enablers to facility their strategic, business and product innovation objectives.
To fulfill their strategic and business objectives the company want to transform their current way of working towards an integrated horizontal and vertical value chain.
Although the company has excellent data scientists, the current data management and analytics methods & technics are not sufficient to support the strategic and business objectives.
The company wants enhance their data management and analytics methods and technics to speed up innovation, do proactive analytics and do faster root cause analysis in the most efficient way.
This use case will show how using a holistic based models immediately helps to contextualized data and speed up insight using analytics. The use case will also show how this lead to broad and in-depth insight through the manufacturing enterprise on multiple user levels.
The following business objectives are in scope:
• Analytics capability to speed up innovation
• Reduce root cause from several months to days
• End to End insight on production process details
• End to end insight on product quality
• Product control and improvement
• Process control and improvement
• Reduce Waste
• Fast Return on Investment
Continuous delivery of insights for the millions of experts to make smarter, better and faster decisions
that can be controlled and managed during the full transformation lifecycle.
The company current data landscape exists of multiple home grown solutions using obsolete technology combines with GE Smart Intelligence solutions and Oracle ERP. The systems are not integrated and data is used on a high aggregation level, that leads to loss of details needed for analytic insights which go beyond BI reporting.
Knowledge is predominantly concentrated at a few experts which creates a culture of ‘hero’s’, where each one has their ‘own data’ gathering based on experience.
The pain points can be summarized as:
• Senior management fully depends on results communicated by the experts
• Backwards history of product and process is difficult to generate
• No possibility for proactive insight
• No capturing of lessons learned and best practice
• Analytics takes very long
• Difficulty to train new employees
• Lot of data, but no contextualization
• No proactive analytics
We used the unique Smart Industrial Transformation approach and Models4Insight holistic modelling platform to create and manage digital representations of the users, processes, applications and physical assets, taking into account the actual current situation and the ‘To-Be’ scenarios.
The approach uses models to describe the different constituents ranging from business goals down to the shopfloor infrastructure and physical assets.
Data is collected through a dynamic data lake and linked to the models, creating contextualized data. The analytics techniques and methods used are process mining, data fusion and traditional based data mining analytics.
With specific unique data fusion techniques, streaming data from the shopfloor can be used by process mining to create process models showing what is really happening in the process. This than can be compared with the expected process, with this improvement is driven with real-time insight.
Mapping the data with the digital models give insight on the multiple levels of dimensions that influences product and process quality. Now 360° improvement with proactive insight is possible.
In particular, data with different characteristics have to be fused to provide a holistic data collection as an input for data analytics:
• Continuous data, like measurements from a motor current collected in a historian,
• Transactional data, like user actions recorded by a MES system and stored in a transactional database, and
• All kinds of other data provided in different file formats, like quality data of suppliers or detailed measurements of lab equipment.
Combining these data requires a good understanding how the different information is related, which is usually captured as genealogy information. A few challenges of data fusion originating from the different data characteristics are e.g.:
• Continuous data has multiple measurements, potentially multiple hundred measurements for a single product at a particular processing step, while in the MES there is only a single record. However, the continues measurements for the different processing steps may vary. A way of dealing with these different granularities is to apply analytics to describe the structure of the continuous signal in a few characteristic number per processing step.
• File based information of a lab equipment may have multiple files for a single test, in case the first test was compromised. A way of dealing with these different repetitions is to use the final test, but document in addition the number of re-tries.
To support the data fusion the models defined in the Smart Industrial Transformation Approach allow to contextualize the data such that the relations and the semantics of the different data is easier to understand and the integration can be executed much faster.
After the data has been fused, analytics can be used to answer business questions. One of the major questions is why quality or throughput is decreasing, which is answered by root-cause analysis. In this case, the fused data is used to determine the most influential parameters for the reduction in quality or throughput by using data mining algorithms. The process engineer is then able to indicate which of the found parameters should be investigated further. The overall approach is also often called deep learning.
Other typical questions are comparison analysis between plants, production lines, or similar products. In this case the focus is on the deviation of the outcome, like quality and throughput. However, the aim is to get a deeper understanding on where the difference originates from. Since the Smart Industrial Transformation Approach is based on models and provides the context of data, process mining techniques can be applied to analyze the actual production process and compare it with the engineered production process or with the actual production process of a different plant, line or comparable product.
In the figure below, the production process of two similar products has been visualized and compared with each other. All processing steps in light blue are common in both processes, while the red and green processing steps indicate the deviations. A process engineer now can see with this picture whether the deviations are well known and understood or whether it is worth to further investigate particular processing steps. Other users can now drill down to investigate depending on their need, from active behavior of the process, till material component and individual equipment level
The Smart Industrial Transformation Approach models allow to combine the results of the two steps since the identified parameters can be related to processing steps in the process and the interesting processing steps identified by process mining can be related to continuous process parameters
In the Smart Industrial Transformation Approach models are used in a specific way:
• Scenarios are modelled from different point of views like e.g. for a manufacturing process: the physical asset view, the machine view, the operator view and the process engineer view. These four views together describe the actual process best.
• Scenarios are modelled in the most detailed way and semi-automatically derive higher level views, thus views with lesser detail. These different views with varying level of detail are required for different groups of people. A manager just wants to see the high level picture, while a process engineer wants to see all details. By deriving the higher level views we ensure that the different levels of details are consistent with each other.
Now it is possible to visualize and have interactive stakeholder involvement providing right level of information at the right time.
Stakeholders are able to visualize the ‘As-Is’ and the ‘To-Be’ situation, and do scenario play and impact analysis to manage process and application migration.
Our assessment framework is uniquely tailored for Industry 4.0, Industrial Internet of Things, and Digital transformation. It is supported by a Smart Industrial Transformation approach, based on holistic modelling.
By using our unique Smart Industrial Transformation deployment framework we make sure that your deployment will be better, smarter and faster.
It is the only solution that is able to integrate and digitize the different dimensions of, Users, Suppliers and Customers, Processes, Applications, Physical assets, Infrastructures and Data, needed for best in class transformation deployments.
The basis is the ability to create digitized templates, which brings your templates alive and enables you to constantly control, manage the uncertainty and have maximal agility during your deployment journey.
The digitized transformation template is typically used to manage the deployment of:
Global (MES) applications;
IT-OT architecture in general as well as more specifically RAMI 4.0 (Reference Architecture Model Industrie 4.0);
Digitized System Architecture Transformation – Architecture and application deployment of OEM machines;
Our Smart Industrial Transformation based roadmap framework is a holistic modelled framework uniquely tailored for Industry 4.0, Industrial Internet of Things and Digital transformation.
It is the only solution that brings alive your roadmap by digitizing it. With this you are in constant control, able to manage the uncertainty and have maximal agility during the journey.
The roadmap framework is typically used to get insight and input:
• To align Users, Suppliers and Customers, Processes, Applications, Physical assets, Infrastructures and Data dimensions;
• To understand the impact and execution of your roadmap items;
• for insight on impacts of roadmap items;
• for your IT-OT (Information Technology – Operational Technology) Architecture;
• for roadmap agility;
By using our unique Smart Industrial Transformation architecture framework we make sure that your architecture will be at the life cycle management level to meet Industry 4.0. IIoT (Industrial Internet of Things) and Digital transformation requirements
It is the only solution that is able to integrate and digitize the different dimensions of, Users, Suppliers and Customers, Processes, Applications, Physical assets, Infrastructures and Data, needed for Industry 4.0 architecture. This brings your architecture alive, enabling you to constantly control, manage the uncertainty and have maximal agility during your transformation journey.
The architecture framework is typically used to design and manage:
IT-OT architecture in general, incl. impact analysis;
Specific RAMI 4.0 (Reference Architecture Model Industrie 4.0);
Digitized System Architecture Transformation – Architecture and application redesign of OEM machines;
Smart Manufacturing (data) architecture with advanced analytics capabilities;
We offer modelling services to be able to create digital formal models (digital twins) for Industry 4.0, II0T and Digital transformation. Those models are digital representations covering processes, applications, infrastructures, physical assets and contextualized data.
The modelling is based on de ArchiMate architecture language using our Models4Insight™, IP based Modelling & Insight solution platform, It enables you to design, create, enhance, manage, store and retrieve digitized integrated models giving a formal digital representation making you in control of your Industry 4.0, IIoT and Digital Transformation journey. It is offered as a free public version or private subscription based service.
Our mission is crisp and clear: Continuous delivery of insight for the millions of experts to make smarter, better and faster decisions that can be controlled and managed during the full lifecycle. Read more