Condition monitoring in engine development

Condition monitoring in engine development

Condition monitoring in engine development

Expert: Michael Scharpf

Industry: Automotive & Engineering

Area: Production

Learn how to improve the long-term quality of engines in the automotive industry through effective condition monitoring.

OUR AI AND DATA SCIENCE Case studies:
EXPERIENCE FROM OVER 2,000 CUSTOMER PROJECTS

[Challenge]

Our customer from the automotive industry had the need to monitor the long-term quality of components in the area of fuel systems. Our task was to develop a concept for data analysis and validate a prototypical application to optimise the condition monitoring of the engine.

[Solution]

To validate the concept and optimise the data analysis, we consolidated the existing database queries and added more data. We extended the data analysis by adding more engines, the scope of which can be varied via an external control list. The optimised database queries and the extended data were then further developed into a fully automated ETL load path.

[Result]

The extended data enabled us to create vehicle life histories and analyse series-specific fault histories based on the long-term quality data. Our customer was able to improve the quality of the fuel systems and optimise the condition monitoring of the engine.

For the data analysis, we used data science methods to consolidate and extend the existing database queries. We used machine learning methods to automate the analysis and improve the results. The ETL load path was implemented using Apache Kafka and Apache Spark. By using these technologies, we were able to make the data analysis more effective and efficient.

Curious now? Let us show you what sets us apart from other companies and how we can help you achieve your goals.

Michael Scharpf - Key Account Manager

Your expert

Michael Scharpf | Sr. Principal Key Account Manager | Alexander Thamm GmbH

Machine learning workshop for a software manufacturer

Machine learning workshop for a software manufacturer

Machine learning workshop for a software manufacturer

Expert: Michael Scharpf

Industry: Automotive & Engineering

Area: Production

Unique Machine Learning Workshop for Software Vendors: Gain the knowledge and skills to revolutionise your data analytics and leave the competition behind.

OUR AI AND DATA SCIENCE Case studies:
EXPERIENCE FROM OVER 2,000 CUSTOMER PROJECTS

[Challenge]

Our customer, a renowned software house, was faced with the challenge of expanding the monitoring software of painting robots of a machine manufacturer in order to introduce an innovative component for the early detection of errors. In order to prove the functionality of this early detection within the framework of a proof of concept, it was crucial for the software manufacturer to develop functioning detection models.

[Solution]

Working closely with our company's data science team, a customised machine learning workshop was conducted to meet the client's specific requirements. In this workshop, meaningful variables for the fault patterns were developed using the existing log data, a process also known as feature engineering. By carefully selecting and preparing these variables, we were able to create a solid foundation for the model development.

In the next step, classification models were developed to effectively identify the error patterns. Different methods were applied and their performance was assessed using evaluative metrics. Our experts were thus able to identify the best models and derive specific recommendations for implementation. We worked closely with the software developers to provide them with clear instructions and guidelines for integrating the error detection component into the existing monitoring software.

[Result]

Thanks to the successful proof of concept, our customer was able to demonstrate the impressive performance of the developed component to its machine manufacturer. The precise detection models and robust evaluation of the processes delivered convincing results that strengthened confidence in the new early detection solution. Our customers were able to highlight the benefits of the improved defect detection for their painting robots, thus increasing the efficiency and quality of their processes.

In addition, the software developers received concrete instructions on how to implement the error detection component. This included detailed steps required to integrate the models into the existing software. Our comprehensive documentation and clear guidelines facilitated the developers' implementation and ensured a smooth integration of the new functionality.

With our expertise in data science and artificial intelligence, we were able to help the software house overcome their challenges in the area of error detection. Our machine learning workshop and the model developments based on it not only clarified the performance of the component, but also led to concrete recommendations for action for the implementation.

Our machine learning workshop is specifically designed to help companies implement data analytics and artificial intelligence into their business processes. By using relevant keywords, such as "machine learning workshop", and placing them strategically in the text, we optimise the content for search engines. This helps potential customers looking for data analytics and artificial intelligence solutions to find our company as a trustworthy partner.

If you want to optimise your business processes and benefit from the advantages of advanced data analysis and artificial intelligence, contact us. Our team is at your side with its expertise and commitment to make your projects a success.

Curious now? Let us show you what sets us apart from other companies and how we can help you achieve your goals.

Michael Scharpf - Key Account Manager

Your expert

Michael Scharpf | Sr. Principal Key Account Manager | Alexander Thamm GmbH

Data analytics training for an insurance company

Data analytics training for an insurance company

Data analytics training for an insurance company

Within the framework of a bilingual WBT, all employees are to be provided with basic knowledge in the area of data analytics.

Training of approx. 20,000 employees in two languages

*

Modules of the WBT can be carried out independently of each other and are reusable

Employees have a basic understanding of data analytics and strive for deeper knowledge development along the curriculum

Challenge

A global reinsurer wants to introduce all employees to the topic of data analytics in the reinsurance sector and thus contribute to the digital transformation. The level of knowledge and practical experience of the employees in the area of data is very heterogeneous.

Solution

A customised curriculum for data analytics is designed with corresponding development stages. A web-based training (WBT) serves as a basic course to familiarise as many employees as possible with data analytics as a topic and to bring it into context with their everyday work. Industry-related examples and varied interactions during the transfer of knowledge maximise the didactic transfer online. The topics are divided into 10 flexible modules.

Result

A 90-minute web-based training on data analytics in the insurance/reinsurance sector delivers easy-to-understand data analytics content in a general context and in relation to their everyday work. Future training elements of the curriculum will build on the basic WBT.

Are you interested in your own use cases?

Challenge

An automotive company would like to visualise various market-specific data in order to create a Competitive analysis for the US market.

Solution

There will be a interactive and Flexible application, including of different maps with two different views implemented.

Result

Relevant markets are identifies, analyses and visualises. The dealer or the respective sales department have the possibility to compare the direct competition with their own product and to visualise the relevant data.

Our Case Studies

- Get even more detailed insights into our customer projects -

Smart cooking with Thermomix

Smart cooking with the Thermomix

Download
Case Study AI at Munich Re

Data Operations at Munich Re

Download

Data & AI Knowledge

Creating added value from data & AI together

Blog

Discover professional articles on Data & AI as well as the latest industry news.

Webinars

Dive into our Best Practices and Industry Exchanges. Discover new dates and recordings of past webinars.

Whitepaper

Learn more about the use of Data & AI in your industry with our white papers, case studies and research.

Ongoing assortment analysis through a web application in the tool trade

Ongoing assortment analysis through a web application in the tool trade

Ongoing assortment analysis through a web application in the tool trade

With the help of an interactive analysis tool, the assortment adjustment process of a tool dealer could be significantly simplified and accelerated.

!
The complex process of assortment cleansing can be carried out within a few minutes
Z

The prototype combines the quality of heterogeneous demand signals from different markets

The prototype combines the quality of heterogeneous demand signals from different markets

Challenge

The constantly growing assortment of a tool retailer must be regularly reviewed with regard to various criteria. These include, for example, the sorting out of products with low sales and restrictions on storage space and advertising space. There are many interdependencies between the individual products that must be taken into account when streamlining the assortment.

Solution

The relevant information on the product range is presented to the user simply and clearly in a web application. Various criteria and business logics for assortment adjustment can be activated via sliders and check boxes and their influence tested.

Result

With the help of the solution, the assortment adjustment can be reduced to a few minutes. The process can be carried out completely in the web application and there is no longer any need to create Excel evaluations, for example.

Are you interested in your own use cases?

Challenge

An automotive company would like to visualise various market-specific data in order to create a Competitive analysis for the US market.

Solution

There will be a interactive and Flexible application, including of different maps with two different views implemented.

Result

Relevant markets are identifies, analyses and visualises. The dealer or the respective sales department have the possibility to compare the direct competition with their own product and to visualise the relevant data.

Our Case Studies

- Get even more detailed insights into our customer projects -

Smart cooking with Thermomix

Smart cooking with the Thermomix

Download
Case Study AI at Munich Re

Data Operations at Munich Re

Download

Data & AI Knowledge

Creating added value from data & AI together

Blog

Discover professional articles on Data & AI as well as the latest industry news.

Webinars

Dive into our Best Practices and Industry Exchanges. Discover new dates and recordings of past webinars.

Whitepaper

Learn more about the use of Data & AI in your industry with our white papers, case studies and research.

Optimisation of production in the textile sector

Optimisation of production in the textile sector

Optimisation of production in the textile sector

Recommending production volumes by assessing the risk of demand signals in high volatile markets in the fashion industry.

!

The total quantity for the production of items could be increased by 43 % without achieving a higher residual risk than before.

Z

The prototype combines the quality of heterogeneous demand signals from different markets

h
The Level Loading prototype is embedded in a well-documented R package

Challenge

A German fashion manufacturer and retailer has to cope with the dynamic demand for its items in the highly volatile fashion industry. In the fashion industry, volatile demand is an even bigger problem due to comparably high production and transport lead times. The financial risk of overproduction is to be limited to 1%. Demand signals from different markets that differ in forecasting quality are to be integrated.

Solution

Low-risk items are identified that have a high probability of future actual orders and recommend an early production start. By bringing forward the production of safe items, the freed-up factory capacity could be used to produce risky items later, when demand signals are more reliable. Machine learning algorithms are applied using historical demand signals, production quantities and item attributes.

Result

A developed R-package is available that recommends specific items and corresponding quantities for all factories by assessing their individual risks and calculating a portion of the original demand signal that is covered with a high degree of certainty.

Are you interested in your own use cases?

Challenge

An automotive company would like to visualise various market-specific data in order to create a Competitive analysis for the US market.

Solution

There will be a interactive and Flexible application, including of different maps with two different views implemented.

Result

Relevant markets are identifies, analyses and visualises. The dealer or the respective sales department have the possibility to compare the direct competition with their own product and to visualise the relevant data.

Our Case Studies

- Get even more detailed insights into our customer projects -

Smart cooking with Thermomix

Smart cooking with the Thermomix

Download
Case Study AI at Munich Re

Data Operations at Munich Re

Download

Data & AI Knowledge

Creating added value from data & AI together

Blog

Discover professional articles on Data & AI as well as the latest industry news.

Webinars

Dive into our Best Practices and Industry Exchanges. Discover new dates and recordings of past webinars.

Whitepaper

Learn more about the use of Data & AI in your industry with our white papers, case studies and research.