Project

Automotive Production Engineering Unified Perspective based on Data Mining Methods and Virtual Factory Model

Goal: The scientific objective of the AutoUniMo project is a fusion between emerging research areas (RA) in engineering like Component Based Automation (CBA), Virtual Factories (VF) and advanced IT methods like Data Mining (DM) , Artificial Intelligence (AI) and Multi-Agent Systems (MAS). Researches will be conducted in Manufacturing Execution Systems (MES) applied in short series production, Advanced Driver Assistance Systems (ADAS) and control systems dedicated for energy efficient production in automotive.

Proper identification of patterns and data structures available in production systems will allow to find more efficient ways for converting raw materials into useful goods within given industrial production process. AutoUniMo consortium gathers academic and industrial partners for which modern methods used in production systems are the critical path of their activity. Industrial partner Continetal is recognized by drivers as a tire manufacturer, but few people know that it is also an important producer of automotive electronics. Conti Temic microelectronic GmbH (CONTI) is specialised in design of advanced sensing and control devices for automobile. CONTI cannot get a sustainable position on the automotive market without effective informatics system that supports the short series production. Industrial partner AIUT is SME company that supplies machines and systems for automotive production. AIUT cannot operate in a highly competitive environment without advanced engineering solutions which not only fulfil functional requirements of the customer but also ensure the efficient production. Nowadays, cheaper sources of raw materials and availability of cheaper labour cause that automotive production moves from Europe to the developing economies. European automotive manufacturers are beginning to lose their advantage. This causes negative impact on the European economy and reduces the number of employees associated with automotive industry. AutoUniMo academic partners will help to solve these problems by applying modern engineering and informatics methods that will support industrial partners in their critical paths defined above. Institute of Informatics, Silesian University of Technology (SUT) has advanced research activity in Data Mining and in Artificial Intelligence areas. Hochschule Ingolstadt, Faculty of Mechanical Engineering (HI) has large experience in the automotive industry, supported by many realised research projects with main focus on automotive industry. AutoUniMo consortium will assemble two European academia partners which conduct research on automotive engineering (HI) and informatics (SUT) with two European industrial partners with main focus in automotive. AutoUniMo consortium will assemble two European academia partners which conduct research on automotive engineering (HI) and informatics (SUT) with two European industrial partners with main focus in automotive area. Existing local research cooperation: SUT – AIUT and HI – CONTI will be expanded into international knowledge and expertise exchange SUT – CONTI and HI - AIUT which will able to fulfil knowledge gaps in complementary research areas. Although the main point of gravity will be automotive area but planned broad result dissemination activities will enable to use the output of AutUniMo’s methodologies and tools in other branches of European industry.

Methods: Automotive Production, Data Mining, Manufacturing Execution Systems, Virtual Factories, Component Based Automation, Multi Agent Systems, Advanced Driver Assistance Systems, Energy Efficiency

http://autounimo.aei.polsl.pl/

This project has received funding from the European Union’s Seventh Framework Programme for research, technological development and demonstration under grant agreement no 612207

Date: 1 October 2013 - 30 September 2017

Updates
0 new
1
Recommendations
0 new
0
Followers
0 new
14
Reads
1 new
309

Project log

Paweł Rybka
added a research item
The following paper presents advanced methods for evaluating the reliability of ADAS module readings, based on an analysis of the transient supply current. Changes in the transient current waveform occur due to environmental conditions and damage to a module's inner circuitry. Specific deviations in the waveforms may indicate a certain event – either internal or external. This paper presents how to successfully distinguish certain anomalies using artificial neural network-based classification algorithms without having to interfere with the module's internal circuitry. DOI: http://dx.doi.org/10.5755/j01.eie.24.3.20944
Adam Ziębiński
added 2 research items
This paper presents a test stand for the CAN-based systems that are used in automotive systems. The authors propose applying an Ethernet-based test system that supports the virtualisation of a CAN network. The proposed solution has many advantages compared to classical test beds that are based on dedicated CAN-PC interfaces: it allows the physical constraints associated with the number of interfaces that can be simultaneously connected to a tested system to be avoided, which enables the test time for parallel tests to be shortened; the high speed of Ethernet transmission allows for more frequent sampling of the messages that are transmitted by a CAN network (as the authors show in the experiment results section) and the cost of the proposed solution is much lower than the traditional lab-based dedicated CAN interfaces for PCs.
New cars can be equipped with many advanced safety solutions. Airbags, seatbelts and all of the essential passive safety parts are standard equipment. Now cars are often equipped with new advanced active safety systems that can prevent accidents. The functions of the Advanced Driver Assistance Systems are still growing. A review of the most popular available technologies used in ADAS and descriptions of their application areas are discussed in this paper.
Marek Drewniak
added 3 project references
Krzysztof Tokarz
added an update
Adam Ziębiński
added 2 research items
Advanced Driver Assistance Systems (ADAS) are essential parts for developing the autonomous vehicle concept. They cooperate with different on-board car equipment to make driving safe and comfortable. There are many ways to monitor their behaviour and assess their reliability. The presented solution combines the versatility of applications (it can be used with almost any kind of sensors), low cost (data acquisition using this method requires only a simple electronic circuit) and requires no adjustments of the sensor’s software or hardware. Using this type of analysis, one can determine the device’s family, find any over- and under-voltages that can damage the sensor or even detect two-way CAN communication malfunctions. Since the data acquired is complex (and can be troublesome during processing) – one of the best solutions is to cope with the problem by using a variety of neural networks.
This paper presents the concept of using embedded MEMS sensors position objects especially when the GPS signal is weak, e.g. in underground car parks, tunnels. Such an approach is important for controlling indoor objects or autonomous vehicles. The signals are acquired by a Raspberry Pi platform with external sensors such as an accelerometer, gyroscope and magnetometer. A self-propelled vehicle was used and several exemplary paths were designed for acquiring signals. It was proven that appropriate signal filtering allows a position to be determined with a small error at a constant velocity condition. Comparing filters such as the moving average, median, Savitzky-Golay and Hampel filters were investigated. Moreover, the system offers a high degree of accuracy in a short time for indoor hybrid positioning systems that also have video processing capabilities. The cyber-physical system can also be used with the existing infrastructure in a building, such as Wi-Fi access points and video cameras.
Flavian Meltzer
added a research item
For a decade, it has been officially known that the most cost-intensive part of a body-building project is software engineering. The reason for this is the fact that in the engineering process many different types of information from their respective tool chains must come together and be combined. This situation is intensified by the heterogeneous engineering tool landscape that makes it difficult to reuse existing data and information from finished engineering steps without resorting to a paper interface. For this reason, many representatives of the automotive industry came together to solve these problems which resulted in the AutomationML format. AutomationML is an independent data format that allows bridging the gap between the various engineering fields and tool chains, thereby improving the overall process. The goal of this article is to provide an insight into the currently defined AutomationML standard and its possibilities.
Rafał Cupek
added 5 research items
This document examines OData protocol as a new service oriented approach for distributed IT architectures. The main features of OData were compared with properties of the well-established solutions like: REST, DCOM and Java RMI. OData’s protocol was presented in the context of its application in Service-Oriented Architectures.
This document examines the OData protocol as a new service oriented approach for distributed IT architectures. The main features of OData were compared with properties of well-established solutions like: REST, DCOM and Java RMI. OData's protocol is presented in the context of its application in Service-Oriented Architectures.
Nowadays, Advanced Driver Assistance Systems (ADAS) support drivers of vehicles in emergency situations that are connected with vehicular traffic. They help to save people’s lives and minimise the losses in accidents. ADAS use information that is supported by a variety of sensors, which are responsible for tracking the vehicle’s surroundings. Unfortunately, the range of the sensors is limited to several dozen metres and even less in the case of obstacles. This shortens the time for a reaction and, therefore, there may not be enough time to avoid an accident. In order to overcome this drawback, vehicles have to share the information that is available in ADAS. The authors investigated different vehicle-to-vehicle communication possibilities. Based on an analysis of the state of the art, the authors present an original concept that is focused on applying the OPC UA (IEC 62541) communication protocol for services that correspond to the Internet of Vehicles concept.
Adam Ziębiński
added 2 research items
Cyber Physical Systems are often used in the automotive industry as embedded systems for constructing Advanced Driver Assistance Systems. Further development of current applications and the creation of new applications for vehicle and mobile platforms that are based on sensor fusion are essential for the future. While ADAS are used to actively participate in the controlling a vehicle, they can also be used to control mobile platforms in industry. In the article, the results of tests of different rates of data acquisition from Hall sensors to measure speed for mobile platform are presented. The purpose of the research was to determine the optimal platform parameter to indicate the refresh frequency in such a way that the measurements obtained from a Hall sensor will be reliable and will require less of the available computing power. Additionally, the results from investigations of the precise movement for a specified distance using a Hall sensor for a mobile platform are presented.
The problems of obstacle avoidance occur in many areas for autonomous vehicles. In automotive field, Advanced Driver Assistance Systems modules equipped with sensor fusion are used to resolve these problems. In the case of small mobile platforms, electronic sensors such as ultrasound, gyroscopes, magnetometers and encoders are commonly used. The data obtained from these sensors is measured and processed, which permits the development of automatic obstacle avoidance functions for mobile platforms. The information from these sensors is sufficient to detect obstacles, determine the distance to obstacles and prepare actions to avoid the obstacles. This paper presents the results of research on two obstacle avoidance algorithms that were prepared for small mobile platforms that take advantage of an ultrasonic sensor. The presented solutions are based on calculating the weights of the possible directions for obstacle avoidance and the geometric analysis of an obstacle.
Tomasz Jastrząb
added 2 research items
In the paper we present a novel method of wordnets’ data integration. The proposed method is based on the XML representation of wordnets content. In particular, we focus on the integration of VisDic-based documents representing the data of two Polish wordnets, i.e. plWordNet and Polnet. One of the key features of the method is that it is able to automatically identify and handle the discrepancies existing in the structure of the integrated documents. Apart from the method itself, we briefly discuss a C#-based implementation of the method. Finally, we present some statistical measures related to the data available before and after the integration process. The statistical comparison allows us to determine, among other things, the impact of particular wordnets on the integrated set of data.
In the paper we discuss the idea of ontology reuse as a way of fast prototyping of new concepts. In particular, we propose that instead of building a complete ontology describing certain concepts from the very beginning, it is possible and advisable to reuse existing resources. We claim that the available online resources such as Wikidata or wordnets can be used to provide some hints or even complete parts of ontologies aiding new concepts definition. As a proof of concept, we present the implementation of an extension to the Ontolis ontology editor. With this extension we are able to reuse the ontologies provided by Wikidata to define the concepts that have not been previously defined. As a preliminary evaluation of the extension, we compare the amount of work required to define selected concepts with and without the proposed ontology reuse method.
Adam Ziębiński
added 12 research items
The real time processing of sensors signal and real time response of control system is crucial for autonomous mobile platforms. One of the assumption in the project, which part is presented in this article, was the cost of the sensor and control system. That’s the reason, that Raspberry Pi platform has been chosen for this purpose. The article describes connection and performance testing performed on two different GPS and ultrasonic distance sensors, which are the part of Autonomous Mobile Platform in the AutoUniMo project. The results shows, that the URM37 V3.2 ultrasonic distance sensor is very reliable device with almost non-existent error in whole measuring range. While the much cheaper HC-SR04 is very easy to implement, thanks to its simple mode of operation but offers less accurate measurements. In case of GPS sensors, the GY-GPS6MV2 has proven to be more accurate than Digilent PmodGPS, so it will be chosen as main GPS sensor for the mobile platform.
Day-to-day everywhere in the world grows a tendency automate various areas of our everyday life. For many recent years worldwide companies compete with each other in developing a conception of fully automated, autonomous car. Such idea is now being analyzed and investigated by scientists at universities and engineers from automotive companies. This article describes a part of AutoUniMo project concerning importance and usage of different sensor modules in design and construction of autonomous mobile platform based on the Raspberry Pi with Linux operating system. The project consists of following modules – accelerometer, gyroscope, magnetometer, wheel encoder and dedicated Raspberry Pi HAT (Hardware Attached on Top) for power management.
The paper presents examples of the functionalities of the lidar that is used in the automotive industry for advanced driving assistance systems. Firstly, a brief overview of lidar technology and an introduction to communication that is built on a CAN bus is presented. Then, the lidar that was selected for the tests is described along with the principles of how it works and its startup conditions. Finally, a description of the experiment is presented along with the results.
Adam Ziębiński
added a project goal
The scientific objective of the AutoUniMo project is a fusion between emerging research areas (RA) in engineering like Component Based Automation (CBA), Virtual Factories (VF) and advanced IT methods like Data Mining (DM) , Artificial Intelligence (AI) and Multi-Agent Systems (MAS). Researches will be conducted in Manufacturing Execution Systems (MES) applied in short series production, Advanced Driver Assistance Systems (ADAS) and control systems dedicated for energy efficient production in automotive.
Proper identification of patterns and data structures available in production systems will allow to find more efficient ways for converting raw materials into useful goods within given industrial production process. AutoUniMo consortium gathers academic and industrial partners for which modern methods used in production systems are the critical path of their activity. Industrial partner Continetal is recognized by drivers as a tire manufacturer, but few people know that it is also an important producer of automotive electronics. Conti Temic microelectronic GmbH (CONTI) is specialised in design of advanced sensing and control devices for automobile. CONTI cannot get a sustainable position on the automotive market without effective informatics system that supports the short series production. Industrial partner AIUT is SME company that supplies machines and systems for automotive production. AIUT cannot operate in a highly competitive environment without advanced engineering solutions which not only fulfil functional requirements of the customer but also ensure the efficient production. Nowadays, cheaper sources of raw materials and availability of cheaper labour cause that automotive production moves from Europe to the developing economies. European automotive manufacturers are beginning to lose their advantage. This causes negative impact on the European economy and reduces the number of employees associated with automotive industry. AutoUniMo academic partners will help to solve these problems by applying modern engineering and informatics methods that will support industrial partners in their critical paths defined above. Institute of Informatics, Silesian University of Technology (SUT) has advanced research activity in Data Mining and in Artificial Intelligence areas. Hochschule Ingolstadt, Faculty of Mechanical Engineering (HI) has large experience in the automotive industry, supported by many realised research projects with main focus on automotive industry. AutoUniMo consortium will assemble two European academia partners which conduct research on automotive engineering (HI) and informatics (SUT) with two European industrial partners with main focus in automotive. AutoUniMo consortium will assemble two European academia partners which conduct research on automotive engineering (HI) and informatics (SUT) with two European industrial partners with main focus in automotive area. Existing local research cooperation: SUT – AIUT and HI – CONTI will be expanded into international knowledge and expertise exchange SUT – CONTI and HI - AIUT which will able to fulfil knowledge gaps in complementary research areas. Although the main point of gravity will be automotive area but planned broad result dissemination activities will enable to use the output of AutUniMo’s methodologies and tools in other branches of European industry.
Methods: Automotive Production, Data Mining, Manufacturing Execution Systems, Virtual Factories, Component Based Automation, Multi Agent Systems, Advanced Driver Assistance Systems, Energy Efficiency
This project has received funding from the European Union’s Seventh Framework Programme for research, technological development and demonstration under grant agreement no 612207