Virtuaalinen käyttöönottoympäristö automaatiojärjestelmälle

Valmistavan teollisuuden kiristyvät vaatimukset suunnittelusta markkinoille -ajassa (engl. time-to-market), laadussa, kustannustehokkuudessa ja turvallisuudessa luovat paineita uusien toimintatapojen etsimisessä. Usein laitteiston ohjausalgoritmeja ei ole mahdollista testata todellisen laitteiston kanssa, vaan ainoaksi ennakoivaksi vaihtoehdoksi jää todellisen laitteiston virtuaalinen mallintaminen. Eräs uusista toimintavoista on virtuaalinen käyttöönotto, jossa tuotantolinja tai laitteisto mallinnetaan ja sen käyttäytymistä simuloidaan ohjausalgoritmien parantamista ja todentamista varten. Tämän diplomityön tavoitteena oli toteuttaa virtuaalinen käyttöönottoympäristö, jolla laitteiston 3D-mallinnettua virtuaalista mallia voidaan ohjata reaaliajassa todellisen laitteiston ohjauslaitteistolla. Käyttöönottoympäristön toteuttamisen lopullisena tavoitteena on tutkia, millaisia hyötyjä sillä voidaan saavuttaa Outotec (Finland) Oy:n automaatiojärjestelmien suunnittelussa ja käyttöönotossa kiristyvien vaatimusten täyttämiseksi. Työssä toteutetulla käyttöönottoympäristöllä pystytään simuloimaan 3D-mallinnetun laitteiston osan toimintaa reaaliajassa. Todellisen laitteiston ominaisuuksista määritettyjä vaatimuksia ei kustannussyistä täytetty, sillä ennen sitä haluttiin varmistua valitun alustan ominaisuuksista, toimivuudesta ja soveltuvuudesta. Toteutuksen katsotaan kuitenkin täyttävän pehmeän reaaliaikaisuuden kriteerin noin 40 ms aikatasolla ja 80 ms reaktioajalla. Toteutettu virtuaalinen käyttöönottoympäristö osoittautui toimivaksi ja soveltuvaksi, sekä sen todettiin tuovan potentiaalisia hyötyjä Outotec (Finland) Oy:lle, esimerkiksi kosketusnäyttöjen visualisoinnin parannus, hybridikäyttöönottomahdollisuus sekä automaatio-ohjauksien kehittäminen. Työn perusteella arvioidaan onko Outotec:lla tarvetta jatkaa valitulla alustalla todellisen laitteiston aikavaatimukset täyttävään reaaliaika-toteutukseen, jota työssä esitellään.

The HOSHIN KANRI TREE. Cross-Plant Lean Shopfloor Management

Shopfloor Management (SM) empowerment methodologies have traditionally focused on two aspects: goal achievement following rigid structures, such as SQDCME, or evolutional aspects of empowerment factors away from strategic goal achievement. Furthermore, SM Methodologies have been organized almost solely around the hierarchical structure of the organization, failing systematically to cope with the challenges that Industry 4.0 is facing. The latter include the growing complexity of value-stream networks, sustainable empowerment of the workforce (Learning Factory), an autonomous and intelligent process management (Smart Factory), the need to cope with the increasing complexity of value-stream networks (VSN) and the leadership paradigm shift to strategic alignment. This paper presents a novel Lean SM Method (LSM) called ?HOSHIN KANRI Tree? (HKT), which is based on standardization of the communication patterns among process owners (POs) by PDCA. The standardization of communication patterns by HKT technology should bring enormous benefits in value stream (VS) performance, speed of standardization and learning rates to the Industry 4.0 generation of organizations. These potential advantages of HKT are being tested at present in worldwide research.

A deep learning model for controlling the galvanizing process in a production line

In the industry of steelmaking, the process of galvanizing is a treatment which is applied to protect the steel from corrosion. The air knife effect (AKE) occurs when nozzles emit a steam of air on the surfaces of a steel strip to remove excess zinc from it. In our work we formalized the problem to control the AKE and we implemented, with the R&D dept.of MarcegagliaSPA, a DL model able to drive the AKE. We call it controller. It takes as input the tuple : a tuple of the physical conditions of the process line (t,h,s) with the target value of the zinc coating (c); and generates the expected tuple of (pres and dist) to drive the mechanical nozzles towards the (c). According to the requirements we designed the structure of the network. We collected and explored the data set of the historical data of the smart factory. Finally, we designed the loss function as sum of three components: the minimization between the coating addressed by the network and the target value we want to reach; and two weighted minimization components for both pressure and distance. In our solution we construct a second module, named coating net, to predict the coating of zinc resulting from the AKE when the conditions are applied to the prod. line. Its structure is made by a linear and a deep nonlinear “residual” component learned by empirical observations. The predictions made by the coating nets are used as ground truth in the loss function of the controller. By tuning the weights of the different components of the loss function, it is possible to train models with slightly different optimization purposes. In the tests we compared the regularization of different strategies with the standard one in condition of optimal estimation for both; the overall accuracy is ± 3 g/m^2 dal target for all of them. Lastly, we analyze how the controller modeled the current solutions with the new logic: the sub-optimal values of pres and dist can be optimize of 50% and 20%.

A hybrid measurement systems analysis and uncertainty of measurement approach for industrial measurement in the light controlled factory

The uncertainty of measurements must be quantified and considered in order to prove conformance with specifications and make other meaningful comparisons based on measurements. While there is a consistent methodology for the evaluation and expression of uncertainty within the metrology community industry frequently uses the alternative Measurement Systems Analysis methodology. This paper sets out to clarify the differences between uncertainty evaluation and MSA and presents a novel hybrid methodology for industrial measurement which enables a correct evaluation of measurement uncertainty while utilising the practical tools of MSA. In particular the use of Gage R&R ANOVA and Attribute Gage studies within a wider uncertainty evaluation framework is described. This enables in-line measurement data to be used to establish repeatability and reproducibility, without time consuming repeatability studies being carried out, while maintaining a complete consideration of all sources of uncertainty and therefore enabling conformance to be proven with a stated level of confidence. Such a rigorous approach to product verification will become increasingly important in the era of the Light Controlled Factory with metrology acting as the driving force to achieve the right first time and highly automated manufacture of high value large scale products such as aircraft, spacecraft and renewable power generation structures.

Virtual Learning Factory on VR-Supported Factory Planning

Part 13: Virtual Reality and Simulation

Designing a S2-Enterprise (Smart x Sensing) Reference Model

Part 11: Reference and Conceptual Models

Conceptual Reference Model for Virtual Factory: Potentials for Collaborative Business

Part 11: Reference and Conceptual Models

Smart Alerts: Development of Software to Optimize Data Monitoring

Dherte PM, Negrao MPG, Mori Neto S, Holzhacker R, Shimada V, Taberner P, Carmona MJC - Smart Alerts: Development of a Software to Optimize Data Monitoring. Background and objectives: Monitoring is useful for vital follow-ups and prevention, diagnosis, and treatment of several events in anesthesia. Although alarms can be useful in monitoring they can cause dangerous user`s desensitization. The objective of this study was to describe the development of specific software to integrate intraoperative monitoring parameters generating ""smart alerts"" that can help decision making, besides indicating possible diagnosis and treatment. Methods: A system that allowed flexibility in the definition of alerts, combining individual alarms of the parameters monitored to generate a more elaborated alert system was designed. After investigating a set of smart alerts, considered relevant in the surgical environment, a prototype was designed and evaluated, and additional suggestions were implemented in the final product. To verify the occurrence of smart alerts, the system underwent testing with data previously obtained during intraoperative monitoring of 64 patients. The system allows continuous analysis of monitored parameters, verifying the occurrence of smart alerts defined in the user interface. Results: With this system a potential 92% reduction in alarms was observed. We observed that in most situations that did not generate alerts individual alarms did not represent risk to the patient. Conclusions: Implementation of software can allow integration of the data monitored and generate information, such as possible diagnosis or interventions. An expressive potential reduction in the amount of alarms during surgery was observed. Information displayed by the system can be oftentimes more useful than analysis of isolated parameters.

Innovation in Queensland firms: implications for the smart State

The challenges in the business environment are forcing Australian firms to be innovative in all their efforts to serve customers. Reflecting this need there have been several innovation policy statements both at Federal and State government level aimed at encouraging innovation in Australian industry. In particular, the innovation policy statement launched by the Queensland government in the year 2000 primarily intends building a Sman State through innovation. During the last few decades the Australian government policy on innovation has emphasized support for industry R&D. However industry stakeholders demand a more firm-focused policy of innovation. Government efforts in this direction have been hindered by a lack of a consistent body of knowledge on innovation at the firm level. In particular the Australian literature focusing on firm level antecedents of innovation is limited and fragmented. This study examines the role of learning capabilities in innovation and competitive advantage. Based on a survey of manufacturing firms in Queensland the study finds that both technological and non·technological innovations lead to competitive advantage. The findings contribute to the theory competitive advantage and firm level antecedents of innovation. Implications for firm level innovation strategies and behaviour are discussed. In addition, the findings have important implications for Queensland government's current initiatives to build a Smart State through innovation.