4
Page 1 GreyLetter Series 6 Issue 11 September 2018 In This Issue Page 1 APRIL Group seeks to improve customer service Biofilm to improve BOPP production planning Page 2 IOT and its importance Page 3 Spotlight on Fehmi Hüdayioğlu, Group IT Manager Kipaş Holding Page 4 Greycon previews machine learning APRIL Group seeks to improve customer service Greycon was recently appointed by the APRIL Group, one of the largest, most technologically advanced and efficient makers of pulp and paper products in the world, to further optimize its sales and operations planning, by integrating Greycon sales and operations solution “opt-Studio” with APRIL’s Enterprise Resource Planning and Manufacturing Execution Systems. Greycon worked together with the APRIL Group and Accenture to deliver this solution. Praveen Singhavi, President, APRIL Group, said: “In order to continue to meet customer demand and deliver high levels of customer service, we have integrated opt-Studio with our existing solutions. opt-Studio has improved end-to- end visibility of our sales orders, while being able to better optimize paper production (block planning) and finishing area scheduling.” Vassilis Gkamouras, Senior Consultant at Greycon said: “APRIL Group’s pulp mill in Kerinci is the world’s largest. The project was divided in three phased roll-outs to enable quick deployment of capabilities and took 14 months to complete.” “The roll-out required expertise in global project management, change management, supply chain enablement and systems integration. The project was delivered on-time, in-full and within budget due to excellent team work between the partners involved.” Biofilm to improve BOPP production planning Greycon won new business with BOPP Film Manufacturer, Biofilm. Greycon will be implementing X-Trim at Biofilm’s facilities in Mexico and Colombia. Biofilm is a major player in the international BOPP Film market. Over the years, Biofilm has added to its product lines by increasing the number of manufacturing sites and capacity thus ensuring a need for a powerful trim optimisation system by Greycon. Greycon’s presence in the plastic film industries has grown tremendously, with the realisation that Greycon’s solutions provide a competitive edge and a return-on-investment that is measured in months for both bubble and conventional line processes. Greycon’s advanced trim system will bring numerous benefits to Biofilm including: increased production throughput (at primary lines and metallizers), reduced waste, improved use of inventory (trim around faults, consume semi-finished stock, and reduced inventory levels due to better trim planning). Jeronimo Alvarez, Senior Consultant at Greycon commented: “We are very pleased to announce this new partnership with Biofilm and look forward to starting the project with them. We are continuously striving to improve our solutions and ensure our clients receive the best ROI. Winning new business like Biofilm and working on new projects will support the further development of our highly-focussed software.”

In This Issue GreyLetter APRIL Group seeks to …...Biofilm is a major player in the international BOPP Film market. Over the years, Biofilm has added to its product lines by increasing

  • Upload
    others

  • View
    1

  • Download
    0

Embed Size (px)

Citation preview

Page 1: In This Issue GreyLetter APRIL Group seeks to …...Biofilm is a major player in the international BOPP Film market. Over the years, Biofilm has added to its product lines by increasing

Page 1

GreyLetter Series 6 Issue 11 September 2018

In This Issue

Page 1 APRIL Group seeks to improve

customer service Biofilm to improve BOPP

production planning

Page 2 IOT and its importance

Page 3 Spotlight on Fehmi Hüdayioğlu, Group

IT Manager Kipaş Holding

Page 4 Greycon previews machine learning

APRIL Group seeks to improve customer serviceGreycon was recently appointed by the APRIL Group, one of the largest, most technologically advanced and efficient makers of pulp and paper products in the world, to further optimize its sales and operations planning, by integrating Greycon sales and operations solution “opt-Studio” with APRIL’s Enterprise Resource Planning and Manufacturing Execution Systems. Greycon worked together with the APRIL Group and Accenture to deliver this solution.

Praveen Singhavi, President, APRIL Group, said: “In order to continue to meet customer demand and deliver high levels of customer service, we have integrated opt-Studio with our existing solutions. opt-Studio has improved end-to-end visibility of our sales orders, while being able to better optimize paper production (block planning) and finishing area scheduling.”

Vassilis Gkamouras, Senior Consultant at Greycon said: “APRIL Group’s pulp mill in Kerinci is the world’s largest. The project was divided in three phased roll-outs to enable quick deployment of capabilities and took 14 months to complete.”

“The roll-out required expertise in global project management, change management, supply chain enablement and systems integration. The project was delivered on-time, in-full and within budget due to excellent team work between the partners involved.”

Biofilm to improve BOPP production planning Greycon won new business with BOPP Film Manufacturer, Biofilm. Greycon will be implementing X-Trim at Biofilm’s facilities in Mexico and Colombia.

Biofilm is a major player in the international BOPP Film market. Over the years, Biofilm has added to its product lines by increasing the number of manufacturing sites and capacity thus ensuring a need for a powerful trim optimisation system by Greycon.

Greycon’s presence in the plastic film industries has grown tremendously, with the realisation that Greycon’s solutions provide

a competitive edge and a return-on-investment that is measured in months for both bubble and conventional line processes.

Greycon’s advanced trim system will bring numerous benefits to Biofilm including: increased production throughput (at primary lines and metallizers), reduced waste, improved use of inventory (trim around faults, consume semi-finished stock, and reduced inventory levels due to better trim planning).

Jeronimo Alvarez, Senior Consultant at Greycon commented: “We are very pleased to announce this new partnership with Biofilm and look forward to starting the project with them. We are continuously striving to improve our solutions and ensure our clients receive the best ROI. Winning new business like Biofilm and working on new projects will support the further development of our highly-focussed software.”

Page 2: In This Issue GreyLetter APRIL Group seeks to …...Biofilm is a major player in the international BOPP Film market. Over the years, Biofilm has added to its product lines by increasing

Page 2

IoT Greycon’s Vassilis Gkamouras presented at Asian Paper Conference, Bangkok

The growth of IoT is surprising, starting in 2009 when more devices (objects) were connected to the Internet or between them than the number of people living on earth. It is predicted that by 2020 50 billion devices will be connected. The number of connected devices will be around 6.6 devices per person.

Internet of Things (IoT) is the communication of anyTHING with another device via the Internet through a cloud based data storage provider for the purpose of sharing information. Human intervention for the information exchange is optional.

IoT essential technologies for manufacturing

Many new technologies fall under the IoT umbrella:

• Real Time, Big Data Analytics: The information collected by all IoT “things” will populate huge volumes of data, creating problems of scale. Machine learning and Artificial Intelligence (AI) will be employed to identify patterns and feedback dynamically to modify machine settings and parameters to achieve the target output quantity and quality. Real time analysis of data streams will be needed and new tools such as high-volume event stream platforms with the ability to operate on new data types and new architectures where analytics is distributed throughout the network of things will be created.

• Device Management: Management and monitoring will be required for all smart sensors (“things”) to find out if they are alive and/or connected, checking software and firmware updates, reporting, etc. Platforms managing and monitoring thousands of connected devices over wireless or cellular networks will be needed.

• Low-Power, Short-Range Networks: Many more objects will be using wireless networks, which could create noise and interference issues. Networks need to be of low bandwidth and high connection density because of the increased number of devices which will be connected to the network. IoT networking technologies will focus on short range (tens to hundreds of metres), long battery life (years), relatively low bandwidth, low endpoint cost and medium to high density (hundreds of adjacent devices).

• Processors: Low-end, 8-bit microcontrollers will dominate the IoT through 2019 at least, implying that many IoT devices will be extremely simple and incapable of running an operating system or performing sophisticated functions.

• Operating Systems: Traditional operating systems consume too much power, need fast processors and too much memory for IoT devices of the future. Embedded operating systems will emerge, probably from open-source projects.

IoT’s effect on the design of applications for the shop floor

Security technologies will evolve to protect IoT devices and platforms from both information attacks and physical tampering. Communications will need to be encrypted to address new challenges such as impersonating “things” or denial-of-sleep attacks that drain batteries. Critical

applications such as software managing the equipment which runs the shop-floor of a manufacturing plant will not be accepted with the current security standards. Security is a key inhibitor for IoT technologies.

Devices on the shop floor must make quick and smart decisions based on data they acquire constantly whilst also communicating with each other. Does this lead to a flat organisation where all devices are on one level and ERP on top, orchestrating the production? Our estimation is technology is not yet ready for self-autonomous and self-directed cells (“things”) sending meaningful aggregated messages to ERP without exceeding the required volume and eliminating the useless information in each message.

The systems architecture where different devices talk to each other using a Data Bus will still be used. This enables meaningful data to flow among the different devices horizontally, but also to have the right aggregation level enabling only important information to reach higher levels of the information hierarchy.

The customer intentions will be recorded and travel across the supply chain much faster than currently. Companies looking to move forward with these technologies will benefit from the ability to adjust production targets. Fast-changing customer requirements must be met without decreasing output quality. Software in Level 4 (Advanced Planning Solutions) and Level 3 (Manufacturing Execution Systems) will be more important. Nimble and issue free communication of the production plan from APS to MES will be needed. Low volume of quality defects and stoppages of equipment will be achieved because of IoT technologies, allowing users to optimise performance and uncover the hidden capacities of existing production lines and enabling machinery to work with a higher Overall Equipment Effectiveness (OEE). MES will need to communicate seamlessly with APS when defective production happens in order to re-plan, minimise the waste and send the new plan to production.

Bottom line

IoT deployment demands a wide range of new technologies and skills that many organisations have yet to master. It is still a very immature domain with many software vendors claiming IoT solutions but none cover the new key technology areas.

Greycon believes its award-winning planning software opt-Studio and X-Trim that integrate seamlessly with Greycon’s MES, GreyconMill, will enable these IoT benefits. Greycon evolves to match the needs of the changing future. Recent additions to its offering include GreyconMill’s Historian and Machine Learning modules.

Page 3: In This Issue GreyLetter APRIL Group seeks to …...Biofilm is a major player in the international BOPP Film market. Over the years, Biofilm has added to its product lines by increasing

Page 3

Spotlight Fehmi Hüdayioğlu Group IT Manager Kipaş Holding

Fehmi Hüdayioğlu is Group IT Manager at Kipaş Holding. He joined the company in 2006 after qualifying as an industrial engineer at Bosphorus (Bogazici) University and working as an IT consultant for six years developing IT software for financial institutions such as DekaBank and Allianz in Frankfurt, Germany.

Born in Kahramanmaras, Turkey, when Fehmi returned to his home town to join Kipaş Holding in 2006, the company was operating only in the textile industry and its capacity was one third of what it produces today.

Kipaş Kağıt A.Ş started as a joint venture of Kipas Holding and Erdem Tekstil in 2011 and is committed to produce high-quality container board paper from waste paper by employing best-of-breed manufacturing technologies, human resources and ethical values inherited from our founders.

The paper industry is one of the main sectors in which the company has operations. In addition to the paper business, it has cement, textile and energy businesses where it owns one of the biggest companies in each sector in Turkey. Today Kipaş Holding is one of the fastest growing group of companies in Turkey.

The Kipaş Kağıt paper factory is located in Kahramanmaras with a capacity of 450.000 Tonnes annually, producing fluting, testliner and opticraft papers between 70 and 200 g/m2. It saves 6.000 hectares of forest by producing 425.000 tonnes of paper from 100% recycled waste paper annually. One of its commitments is to run a sustainable, ethical, socially responsible business, which it can proudly hand over to generations yet to come.

Heading up the group’s IT, Fehmi typically spends about 4-5 hours a week for Kipaş Kağıt addressing solution architecture issues, IT strategy, project development and likewise. He is not involved much in daily operations and only deals with escalated problems.

Home life

Fehmi has three children, two young boys and a baby girl. In his free time, Fehmi enjoys spending time on his land where he has walnut trees and hachiya trees, as well as hiking and barbecues.

Working with Greycon

“We chose Greycon from a list of MES solution providers while the factory was being erected. Thus Greycon’s X-Trim, opt-Studio and GreyconMill software was used from day one as we started production.

“Because of the expertise of our and Greycon’s teams, the latest technologies used in the factory and a timely project plan, we didn’t experience any major challenges. We have integrated our ERP system (MS AX) with Greycon through established Greycon interfaces; while Greycon is integrated with various machine automation systems (such as Metso, Kone, QCS etc.).”

Fehmi Hüdayioğlu added: “We have special thanks to Mr Armando, Mr Abder and Greycon team for its attitude while running the project.”

The future

A new paper factory with a capacity of 720.000 Tonnes annually is undergoing in Söke. The production is planned to start in early 2020. A new corrugated factory is about to start production in this month (September 2018). The team is now currently busy building its systems.

The roots of Kipas Holding date back to Kahramanmaras Iplik Pamuk A.S. yarn manufacturing company founded in 1984. Under the guidance of its industrial experience of nearly 35 years, Kipas Holding bases its primary mission on high-quality production, efficient and well-orchestrated human resources, unconditional customer satisfaction, respect to the environment and human, investing in advanced technologies and technical innovation, and operational dynamism.

Page 4: In This Issue GreyLetter APRIL Group seeks to …...Biofilm is a major player in the international BOPP Film market. Over the years, Biofilm has added to its product lines by increasing

Page 4

Thank you for reading, if you have any comments or questions regarding this current newsletter or future editions please do not hesitate to contact us.

Greycon Ltd, 7 Calico House, Plantation Wharf, York Road, SW11 3TN.

+44 207 978 0700 | [email protected] | www.greycon.com

Greycon previews machine learning Greycon has introduced its first machine learning module aimed at reducing defects before they happen. Improvement in defect rates help lower production costs and delivery times, and improve efficiency. Greycon’s first machine learning pilot obtained data from one of its existing clients and 70% of the jumbos classified as faulty were predicted successfully by the algorithm.

Machine learning is a subset of artificial intelligence in the field of computer science that often uses statistical techniques to give computers the ability to “learn” from data, without being explicitly programmed.

GreyconMill, Greycon’s industry specific manufacturing execution system (MES) records production and the associated quality test results. Starting with version 3.4 released in July 2018, GreyconMill now includes a lightweight data historian tool that captures all the signals from the machinery.

Peter Purnell, GreyconMill Product Manager said: “The collection and storage of this information presents an obvious opportunity to use machine learning to try and predict the quality of the item being produced, while it is being produced, based on all the historical data available. The machine learning algorithm we used produces a percentage chance of the current item being of low quality. If this probability goes beyond a configurable threshold, GreyconMill notifies operators with an alarm event.”

When a machine learning profile is configured, a dashboard is configured automatically in the Historian to show the signals the machine learning algorithm is monitoring. This can be viewed from within GreyconMill that enables the operators to determine what may be causing the problem quickly.

Greycon has developed five different machine learning algorithms available for use, and each model configured can be trained on the Historian data to determine which model gives the best results. The five algorithms include: Decision Tree; KNN; Linear Regression; Logarithmic Regression and Random Forest

“When a model has been trained, a probability curve is produced showing where the alarm threshold should be set to achieve the best results. We can also see the most relevant signals and switch their use on and off, to experiment with getting the most optimal prediction.

“The frequency of training can also be set along with the percentage of the data to be used for training. Usually this percentage is set to 70% and the remaining 30% is used to validate the model and give a prediction accuracy. The training frequency is a delicate balance between ensuring the model is working on up-to-date data and server resources.

“Our pilot’s prediction rating of 70% is a very promising start and even without any further development the model will improve over time as it continues to learn. We used a year’s worth of machine signals and quality results.

“Some models give a true or false classification while others give a probability return. One such measure of accuracy for this probability is the AUROC or Area Under the Receiver Operating Characteristic (ROC) curve. It plots sensitivity, or probability of detection, on the Y-axis and the False Positive Rate, or probability of a false alarm, on the X-axis. The higher the ROC curve is from the diagonal, the larger the AUROC resulting in a more accurate model.

“We have trained models using all five of the available algorithms and found the best result resulted from the RevoScaler Random Forest algorithm - this model yielded an AUROC of 0.73.

“Developing and testing this new functionality has been rewarding and we are excited about the future development of this and other functionality. If you have an area you feel would benefit from this, please get in touch and we can work with you to create a solution,” Purnell said.