Operations & Maintenance

Youtube search... ...Google search

• Case Studies
• AI for Predictive Maintenance Applications in Industry – Examining 5 Use Cases | Pamela Bump - Techemergence
• Industrial AI Applications – How Time Series and Sensor Data Improve Processes | Daniel Faggella - Techemergence
• Deloitte Consulting takes aim at artificial intelligence (AI) software tools for predictive maintenance | Military/Aerospace Electronics ...to build the Joint Common Foundation (JCF) artificial intelligence development environment for the Joint Artificial Intelligence Center (JAIC).

Artificial Intelligence for Predictive Maintenance Case Study - Blair Fraser, Lakeside ARC Advisory Group is the leading technology research and advisory firm for industry, infrastructure and cities. Our coverage of technology and trends extends from business systems to product and asset lifecycle management, Industrial IoT, Industry 4.0, supply chain management, operations management, energy optimization and automation systems. Our analysts and consultants have the industry knowledge and the first-hand experience to help find the best answers to the complex business issues facing organizations today. Contact us: https://www.arcweb.com/about/contact-us

SAP Predictive Maintenance and Service learn how SAP Predictive Maintenance and Service can help reduce maintenance cost, increase asset availability, improve customer satisfaction and generate new service revenue.

Predictive Maintenance Using Recurrent Neural Network (RNN)s AnacondaCon 2018. Justin Brandenburg. The idea behind predictive maintenance is that the failure patterns of various types of equipment are predictable. If an organization can accurately predict when a piece of hardware will fail, and replace that component before it fails, it can achieve much higher levels of operational efficiency. With many devices now including sensor data and other components that send diagnosis reports, predictive maintenance using big data is increasingly accurate and effective. In this case, how can we enhance our data monitoring to predict the next event? This talk will present an actual use case in the IoT industry 4.0 space. Justin will present an entire workflow of data ingestion, bulk ETL, data exploration, model training, testing, and deployment in a real time streaming architecture that can scale. He will demonstrate how he used Anaconda Python 3.5 and Pyspark 2.1.0 to wrangle data and train a recurrent neural network to predict whether the next event in a real time stream indicated that maintenance was required.

Predictive Maintenance & Monitoring using Machine Learning: Demo & Case study (Cloud Next '18) Learn how to build advanced predictive maintenance solution. Learn what is predictive monitoring and new scenarios you can unlock for competitive advantage. MLAI223 Event schedule → http://g.co/next18 Watch more Machine Learning & AI sessions here → http://bit.ly/2zGKfcg Next ‘18 All Sessions playlist → http://bit.ly/Allsessions Subscribe to the Google Cloud channel! → http://bit.ly/NextSub

Machine Learning for Maintenance We’re putting ideas like machine learning for maintenance to work across our operations to minimize unplanned maintenance, reduce overall maintenance costs and extend equipment life. Through our partnership with Google Cloud and Pythian, we are unlocking new insights from millions of data points we collect to predict issues that were previously unpredictable.

AI: The Future Of Intelligent Maintenance Huawei is leading the development of intelligent maintenance with Robust Network Service. With over 20 projects going on around the world, telecom operators are benefitting from a range of #AI powered maintenance solutions. This video highlights some of the capabilities and benefits of AI prediction maintenance to the telecom industry.

Downer Australia: Transforming train maintenance with AI Downer, a company with over 100 years’ rail experience, is using AI to make sense of operational data and put it into the hands of the workers that need it. Find out how this Australian heavy industry company is working together with Microsoft to support the smooth delivery of Waratah commuter services across Sydney.

Predictive Maintenance and Monitoring using AI and Machine Learning Learn and grow with more BrightTALK webinars and Talks on Artificial Intelligence right here: http://bit.ly/2WNPRfd In this webinar, we will showcase how Google Cloud Platform and its Big Data processing, IOT sensor connectivity and TensorFlow based state of the art machine learning can be used to predict failures and more importantly extend the life of the production equipment leading to break through innovation in production automation and significantly improving productivity and manufacturing flexibility. About the speaker: Salil Amonkar, Global Head of Manufacturing and Ai-ML Practice, Pluto7 Thought Leadership in Digital Business Transformation, Cloud and Saas Solution, Data driven Analytics, Value Chain/Supply Chain and Ai and Machine Learning Overall 25+ years expertise in innovative business transformation services for Value Chain/Supply Chain and Manufacturing, CPG, High Technology and related Industries. Implemented solutions leveraging multiple technologies, Cloud, SaaS, Hybrid architectures leveraging advanced and predictive analytics using data sciences, AI and machine learning for Sales and Marketing, Services, Quote to Cash and Supply Chain. Have led several business transformational initiatives for Large Enterprise customers such as ABinBev(Anheuser Busch) Cisco, General Electric, IBM, Vodafone, General Motors, Tata Motors and many others. Certified Google Professional-Data Engineer

Predictive maintenance & AI in manufacturing leads to new risk opportunities What are the new risks that come with insuring predictive maintenance systems in manufacturing industry? Will AI end the role of engineers? And how can companies save costs when buying a predictive maintenance system? Watch the second in the Swiss Re Institute Spotlights webinar series produced with Swiss Re Corporate Solutions, where these topics were covered by leading experts. Please see below Deep learning and artificial intelligence for predictive maintenance applications - Olga Fink, SNSF Professor for Intelligent Maintenance Systems, ETH Zurich Predictive maintenance from a risk engineering perspective - André Kreul, Senior Risk Engineer Property, Swiss Re Corporate Solutions Moderated by Daniel Andris - Head Risk Engineering Services Casualty, Swiss Re Corporate Solutions

Predictive Maintenance Manufacturers of aircraft, engines, propellers and appliances have traditionally called for performing preventive maintenance on a fixed timetable. A prime example is engine and propeller TBOs. More recently, this time-based approach has given way to condition-based preventive maintenance based on regular repetitive inspections. Now we're beginning to see this inspection-driven approach giving way to predictive maintenance based on analysis of data from sensors installed on the aircraft and engine. In this webinar, Mike Busch A&P/IA discusses this latest trend and how its starting to trickle down to owner-flown piston GA. Savvy Aviation offers Professional Maintenance Services to owners of General Aviation aircraft, such as: SavvyMx (Professional Maintenance Management), SavvyQA (Expert Consulting), SavvyPrebuy, SavvyAnalysis (Engine Data Analysis) and Breakdown Assistance. Savvy also publishes a monthly newsletter with lots of interesting information for the general aviation enthusiast; subscribe to it at http://www.savvyaviation.com/home/ge.... For more information, visit us at http://savvyaviation.com. This webinar was hosted by the Experimental Aircraft Association (EAA).

AWS re:Invent 2019: Combining IoT and machine learning for predictive maintenance (IOT309-R1) Predictive maintenance captures the state of your devices to identify potential breakdowns before they impact operations, often resulting in an increase in equipment life span. In this session, learn how to progress your IoT journey and move from reactive to proactive with Amazon AWS IoT services and AWS machine-learning services. We also teach you how you can train ML models in the cloud and infer at the edge to predict problems faster.

Webinar: AI Predictive Maintenance - Empowering Your Remote Operations Our CEO and Founder, Trevor Bloch, explores how AI Predictive Analytics can be applied to critical industrial infrastructure, to assist with reduced personal due to COVID-19 and provides an opportunity for significant maintenance savings which are critical to every business in the current economic climate. The webinar also includes an 'under the hood' look at the VROC platform.

Practical Machine Learning for Predictive Maintenance Simon Xu

Beyond Predictive Maintenance – The Art Of The Possible With IoT | #IOTSWC19 IoT is fundamentally transforming how we live, work and play. As companies begin to move past the now well-trodden path of initial use cases in IoT such as predictive maintenance, they are beginning to harness the power of sensor-enabled, real-world data to reimagine why, how, and where they deploy IoT- and ultimately, how they make money from it. Lessons from these trailblazers illustrate that success lies in focusing not just on the technology, but more holistically, on a true transformation of the business. In this session we will cover novel IoT use cases and critical ingredients for success in enterprise IoT initiatives. The IoT Solutions World Congress is the leading international event that links the Internet of Things with industry. For more information visit http://www.iotsworldcongress.com/

Predictive Maintenance at the Dutch Railways (Ivo Everts) Ivo Everts, a data driver at GoDataDriven, talks about how at the Dutch Railways, we are collecting 10s of billions sensor measurements coming from the train fleet and railroad every year. We use these data to conduct predictive maintenance, such as predicting failure of the train axle bearings and detecting air leakage in the train braking pipes. This is extremely useful, as these failures are notoriously difficult to detect during regular maintenance, while occurring frequently and causing severe delays, damage to material and reputy, and costs.

"Aircraft predictive maintenance using Python/ML" - Amar Verma (Kiwi Pycon X) Amar Verma Applied machine learning for predictive maintenance (PdM) with objectives to reduce aircraft downtime & in-workshop costs "Aircraft engines must be serviced, overhauled and examined on a very regular basis. This is driven by several factors, such as the total flying hours, on-ground taxi time, time from last overhaul, parts with limited life cycle, FAA bulletins & advisories, as well as for issues reported by sensors, ground crew & flight deck. In case of more than one engines on the aircraft, most possibly the engines are non-coordinated in their maintenance requirements. This is very obvious as the engines could be maintained, installed on separate occasions. Whenever an aircraft engine is needed to be serviced, it causes direct impact to cashflows due to some of these factors: plane need to be grounded if alternative engine not available engine maintenance is delayed due to parts not available * specifically skilled engineer not available workshop space not available * Aircrafts (generally) use more than one engine, so the negative impact is amplified * Aircraft's flying schedule can be impacted causing rebookings, schedule conflicts and direct impact to cashflows Our solution addressed this challenging problem by combining & deriving few different algorithms for different parts of the problem: - determine extent of the engine deterioration using a simplified variant of Kalman filtering method - predict the optimal scheduling window using adaptation of genetic algorithm Innovation & Engineering hacker. Expert in AI/ML, Algorithms & Big Databases #kiwipycon #kiwipycon2019 #python #pycon #wellington #programming Kiwi PyCon is an annual conference aimed at promoting and educating people about the Python programming language. The New Zealand Python User Group is proud to present the ninth national Python conference in New Zealand.

Case Study: How a Large Brewery Uses Machine Learning for Preventive Maintenance (Cloud Next '18) Learn how machine learning is used to optimize the beer manufacturing process. This use case has a direct impact on the production line and identifying downtime of equipment, and huge impact on cost, time, and quality of beer being produced. The role of machine learning is to improve the manufacturing process and quality while driving higher ROI through an undisruptive production process. Listen to experts on how Deep Learning was used with classifications of good parts vs. bad parts using TensorFlow. The model will be deployed to Google Cloud Machine Learning Engine where it will make predictions of the new data that is fed every day with an interactive dashboard using Data Studio.

NASA IoT - Different Ways to Model Predictive Maintenance and Engine Degradation Manuel Amunategui Let's go over another great dataset. This one is from NASA and covers IoT-predictive maintenance. They recorded/simulated Turbofan engine degradation. We'll prepare the data and run through the Fastml.io automl engine (same engine we've in previous classes). The link to the data is included in the source and so is the data prep code. It contains over 20-sensor measurements and some operational settings and represents a series of prop engine runs - going from optimally running to dead-in-the-water. For source code

Deep Dive: Machine Learning on the Edge - Predictive Maintenance Learn and ask questions about: Azure Machine Learning, IoT Edge, Visual Studio Code, Visual Studio Guest Speakers: Mark Mydland and Pamela Cortez from the Microsoft Azure IoT team Live Event! Our team will be live on chat and actively answering your questions! Frequently, IoT applications want to take advantage of the intelligent cloud and the intelligent edge. In this Deep Dive, we walk you a predictive maintenance example that goes through training a machine learning model with data collected from IoT devices in the cloud, deploying that model to IoT Edge, and maintaining and refining the model periodically. Learn tips and resources you can use when building your own model and IoT Edge solution. The ML on the Edge Walk-through Example can be found here

Predictive Maintenance Use Cases From The Energy Sector - Umid Akhmedov In this session Umid will discuss some use cases from an energy company that is taking advantage of predictive analytics to make the world greener. Key takeaways: Align with the business strategy, Build a solid data backbone, formalize the process. #HyperightDataTalks is a video podcast of interviews with some of the most innovative minds, enterprise practitioners, technology and service providers, start-ups and academics, working with Data Science, Data Management, Big Data, Analytics, AI, IOT and much more. For more interviews, audio podcast and videos from some of the best presentations from our Data Summits, please visit http://www.hyperight.com Presentation recorded during Maintenance Analytics Summit 2018 - http://maintenanceanalyticssummit.com/

Deep Learning for Predictive Quality And Predictive Maintenance Artificial Intelligence plays a major role in Industry 4.0 and more industrial companies than ever are starting to utilize their data to gain value and insights. The industrial domain offers very promising opportunities but this potential also comes with very specific requirements and challenges. This talk gives insights into the characteristics of Industrial AI and how state of the art deep learning methods can be applied to solve complex problems and bring more value to companies. Simon Stiebllehner (Head of AI at craftworks and lecturer in statistics and digital marketing at Vienna University of Economics and Business and University of Applied Sciences of WKW) and Daniel Ressi (Data Scientist at craftwork) talk at Vienna Data Science Group – Knowledgefeed vol. 27. Slides are available here: http://bit.ly/VDSG_Kf27rev

Developing a Predictive Maintenance Program - Noah Schellenberg, Tetra Pak Data Science CoE The session will talk about the life cycle approach to building a predictive maintenance model always focusing on the value. Tetra Pak has been on a predictive maintenance journey for several years and we will walk through the steps made and lessons learned in building the program. Particularly focus will be on how Data Science experts are best deployed in PdMA projects and the PoV process. Key Takeaways Identifying the Total Opportunity, Driving towards the Empirical Business Case, Sustaining the Value, Lesson Learned #HyperightDataTalks is a video podcast of interviews with some of the most innovative minds, enterprise practitioners, technology and service providers, start-ups and academics, working with Data Science, Data Management, Big Data, Analytics, AI, IOT and much more. For more interviews, audio podcast and videos from some of the best presentations from our Data Summits, please visit http://www.hyperight.com/

Preventing Failures with Predictive Maintenance Webinar What would it mean to your organization if you could predict system failures or quality issues before they happen? Preventing failures can help your organization reduce unscheduled downtime, waste, and rework – and avoid costly disruptions in operations. With predictive analytics, it’s possible to proactively manage maintenance and improve operational efficiency by discovering the chance of a failure before it takes place. In this past webinar, we discussed how you can utilize Microsoft Azure Machine Learning, R, and the Cortana Intelligence Suite to predict and prevent system failure, and explored the benefits of calculating KPIs such as Remaining Useful Life, Time to Failure, and Failure within a certain tim

Building Machine Learning Models for Predictive Maintenance in the Oil & Gas Industry w/ Databricks For each drilling site, there are thousands of different equipment operating simultaneously 24/7. For the oil & gas industry, the downtime can cost millions of dollars daily. As current standard practice, the majority of the equipment are on scheduled maintenance with standby units to reduce the downtime. Scheduled maintenance treats each equipment similarly with simple metrics, such as calendar time or operating time. Using machine learning models to predict equipment failure time accurately can help the business schedule the predictive maintenance accordingly to reduce the downtime and maintenance cost. We have huge sets of time series data and maintenance records in the system, but they are inconsistent with low quality. One particular challenge we have is that the data is not continuous and we need to go through the whole data set to find where the data are continuous over some specified window. Transforming the data for different time windows also presents a challenge: how can we quickly pick the optimized window size among the various choices available and perform transformation in parallel? Data transformations such as the Fourier transforms or wavelet transforms are time consuming and we have to parallelize the operation. We adopted Spark dataframes on Databricks for our computation. Here are the two major steps we took to carry out the efficient distributed computing for our data transformations: 1. Identify which segments have continuous data by scanning through a sub-sampled data set. 2. Pick different windows and transform data within the window. 3. Transform each window column into one cell as a list. 4. Preserve the order of the data in each cell by collecting the timestamp and the corresponding parameter as a list of dictionaries, and then reorder the list based on the timestamp element in the dictionaries. About: Databricks provides a unified data analytics platform, powered by Apache Spark™, that accelerates innovation by unifying data science, engineering and business.

Optimised Predictive Maintenance: a Dataiku x HPE Webinar The predictive maintenance market will reach $11 Billion by 2022, driven by Internet of Things (IoT) technology and new services. Predictive maintenance translates into profound business benefits: reduced costs (resources and parts), less downtime, optimized maintenance scheduling, accurate defect diagnosis, and much more. In this webinar, learn how to build an end-to-end predictive and prescriptive maintenance solution open framework based on machine learning and deep learning techniques with Dataiku and HPE. The webinar will be broken down into three parts: - Introduction to predictive and prescriptive maintenance, answering questions like "What is predictive maintenance?" and "How can you move from a model where you know what can happen to a prescriptive model where you will know exactly what will happen along with the associated costs?" - Step-by-step demo of a use case going from data acquisition to action activation through optimized prediction algorithms. We will explain how to implement an effective predictive solution using different data sources (PMU, ERP, Prot, network repository, etc.).

Tech Talk | Predictive Maintenance (PdM) on IoT Data for Early Fault Detection w/ Delta Lake Join us for an online tech talk on Delta Lake. Tech talks include a technical presentation with slides and a demo, with time for Q&A at the end. Predictive Maintenance (PdM) is different from other routine or time-based maintenance approaches as it combines various sensor readings and sophisticated analytics on thousands of logged events in near real time and promises several fold improvements in cost savings because tasks are performed only when warranted. The top industries leading the IoT revolution include manufacturing, transportation, utilities, healthcare, consumer electronics & cars. The global market size for this is expected to grow at a CAGR of 28%. PdM plays a key role in Industry 4.0 to help corporations not only reduce unplanned downtimes, but also improve productivity and safety. The collaborative Data and Analytics platform from Databricks is a great technology fit to facilitate these use cases by providing a single unified platform to ingest the sensor data, perform the necessary transformations and exploration, run ML and generate valuable insights.

HPE: Ultra-Reliable Low-Latency Solutions for Industry 4.0 Predictive Maintenance Use Cases The Fourth Generation of the Industrial (Iv4) revolution parallels the global launch of the Fifth Generation (5G) of wireless networks. Comprised of Cyber Physical Systems (CSP), Industrial Internet of Things (IIoT), Cloud Solutions & Decentralized Services, Extreme-Scale Big Data and Real-Time Streams Processing Frameworks, Artificial Intelligence is imbedded in Iv4. In order for these novel Iv4 solutions to leverage 5G's new Ultra-Reliable Low-Latency Communication (URLLC) service paradigm, comparable real-time, low-latency tools like Aerospike Enterprise Server are placed on the front lines to support these Iv4’s intelligent products, processes, and machine use cases. This intelligent automation and data exchange is showcased in the predictive maintenance use cases for wind turbines and railways.

Rethinking Predictive Maintenance | Zaid Tashman | AI Conference London Traditional approaches to predictive maintenance fall short in today’s data-intensive and IoT-enabled assets. In this talk we introduce a novel machine learning based approach to predicting the time of occurrence of rare events using mixed membership hidden markov models. We show how we use these models to learn complex stochastic degradation patterns from data by introducing a terminal state that represents the failure state of the asset, whereas other states represent “health” states of the asset as it progresses towards failure. The probability distribution of these non-terminal states and the transition probabilities between states are learned from data.

Delivering Value Through Predictive Analytics in Chemical Process Industries In this webinar with our partner, PPT, learn how machine learning and predictive analytics was used to save a million dollars in a petrochemical facility through optimizing parameters of cracked gas compressor loop. In this 40-minute session we’ll take you through the following agile analytics implementation approach of: 1. Defining the Problem Statement and Hypothesis 2. Extracting-transforming-loading (ETL) of data silos (DCS, SCADA, PLS, LIMS, ERP and others) 3. Developing ML models to realize the deliverables 4. Deploying the final model for real time predictions and delivering value

Webinar: Business manufacturing applications for AI AI isn't just for technology pioneers or academic organizations. The path to using advanced techniques like deep learning is realistic (and realizable) for businesses from the enterprise on down. In manufacturing, in particular, AI can be applied to customer-facing, support and internal systems — and can revolutionize predictive maintenance — right now. Led by AI experts at Peltarion and Futurice, this manufacturing-focused webinar will educate you on how to extract business value from AI and goes through relevant AI use cases for the manufacturing industry to help illustrate this, getting your business enabled quickly to leverage deep learning. To find out more about operational AI and the Peltarion Platform, go to peltarion.com/platform

The Core Principles of Predictive Maintenance (PDX ML Meetup) This talk was given by Ian Downard at the Portland Machine Learning Meetup on 12/13/2018. Slides at http://bit.ly/2A13J9p. In this presentation, Ian describes the core principles around data collection, feature engineering and machine learning for predictive maintenance.

On Demand Webinar: The Right Solution for Predicting Machine Failure Predictive maintenance is a technique used in various industries to reduce machine downtime by predicting its failure. It is fair to say that most enterprises consider this a difficult technique to deploy in production. The right implementation uses a combination of the following steps: - Real-time data ingestion from IoT devices - Extract-transform-load (ETL) of this data and writing it into a data store - Developing machine learning (ML) algorithms to extract insights into failure events and training these algorithms using the stored data - Deploying the final algorithm(s) in production onto the target environment - Monitoring the performance of the system and tuning the implementation as physical conditions change over time MapR has partnered with RapidMiner to bring a holistic solution to help manufacturers predict machine failure accurately. The solution offers unique flexibility in design, multiple deployment options for convenient transition to production, and an easy-to-use UI.