TIBCO Manufacturing Solutions
Introduction and Overview
There is currently a major transformation taking place in the manufacturing industry. It is made possible by new capabilities for processing sensor data, along with big data, machine learning and artificial intelligence, cloud and edge technologies. These capabilities are enabling a shift from reactive problem solving towards increasingly proactive management of equipment, processes, product and factories. The TIBCO Connected Intelligence Platform can help you speed up and automate problem identification, diagnosis and solution.
TIBCO provides the ability to build out a wide range of solutions to better understand equipment, processes, products, operations, customers and sales; and then to act on the insights gained. TIBCO Solutions are used in many manufacturing companies throughout the world in the following industries: semiconductor, electronics and medical devices; automotive & aviation; equipment manufacturing, pharmaceuticals; chemicals, metals and mining and consumer packaged goods.
General Manufacturing Overviews
Watch a Webinar on TIBCO Smart Manufacturing Solutions
View the slide presentation smart_manufacturing_analytics_distn.pdf
Read the solution brief: Manufacturing Intelligence in the Age of Industry 4.0 and the IoT
- Applications in Industrial IoT slide deck - Remote real-time monitoring of industrial equipment, combined with modern analytic techniques, drives significant value in industries such as Energy, Logistics, and Manufacturing. An architecture is presented for integrating all the critical capabilities together into robust enterprise solutions. We show how to use TIBCO Visualization, Data Science, Streaming and Edge capabilities to monitor and control equipment and processes. The presentation includes several real-world customer case studies and examples: iiot_applications_distn.pdf
Semiconductor Manufacturing Overview Presentation
Presentation Slide Deck: tibco_semiconductor_manufacturing_analytics_distn.pdf
- Video recording of presentation:
Some of the key capabilities and use cases relevant in this sector include:
- Ad-hoc data discovery with interactive visualizations and built-in statistics
- Seamlessly integrate advanced analytics and machine learning into dashboards using in-built TIBCO Enterprise Runtime for R, Statistica and other (SAS, Matlab, etc.) engines
- Big Data analysis via Spark, Hadoop and other connectors
- Scheduled to real-time Alerting with streaming sensor data
- Enterprise-class platform to quickly and easily configure lowest-cost custom solutions
- Dashboards available on cloud, desktop, tablet or mobile devices
Key Use Cases
- Product Quality and Reliability
- Machine learning to accurately model and predict equipment, process and product results
- Process Control and Capability with alerting
- Equipment maintenance: Predictive, condition-based and scheduled with alerting
- Factory Monitoring including Management dashboards , KPI charts and OEE.
- Supply Chain: Demand forecasting, inventory optimization, supplier performance
- Resource modeling and optimization
- Customer Analytics – customer & product segmentation, cross-sell / up-sell opportunities
- Sales - Pricing optimization and Account management
OEE Global Operations dashboard
Core Manufacturing Use Cases
Quality and Reliability of Products and Processes
Gain insight into quality and reliability issues. Spotfire helps manufacturers to identify, understand and minimize problems due to process variability, incoming supplies, test or design. An intensified interest in product quality and reliability analysis is being driven by a number of market forces. As Lean and Six Sigma manufacturing methodologies take hold in industry after industry, customers’ expectations continue to rise. Reliability failures are more visible and sometimes more costly than ever before. Meanwhile the forces of technology, globalization and regulation make our quality and reliability calculations more complex and urgent. Many of the world’s largest manufacturers are turning to TIBCO Spotfire to identify issues earlier, respond more rapidly and effectively and then build better products.
Equipment Commonality Analysis - Effect of Machine on Paper Towel Product Quality
For semiconductor manufacturers, yield analysis can include wafermaps, zonal, pattern and defect analysis
Semiconductor wafer yield analysis
See how Statistica helps understand the effects of processing on product characteristics using the Product Traceability add-on
Read the Six Sigma datasheet - Six Sigma is a business management approach that seeks to improve performance by reducing errors, outliers and process variability.
Big and Wide Data Digital Twins (Models) for Product Quality and Yield
TIBCO has recently been working with manufacturing customers to make a new, high-value capability available: digital twins for yield. It's about real-time, continuous analysis of manufacturing equipment sensor and process data at very large scales - up to millions of predictor columns - to understand and address the causes of product yield loss. Digital twins are virtual representations (models) of physical systems. The current interest in them is fueled by recent breakthroughs in IoT, machine learning and big data. These technologies are now being directed at the growing volumes of data available from sensors on process equipment and physical measurements from metrology tools. As process complexity increases, these digital twins are becoming a requirement for efficient operations and high product yields. They are an important element of the evolution towards increasingly data-driven problem-solving and real-time operational control.
For more information about our work on this use case:
- View a 15 minute demo that shows how the results can be visualized in Spotfire and how a TIBCO Data Science big data workflow is used to generate the data.
- Watch this 30 minute webinar that includes the demo, adds context to the use case and presents performance results for the solution.
- Read this Whitepaper
- View this slide deck: digital_twin_for_yield_v4_distn.pdf
Read this customer story about how Zpower uses TIBCO for root cause analysis to reduce scrap and improve product quality
Machine Learning is a recent evolution in advanced analytics that can help uncover the causes of complex manufacturing problems and make accurate predictions about when and how to improve maintenance and operations. The following assets provide an overview of relevant machine learning techniques and how they are being applied to yield and quality improvements, predictive and condition-based maintenance, micro-segmentation of markets, and resource optimization. Watch Video. View Slides. Read Whitepaper.
Machine Learning - Effect of process measurements on product yield - shows nonlinearities & interactions
To learn more:
- Read the blog article on Creating a Big Data Analytic workflow that features use of a machine learning algorithm to understand a manufacturing big data product quality problem
- View the video presentation on Integrating Spotfire with H20 machine learning featuring manufacturing quality use cases
- Visit the Machine Learning Wiki page
- Download machine learning analysis templates and data functions for manufacturing from the Community Exchange
Design of Experiments
Design of Experiments is an important tool for experimentally identifying the most important factors and finding their optimum settings in order to improve processes and products. Statistica has comprehensive capabilities for design and analysis of fractional factorial, Box-Behnken, Central Composite, Optimal, Mixture, Taguchi and a number of other design types. It also features a prediction profiler for simultaneous optimization of multiple responses.
Reliability and Warranty Claims
See how Spotfire can help you monitor and predict claim rates. analyze root causes of reliability failures and analyze warranty repair and call center activity.
Warranty analysis for all components of an automobile model
Read the Warranty and Reliability datasheet
View the Warranty claims demo
See how customers are addressing quality and reliability problems with Spotfire:
- Dialog Semiconductor
- Hard Drive manufacturer
- REC Solar Cells
- Triquint Semiconductor
- Zpower batteries
Factory Monitoring and OEE
Modern factories are populated with complex, expensive equipment. Manufacturers want to extract the greatest value from their factory equipment by maximizing equipment uptime, product throughput and quality and minimizing cycle times. Identifying bottlenecks in processing, taking proactive action in response to developing situations, and increasing operational system awareness are all key themes in sensor-driven manufacturing monitoring.
Overall Equipment Effectiveness or OEE is a high-level measure of equipment productivity. The OEE model combines measures of equipment availability, performance and quality.
- Availability is the percentage of time that the equipment is available to operate … or Uptime. Scheduled downtime, unscheduled downtime and non-scheduled downtime (holidays or training) all contribute to availability losses.
- Performance is the speed at which the Work Center produces product as a percentage of its designed speed. Performance losses are categorized as either due to Rate or Operational inefficiencies. Rate losses are caused by equipment running slower than theoretical speed. Operational Losses may be further broken down into Engineering and Standby Losses. Engineering losses occur when production turns equipment over to engineering, often to perform tests or experiments. Standby losses occur when the equipment is available but there is no product or operator to run it.
- Quality is Good Units produced as a percentage of the Total Units Started. Sometimes referred to as First Pass Yield or FPY. Rework and scrap contribute to Quality losses
- OEE is calculated by multiplying Availability, Performance and Quality percentages together.
You can find more information about OEE here.
The High Tech Manufacturing Accelerator contains components to allow monitoring of production line performance against established metrics using Overall Equipment Effectiveness (OEE). It caputres data feeds from sensors on production equipment, validates the feeds, and evaluates the data against configurable business rules. It includes components to visualize all these activities in a custom web dashboard, allowing operators to take corrective action when production issues are identified.
Download the Hi Tech Manufacturing Accelerator from the Exchange
Watch a video of the High-Tech Manufacturing Accelerator in action
Predictive and Scheduled Equipment Maintenance
The expansion of connected sensor data creates new business opportunities for monitoring machine performance and failures in the field and on the factory floor. Service organizations have up-sell opportunities to offer options to their customers for maximizing value of their assets. Manufacturers can increase uptime, minimize costs, and optimize processes for expensive equipment on the factory floor. TIBCO Spotfire® helps organizations optimize maintenance schedules by monitoring and responding to key signals in sensor data. In general, fixed assets— vehicles, plants, and machinery, communication devices and computers, and even buildings, are becoming smarter. But they are also becoming more complex and more costly to repair. Spotfire can help you understand these machines more fully, monitor them in real time, and react faster to impending issues. TIBCO supports the following maintenance use cases: • Predictive maintenance with automatic notification of impending failures • Minimizing scheduled maintenance costs • Root cause analysis of equipment failures.
Real-time dashboard showing predicted pump fails
View a short video on Using pump sensor data to predict and prevent failures
Read the Spotfire and OSIsoft PI System Interactive Analytics data sheet - Analyze OSIsoft PI System data, mashed up with other data sources and visualized within Spotfire, to bring new, rich insights into product quality, operations, distributed assets, and the Internet of Things.
Read a brief customer story from Bosch on Predictive Maintenance
To learn more:
- Watch a webinar on Event Analytics in Machine Management
- Download and try out the Industrial Equipment Accelerator on the Community Exchange
Process Control and Exception Reporting
Shewhart and Multivariate Control Charts
Control charts are widely used in Manufacturing, Energy, Telco, Technology and many other sectors. They are the foundation of early warning systems that monitor key metrics, detect deviations from the baseline, and generate automated alerts. TIBCO supports many types of Shewhart (univariate) and multivariate charts; integrated limits generation, storage and deployment; selection of rules to detect out-of-control points; tagging and annotation; management and operations dashboards; periodic or real-time alerts; process capability studies and root cause drill-downs
Process Control Summary with drill-down to Control Chart
Download a Spotfire Quality Control Charts template and data functions, that you can use with your own data, from the Exchange.
Try the Dynamic Control Chart demo
TIBCO Data Science (Statistica) has comprehensive out-of-the-box Process Control capabilities including Quality Control Charts, Multivariate Statistical Process Control and the Monitoring and Alerting Server for automated monitoring of large numbers of charts. The capabilities are tightly integrated with Spotfire, via the Statistica-in-Spotfire data function, to enable calculations in Statistica with data visualization in Spotfire.
Read this customer story about how Zpower used multivariate process control to ramp into high volume production.
Using AI to detect complex anomalies in time series data
The TIBCO Data Science team is actively engaged in developing applications of Deep Learning Autoencoders for Anomaly Detection in Manufacturing. In a dynamic manufacturing environment, it may not be adequate to only look for known process problems, but also important to uncover and react to new, previously unseen patterns and problems as they emerge. Univariate and linear multivariate Statistical Process Control methods have traditionally been used in manufacturing to detect anomalies. With increasing equipment, process and product complexity, multivariate anomalies that also involve significant interactions and nonlinearities may be missed by these more traditional methods. This is a method for identifying complex anomalies using a deep learning autoencoder. Once the anomalies are detected, their fingerprints are generated so they can be classified and clustered, enabling investigation of the causes of the clusters. As new data streams in, it can be scored in real-time to identify new anomalies, assign them to clusters and respond to mitigate potential problems. These tools are no longer the exclusive province of data scientists. After an initial configuration, the method shown can be routinely employed by engineers who do not have deep expertise in data science. Watch the video and view the slides below:
Download the Spotfire Anomaly Detection template from the Component Exchange.
For more details on the technology, visit the Anomaly Detection and Autoencoder Machine Learning Models community page.
The Hi Tech Manufacturing Accelerator provides a framework for real-time monitoring of univariate and multivariate control charts. (See section on Factory Monitoring and OEE above.) Watch a video of the Autoencoder deployed to the Hi Tech Manufacturing Accelerator for real-time monitoring:
The TIBCO Data Science (Statistica) Monitoring and Alerting Server enables automated monitoring of a large numbers of charts:
The Spotfire Plug-in for Alerting allows you to configure alerts directly from any Spotfire analysis file and can be used to alert when rules on any control chart are violated. It is an extension for TIBCO Spotfire that integrates with Automation Services via an alerting task. The task can generate e-mail, text or pop-up alerts.
Blockchain Opportunities in the Manufacturing Supply Chain
Manufacturers today face a number of logistics and supply chain challenges that could be overcome by systems providing a secure, tamper-resistant, single source of truth. Chief among these challenges is limited data sharing due to data security barriers among suppliers, shippers, manufacturers and test houses, an impediment to achieving optimal product quality and regulatory compliance. Additionally, inefficient and inadequate processes for tracking goods make it more difficult to isolate shipping problems, track faulty parts and verify product authenticity. Counterfeiting has become a serious problem that costs US-based semiconductor manufacturers $7.5 billion annually.
For more information:
Read this Whitepaper: Blockchain and Manufacturing: A Match Made in the Factory
Watch this Webinar: Blockchain and Manufacturing - A Match Made in the Factory
- Visit the TIBCO Blockchain Solutions page
- Hemlock Semiconductor
- Dialog Semiconductor
- Hard Drive manufacturer
- REC Solar Cells
- Triquint Semiconductor
- Zpower - batteries
- Aluminum Manufacturer
- Brembo - brakes
- General Mills - food
- Hi Tech Equipment manufacturer - imaging systems
- Medical Device manufacturer
- Mercedes-AMG Petronas Motorsport
Download Manufacturing Industry templates, data functions and acclerators from the TIBCO Exchange.
Visit the Spotfire Community Wiki Home Page: This is the starting point for an extensive, constantly expanding collection of linked Wiki pages covering all things Spotfire. Links to comprehensive, current information on these Main Topics landing pages: Getting Started, Data Access and Wrangling, Visualizations, Maps, Advanced Analytics, Applications and Vertical Solutions, Extending Spotfire, Administration, Partners and more.
Sites with good content about Smart Manufacturing & Digital Transformation
Back to Spotfire Wiki home page