Choose Language Hide Translation Bar

cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Revolutionizing Semiconductor Manufacturing Tests with Predictive Modeling
Tuesday, October 22, 2024
Executive Briefing Center 150
The semiconductor manufacturing industry stands on the brink of a transformative era, powered by advanced analytical techniques. This presentation delves into the application of predictive modeling and diagnostic analysis within JMP software to significantly enhance manufacturing outcomes, particularly during the crucial early sort and class test phases. By leveraging comprehensive parametric data collected across various stages of the semiconductor production process, we embark on a journey to refine the prediction of unit-level pass/fail outcomes and unearth the underlying causes of potential defects. Our study highlights the strategic use of JMP’s predictive modeling capabilities to accurately forecast the final system-level test status of semiconductor products. This approach not only allows for early detection of issues but also facilitates the implementation of corrective measures in a timely manner, thus ensuring higher yield rates and superior product quality. In parallel, diagnostic analysis within JMP offers a deep dive into the data, enabling manufacturers to identify and address root causes of failures across the intricate web of production processes. This presentation showcases real-world applications of these JMP features, demonstrating their pivotal role in streamlining semiconductor manufacturing workflows. See how predictive modeling and diagnostic analysis can be effectively employed to optimize production outcomes, reduce costs, and enhance product reliability. Join us in exploring the cutting-edge analytical strategies that promise to redefine the future of semiconductor manufacturing.
DOE and Consumer Research: Tackling Consumer Preference Variability
Tuesday, October 22, 2024
Executive Briefing Center 8
One of the great things about humans is that we are all unique. Diversity has benefits all around us, but variation in preferences with regard to consumer goods makes it challenging to predict what will delight the greatest number of people. The use of design of experiments (DOE), facilitated by JMP, is critical to designing formulations with the most appeal.  The objective of this presentation is to interactively present methods to optimize formulations for the greatest consumer liking. Two DOE approaches from a real food formulation case study will be presented: an 18-run definitive screening design (DSD) and an 18-run space-filling design modeled using SVEM and neural networks. To prepare data for modeling, multidimensional scaling is demonstrated to remove anomalous participants’ data. Participant clusters built using hierarchical clustering are used when fitting models using fit definitive screening and SVEM neural networks. The power of the JMP profiler will highlight how consumer preferences differ by cluster. Text Explorer is used to show how to verify insights gained through modeling by exploring verbatim comments by study participants. Lastly, insights gained from each experimental design and modeling approach are compared along with limitations of each. Attendees are presented with a more information-rich alternative to traditional DOE and consumer testing strategies.
Golf is Hard, but Designing Experiments is Easy
Tuesday, October 22, 2024
Executive Briefing Center 8
Once you’ve learned how easy it is to design an experiment in JMP, you never look at the world around you the same. Everything becomes an opportunity for an experiment! This presentation uses a practical example to demonstrate the process of design of experiments (DOE), including designing the experiment, modeling the results, and optimizing the inputs to provide the most desirable output. Attendees at last year’s Discovery conference were treated to an evening of unique fun: hitting glow-in-the-dark golf balls on the driving range at Indian Wells Golf Resort. The driving range has Toptracer technology that monitors each shot. Total distance, carry, ball speed, launch angle, and curve are some of the variables reported with each shot. A driving range that provides so much data provided a perfect opportunity to design an experiment using JMP! After an evening with fellow JMP users and friends, an experiment was designed using the Custom Designer in JMP. The design took only minutes to create. Input variables based on the golf stance setup were used in the design. These included variables such as grip, club head alignment, stance width, and ball location. The designed experiment was executed on the driving range, a model was created, and optimum settings to create the longest and straightest shot were discovered. The modeling and optimization were completed in minutes, while still on the driving range! This allowed for confirmation runs to immediately be performed. The benefits were later transferred the golf course as well.
Comparing optimization strategies in complex multi-dimensional processes
Tuesday, October 22, 2024
Executive Briefing Center 9
There have been numerous studies showing efficacy of strategies in process optimization. The common comparisons made are usually between the ‘one factor at a time’ or OFAT experiments and a ‘design of experiments’  approach. When faced with an unfamiliar, high-dimensional process space (e.g. >10 factors), researchers often resort to the OFAT methods as they are easy to interpret.   Generally, it would be cost-prohibitive and logistically challenging to run multiple experiments geared towards the same objective just to evaluate which strategy outperforms others. To circumvent these issues, we used a Polymerase Chain Reaction (PCR) simulator with 12 unfamiliar continuous and categorical factors to explore these questions. Our team comes from decades of experience in process optimization in the electronic materials industry (former employees of Apple and others). We intentionally sought and selected a simulator from a research area completely unknown to us that has the ability to simulate a large number of factors and their complex interactions on many responses. To automate experimentation, we used a python web automation script. By using a simulator and our script, we can run through many experiments while mimicking real-life constraints and experimental budgets as seen in our own professional careers. While adhering to run budget rules, we compare the efficiency and accuracy of four strategies; two OFAT type strategies as commonly used in the industry, and two strategies from the DOE and advanced DOE genre. JMP is used for all experimental analyses and modeling and an objective attempt is made to compare the strategies.
Modeling Antibiotic Tolerance in Chronic Lung Infection
Tuesday, October 22, 2024
Executive Briefing Center 7
The airway environment in individuals with muco-obstructive airway diseases (MADs) is characterized by dehydrated mucus due to hyperabsorption of airway surface liquid and impaired mucociliary clearance. As MADs progress, pathological mucus becomes increasingly viscous due to mucin overproduction and host-derived extracellular DNA (eDNA) accumulation. Pseudomonas aeruginosa, a major pathogen in MADs, colonizes this mucus niche persistently. Despite inhaled antibiotic therapies and the absence of antibiotic resistance, antipseudomonal treatment failure remains a clinical challenge. We used JMP's data visualization and statistical modeling to investigate how mucin and eDNA concentrations – dominant polymers in respiratory mucus – affect P. aeruginosa’s antibiotic tolerance to understand antibiotic recalcitrance. Our findings reveal that polymer concentration and molecular weight impact P. aeruginosa survival after antibiotic exposure. Surprisingly, polymer-driven tolerance is not solely linked to reduced antibiotic diffusion. Additionally, we established an in vitro model that mirrors ex vivo antibiotic tolerance observed in expectorated sputum across different MAD etiologies, ages, and disease severities, highlighting the intrinsic variability in host-evolved P. aeruginosa populations. 
Assessment of Dielectric Reliability in Semiconductor Manufacturing
Wednesday, October 23, 2024
Executive Briefing Center 9
Reliability assessment of devices and interconnects in semiconductor technologies is typically done for technology certification and periodic monitoring, using relatively small (single digit to tens) sample sizes per condition. Volume manufacturing data can be used over time to assess dielectric reliability by ramped voltage-breakdown measurements on scribe-lane test structures. Over time, this can provide a detailed view of dielectric behavior, including a mixture of intrinsic and extrinsic mechanisms affecting dielectric integrity. In particular, low failure-rate outliers or tails can be detected and addressed, which may otherwise pose field-quality risks. For practical reasons, the ramp may be stopped at a target voltage to reduce test time and avoid damage to probe cards and needles, which may result in a small number of data points being censored. Fitting large data sets with a small number of censored data points can lead to convergence challenges, resulting in incorrect fitting parameters and lack of confidence intervals, as well as posing significant computational challenges. This work explores these challenges with the JMP Life Distribution platform and examines alternatives and solutions to allow correct analysis, fitting, and extrapolation.
Machine Learning-Assisted Experimental Design for Formulation Optimization
Wednesday, October 23, 2024
Executive Briefing Center 7
Design of experiments (DOE) is a statistical method that guides the execution of experiments, analyzes them to detect the relevant variables, and optimizes the process or phenomenon under investigation. The use of DOE in product development can result in products that are easier and cheaper to manufacture, have enhanced performance and reliability, and require shorter product design and development times. Nowadays, machine learning (ML) is widely adopted as a data analytics tool due to increasing availability of large and complex sets of data. However, not all applications can afford to have big data. For example, in pharma and chemical industries, experimental data set is typically small due to cost constraints and the time needed to generate the valuable data. Nevertheless, incorporating machine learning into experimental design has proved to be an effective way for optimizing formulation in a small data set that can be collected cheaper and faster. There are three parts in this presentation. First, the literature relevant to machine learning-assisted experimental design is briefly summarized. Next, an adhesive case is presented to illustrate the efficiency of combining experimental design and machine learning to reduce the number of experiments needed for identifying the design space with an optimized catalyst package. In the third part, which pertains to an industrial sealant application, we use response surface data to compare the prediction error of the RSM model with models from various machine learning algorithms (RF, SVR, Lasso, SVEM, and XGBoost) using validation data runs within and outside the design space.   
Using Point-and-Click and Basic Code-Cracking Skills to Import Tricky Data
Wednesday, October 23, 2024
Executive Briefing Center 8
During my time working as a scientist in R&D, there were times I wanted to augment my analyses with data that was not always in a straightforward file type that could be imported efficiently into JMP. For example, think of multiple PDF pages with chemical composition information – each with slightly different formatting. Or think about multiple web pages with data for different regions – with a different URL for each page. Another example would be including experimental pictures in a data table – and matching each of the hundreds of pictures with the corresponding file names. Although JMP supports bringing in data from PDF formats and websites, as well as allowing you to bring in pictures into a data table, it is not always obvious how to do this efficiently when you have lots of pages or images to import. If you are not a proficient scripter (or don't know someone who is) you may end up doing each import manually…or simply forgoing the information and moving on. The good news is that even without being able to write a script from scratch, you can use basic JSL decoding skills to bring in data from these kinds of sources efficiently. In this paper, we show a few examples of how we used JMP’s point-and-click tools, along with basic JSL deciphering skills, to automate the import of images, data from PDFs and web pages with scale.
Labels (2)
Using DOE to Improve the Performance of a High-Speed Dynamic Seal
Wednesday, October 23, 2024
Executive Briefing Center 9
At Francis Medical, the cannula of our disposable delivery device is inserted into the urethra and then a small round catheter exits the cannula into the prostate where steam exiting from the catheter is used to ablate tissue. Due to hydrostatic pressure from the bladder, the dynamic seal between the cannula and catheter is the only barrier for a possible fluid ingress pathway into the delivery device, which is undesirable.  Testing the dynamic seal on the bench is accomplished by pressurizing the cannula using a pneumatic pressure decay tester. While the output of this tester is continuous, the distribution is bimodal and is best modeled as a binary output: either the seal leaks or the seal does not leak. In JMP, there is no straightforward method to calculate the power and sample size to allow for comparison of different design of experiment (DOE) studies for an attribute output. In this paper, we outline the process methodology we used to determine the number of factors to test and how many runs to complete, including a simulated power analysis. In addition, we discovered a unique way to condition the samples prior to pressure decay testing to create more dynamic seal failures than achieved through historical testing. In the end, the results of the experiment allowed us to make definitive design decisions with confidence and improve the dynamic seal performance by a factor of 25 from the current design.
Streamlining Manufacturing Excursion Investigations with JMP
Wednesday, October 23, 2024
Executive Briefing Center 9
Excursions can lead to significant costs at a manufacturing facility. In the semiconductor industry, production downtime, scrapped and low-yield wafers, and decreased output can result in substantial revenue losses. Engineers tasked with investigating these excursions must quickly uncover actionable insights for data-driven decisions that minimize downtime and improve product quality. JMP's Analytic Workflow can help you outline the steps and tools needed to efficiently investigate excursions. Explore how Query Builder facilitates data access from databases and how JMP's powerful Tables menu aids in data manipulation. Discover optimal table formats for visualizing and analyzing wafer map data. Utilize exploratory and analytical techniques to discover hidden relationships across manufacturing process steps.  Enhance your analysis with JMP Pro, leveraging features like image analysis in the new Torch Deep Learning Add-In for JMP Pro 18 to gain advanced insights. Automate and rerun your entire analysis using Workflow Builder in JMP, ensuring speed, repeatability, flexibility, and analytical power without the need for coding. Learn how leveraging these tools and techniques in JMP and JMP Pro can lead to efficient resolution and substantial cost savings in a fast-paced manufacturing environment.   Note:  The Workflow contained in the "Semiconductor Defects Workflow.zip" folder uses CSV import instead of Query Builder, although Query Builder will be used in the presentation.
Modeling Coral Reef Resilience in the Republic of Palau
Wednesday, October 23, 2024
Executive Briefing Center 150
Coral reefs across the planet are threatened by the rising seawater temperatures driven by climate change. Although many corals indeed "bleach," and consequently perish, as a result of prolonged exposure to abnormally high temperatures, some species (or even genotypes within a single species) maintain a marked level of climate resilience. Historically, we have identified these "super corals" in post-hoc fashion: searching through the proverbial rubble of a highly impacted reef to find the survivors. For coral reef restoration and other purposes, a more targeted, proactive means of identifying climate-resilient corals would be preferred to this "needle in a haystack" approach. To this end, I showcase a rich coral eco-physiological data set acquired during a month-long research expedition to the most remote corners of the Micronesian nation of Palau. After some rudimentary data processing and visualization, I show, using JMP Pro 17, how predictive models of coral resilience can be built relatively easily. I then demonstrate how GUIs derived from the models' prediction profilers can be embedded on web pages so that they can be used by scientists as a planning tool. Specifically, the model-based profilers allow researchers to predict the environmental conditions (e.g., depth, type of coral reef, salinity) at which they are most likely to find resilient corals during their bioprospecting surveys. This analytical tool will therefore aid marine biologists in locating corals with high climate tolerance that should be propagated in efforts to restore degraded reefs. 
Using Easy DOE to Evaluate Optimal Conditions for Organometallic Catalysis
Wednesday, October 23, 2024
Ped 6
Often involving sensitive reagents and complex, unstable products, the synthesis of organometallic catalysts can be challenging. Relatively weak bonds between metal centers and coordinating groups mean that aquo and dioxygen ligands can interrupt the desired molecular structure, frequently necessitating oxygen- and water-free working conditions. Following synthesis and characterization, the optimal conditions for these catalysts must be found. Costly and unsustainable metals such as rhodium, iridium, and palladium often form the centers of catalysts, and thus their consumption must be minimized. In this work, the relevance of Easy DOE to the optimization and analysis of three iridium catalysts is discussed in two groups of variables. The first set of conditions informs what the best working conditions of the catalysts are and helps outline its capabilities. Variables that are tested are the catalyst substituent (crown ether, methoxyethyl, or methyl), the substrate, the addition sodium or lithium salts, and the addition of water. The second set of conditions form an evaluation of environmental friendliness, nodding to Anastas and Warner’s criteria for green chemistry. Variables that are tested are the solvent (traditional solvents such as dichloromethane vs. greener choices such as acetonitrile), the pressure of hydrogen, and the sensitivity to oxygen. Easy DOE is employed to design these runs, slimming the input required to obtain meaningful data. Together, these two sets of conditions give a picture of the chemical environment that best suits the catalysts, as well as how to tune this chemistry for the greener.
Plate Map Dashboard: Unveiling Data Patterns with Multiview Visualization
Wednesday, October 23, 2024
Ped 2
Microtiter plate maps are a standard tool in laboratory experiments, allowing scientists to investigate physical, chemical, and/or biological reactions of test articles in various assays. Traditional data visualization methods of microtiter plates are often inefficient when conveying relationships unique to plate data, to include capturing both the spatial and temporal sources of variability. To address this problem, we created a JMP dashboard to visualize plate maps, providing users with unique insights into the spatial distribution and elements of their data. The dashboard facilitates easy visualization and exploratory data analysis through multiple interactive views of heat maps, scatter plots, and dose response curves on data simulated to highlight typical issues encountered in plate experiments. Users can dynamically switch between views, customize visualizations, and interact with individual or groups of data points that warrant probing. Additionally, the dashboard supports data filtering and annotation through row labeling, enhancing the interpretability and utility of plate map visualizations. The dashboard also serves as an effective tool in communicating data quality and potential areas of concern, such as plate and/or lab variability, or other process errors that may exist in the data. By facilitating flexible exploration and analysis of complex data sets, the dashboard empowers users to gain deeper insights from their plate-based experiments, accelerating scientific discovery and knowledge.
Narrowing Down Choice: Using Bayesian Methods to Determine the Right Yeast
Wednesday, October 23, 2024
Ped 4
In Novonesis’ pursuit to understand the performance of industrial yeast products in specific customer conditions, our application research and development groups excel in generating insightful data sets for screening top yeast candidates at customer scale. Scientists regularly employ statistics to address complex questions related to both broad and specific customer scenarios. The introduction of Bayesian methods into Python libraries has significantly enhanced our ability to compute models and facilitate data-based decisions based on probabilities, even when traditional statistically significant results are not available. Additionally, the new capabilities in JMP 18 enable seamless integration with Python, empowering our scientists to generate large data sets and address customer-specific inquiries without leaving JMP. By leveraging application research data, customer trial data, and prior information, we are embarking on a journey to characterize our decisions based on informed data and Bayesian statistics, rather than relying on statistically insignificant trends. This approach aims to provide a more comprehensive understanding and quantification of performance, ultimately leading to more informed decision making.
Using DOEs and MCSs in Structural Assessments of Subsea Equipment
Wednesday, October 23, 2024
Ped 7
A marine drilling riser system is used in offshore exploration as a conduit connecting the drilling vessel with the subsea well. It is a complex structural subsea piping system commonly constructed by 75-90-feet long joints, typically sequentially assembled until they reach the wellhead, sometimes at water depth exceeding 10,000 feet. In a recertification project of a riser system meant to ensure compliance with regulatory requirements, inspection findings strongly indicated that the system had been exposed to an accelerated corrosion process. Corrosion rates for carbon steel in a seawater submerged application are normally measured to 0.1-0.4 mm per year. The inspection data showed localized corrosion rates exceeding 4 mm per year. Thirty riser joints were completely disassembled and inspected. However, 65 riser joints were inaccessible as they were located offshore and already in service. To quantify the operational risks and estimate the probability of non-compliance with the governing code, it became urgently necessary to extrapolate the corrosion data from the 30 inspected units to the inaccessible 65 units. Data distributions from the sample of 30 riser joints was used to run Monte Carlo simulations, using transfer equations modelled through a Fast Flexible Filling Design DOE in which the responses were generated through deterministic computer simulations. While the results of the simulations showed that the risk of non-compliance was unacceptable if the system was utilized to its design limits, even a slight reduction of the pressure level in the pipes reduced the risk of non-compliance to acceptable levels.
LEGO: Predicting New Sets That Have a Better Return on Investment Than Gold
Wednesday, October 23, 2024
Ped 5
LEGO has had a long history of manufacturing toys, particularly in the development of their branded interlocking plastic bricks. Over the years, this history has created generations of block-building enthusiasts who grew up with LEGO and continue to collect new sets into adulthood. It's no wonder that LEGO has become a semi-mainstream investment, as a study published in Science Direct in 2022 reported these sets have a better rate of return than even gold. Is it possible to predict which sets are worth purchasing over others? In our study, we calculated return on investment (ROI) for each set based on the original USD MSRP of the set vs the current price it fetches. We then compared the LEGO set ROI against ROI for gold calculated from the average yearly opening/closing stock price for gold since 2014. The model then determined if a LEGO should be purchased if the set's ROI was greater than gold's. Of five tested, XGBoost was the winning model, as the model predicted it performed 1.8 times better than a random selection in the top 30% of LEGO sets. Our research proved that many LEGO sets have a higher ROI than gold; our model can even predict which sets will have higher ROI. Collectors can use our model to determine if a purchase will be a worthwhile investment, and even novices can feel confident that they are making a valuable purchase. This research used JMP Pro 17.
Using Graph Builder to Improve Data Quality in Fiber Photometry Data Sets
Wednesday, October 23, 2024
Ped 7
Fiber photometry is a cutting-edge technique that captures real-time in-vivo brain activity in laboratory animals. Often aligned with video-tracked behavioral data, fiber photometry allows scientists to directly pair observed behavior and brain signaling. While fiber photometry is useful for novel behavioral experiments, each experimental step (data collection, processing, analysis) introduces the possibility of error. As such, ensuring research is reproducible is critical, but the size of the data sets (up to 0.25 gigabytes) makes quality control a cumbersome task. JMP Graph Builder provides an excellent interface for dynamically and efficiently identifying quality control issues. In a project using fiber photometry to understand how norepinephrine signaling accompanies fear behavior in rodents, we used JMP to detect misalignment between the Ethovision XT-tracked behavior data and the fiber photometry data, to provide easy identification of behavioral tracking disruptions and to ensure that expected patterns were present. These quality control checks allowed for timely understanding of, intervention to, and correction to the data set, thus promoting research integrity. Additionally, the quality control plots gave scientists a novel and insightful way to understand their experiments. Graph Builder provided data quality checks for a sound analysis via JMP’s modeling platform. The scientists were also able to use JMP scripts and were motivated to learn how to use JMP themselves from this process. In this talk, we showcase the problem of quality control for large, complicated data sets, as exemplified through fiber photometry, and how JMP’s graphing capabilities allowed us to ensure quality data and reproducible research.