BigData_ass6

docx

School

Southern New Hampshire University *

*We aren’t endorsed by this school

Course

260

Subject

Industrial Engineering

Date

Dec 6, 2023

Type

docx

Pages

3

Uploaded by jfoll

Report
Katie Letson DAT-260 Module 6 assignment 10/6/2023 I chose the category predictive maintenance. I picked a heavy equipment company that would use a prognostics algorithm to predict the machines (RUL) remaining useful life or time -to-failure prediction by analyzing the machines current state. Unsupervised learning algorithms use clustering and anomaly detection as well. Machine learning possess the ability to handle multivariate, high dimensional data and can extract hidden relationships within data in complex, dynamic, and chaotic environments[ CITATION Zek20 \l 1033 ]. Machine learning and modeling are used by prognostics to predict the future value of condition indicators. Doing this enables this company to be alerted to diagnosed faults and equipment failure estimations of occurrence. This allows the company to plan maintenance before a problem occurs, cutting down on expensive equipment or part replacement. The company will be able to reduce downtime, increase efficiency of the operation, and manage inventory more accurately. It will also keep the company from costly stand-still time because they are waiting for parts, equipment, or for a mechanic to fix broken equipment. This can change a company that is failing or struggling to survive into a thriving company that has a competitive edge. Customers will notice less incidents where timing is of importance. They will want to come back to this company repeatedly for this service because it will gain a reputation for reliability, little wait time, and maximum efficiency. Using smart sensors, your understanding of the industries interworking’s, actuators, radio frequency tags, and many more can enhance industry processes and in turn elevate customers satisfaction and security[ CITATION Pri23 \l 1033 ]. All these aforementioned components are networked together to collect data, exchange, and analyze. They will merge historical performance data,
engineering specs, and real-time analytics[ CITATION Mic201 \l 1033 ]. Then based on this specific to the user alarms based on conditions and alerts are set up to allow the user to fix this problem long before it ever occurs if it even does. There are many tools that AI may use such as ultra sonic analysis, infrared analysis, oil analysis, motor circuit analysis, vibration analysis, or laser shaft alignment. Usually a program will be set up by identifying critical assets, creating a data base with historical data, analyzing failure mode, and then the failure predictions are made. Then you will deploy the predictive maintenance technology to pilot equipment groups to validate the program. In the past people had very little idea when a machine was going to have an issue or breakdown and it left companies with costly downtime. It also caused customers to have to wait for mechanical work, adjustments in time frame for job to be completed, and changes in cost from original estimate. Theses are only a few examples and there are many more. Now with ML and IoT being utilized in companies to predict maintenance needed before an event or occurrence of breakdown ever takes place it has helped many businesses to optimize their company performances, cut cost, better utilize time and employee’s workload, and see a rise in repeat customers and customer satisfaction. There are so many benefits to utilizing machine learning because it can identify clusters, patterns, and trends using historical data and sensors that indicate many helpful, efficiency boosting, and cost cutting processes or maintenance is needed. This eliminates the guess work and cuts out downtime and wait-time keeping a company running at maximum production efficiency. It is a revolutionary tool that has changed the industry completely to optimize operations and I foresee this developing more and being used much more in the years to come. References
Apple, S. (2019). Smarter, healthier, more productive: how Uptake is revolutionizing heavy industries with AI+IoT. Havard Business School . Michael Horrell, L. R. (2020). Data Science in Heavy Industry and the Internet of Things. Havard Data Science Review, 2 (2). Sinha, P. (2023). Introduction To Industrial Digitalization. Evalueserve . Zeki Murat Çınar, A. A. (2020). Machine Learning in Predictive Maintenance towards Sustainable Smart Manufacturing in Industry 4.0. Sustainability, 8211 , 1-42. doi:10.3390/su12198211
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help