DATA ANALYTICS IN MANFACTURING.pptx.hhhhh
- 1. DATA ANALYTICS IN MANFACTURING :IMPROVING DECISION MAKING -ASHOK GODARA
- 2. Data Analytics in Manufacturing Data analytics in manufacturing means using data collected from machines, processes, and systems to understand how a factory is performing. This data is then studied (or analyzed) to find ways to improve production, reduce costs, and increase efficiency. WHY IS IT IMPORTANT ? 1. REDUCED ERRORS : When we analyze data, we can find issues before they cause big problems. This helps reduce errors during production. 2. SAVES MONEY : By predicting when machines need maintenance or by improving how things are made, manufacturers can save money on repairs and materials. 3. IMPROVES EFFICIENCY : With the help of data, factories can work faster and smarter, making more products in less time.
- 3. Types of Data Collected in Manufacturing 1. Operational Data : This type of data is collected from machines and production lines. It includes details like the speed at which machines are running, their temperature, energy consumption, and any malfunctions that occur during production . Example : Machine RPM (Revolutions Per Minute), machine temperature 2. Product Data : Product data focuses on the quality of the items being produced. It includes measurements, tolerances, defect rates, and information about any issues with the final products. Example : Defect rates in a batch, measurements of product dimensions 3. Supply Chain Data : Supply chain data includes information about materials coming in and out of the factory, such as raw material deliveries, supplier performance, and inventory levels. Example : Delivery schedules, supplier lead times
- 4. How Data Improves Decision Making in Manufacturing • Faster Problem Solving : Data analytics tools provide real-time data from machines and processes, alerting workers immediately when something goes wrong. Instead of waiting until a machine breaks down or a defect is spotted, the system can notify teams of potential issues as they happen. • Cost Savings : Data from sensors can predict when machines are likely to fail. This allows manufacturers to perform maintenance before something goes wrong. By addressing maintenance issues early, companies can avoid expensive repairs and prevent machine downtime. • Quality Improvement : Data analytics can be used to track whether products meet quality standards and immediately flags any deviations from the desired specifications. • Data-Driven Decisions : With data readily available, factory managers can make decisions based on facts rather than guesswork. By using data, they can optimize everything from production schedules to workforce management.
- 5. Challenges in Implementing Data Analytics in Manufacturing 1. High Initial Investment : Implementing data analytics requires significant upfront costs. Companies need to invest in advanced technologies like sensors, data collection systems, and analytics software. They may also need to upgrade their machinery to be compatible with these new technologies. 2. Data Integration Issues : Many factories use different machines and software systems that do not naturally “talk” to each other. Bringing all the data together from these different sources (sensors, machines, supply chains) into one unified system can be a complex task. 3. Skill Gaps and Training : Data analytics requires skilled workers who understand how to use the tools and interpret the data. Many manufacturers may not have employees with the necessary skills or may find it hard to train their existing workforce to use these new systems effectively. 4. Data Security and Privacy Concerns : As more manufacturing data is collected and stored, there is an increased risk of cyberattacks and data breaches . Sensitive information about production processes, designs, and supply chains could be vulnerable to hackers
- 6. Future Trends in Data Analytics for Manufacturing 1. AI and ML for Predictive Analytics : AI and ML will continue to play a bigger role in predicting outcomes, optimizing processes, and automating decision-making. In the future, AI-driven analytics will be able to predict machine failures, optimize production schedules, and suggest the most efficient use of resources with even greater accuracy. 2. Digital Twins : A digital twin is a virtual model of a physical process, machine, or system. In the future, manufacturers will increasingly use digital twins to simulate, predict, and optimize their operations. 3. Edge Computing and Real-Time Analytics : Edge computing refers to processing data at or near the source of data generation (e.g., on the factory floor) instead of sending it to a centralized cloud. 4. Autonomous Factories : n the future, manufacturing will move toward more autonomous operations, where machines, robots, and processes can run with minimal human intervention. . Data analytics will drive this trend, allowing machines to self-optimize and self-diagnose issues. 5. Greater Focus on Sustainability : Data analytics will increasingly be used to support sustainability efforts in manufacturing. Manufacturers will use data to optimize energy use , reduce waste and improve environmental performance .
- 7. THANK YOU