Discrete manufacturing is used in many varied industries, a few examples being automotive, electronics, aerospace, consumer goods, and machinery manufacturing. Unlike continuous manufacturing, which involves continuous processes like oil refining, discrete manufacturing often involves assembly processes where individual parts and components are combined to create the final product.
In the realm of discrete manufacturing, factory archetypes provide a practical framework to categorize factories based on two vital factors: the range of product variants produced and the average lot size.
By analyzing the impact of AI on specific industries in discrete manufacturing, we can offer insight into how these archetypes are tackling their corresponding challenges.
The provided chart offers valuable insights into factory archetypes. By analyzing this, we can better understand how Industry 4.0’s key value drivers impact different industries.
Discrete manufacturing finds itself ideally suited for a range of AI applications, including:
- Quality Control and Defect Detection on assembly parts and final product
- Anomaly Detection for different stages of production
- Predictive Maintenance
- Inventory Optimization
- Supply Chain Management
- Demand Forecasting
Discrete manufacturing is increasingly incorporating digital technologies, such as IoT (Internet of Things), data analytics, and automation, to enhance productivity, traceability, and real-time monitoring of production processes. This digitalization would be the first step towards identifying the right opportunities where AI/ML can help, while also making it financially viable. At Bridge Automation, we specialize in helping you identify these opportunities, harnessing the power of AI and ML to optimize your manufacturing operations. By leveraging data analytics, machine learning algorithms, and automation solutions, we enable you to make data-driven decisions, reduce downtime, improve product quality, and ultimately increase your competitive edge in the ever-evolving landscape of discrete manufacturing.
To give you a better understanding of how AI/ML could solve problems and add long-term value to your manufacturing operations, here are several examples of AI in action!
AI in Action: Real-world Examples
Automotive Manufacturing
In automotive manufacturing, one archetype stands out prominently: Mass Customized Production. In this highly competitive industry, where innovation and adaptability are paramount, the mass-customized production archetype takes center stage. This approach involves striking a delicate balance between product customization and the relentless pursuit of efficiency.
Now, as artificial intelligence (AI) continues to revolutionize manufacturing processes, the automotive sector finds itself at the forefront of adopting these technologies.
- AI-powered robotic vision systems are used to inspect and identify defects in real time. Examples include:
- Check whether all the parts have been mounted and are mounted at the right place in the assembly lines
- Compare and verify if the produced car and the vehicle order data are an exact match
- Paint quality prediction with great accuracy
- Detection of oil residues or dust particles on metal sheets
- Bots to inspect areas of products that fixed cameras simply can’t access
- Dust level detection: monitor trends and notify at an early stage
- Predictive Maintenance: AI algorithms analyze sensor data from manufacturing equipment to predict when maintenance is needed, reducing unplanned downtime.
- Inventory Management: AI-driven systems optimize inventory levels, ensuring that essential components are always available without overstocking.
Electronics Manufacturing
- Root cause analysis using test machine data: Testing electronic components during manufacturing is a critical step to ensure the quality, reliability, and functionality of the final products. Various tests are conducted to ensure components meet specifications and guarantee they can perform under expected operating conditions. The data from these tests can help identify problem areas and potentially the cause behind test failures. These tests include but aren’t limited to Temperature, Burn-In, Emissions and Interference, and Life Cycle Testing.
- Visual Inspection: Small defects in electronics can easily be overlooked by a human who can become tired, or simply not be able to see the defect. AI solutions, on the other hand, are constantly able to use data and sensors to carry out quality control tasks consistently and accurately. Many manufacturers employ engineers to hard-code algorithms that help the system identify faulty and good units. While they can be effective, they cannot adapt and learn, which has the potential to create a high false-positive rate. An example of small defects in printed circuit boards (PCBs) is shown below. [1]
Consumer goods: Apparel Manufacturing
Visual Inspection: In apparel manufacturing, AI-powered visual inspection systems can be seamlessly integrated into production lines to detect defects like color mismatches, stitching issues, and stains. This technology ensures consistent product quality and enhances production efficiency, reducing the need for manual inspection and saving costs.[2]
Furniture Manufacturing
- Process Improvement such as increasing varnishing process efficiency: By gathering data from machines a predictive model can be developed to estimate the amount of varnish that the machine deposits on a piece. These models can take into account various factors to provide accurate predictions, such as machine settings, material characteristics, and environmental conditions. This information not only ensures consistent product quality but also helps optimize varnish usage, reducing wastage and cost [3].
- Visual inspection in furniture manufacturing involves ensuring the quality of both the fabric and wood used in furniture production. AI-powered visual inspection systems can be trained to identify specific types of defects that manufacturers need to detect.
- Size and Length Inspection: By deploying sophisticated machine learning algorithms and computer vision technology, manufacturers can ensure precise and consistent measurements of furniture components. Cameras and sensors can accurately detect deviations from specified dimensions, identifying any inconsistencies or defects that may arise during production. This real-time monitoring not only enhances the quality control process but also significantly reduces human error and the need for manual inspections.
BOTTOM LINE
In discrete manufacturing, the collaboration of digitalization and AI presents a transformative opportunity. As we’ve seen across industries, AI applications are optimizing production processes, ensuring quality, and driving efficiency. Bridge Automation helps manufacturers within this sector reach these goals and drive change toward Industry 4.0/5.0. Contact us to learn more about these tailored solutions at info@bridgedata.tech.
References
Venkat Anil Adibhatla, Huan-Chuang Chih, Chi-Chang Hsu, Joseph Cheng, Maysam F. Abbod, Jiann-Shing Shieh. “Applying Deep Learning to Defect Detection in Printed Circuit Boards via the Newest Model of You-Only-Look-Once.” Mathematical Biosciences and Engineering 18, no. 4 (2021): 4411-4428.
Rocha, Daniel, Leandro Pinto, José Machado, Filomena Soares, and Vítor Carvalho. “Using Object Detection Technology to Identify Defects in Clothing for Blind People.” Sensors 23, no. 9 (2023): 4381.
Juan Del Agua and Gabriel Modia. “A Practical Experience of AI Solution Used to Improve Varnishing Process Efficiency in Furniture Manufacturing.” In Proceedings of the Workshop of I-ESA’22, March 23–24, 2022, Valencia, Spain.
McKinsey & Company. (2019). Capturing value at scale in discrete manufacturing with Industry 4.0. McKinsey & Company. https://www.mckinsey.com/industries/industrials-and-electronics/our-insights/capturing-value-at-scale-in-discrete-manufacturing-with-industry-4-0