Sometimes, when it rains it pours.
Amidst an ongoing in war in Ukraine, a powerful earthquake hits Japan, and a COVID-19 surge leads to a lockdown in China. These black swan events have devastated millions of lives and disrupted operations on every continent. This week, I was going to rehash the tough decisions business leaders are making to continue doing business in Russia, navigate sanctions on Russia, shut down production in China, or monitor the situation in Japan, but instead let’s look to the future and how technology is making industry more resilient to an increasingly chaotic world.
Imagine a world where manufacturing moves at the pace of software. Artificial intelligence instantly revises demand forecasts and provides new scenarios to leaders they may have never dreamed of. Machine learning sifts the product catalog to identify any products that may face sanctions and surfaces the best possible parts that can be manufactured at a different location. Digital twins of factory layouts and machinery run optimization algorithms to find extra space for more production or different product mixes. Operators log in to the metaverse to receive interactive virtual training with digital work instructions on the new equipment headed their way. Industrial robots adapt in real time to changing material handling routes and assembly tasks. Missing part schematics are downloaded from the cloud and printed via additive manufacturing locally while intellectual property is protected. This world is not far from where we are today, let’s keep building it.
Ford rolls out autonomous robot-operated 3D printers in vehicle production
Leveraging an in-house-developed interface, Ford has managed to get the KUKA-built bot to ‘speak the same language’ as its other systems, and operate them without human interaction. So far, the firm’s patent-pending approach has been deployed to 3D print custom parts for the Mustang Shelby GT500 sports car, but it could yet yield efficiency savings across its production workflow.
“This new process has the ability to change the way we use robotics in our manufacturing facilities,” said Jason Ryska, Ford’s Director of Global Manufacturing Technology Development. “Not only does it enable Ford to scale its 3D printer operations, it extends into other aspects of our manufacturing processes – this technology will allow us to simplify equipment and be even more flexible on the assembly line.”
At present, the company is utilizing its setup to make low-volume, custom parts such as a brake line bracket for the Performance Package-equipped version of its Mustang Shelby GT500. Moving forwards though, Ford believes its program could be applied to make other robots in its production line more efficient as well, and it has filed several patents, not just on its interface, but the positioning of its KUKA bot.
Automation: Why software is the star
As fulfillment centers and warehouses become more highly automated facilities with multiple types of automation, software’s role looms larger. Issues like coordinating multiple systems around cut-off times and service levels, as well as knowing when and how to scale automated systems to accommodate peaks in demand, are two leading reasons why.
One way a warehouse execution system (WES) coordinates the allocation of work across automated systems is with smart order release, which instead of the big “waves” of work, releases work to systems in smaller chunks with the current status and capacity of multiple zones of automation in mind. This order release function can be thought of as the starting point for orchestration, with WES’s ties to lower-level control systems alerting of any unexpected events, or bottlenecks, that might be developing, with some software offering “load balancing” features to help adjust to the present reality on the floor.
With robotics solutions, software plays at multiple levels. Autonomous mobile robot (AMR) vendors, for example, don’t just make robots, they also offer fleet manager software, performance monitoring and analytics. Some vendors are also expanding into broader orchestration with functions like pack-out lines. Of course, artificial intelligence (AI) is in many robotics solutions, so the system can continuously learn over time when it comes to issues like path optimization, or how to best grasp and manipulate items.
Action-limited, multimodal deep Q learning for AGV fleet route planning
In traditional operating models, a navigation system completes all calculations i.e., the shortest path planning in a static environment, before the AGVs start moving. However, due to constant incoming offers, changes in vehicle availability, etc., this creates a huge and intractable optimization problem. Meanwhile, an optimal navigation strategy for an AGV fleet cannot be achieved if it fails to consider the fleet and delivery situation in real-time. Such dynamic route planning is more realistic and must have the ability to autonomously learn the complex environments. Deep Q network (DQN), that inherits the capabilities of deep learning and reinforcement learning, provides a framework that is well prepared to make decisions for discrete motion sequence problems.
Highly flexible AGV solution in truck cabin production
The Hidden Factory: How to Expose Waste and Capacity on the Shop Floor
Without accurate production data, managers simply cannot hope to find the hidden waste on the shop floor. While strict manual data collection methods can take job shops to a certain degree, the sophisticated manufacturer is leveraging solutions that collect, aggregate, and standardize production data autonomously. With this data in hand, accurate benchmarks can be set (they may be quite surprising) and areas of hidden capacity, as well as waste-generators, can be far more easily identified.
How to Use Data in a Predictive Maintenance Strategy
Free-Text and label correction engines are a solution to clean up missing or inconsistent work order and parts order data. Pattern recognition algorithms can replace missing items such as funding center codes. They also fix work order (WO) descriptions to match the work actually performed. This can often yield a 15% shift in root cause binning over non-corrected WO and parts data.
With programmable logic controller-generated threshold alarms (like an alarm that is generated when a single sensor exceeds a static value), “nuisance” alarms are often generated and then ignored. These false alarms quickly degrade the culture of an operating staff as their focus is shifted away from finding the underlying problem that is causing the alarm. In time, these distractions threaten the health of the equipment, as teams focus on making the alarm stop rather than addressing the issue.
Nakamura Tome Plant Tour
A new perspective on the mining industry
Certain geologies and structures ultimately have different vulnerabilities. Entering known data into a simulated environment or kind of digital twin, can help figure out the unknowns, assisting miners to decide where and how to apply their efforts. This is essential for remotely managed or autonomous vehicles that can achieve low waste, and efficient extractions in harsh or dangerous locations. Autonomous vehicles can actually extend operation hours, increasing productivity as well as reducing the use of energy hungry and personnel centred equipment. In an IoT network these may increasingly incorporate ‘intelligent’ or ‘smart’ devices that not only store or transmit but process data – as in a ‘smart factory’. “We’re seeing opportunities with sustainability oriented projects in Canada and Europe,” Sym-Smith says.
Minexx’s software platform uses blockchain digital distributed ledger, payments, biometric and IoT technologies to create much-needed trust and transparency around quality and methods of production. This helps clients manage aspects of know your customer (KYC) and anti-money laundering regulations as well, giving them and the artisanal miners access to markets and better prices. “Once data is on the blockchain, you can’t change it. Then essentially you give the manufacturer the key,” Scaramanga says.
The business of sustainability in steelmaking
These upgrades at the Train 2 plant allowed ArcelorMittal to save 15-20% on installation, reduce downtime by 5-10%, save 170 equivalent metric tons of CO2, and prevent reprocessing 26 tons of materials. Sensor-based equipment condition monitoring also let the steelmaker’s staff track energy use and identify potential faults before they cause downtime. These improvements also increase the facility’s installation reliability, energy efficiency, personnel safety and equipment life with predictive maintenance.
Robots move on from flipping burgers and into frying tortilla chips. While instant noodles are getting a new US factory. Defense tech remains hot, but start-ups are struggling to break in and AI suggests thousands of new chemical weapons. MIT makes progress on AI that has some common sense.