Worker Safety
Assembly Line
Time series prediction model using LSTM-Transformer neural network for mine water inflow
Mine flooding accidents have occurred frequently in recent years, and the predicting of mine water inflow is one of the most crucial flood warning indicators. Further, the mine water inflow is characterized by non-linearity and instability, making it difficult to predict. Accordingly, we propose a time series prediction model based on the fusion of the Transformer algorithm, which relies on self-attention, and the LSTM algorithm, which captures long-term dependencies. In this paper, Baotailong mine water inflow in Heilongjiang Province is used as sample data, and the sample data is divided into different ratios of the training set and test set in order to obtain optimal prediction results. In this study, we demonstrate that the LSTM-Transformer model exhibits the highest training accuracy when the ratio is 7:3. To improve the efficiency of search, the combination of random search and Bayesian optimization is used to determine the network model parameters and regularization parameters. Finally, in order to verify the accuracy of the LSTM-Transformer model, the LSTM-Transformer model is compared with LSTM, CNN, Transformer and CNN–LSTM models. The results prove that LSTM-Transformer has the highest prediction accuracy, and all the indicators of its model are well improved.
Upgrading Safety Asset Planning and Incident Investigations with Digital Twins
Using the Optelos Safety Asset Planning capabilities with digital twins, facilities can more effectively manage the placement and oversight of safety equipment, create turnaround safety plans, investigate incidents, and more easily and effectively present safety data to leadership and employees.
Recent technology developments put significant safety improvements and risk reduction within reach. The powerful combination of drone data collection, digital twin reality models, and visual data management can enhance site safety and reduce risks to personnel through geolocation of safety-related assets in a digital twin model, enabling visualization of safety and incident response data.
Industry must tackle its first-lift/last-lift manual handling blind spot
For example, an injection mould, press or progression tooling, welding, drilling and boring jigs, heavy batteries and gearboxes or CNC tooling will often be heavier than the recommended maximum manual lifting weight of 25kg or 55lb. Moving this sort of equipment around a facility will typically require lifting, lowering, carrying, pushing and pulling by either an employee or by equipment such as a forklift.
What is required is a low-cost, easily installed solution for this first-lift and last-lift problem. The answer may lie in the use of omnidirectional ball transfer units, expertly designed to facilitate the movement of tools and other equipment around a storage facility and onto a transporter. They can be installed in existing racking and require neither power nor software, making them quick to implement.
AI, chip manufacturing helping grow Trane Technologies workforce in Fort Smith
The workforce at the Trane Technologies commercial HVAC manufacturing facility in Fort Smith has grown by more than 50% in the past year thanks to unique products made at the plant used in the growing AI and chip manufacturing sectors. They’ve experienced this work while managing to continue a standard in safety that led them to celebrate Wednesday (Feb. 21) 5 million hours, approximately 12 years, without a lost day from work due to a work-related injury or illness.
The Fort Smith facility has been in operation for 29 years at the site near the City of Fort Smith Landfill. The plant has 200 employees who manufacture custom HVAC units, custom air-handling systems, and components for commercial applications. The ultra-high efficiency and precise space heating and cooling capabilities of these products are ideal for a variety of commercial building applications, including schools, office buildings, health care, multi-family residential, hotels, and more, a news release said.
Making air conditioner manufacturing cool again
In just six months, Liebherr-Transportation Systems completely reconstructed two manufacturing lines, significantly upgrading them in the process. “The facility was divided into these three manufacturing lines because the three areas require very different manufacturing steps, and need to handle components of differing sizes,” Ahmad said.
The manufacturing lines – apart from the E-Box manufacturing – were first set up and tested in Korneuburg. What was especially pleasing to the two responsible persons in Korneuburg was the fact that many previously absent technologies were being used. A Kanban material delivery system and semi-automatic test steps were developed, the manufacturing became paperless, and the issue of safety gained an entirely new importance as it was able to be completely revisited.
The new production lines use, among other things, the intelligent deTec safety light curtains, TR110 Lock safety switches with locking function, various safety command devices (like emergency stop, reset, and enabling switches), signal lamps, various safety switches, and the versatile, programmable Flexi Soft safety controller.
Using the Power of AI to Make Factories Safer
AI-powered stationary outside-in safety platforms, which monitor activity across many distributed machines or robots, can predictively and proactively orchestrate consistent safety policies. Machines and robots equipped with inside-out reactive safety can detect any specific interaction within their workspace and take appropriate measures.
If the worker continues or crosses the stop safety zone, the FORT safety stack on IGX commands (WiFi) the FORT endpoint (embedded in the machine) to activate the emergency stop (reactive safety). The Protex edge computer vision app uses NVIDIA DeepStream 6.2 and the Protex model has been trained with NVIDIA TAO Toolkit and quantized with NVIDIA TensorRT.
Teardown: What’s Inside a Solenoid-Controlled Safety Interlock?
There are multiple signals inside a safety switch - even more than inside standard E-stop buttons. Four of the terminals are dedicated to sensing the condition of the switch internally, both the solenoid’s position and the actual position of the lock. Two terminals provide control power to the solenoid (supplied from another safety circuit). Two other terminals provide an auxiliary monitor for the status of the lock. Finally, the last two terminals provide a selectable input, either to provide power to an indicator LED or to monitor the position of the solenoid.
Comau’s MATE-XT wearable exoskeleton supports ergonomic well-being at John Deere’s parts distribution center in Brazil
Comau has equipped John Deere with multiple MATE-XT wearable exoskeletons to help sustain worker well-being, alleviate physical stress and reduce the ergonomic risk within its parts logistics operations. MATE-XT accurately replicates all movements of the shoulder, helping employees perform their jobs comfortably by reducing muscle fatigue without limiting mobility or adding bulk. Its ergonomic design can be easily adjusted to fit different people with different body types – changing the length of the shoulder straps and the required level of assistance based on the worker or the job at hand is quickly achieved in a few simple steps. Working closely with John Deere to implement the exoskeleton within its daily operations, Comau provided a hands-on training course held at John Deere’s 75,000m2 parts distribution center in Campinas, in the state of São Paulo.
Even when working with small and lightweight objects, the apparently minimal effort of repeated manual movements can take a toll on the body. To help John Deere quantify the benefits of using MATE-XT, Comau performed an electromyographic analysis of the ergonomic risk factor. MATE-XT kept the muscle at a rest stage for 98.5% of the activity time (compared to only 2.4% of the time without MATE-XT).
Cobots Install Cable Ties
The cobot program for installing the cable ties was designed in Polyscope, Universal’s programming software. The program works for two different harness assembly boards.
Finally, we did an ergonomic analysis of the new cable tie installation process using RULA and JSI. After measuring the angles of various body parts, the values of Groups A and B were calculated according to RULA. The value for Group A was 3, and the value for Group B was 4, resulting in a final score of 4. This score is significantly lower than the original manual operation. Similarly, the JSI for the automated station was 4.5, which is lower than the risk level for the manual operation. Our project clearly shows that cable tie installation task could be automated, improving ergonomics.
Improving Conveyor Belt Safety For Mining Worksites
In 2020 alone, the Mine Safety and Health Administration (MSHA) reported 29 fatalities in the mining industry in the United States. Additionally, the MSHA reports that the rate of non-fatal injuries in mining was 2.9 per 100 full-time workers in 2020–indicating the importance of ensuring proper safety measures are in place to prevent accidents and injuries in mining operations.
While essential to many large-scale mining operations, conveyor belts are involved in many mining site safety incidents. Conveyor belt accidents often highlight a lack of training, an absence of proper PPE, or a failure to implement the right safety measure to protect the employees who operate, maintain, or work alongside of these belts.
Lockout Tagout (LOTO) is a safety procedure used to protect workers from hazardous energy machinery and equipment, such as conveyor belts. Wireless emergency stops are a valuable safety feature that can make bulk material handling on conveyor belts in mining safer. These stops allow workers to shut down the conveyor belt quickly and safely from a distance if an emergency arises. Unlike traditional emergency stops that require physical contact with the machinery, wireless emergency stops can be activated remotely, providing an additional layer of safety if something unexpected occurs.
👷 How smart manufacturing can alter safety standards
An essential component of smart manufacturing is the ability to automate hazardous activities. The evolution of automation in manufacturing has been a game-changer, and it’s why workplace injuries have steadily decreased over the years.
An example of this is at Rolls-Royce, where the adoption of cutting-edge Industry 4.0 technologies is helping to enhance safety and ensure a safer working environment for employees. With the use of 3D visualisation software, employees can have a better understanding of their workplace, including potential hazards. Meanwhile, machine learning technology is assisting in monitoring personal protective equipment (PPE) compliance, and the deployment of robotic arms is taking over tasks that were once considered dangerous, such as furnace operations, thus reducing the need for manual labour.
New NVIDIA IGX Platform Helps Create Safe, Autonomous Factories of the Future
NVIDIA today introduced the IGX edge AI computing platform for secure, safe autonomous systems. IGX brings together hardware with programmable safety extensions, commercial operating-system support and powerful AI software — enabling organizations to safely and securely deliver AI in support of human-machine collaboration. The all-in-one platform enables next-level safety, security and perception for use cases in healthcare, as well as in industrial edge AI.
Gas-Detecting Wearable Reduces Injury, Increases Safety
A new worker safety wearable has entered the market – one that can rapidly detect gas, connect workers to managers and store data to give a holistic understanding of operational risks. The wearable device features direct-to-cloud cellular connectivity, a single platform to connect and view all devices from a single portal, and GPS mapping to allow managers to quickly locate workers in trouble and understand on-the-ground incidents.
Stray Magnetic Fields and Safety
Bunting is at the heart of the electrification program of the world’s vehicles. By producing magnetising systems that allow for genuinely error-free assembly and providing 100% inline testing, Bunting supports automotive and aerospace programmes looking to create new modes of travel and improve efficiency. Bunting is proud to support this sustainable engineering activity to provide a greater level of energy security for all future generations.
During the development of these electric machine magnetising systems, one of the most common questions our customers ask our engineers is: “How can we keep our staff safe from stray electromagnetic fields?”.
TELUS: Solving for workers’ safety with edge computing and 5G
Together with Google Cloud, we have been leveraging solutions with the power of MEC and 5G to develop a workers’ safety application in our Edmonton Data Center that enables on-premise video analytics cameras to screen manufacturing facilities and ensure compliance with safety requirements to operate heavy-duty machinery. The CCTV (closed-circuit television) cameras we used are cost-effective and easier to deploy than RTLS (real time location services) solutions that detect worker proximity and avoid collisions. This is a positive, proactive step to steadily improve workplace safety. For example, if a worker’s hand is close to a drill, that drill press will not bore holes in any surface until the video analytics camera detects that the worker’s hand has been removed from the safety zone area.
Boeing Bionics Allow Teammates to Suit up for Safety
In Boeing’s commercial division, the exoskeleton vest is in use or planned for use as personal protective equipment in the 737, 767, 777 and 787 Dreamliner programs. Teams at a number of Boeing sites have tested the vest since 2018. It is rolling out as an innovative enterprise standard tool designed to lessen the pressure mechanics bear as they work repetitive jobs at chest level and above.
“When you activate the vest, it’s somewhere between 5 to 18 pounds (2 to 8 kilograms) offloaded from the wearer,” said Dr. Christopher Reid, a Boeing engineer and Associate Technical Fellow who specializes in ergonomics and wearable technology. “It reduces the stress on the shoulders and ultimately reduces injuries.”
How AMRs change the safety equation
Soon, manufacturers and buyers wanted clear safety standards for AMRs from organizations like A3. They asked, “What guidance can you provide through a standard to help us understand how we can assess the safety of these devices?” Wise was on the committee that created Mobile Robot Standard R15.08-1-2020, the new Mobile Industrial Safety Standard. In April, Fetch announced full conformance with the standard.
As far as safety standards, Universal Robots follows the ISO standard that came out in 2011 (ISO 10218-1). This ISO standard is Part 1 of ANSI/RIA R15.06. She noted that European companies, like Universal Robots, tend to have higher requirements for safety, given the requirements of the European Directives.
A Framework for Ensuring Safe Plant Design and Operation in the Process Industries
The safety of industrial plants is a prerequisite for reassuring local communities and achieving a sustainable society. The process industries operate large, complex man-machine systems and even a single accident in a plant could cause immense damage to facilities, local communities, and the environment, and, in an extreme case, could destabilize the whole of society. To prevent such serious accidents, laws and regulations concerning process safety were discussed globally and the concept of risk reduction with multiple protection layers and a management system through the design and operation of safety instrumented systems was established as a framework for the safety of the process industries. This paper reviews this framework with reference to the trend of related standardization activities and introduces how AI is used to support safety in the process industries.
Where Four-Legged Robot Dogs Are Finding Work
How a startup uses AI to put worker safety first
Everguard.ai, a startup based in Irvine, California, combines AI, computer vision, and sensor fusion to reduce the risk of injuries and accidents by preventing them before they happen. The company’s SENTRI360 platform proves effective in preventing workplace injuries and operational downtimes at several steel-heavy manufacturing companies, including Zekelman Industries and SeAH Besteel.
Everguard’s CEO, Sandeep Pandya shared details about workers’ privacy, given the massive amount of data it captures and analyzes at client sites. “The most important thing is to give shop floor workers and their leaders the complete visibility into how the data collected is used. Our implementation teams work with them and provide complete access to our systems, how data is anonymized for specific tasks, and how we are careful to protect each workers’ identity,” Sandeep said.
Accelerating mining safety and smart mines with limitless connectivity
Digitalization can have a tremendous impact on safety, giving mine operators a clearer picture of the full breadth of operations, monitoring critical factors like air quality and tunnel strength. An optimized mine, especially one with the latest in 5G-enabled private networks, can give miners those crucial seconds that can save lives.
As private wireless networks, including the latest generation in 5G, help revolutionize mission critical industries across the country, mining stands out as a place where connectivity can foster major improvements, from safety to efficiency and productivity to better sustainability. Mine operations can be optimized by collecting and analyzing tracking data on the precise location and performance of vehicles, equipment and personnel.
The Semiconductor Health and Cancer Problem
Smart apparel that evaluates workers' physical workload
One of the biggest challenges faced by society in developed countries is an aging society due to a declining birth rate. What this means is that there is or will be a serious labor shortage both in terms of overall numbers as well as those with expertise or experience. To overcome this shortage, older people or foreign workers are being increasingly employed to fill the gap. At such sites, accidents or injuries due to unfamiliar work may occur. Thus, it is important to understand how the physical workload is being handled in order to ensure a healthy and safe work environment. In this blog, I’d like to talk about the work that we are doing to quantitatively visualize strain and enable the most appropriate response based on the physical load.
In collaboration with Xenoma Inc., the German Research Center for Artificial Intelligence (DFKI) and its spin-off sci-track GmbH, Hitachi is pursuing the research and development of wearable AI technology that monitors workers physical load at all times in an effort to achieve solutions that improve worker safety and health in industrial fields.
Break Through Supply Chain Blocks with Automated Container Unloading
Boston Dynamics is beginning to deploy Stretch, an autonomous case-handling robot poised to change the way warehouses and ports operate. Expected to be available later in 2022, the robot can work up to 16 hours on a single battery charge, so companies can send Stretch to unload trucks or containers for full shifts both day and night.
Built on a compact, wheeled base, Stretch can travel easily to each point of activity in a distribution center. The robot is self-reliant, untethered by power cables or air lines. Its vacuum-based gripper, at the end of a robotic arm with long reach, is designed to grasp a wide variety of box types required for a truly valuable solution in the logistics industry. With its small, pallet-sized footprint and embedded smarts, Stretch needs no pre-programming or overhaul of existing warehouse equipment to begin working, and is ready to deploy in just days.
Hyundai Motor Group x Boston Dynamics Factory Safety Service Robot
Real-World ML with Coral: Manufacturing
For over 3 years, Coral has been focused on enabling privacy-preserving Edge ML with low-power, high performance products. We’ve released many examples and projects designed to help you quickly accelerate ML for your specific needs. One of the most common requests we get after exploring the Coral models and projects is: How do we move to production?
- Worker Safety - Performs generic person detection (powered by COCO-trained SSDLite MobileDet) and then runs a simple algorithm to detect bounding box collisions to see if a person is in an unsafe region.
- Visual Inspection - Performs apple detection (using the same COCO-trained SSDLite MobileDet from Worker Safety) and then crops the frame to the detected apple and runs a retrained MobileNetV2 that classifies fresh vs rotten apples.
Augmented reality becomes actual reality
When applied to electrical power distribution across a wide range of businesses and industries, AR has the potential to greatly increase power availability, electrical safety, and efficiency. Here’s why:
- Availability: AR helps organizations optimize operations and maximize continuity for better productivity and profitability
- Safety: AR helps to reduce the risk of occupational injuries and fatalities
- Efficiency: AR help reduces the total cost of ownership by offering more accessible and effective training
AI Vision for Monitoring Applications in Manufacturing and Industrial Environments
In traditional industrial and manufacturing environments, monitoring worker safety, enhancing operator efficiency, and improving quality assurance were physical tasks. Today, AI-enabled machine vision technologies replace many of these inefficient, labor-intensive operations for greater reliability, safety, and efficiency. This article explores how, by deploying AI smart cameras, further performance improvements are possible since the data used to empower AI machine vision comes from the camera itself.
Collaboration requires presence sensing
The challenge of automation has always been to keep people safe while trying to produce more product in the same footprint. The faster a machine runs, the more physical space is required to guarantee that, if something goes wrong, the machine has enough time to come to a complete and safe stop before potentially making contact with humans or other machines around it. Traditionally, this would involve a physical cage around the piece of automation. This cage could take the form of a frame with either polycarbonate or expanded steel (fence) panels.
Made to physically defend a person from getting too close, these types of guarding systems also take up a lot of real estate. For this reason, they are not well-suited to a cobot application where we don’t want the new automated device taking up any more space than the human it is replacing.
The technology required to respond to this need for an ever tighter operating envelope has advanced dramatically, especially over the past two or three years. While we will delve into that momentarily, it is important to note that the robot manufacturers, in addition to coming up with new ways to sense the presence of people in proximity to the robot, have had to come up with ways to safely limit the range of operation to be inside the normal operating range of the robot.
Amazon’s robot arms break ground in safety, technology
Robin, one of the most complex stationary robot arm systems Amazon has ever built, brings many core technologies to new levels and acts as a glimpse into the possibilities of combining vision, package manipulation and machine learning, said Will Harris, principal product manager of the Robin program.
Those technologies can be seen when Robin goes to work. As soft mailers and boxes move down the conveyor line, Robin must break the jumble down into individual items. This is called image segmentation. People do it automatically, but for a long time, robots only saw a solid blob of pixels.