Hitachi Energy's new AI solution analyzes trees to prevent wildfires


The massive, beautiful tree canopies in the Western U.S., which may grow perilously close to power lines, can quickly spark destructive wildfires. In fact, 70% of electrical outages are caused by vegetation, and this number has increased by 19% year over year from 2009-2020. The second-largest wildfire in California's history, The Dixie Fire, sparked when power lines came into contact with a fir tree. Could AI-driven solutions help prevent wildfires before they start by analyzing the tree growth that can spark them? Hitachi Energy, the Zurich, Switzerland-based global technology company, says yes. Hitachi Energy, formerly known as Hitachi ABB Power Grids (the name was changed last October) is currently focused on "powering good for a sustainable energy future."

'A train wreck': what happens to workers and towns when the lights go out on coal power?

The Guardian > Energy

When Jacqui Coleman heard that Australia's largest coal-fired power station was to close seven years earlier than planned, she initially didn't believe it. Coleman is a retail worker in Dora Creek, the closest suburb to the Eraring power station on the shores of Lake Macquarie in New South Wales. For years, she has been selling pies, coffees and sandwiches to some of the hundreds of workers who pass through the News'n' More grocery store on either side of a shift. On Thursday morning, Origin Energy announced it was bringing forward the station's closure to 2025. Many workers at the site first learned their jobs were to be terminated seven years early when they heard it reported on the radio.

A generic physics-informed neural network-based framework for reliability assessment of multi-state systems Artificial Intelligence

In this paper, we leverage the recent advances in physics-informed neural network (PINN) and develop a generic PINN-based framework to assess the reliability of multi-state systems (MSSs). The proposed methodology consists of two major steps. In the first step, we recast the reliability assessment of MSS as a machine learning problem using the framework of PINN. A feedforward neural network with two individual loss groups are constructed to encode the initial condition and state transitions governed by ordinary differential equations (ODEs) in MSS. Next, we tackle the problem of high imbalance in the magnitude of the back-propagated gradients in PINN from a multi-task learning perspective. Particularly, we treat each element in the loss function as an individual task, and adopt a gradient surgery approach named projecting conflicting gradients (PCGrad), where a task's gradient is projected onto the norm plane of any other task that has a conflicting gradient. The gradient projection operation significantly mitigates the detrimental effects caused by the gradient interference when training PINN, thus accelerating the convergence speed of PINN to high-precision solutions to MSS reliability assessment. With the proposed PINN-based framework, we investigate its applications for MSS reliability assessment in several different contexts in terms of time-independent or dependent state transitions and system scales varying from small to medium. The results demonstrate that the proposed PINN-based framework shows generic and remarkable performance in MSS reliability assessment, and the incorporation of PCGrad in PINN leads to substantial improvement in solution quality and convergence speed.

Cyberphysical Sequencing for Distributed Asset Management with Broad Traceability Artificial Intelligence

Cyber-Physical systems (CPS) have complex lifecycles involving multiple stakeholders, and the transparency of both hardware and software components' supply chain is opaque at best. This raises concerns for stakeholders who may not trust that what they receive is what was requested. There is an opportunity to build a cyberphysical titling process offering universal traceability and the ability to differentiate systems based on provenance. Today, RFID tags and barcodes address some of these needs, though they are easily manipulated due to non-linkage with an object or system's intrinsic characteristics. We propose cyberphysical sequencing as a low-cost, light-weight and pervasive means of adding track-and-trace capabilities to any asset that ties a system's physical identity to a unique and invariant digital identifier. CPS sequencing offers benefits similar Digital Twins' for identifying and managing the provenance and identity of an asset throughout its life with far fewer computational and other resources. Across domains, manufactured and assembled system complexity is increasing. Constituent components require compliance with stringent specifications, must have low defect rates, and increasingly require known provenance relating to origin and interaction histories. At the same time, economic and other constraints affecting production and assembly may necessitate involving diverse and untrusted vendors: a vehicle's parts may be made abroad and assembled domestically, while a medication might be compounded in one country before being shipped to another for packaging and a third for distribution. Power generation plant components might be manufactured globally but require certification in the country of use, while electronics manufacturing for a globally-distributed device may require trust-related integrated circuits to be provided and validated by a single-source vendor.

Models Trained to Keep the Trains Running


Steady advances in machine vision techniques such as convolutional neural networks powered by graphics processors and emerging technologies like neuromorphic silicon retina "event cameras" are creating a range of new predictive monitoring and maintenance use cases. We've reported on several, including using machine vision systems to help utilities monitor transmission lines and towers linked to wildfires in California. Now, AI software vendor Ignitarium and partner AVerMedia, an image capture and video transmission specialist, have expanded deployment an aircraft-based platform for detecting railway track obstructions. The AI-based visual "defect detection" platform incorporates Ignitarium's AI software implemented on Nvidia's edge AI platform used to automatically control onboard cameras. The system is designed to keep cameras focused on the track center during airborne inspections.

The future of maintenance for distributed fixed assets


Industries with distributed fixed assets--be they telecommunication broadband or railway networks, wind turbines or drilling facilities, elevators and escalators or washing machines--share specific challenges when it comes to maintenance. As the assets are distributed throughout a region, there is usually no dedicated maintenance team per asset. To the contrary, maintenance workers cover whole areas, travel to the assets' various locations, and bring the appropriate instructions, spare parts, and tools. Maintenance costs typically range between 20–60 percent of opex spend, depending on industry, asset type, and capex spend--an opportunity that has only been a minor priority over the past couple of years. At the same time, ensuring high levels of asset availability and system reliability is a key priority for operations leaders. Often, regulations severely penalize shortfalls (eg, of power transmission and distribution), breakdowns incur high revenue losses (eg, for wind turbines), or breakdowns result in high safety and environmental dangers (eg, in drilling facilities).

Applications of Linear Defeasible Logic: combining resource consumption and exceptions to energy management and business processes Artificial Intelligence

Linear Logic and Defeasible Logic have been adopted to formalise different features of knowledge representation: consumption of resources, and non monotonic reasoning in particular to represent exceptions. Recently, a framework to combine sub-structural features, corresponding to the consumption of resources, with defeasibility aspects to handle potentially conflicting information, has been discussed in literature, by some of the authors. Two applications emerged that are very relevant: energy management and business process management. We illustrate a set of guide lines to determine how to apply linear defeasible logic to those contexts.

Tackling Climate Change with Machine Learning Artificial Intelligence

Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help. Here we describe how machine learning can be a powerful tool in reducing greenhouse gas emissions and helping society adapt to a changing climate. From smart grids to disaster management, we identify high impact problems where existing gaps can be filled by machine learning, in collaboration with other fields. Our recommendations encompass exciting research questions as well as promising business opportunities. We call on the machine learning community to join the global effort against climate change.

Inspection-by-drone company gets 3.25M in energy sector funding


Add this to the list of feats 3D printers can perform: Fully functioning robots made out of liquid. Heres more proof that drones-as-a-service are gaining ground. Sharper Shape, which sells drone-based automated asset inspection solutions, just announced 3.25 million in new funding led by Straightforward Capital, a European venture capital firm with experience in the energy sector. As I've written, Sharper Shape is using LiDAR, along with analysis tools and long drone flights, to build 3D maps identifying trees, which utility companies can use to measure imminent threats. Fallen trees and swinging branches are a major threat to power lines.