Energy assets demand meticulous maintenance to ensure safe and efficient operations. Traditionally, these programs were labour-intensive and costly, often yielding unclear outcomes due to subjective decision-making.
The advent of artificial intelligence (AI) presents a transformative opportunity to challenge traditional maintenance optimization approaches. Leveraging asset knowledge and AI capabilities, the 'maintAI' program streamlines maintenance optimization, delivering results swiftly and cost-effectively. The program addresses maintenance strategy, backlog, spares, and predictive plans with a focus on value creation, data-driven decisions, and consistent recommendations.
A primary application of maintAI is efficiently reducing overdue maintenance backlogs exacerbated by the COVID pandemic, labour shortages, ageing infrastructure, marginal economics and conflicting priorities. The systematic methodology employs AI to sift through non-value adding tasks, enabling companies to prioritize work that enhances reliability and productivity throughout the production facility lifecycle.
Maintenance backlogs are managed by prioritizing key focus areas and eliminating non-value adding work. AI, including Natural Language Processing (NLP) and Generative AI algorithms, enhances the speed and accuracy of failure mode classification from operational maintenance data. Reliability modelling techniques provide insights into equipment reliability. Recommendations undergo expert review before integration into maintenance systems.
Implementation of this data-driven approach demonstrates rapid deployment and sustained efficiency, yielding substantial gains in production uptime, cost reduction, and safety. The user-centric design ensures agility and ease of configuration. A case study of a recent project, which only took six weeks to deliver, and led to a 20% reduction in backlog, freeing capacity for critical focus areas will be discussed.

The Fengcheng Formation in the Mahu Sag of the Junggar Basin is one of the typical continental shale oil exploration intervals in China and it is rich in alkaline minerals. The water-rock reaction caused by hydraulic fracturing will lead to the dissolution of minerals and block the wellbore, thereby affecting the development efficiency. Supercritical CO2 fracturing can significantly improve the recovery of shale oil reservoirs, but the current research on the reaction of supercritical CO2 to water and rock in shale rich in alkaline minerals is basically blank. This project takes the alkaline mineral shale of the Fengcheng Formation in the Mahu Sag of the Junggar Basin as the research object, and applies geochemical analysis and mineral composition analysis, and clarifies the change of mineral composition before and after supercritical CO2 reaction. Scanning electron microscopy (SEM) and small-angle scattering (SAXS) were used to analyze the changes of pore structure before and after the supercritical CO2 experiment. Atomic force microscopy and nano-indentation method is used to characterize the mechanical properties before and after the reaction. The wettability is analyzed by atomic force microscope contact imaging. This paper comprehensively analyzes the changes of water-rock reaction on mineral composition, porosity and permeability characteristics, mechanical properties and wettability of core before and after the experiment, and analyzes the influence of supercritical CO2 water-rock reaction on alkaline mineral shale from multiple perspectives, so as to provide further theoretical and data support for the follow-up on-site optimization of supercritical CO2 fracturing scheme.

Current models for deep bed filtration describe the particles with uniform properties. Yet, sizes, densities, and mineral composition of particles vary significantly in the same injection well. The aim of this work is to provide effective mathematical model for water injection of particles with distributed properties and formation damage prediction. We average the set of traditional population balance equations for single-property particles and obtain one upscaled equation. The upscaled equation for particle retention rate contains non-linear function of suspended concentration, which we call suspension function. We derive analytical solutions for upscaled equation for linear (coreflood) and radial (well injectivity) flows. Then we treat lab coreflood data to determine the model suspension function and provide a model for well injectivity prediction. The breakthrough concentrations and retention profiles for flow of uniform particles have exponential form. Frequently reported in the literature hyper-exponential forms have been hypothetically explained by multiple particle properties. Lab data related to cores from Australian outcrops have been highly matched by the proposed mathematical model. The inverse solution allows revealing the individual filtration coefficients for binary mixture from total breakthrough concentrations during coreflood. Treatment of the data from lab experiments reveal individual filtration coefficients, that belong to common intervals. For the first time, deep bed filtration of particles with distributed properties is upscaled and presented by a single equation that reflects the particle property distribution. This equation provides an effective mathematical model for tuning lab coreflood data, determines the model function, and uses it for injectivity decline prediction.

Geomechanical pumped storage is a promising modular energy storage technology to integrate variable renewable energy sources into the electricity grid. The concept involves cycling fluid in artificial subsurface lenses, with each lens acting as an intermittent reservoir, storing and releasing pressurised fluid to drive a turbine and generate power. Similar in nature to pumped energy storage, but modular, standardized, and without the specific topography requirements.
This work describes the monitoring and analysis from the surface of several lens injections in the Eagle Ford Shale at Quidnet Energy’s Castilleja pilot storage site. Up to twelve high-precision tiltmeters were used to verify dip and orientation of the lens as well as provide a map of the lens geometry and symmetry or asymmetry of the lens growth.
For analysis surface tiltmeter data is transmitted then cleaned of artificial signals such as local noise, sensor inconsistencies or levelling events. Depending on the length of injection and flowback durations additional processing is required to remove natural noise such as earth tides. This data is analysed to obtain dip, volume, and orientation and fracture shape when using sophisticated inversion methods and models.
The surface tiltmeters used as a diagnostic tool for lens creation has been proved to be useful, it provides operators with confidence and feedback on fundamental lens behaviour and response. These improvements will scale the technology to commercially viable modular energy storage systems.

Based on published reports, Dorado and Pavo fields in Bedout Basin, offshore WA hold an aggregated 2C discovered contingent resource of 210 MMSTB liquid, 0.75 TCF gas. The development of the two core fields can unlock a significant resource potential for the gas market, as over significant amount of un-risked Prospective Resources has been estimated in the basin.
In this paper, we utilised common petroleum engineering judgment and available public domain materials to examine conceptual field development schemes that could reduce technical risk, lower lifecycle CO2 emissions and enable the development of Dorado and Pavo fields better economics in a shorter time frame, paving the way for an accelerated future exploration and development in the basin.
With common petroleum engineering mindset, Pavo could be developed by using a black oil development plan with focus on management of reservoir energy and water disposal.
Whereas Dorado has technical and operational challenges to develop a gas, oil/condensate accumulation. The proposed development is a miscible gas injection project with objective of maximising the liquid recovery. The development scheme requires energy-intensive gas processing and high-pressure re-injection. Significantly amount of greenhouse gas will be emitted.
Alternatively, a simpler development scheme that produces oil and delivers gas for domestic gas or LNG may be much less emissions intensive.