Incomplete sensor data is a major obstacle in industrial time-series analytics. In wastewater treatment plants (WWTPs), key sensors show long, irregular gaps caused by fouling, maintenance, and outages. We introduce STDiff and STDiff-W, diffusion-based imputers that cast gap filling as state-space simulation under partial observability, where targets, controls, and exogenous signals may all be intermittently missing. STDiff learns a one-step transition model conditioned on observed values and masks, while STDiff-W extends this with a context encoder that jointly inpaints contiguous blocks, combining long-range consistency with short-term detail. On two WWTP datasets (one with synthetic block gaps from Agtrup and another with natural outages from Avedøre), STDiff-W achieves state-of-the-art accuracy compared with strong neural baselines such as SAITS, BRITS, and CSDI. Beyond point-error metrics, its reconstructions preserve realistic dynamics including oscillations, spikes, and regime shifts, and they achieve top or tied-top downstream one-step forecasting performance compared with strong neural baselines, indicating that preserving dynamics does not come at the expense of predictive utility. Ablation studies that drop, shuffle, or add noise to control or exogenous inputs consistently degrade NH 4 and PO 4 performance, with the largest deterioration observed when exogenous signals are removed, showing that the model captures meaningful dependencies. We conclude with practical guidance for deployment: evaluate performance beyond MAE using task-oriented and visual checks, include exogenous drivers, and balance computational cost against robustness to structured outages.

Wastewater treatment plants face unique challenges for process control due to their complex dynamics, slow time constants, and stochastic delays in observations and actions. These characteristics make conventional control methods, such as Proportional-Integral-Derivative controllers, suboptimal for achieving efficient phosphorus removal, a critical component of wastewater treatment to ensure environmental sustainability. This study addresses these challenges using a novel deep reinforcement learning approach based on the Soft Actor-Critic algorithm, integrated with a custom simulator designed to model the delayed feedback inherent in wastewater treatment plants. The simulator incorporates Long Short-Term Memory networks for accurate multi-step state predictions, enabling realistic training scenarios. To account for the stochastic nature of delays, agents were trained under three delay scenarios: no delay, constant delay, and random delay. The results demonstrate that incorporating random delays into the reinforcement learning framework significantly improves phosphorus removal efficiency while reducing operational costs. Specifically, the delay-aware agent achieved 36 % reduction in phosphorus emissions, 55 % higher reward, 77 % lower target deviation from the regulatory limit, and 9 % lower total costs than traditional control methods in the simulated environment. These findings underscore the potential of reinforcement learning to overcome the limitations of conventional control strategies in wastewater treatment, providing an adaptive and cost-effective solution for phosphorus removal. • Novel SAC framework handles time delays in wastewater treatment optimization. • Delay-aware RL models improve phosphorus control efficiency by 36%. • SAC agents reduce target deviations by 77% and operational costs by 9%. • Custom LSTM-based simulator enables realistic training for delay scenarios. • Demonstrates RL’s superiority over PID controllers in dynamic industrial processes.

Accurate simulation of wastewater treatment systems is essential for optimizing control strategies and ensuring efficient operation. This study focuses on enhancing the predictive accuracy of a Long Short-Term Memory (LSTM)-based simulator by incorporating exogenous state variables, such as temperature, flow, and process phases, that are independent of output and control variables. The experimental results demonstrate that including these variables significantly reduces prediction errors, measured by Mean Squared Errors (MSE) and Dynamic Time Warping (DTW) metrics. The improved model, particularly the version that uses actual values of exogenous state variables at each simulation step, showed robust performance across different seasons, reducing MSE by 55% and DTW by 34% compared to the model which didn’t include exogenous state variables. This approach addresses the compounding error issue in multi-step simulations, leading to more reliable predictions and enhanced operational effic iency in wastewater treatment.

Phosphorus removal is vital in wastewater treatment to reduce reliance on limited resources. Deep reinforcement learning (DRL) can be used to optimize the processes in wastewater treatment plants by learning control policies through trial and error. However, applying DRL to chemical and biological processes is challenging due to the need for accurate simulators. This study trained six models to identify the phosphorus removal process and used them to create a simulator for the DRL environment. While achieving high accuracy (>97%) in one-step ahead prediction of the test dataset, these models struggled as simulators over longer horizons, showing uncertainty and incorrect predictions when using their own outputs for multi-step simulations. Compounding errors in the models’ predictions were identified as one of the causes of this problem. This approach for improving process control involves creating simulation environments for DRL algorithms, using data from supervisory control and data acquisition (SCADA) systems with a sufficient historical horizon without complex system modeling or parameter estimation.

Computer vision technology has attracted significant interest in the condition monitoring (CM) community due to its potential to automate visual inspection and analysis of structures and components. By facilitating the processing and interpretation of visual information, including images and video data, computer vision holds promise for CM applications. However, it is essential to distinguish computer vision from non-contact CM techniques regarding their underlying principles and methods. While computer vision enables non-contact, remote monitoring, and condition assessment with minimal disruption to daily operations, it is distinct from non-contact CM techniques, which utilize various sensors to assess the condition of assets without physical contact or interference. Building upon the potential of computer vision technology, this survey paper presents a comprehensive overview of the current state-of-the-art CM methods based on computer vision and deep learning (DL) techniques, focusing on their application in monitoring synthetic fiber ropes (SFRs). SFRs are a viable alternative to steel wire ropes for underwater equipment and cranes that handle heavy loads. This is due to their high resistance to frictional wear, high tensile strength, lightweight, and flexibility. New materials, technologies, and processes for CM are being developed to meet the growing demand for SFRs. The paper explores ongoing research in applications that monitor the wear and aging of materials, as well as estimate their remaining useful life. The survey briefly discusses the traditional non-destructive testing and machine learning (ML) methods for CM applications. More importantly, DL-based methods, including supervised, unsupervised, semi-supervised, and self-supervised methods, are discussed in detail, together with the use of deep generative models and the recently developed diffusion models in the generation of synthetic datasets. Furthermore, the paper addresses the difficulties present in DL-based CM applications, including the scarcity of labeled data and the complexity and variety of the models used. The article ends by discussing the benefits of employing DL-based visual methods to understand SFR degradation processes, particularly in monitoring and maintenance.

This paper discusses the implementation of a Deep Reinforcement Learning policy, based on DQN, which optimizes the navigation of the UAV to the front of wind turbine blades. The UAV was trained in simulation using Unreal Engine V4.27 coupled with AirSim. The action space of the UAV was discretized while allowing 6 different actions to be executed. A Yolov5 network trained with images of simulated wind turbines was used for detection and tracking, providing the DQN policy with state information, upon which it has been trained. In addition to this, the dynamic reward has been implemented, which combined both navigation and inspection objectives in the final evaluation of actions. Our tests showed that after 7500 time-steps the exploration rate reached near 0, the mean length of the episodes increased from 10 down to 30, but the mean reward increased from around -60 to stabilizing the output at 26. These results suggest that the proposed method is a promising solution to optimizing the autonomous inspection of wind turbines with UAVs.

In recent years, there have been significant advances in navigation methods for autonomous robotic systems, giving rise to a diverse range of navigation techniques. These techniques include GPS-based, SLAM-based, and monocular depth-based navigation. However, each of these approaches has its limitations. Typically, these techniques rely on either external sensors and positioning systems or require the creation of a local map prior to initiating navigation. This paper introduces a new approach for autonomous navigation of ground robots: mapless navigation using a pre-trained monocular depth network. This technique offers an efficient and cost-effective way of navigating without the need for a pre-existing map of the environment. To evaluate and compare the performance of our method, we conducted experiments using two different depth estimation models tested within the Gazebo simulation environment.

This paper presents a novel approach to the navigation of Unmanned Aerial Vehicles (UAV) for the autonomous inspection of wind turbines. Firstly, a Single Shot Detector (SSD) network is trained to detect wind turbines and their subcomponents. Then, an optimized template matching algorithm is used to estimate the distance between the UAV and the wind turbine, using as the template, the SSD bounding box prediction on the left image of a stereo camera. Lastly, an Extended Kalman Filter (EKF) estimates the position of the wind turbine's hub. The EKF is designed to compensate for CNN's latency while sending setpoints to the controller of the UAV.

Maturing Oil & Gas reservoirs in the North Sea result in constant increases of water-cut, which correspondingly poses an increasing strain on the current offshore Produced Water Treatment (PWT) facilities. As one of the key elements of the PWT facilities, the hydrocyclone systems, are responsible for removing the remaining hydrocarbon content in the produced water before the treated water can be discharged, disposed, or reused as injection water. The hydrocyclone's performance heavily correlates with a number of system's and operational parameters, as well as dedicated control strategies. However, these correlations haven't yet been clearly explored from a control oriented point of view, due to the complex separation dynamics inside the cyclone systems. This work investigates and evaluates the hydrocyclone system's operational performance with respect to the most commonly used control paradigm, Pressure Drop Ratio (PDR) control, based on a lab-scaled pilot-plant. It has been clearly observed that in many situations the PDR is not consistently related to the system efficiency or to the inlet flow-rates, however these are assumed consistent in almost all available studies and control designs. In addition, the dynamic responses of PDR and de-oiling efficiency (measured in terms of Oil-in-Water (OiW) concentration) of the deployed hydrocyclone systems are systematically and experimentally studied in this paper. This data can be used to derive control-oriented dynamic models of the considered system, so that a control solution that is better than the current PID-based PDR control, could be developed based on those models.