Autonomous and cooperative control of UAV cluster with multi-agent reinforcement learning

In this paper, we expolore Multi-Agent Reinforcement Learning (MARL) methods for unmanned aerial vehicle (UAV) cluster. Considering that the current UAV cluster is still in the program control stage, the fully autonomous and intelligent cooperative combat has not been realised. In order to realise the autonomous planning of the UAV cluster according to the changing environment and cooperate with each other to complete the combat goal, we propose a new MARL framework. It adopts the policy of centralised training with decentralised execution, and uses Actor-Critic network to select the execution action and then to make the corresponding evaluation. The new algorithm makes three key improvements on the basis of Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm. The first is to improve learning framework; it makes the calculated Q value more accurate. The second is to add collision avoidance setting, which can increase the operational safety factor. And the third is to adjust reward mechanism; it can effectively improve the cluster’s cooperative ability. Then the improved MADDPG algorithm is tested by performing two conventional combat missions. The simulation results show that the learning efficiency is obviously improved, and the operational safety factor is further increased compared with the previous algorithm.

AI-Enabled Predictive Maintenance Framework for Autonomous Mobile Cleaning Robots

Vibration is an indicator of performance degradation or operational safety issues of mobile cleaning robots. Therefore, predicting the source of vibration at an early stage will help to avoid functional losses and hazardous operational environments. This work presents an artificial intelligence (AI)-enabled predictive maintenance framework for mobile cleaning robots to identify performance degradation and operational safety issues through vibration signals. A four-layer 1D CNN framework was developed and trained with a vibration signals dataset generated from the in-house developed autonomous steam mopping robot ‘Snail’ with different health conditions and hazardous operational environments. The vibration signals were collected using an IMU sensor and categorized into five classes: normal operational vibration, hazardous terrain induced vibration, collision-induced vibration, loose assembly induced vibration, and structure imbalanced vibration signals. The performance of the trained predictive maintenance framework was evaluated with various real-time field trials with statistical measurement metrics. The experiment results indicate that our proposed predictive maintenance framework has accurately predicted the performance degradation and operational safety issues by analyzing the vibration signal patterns raised from the cleaning robot on different test scenarios. Finally, a predictive maintenance map was generated by fusing the vibration signal class on the cartographer SLAM algorithm-generated 2D environment map.

Enhancing Operational Safety Through Mechanization and Intelligent Automation of Drill Floor Operations

Our rig crews regularly work around structures that pose risks such as dropped objects and pinch points. HSE and operational performance is highly dependent on human performance. Human performance or human factors have resulted in a relatively high frequency of serious Health, Safety and Environment (HSE) incidents associated with tubular handling on ADNOC Onshore rigs. An example is the fatality on a rig in Abu Dhabi while preparing to run casing in February 2018. We believe we can prevent major incidents, enhance efficiency and reduce risk by removing our people from harm's way through mechanization and intelligent automation of drill floor activities. The objective of this work is to reduce the human factor as low as reasonably practicable through mechanization and intelligent automation of tubular handling operations on ADNOC Onshore rigs. An incident prevention workshop recommended a technology search to enable hands free operations and reduce the human to machine interaction as much as reasonably practicable. A quick market research and a "Go, See, Assess" exercise with ADNOC Shareholders revealed several potential offerings on the market. ADNOC Onshore collaborated with two major technology providers and jointly designed a mechanized set up for ADNOC Onshore land rigs. The solution involved the use of mechanized equipment such as Casing Running Tools complete with hydraulically actuated single joint elevators, hydraulic catwalk, automated power slips, remote operated tong system with supporting alignment systems, air operated elevators, remote operated stabber, etc. The solution was successfully implemented on multiple rigs. The mechanized set up reduced the number of people in the so called RED Zone by 50% (Stabber, Tong Operator, Thread Inspector and Floor man) during casing and completion running operations. Other benefits realized include: Reduced reliance on human performance Reduced risk of harm to people due to dropped objects and pinch points on the rig floor Assured consistency in executing repetitive tasks such as running casing, etc This level of mechanization and intelligent automation is a first in the ADNOC Group, represents a STEP CHANGE in operational safety and has transformed how we do our business, underpinning HSE as priority number one.

Ergonomic and Psychological Bases of Operational Safety

Depending on the working conditions, jobs are divided into different groups. Of these, special attention should be paid to high-risk and harmful conditions. High-risk work includes work that can result in a high level of injury, trauma, and accidents to the worker during work. Keywords: technical, sanitary, harmful work, harmful factors

A digital twin of the ship hull, purpose and main principles of development

Object and purpose of research. The object under study is ship hulls. The purpose is formulation of the digital twin (DT) objective for the ship hull and approach to its development. Materials and methods. Existing methods of developing digital models and systems of strength, vibration, and stability are used. Main results. The objective of DT is formulated and the approach to its development is presented, which states the main principles of development. Conclusions. Application of ship hull DT will increase the economic efficiency, operational safety and reliability of ship hulls.