A scheme for the classification of explosions in the chemical process industry

Development of an AI-based image/ultrasonic convergence camera system for accurate gas leak detection in petrochemical plants

Outdoor pipeline leaks are difficult to accurately measure using existing concentration measurement systems installed in petrochemical plants owing to external air currents. Besides, leak detection is only possible for a specific gas. The purpose of this study was to develop an image/ultrasonic convergence camera system that incorporates artificial intelligence (AI) to improve pipe leak detection and establish a real-time monitoring system. Our system includes an advanced ultrasonic camera coupled with a deep learning-based object-detection algorithm trained on pipe image data from petrochemical plants. The collected data improved the accuracy of detected gas leak localization through deep learning. Our detection model achieves an mAP50 (Mean average precision calculated at an intersection over union (IoU) threshold of 0.50)score of 0.45 on our data and is able to detect the majority of leak points within a system. The petrochemical plant environment was simulated by visiting petrochemical plants and reviewing drawings, and an outdoor experimental demonstration site was established. Scenarios such as flange connection failure were set under medium-/low-pressure conditions, and the developed product was experimented under gas leak conditions that simulated leakage accidents. These experiments enabled the removal of potentially confounding surrounding noise sources, which led to the false detection of actual gas leaks using the AI piping detection technique.

Feasibility Study for a Chemical Process Particle Size Characterization System for Explosive Environments Using Low Laser Power

The industrial particle sensor market lacks simple, easy to use, low cost yet robust, safe and fast response solutions. Towards development of such a sensor, for in-line use in micro channels under continuous flow conditions, this work introduces static light scattering (SLS) determination of particle diameter using a laser with an emission power of less than 5 µW together with sensitive detectors with detection times of 1 ms. The measurements for the feasibility studies are made in an angular range between 20° and 160° in 2° increments. We focus on the range between 300 and 1000 nm, for applications in the production of paints, colors, pigments and crystallites. Due to the fast response time, reaction characteristics in microchannel designs for precipitation and crystallization processes can be studied. A novel method for particle diameter characterization is developed using the positions of maxima and minima and slope distribution. The novel algorithm to classify particle diameter is especially developed to be independent of dispersed phase concentration or concentration fluctuations like product flares or signal instability. Measurement signals are post processed and particle diameters are validated against Mie light scattering simulations. The design of a low cost instrument for industrial use is proposed.

In Situ Monitoring of RAFT Polymerization by Tetraphenylethylene-Containing Agents with Aggregation-Induced Emission Characteristics

A facile and efficient approach is demonstrated to visualize the polymerization in situ. A group of tetraphenylethylene (TPE)-containing dithiocarbamates were synthesized and screened as agents for reversible addition fragmentation chain transfer (RAFT) polymerizations. The spatial-temporal control characteristics of photochemistry enabled the RAFT polymerizations to be ON and OFF on demand under alternating visible light irradiation. The emission of TPE is sensitive to the local viscosity change owing to its aggregation-induced emission characteristic. Quantitative information could be easily acquired by the naked eye without destroying the reaction system. Furthermore, the versatility of such a technique was well demonstrated by 12 different polymerization systems. The present approach thus demonstrated a powerful platform for understanding the controlled living radical polymerization process.

Designing a reliable leak bio-detection system for natural gas pipelines

Monitoring of natural gas (NG) pipelines is an important task for economical/safety operation, loss prevention and environmental protection. Timely and reliable leak detection of gas pipeline, therefore, plays a key role in the overall integrity management for the pipeline system. Owing to the various limitations of the currently available techniques and the surveillance area that needs to be covered, the research on new detector systems is still thriving. Biosensors are worldwide considered as a niche technology in the environmental market, since they afford the desired detector capabilities at low cost, provided they have been properly designed/developed and rationally placed/networked/maintained by the aid of operational research techniques. This paper addresses NG leakage surveillance through a robust cooperative/synergistic scheme between biosensors and conventional detector systems; the network is validated in situ and optimized in order to provide reliable information at the required granularity level. The proposed scheme is substantiated through a knowledge based approach and relies on Fuzzy Multicriteria Analysis (FMCA), for selecting the best biosensor design that suits both, the target analyte and the operational micro-environment. This approach is illustrated in the design of leak surveying over a pipeline network in Greece.