Gassonic Observer i Ultrasonic Gas Leak Detector with ANN

Gassonic Observer i Ultrasonic Gas Leak Detector with ANN

Truly dangerous pressurized gas leaks can be a challenge to detect reliably by anyone using any of the conventional catalytic bead, point IR and open path IR gas sensing technologies. Although some gas leak releases make a jet-like noise, operators may not be nearby to hear the escaping gas. Strong winds may dilute the gas and the momentum of the gas itself may disperse the material away from installed gas sensors.
Given the challenges that conventional contact-based gas sensors (catalytic bead and infrared types) face in detecting high pressure gas releases in outdoor environments, it is not surprising that the newer ultrasonic gas leak detectors (UGLDs) are becoming common as part of a comprehensive protection scheme that may include the use of all of the technologies (Fig 2), UGLDs offer a number of advantages including immunity to gas dispersion from wind, which is a serious potential limitation with point and infrared sensing detectors.

Gassonic i Ultrasonic Gas Leak Detector

The Variable Background Noise Problem

UGLDs are used today on offshore production platforms, around well heads, compressors, and turbines, and on land where they are used to protect metering stations and gas storage tanks among several other process areas. Being non-contact measurement devices they protect against both combustible and toxic gas releases, and their detection range can be verified by using inert gases with similar molecular weight and heat ratio as those of the gases of interest.In ultrasonic gas detection, a sound wave is simply a pressure pulse in the air that is detected by the human ear the same way that it is detected by a microphone. The human ear can only perceive acoustic sound waves in the frequency range between 20 and 20,000 Hz (20kHz) and that is why this frequency range is called the audible frequency range. Acoustic sound frequencies above 20 kHz are called ultrasound.When pressurized gas is released through a leak, the hissing noise produced is called broadband acoustic noise, ranging from the audible frequency range into the ultrasonic frequency range. Earlier generations of UGLDs only “listened” for the gas leak noise in the ultrasonic frequency range from about 25 kHz and up.
Ultrasonic Gas Leak Detector
Gas Detection Wind
UGLDs measure the sound pressure produced by the escaping gas. As the sound pressure exceeds a preset level normally produced by background noise, the detector indicates an alarm condition. Such threshold-crossing devices essentially record deviations from baseline conditions early enough to detect dangerous leaks of pressurized gases and to initiate appropriate warnings.
Despite the advantages of threshold monitoring, the performance of today’s conventional ultrasonic gas leak detector depends on an assumption of a fixed background ultrasound level at a particular installation. Likewise, the alarm delay setting on such devices is based on a presumption of intermittent ultrasonic sources (false positives)that are fixed in duration.
In any industrial environment such background conditions may vary in terms of both magnitude and time. Furthermore, as operators seek to avoid frequent changes to configured devices, preset sound pressure thresholds and alarm delays significantly limit the instruments’ detection range and speed of response.

The Artificial Neural Network Solution in Acoustic Gas Leak Detectors

To overcome these limitations, we have developed a breakthrough intelligent UGLD based on artificial neural network (ANN) intelligence. This new UGLD design distinguishes the broadband ultrasound produced by pressurized gas releases from other artificial and natural sources. Such design can be implemented with or without a threshold-crossing scheme, enhancing the scalability of gas leak detection. For convenience, the detector can operate with the threshold – crossing scheme or one of several enhanced modes that rely on ANN to classify ultrasound signals.

Furthermore, testing results show that the UGLD with the ANN algorithm achieves a longer detection range(radius ~ 28 m) and a shorter response time in the presence of ultrasonic background noise.An artificial neural network operates in a manner very similar to how the human brain handles the constant flow of information.

When we meet a person, the brain receives a massive amount of visual information through the eyes, and over time this substantial amount of information is used to recognize this person years later or even to identify further family members. When the brain has received visual information about other family members, it is easier for it to distinguish between family and non-family members.

In other words, the more we train our brain to recognize familiarity the better we will be able to recognize or deny a person’s face. The brain does not look for an exact match, it looks for familiarity, and so does the ANN.

Like the brain, however, the neural network needs to be trained first. A UGLD does not have to recognize different people.It needs to recognize the sound signature from a gas leak effectively while at the same time rejecting sound signatures from acoustic background noise that are not related to gas leaks.

Acoustic noise from a real gas leak source normally ranges from 10kHz and up to the 60 to 70 kHz range. Acoustic noise from a false alarm source, such as a gas compressor for example, can easily generate high level frequencies in the range of 100Hz to 20 kHz.

Earlier generations of UGLDs were designed with electronic filters to screen out and ignore noise below 20 kHz, which eliminated false alarms resulting from most normal plant background noise such as gas compressors, but also limited detection of smaller real gas leaks.

With most real gas leaks generating a sound typically with a frequency of 10 to 60 Khz, detecting a higher frequency range of 75 kHz or greater doesn’t add any meaningful capability.

Adding ANN intelligence capability to UGLD’s provides process and plant engineers with a new tool that can help them detect more real gas leaks and avoid nuisance false alarms. The OBSERVER-i UGLD with its capability to reliably detect leaks below 20 kHz provides another layer of safety to the industry, protecting people, equipment and facilities from hazardous gas leaks.

Reference: MSA White Paper, UGLDs with Artificial Neural Network

Comments are closed.