Port Otago – The seaport steering its way to high-tech noise containment
Strict noise regulations restrict noises in seaports above a certain decibel level – but for Port Otago, it was the noises it didn’t make that were causing a headache. Hundreds of man hours were being wasted simply listening back to recordings to check whether the noise came from inside or outside the port. Fortunately Aware Group brought real relief with its automated solution combining Microsoft’s Internet of Things (IoT), artificial intelligence (AI) and Azure technology, so both neighbours and port workers can enjoy total peace.
Situated at Port Chalmers north of Dunedin, Port Otago is a key link in New Zealand’s supply chain. Even before the country’s first shipment of frozen meat sailed from New Zealand to London in February 1882, the port has been at the forefront of New Zealand’s export trade, with containers flowing through its gates every week. These days, international cruise ships also call on their way around the country, carrying tourists to Dunedin’s historic centre and the Otago Peninsula.
Now, through its partnership with Aware Group using Microsoft’s Azure technology, Port Otago’s new AI-based noise monitoring system has steered its way to high-tech noise containment. Through this tech transformation, Port Otago has seen total breakthrough in its ability to control legal noise frequency requirements in the shipping yard, and a remarkable increase in employee productivity and morale.
Noise control leads to screening headache
Port Otago is of extreme importance to the local economy, primarily being used to ship dairy and sawn timber globally. All this activity doesn’t come quietly though. Every day carries a rhythm: the repetitive beeping of machinery, echoing metallic thumps as cranes lift and lower containers, truck engines and horns.
Ports across New Zealand must adhere to strict noise frequency laws, meaning that industrial noise cannot be above a certain decibel level to avoid disturbing neighbours. Any incidents that reach above this level must be reported to the relevant authorities.
Port Otago was being let down by an outdated microphone system, which was unable to cope with the demands of a busy port. One employee spent countless hours manually monitoring noise frequencies, including determining which sounds originated outside the grounds. There were numerous “false positives” from motorbikes on the nearby roads and other sources, that all had to be checked and listened to manually.
“Listening to the sounds and categorising what the sound was from took the staff member a significant amount of time each day, on top of their normal work-load. The employee’s morale was significantly affected too, meaning work just wasn’t as rewarding and enjoyable,” says Sofia Ng, Business Intelligence Lead at Port Otago.
In all, the employee was having to spend up to 18 hours per week on top of a normal 40-hour week just to categorise noises flagged by the existing system.
Port Otago recognised it needed an automated solution that would not only help it remain a good neighbour, but also help its employees. That’s when it called Aware Group.
Machines that hear for us
For Aware Group, it came down to a simple insight – Port Otago’s problem wasn’t about noise, but about time. The measure of success for this project was ultimately around how seamlessly the technology could fit into daily operations so that employees could focus their energy on more significant tasks that added real value to the port’s operations.
Aware Group’s solution: to remove all manual labour by creating an AI-driven machine-learning system. Leveraging Microsoft’s IoT technology and Azure, the system automates the process of noise monitoring by learning to recognise the source of noises above the threshold, then filtering out all false positives automatically.
Port Otago recognised that by deploying connected devices around the shipping yard it would be able to monitor all noise more accurately and at a much faster pace than if it continued with manual monitoring. The project was so successful that its first phase model reached a highly impressive 92.5% accuracy in recognising noises above the threshold and filtering out false positive external noises.
Smart noise monitors bring sound results
The smart devices reduced noise monitoring at the port to 20-30 (human) minutes per week. This not only increased employee productivity and morale, it enabled Port Otago to be more compliant with regulations and even offered real-time access to the data for the local authorities.
“We have seen significant improvements as a result of this deployment. Our sound monitoring employee now has so much more enjoyment when coming to work, as he can spend more time on more enjoyable tasks. The leadership team have also benefitted significantly, as they now have more timely reports that have been streamlined for consumption, creating a report which is easier to disseminate,” says Sofia.
“We have more real-time understanding of our noise impacts as the data is available pretty much instantly rather than at a monthly or quarterly meeting. This allows us to detect issues sooner, identify patterns and contributing factors more easily, and target more of our resources at actually resolving the noise issues at source.”
The project now making a noise of its own
The project’s success has paved the way for Port Otago to innovate even further with technology, with three additional projects in the pipeline for Aware Group. Once the team saw what one solution could achieve, they were eager to see what else could be done.
And what started out as an individual customer project for Port Otago has now led to a much bigger opportunity, with recognition that this same noise monitoring technology can be applied to different industries. Aware Group is now recognised as being ahead of digital signal processing industry standards, and has joined forces with Microsoft to find new applications for this innovative piece of technology in other sectors.
“We couldn’t be more thrilled with the success Port Otago has seen as a result of this project. Aware Group is an extremely valued partner of Microsoft’s, and it seems the positive impact it has had on Port Otago and the wider industry has only just begun,” says Anu Shreen, Port Otago project lead at Microsoft New Zealand.
Seems the little noise-monitoring project is now making a noise of its own.
Microsoft New Zealand Partner Awards entries are open. If you’re a Microsoft Partner with an amazing project that deserves some recognition, enter the awards here. Entries close on 9 October 2020.
We believe in creating solutions that always deliver significant value, remain affordable, and will inspire new innovation.
Microsoft is a technology company whose mission is to empower every person and every organisation on the planet to achieve more. We strive to create local opportunity, growth, and impact in every country around the world.
Data, AI, BI & ML
Artificial Intelligence and Machine Learning are the terms of computer science. Artificial Intelligence : The word Artificial Intelligence comprises of two words “Artificial” and “Intelligence”. Artificial refers to something which is made by human or non natural thing and Intelligence means ability to understand or think. There is a misconception that Artificial Intelligence is a system, but it is not a system. AI is implemented in the system. There can be so many definition of AI, one definition can be “It is the study of how to train the computers so that computers can do things which at present human can do better.” Therefore it is an intelligence where we want to add all the capabilities to machine that human contain. Machine Learning : Machine Learning is the learning in which machine can learn by its own without being explicitly programmed. It is an application of AI that provide system the ability to automatically learn and improve from experience. Here we can generate a program by integrating input and output of that program. One of the simple definition of the Machine Learning is “Machine Learning is said to learn from experience E w.r.t some class of task T and a performance measure P if learners performance at the task in the class as measured by P improves with experiences.”