“As we all know, the operation of any machine will produce vibration, some vibrations represent normal operation, and some vibrations represent the initial signal of failure. In the field of predictive maintenance, detecting vibration characteristics is a key factor in the diagnosis process. Vibration detection can identify and alleviate problems to avoid more serious incidents. Through sensing, amplifying and measuring subtle movements, Filial allows users to see the vibration characteristics of factory assets (such as machines) to ensure the normal operation of the machines.
As we all know, the operation of any machine will produce vibration, some vibrations represent normal operation, and some vibrations represent the initial signal of failure. In the field of predictive maintenance, detecting vibration characteristics is a key factor in the diagnosis process. Vibration detection can identify and alleviate problems to avoid more serious incidents. Through sensing, amplifying and measuring subtle movements, Filial allows users to see the vibration characteristics of factory assets (such as machines) to ensure the normal operation of the machines.
Traditional inspections are time-consuming and labor-intensive, and high downtime costs
The traditional method of detecting machine vibration is to deploy wired sensors (such as a contact accelerometer) on the machine to monitor the vibration. After acquiring the data from the sensor, the data is analyzed for the working mode shape to present the animation model of the machine movement, so as to visualize the vibration mode.
But according to Dr. Jeff Hay, the founder and CEO of RDI Technologies (Knoxville, Tennessee, USA), the technology not only requires time to collect measurement data from multiple points, but also requires access to the machine. When the machine is inconvenient or inaccessible at all (there are many obstacles or glass in front of the machine), this technology is often not possible to use. In addition, the installation of accelerometer in traditional contact measurement often requires the machine to stop running, resulting in high costs due to downtime.
To this end, engineers at RDI Technologies have developed a revolutionary non-contact video processing system called Iris M, which uses FLIR machine vision cameras to sense, amplify and measure the subtle vibrations caused by the machine, eliminating the use of early technology itself. Inherent flaws.
The Iris M system uses a FLIR 2.3Mpixel Grasshoppper3 camera mounted on a Vanguard tripod. This camera acquires monochrome image data with a default resolution of 1920×1050 and a speed of 120 frames per second.
The data obtained from the camera will be transferred to the tablet computer through the USB 3.0 interface, where the company’s special software is used for analysis, so that the user can see the vibration characteristics of the factory assets (such as machines).
Reasons for choosing FLIR machine vision cameras
In the Iris M system, the FLIR machine vision camera is equivalent to a data acquisition device. It collects video images, and then extracts and analyzes motion from it. The FLIR 2.3Mpixel Grasshoppper3 GS3-U3-23S6M-C camera is mounted on a Vanguard tripod and acquires monochrome image data with the default resolution of 1920×1050 and a speed of 120 frames per second. The acquired data will be transferred from the camera to the Getac F110 or Microsoft Surface Book tablet via the USB 3.0 interface via the anti-drop cable.
The Iris M system can directly measure the absolute displacement of factory assets that can be used to quantify movement from the image points,
Rather than interpret the point measurement to determine the type of movement and the error presented.
“The computer software Motion Amplification’s dedicated video processing algorithm will then visualize the vibration of the machine. It will analyze the pixels of each image frame by frame to determine which parts of the scene are moving. Next, it will amplify changes in the amplitude of all motion amplitudes in the scene. To the extent that it is visible to the naked eye, so as to strengthen the understanding between the components that cause any vibration,” Dr. Hay said. By using the graphical user interface running on the computer, the user can select a certain part of the image for further analysis. The system software will Display intensity data associated with these areas or time-dependent. Then various mathematical functions (such as fast Fourier transform, also known as FFT) can be used to convert the time-related intensity data set into frequency-related intensity data. The user will then be presented with absolutely unamplified amplitudes and vibration stages of different frequencies in the selected part of the scene.
The high sensitivity of Iris M system can promote more industries
Since its release in the third quarter of 2016, the Iris M system has changed the way people in the industry use machine monitoring to observe vibrations. The system is not only easy to use, but can also feed back visible, simple and clear video images to the user, so that the user can better understand the operating status of the device.
According to Dr. Hay, the choice of FLIR Grasshopper cameras has become a key reason for the success of the system. The camera has a 12-bit dynamic range that can capture the subtle difference in pixel intensity between bright light and dark areas in the image, allowing the system software to extract more detailed changes compared to other software.
The Grasshopper camera series combines the latest CCD and CMOS technologies with Point Grey’s expertise to achieve high-performance, high-quality imaging.
But equally important is the Motion Amplification algorithm itself. “Thanks to this unique algorithm, Iris is about 100 times more sensitive than traditional image-based measurement tools in measuring displacement. In addition, Iris M can directly read from the image when necessary. Point measurement can be used to quantify the absolute displacement of a motion without having to interpret the point measurement to determine the type of motion and the error presented,” he said. Another big advantage of this technology is the speed of data feedback and the level of detail of the data. Unlike traditional contact measurement systems, it can also be expanded because it can measure all asset vibrations within the camera’s field of view at the same time. In addition, it also makes itself a good communication tool between technical and non-technical users, because the source of any problem with any asset can be directly seen in the video.
The new system has been deployed in various practical applications. In addition to performing condition monitoring of industrial assets (such as machines), the Iris M system can also be used to analyze the structural integrity of bridges, buildings and similar structures. In addition, it can also be used in biomedical monitoring applications to assess individual respiration.