News

Broadsens & Elipsa Use AI for Predictive Maintenance

Broadsens, a leader in low-power industrial sensors, and Elipsa a leader in plug and play AI solutions for IIOT are combining machine data with machine learning to provide easy to configure predictive maintenance at scale.

Industrial equipment such as pumps, compressors, generators, HVAC, etc. are critical to successful business operation.  Unplanned downtime of such equipment can be catastrophic in terms of economic loss to an organization.  Historically, maintaining such equipment has been reactive, incorporating onsite diagnostic or notifications of failures that have already occurred.

With the growth of the Industrial Internet of Things (“IIOT”) this critical equipment is becoming smart and connected.  With this new stream of data, machine learning has proven capable of detecting patterns indicative of future problems allowing for predictions of downtime and a proactive approach to equipment maintenance. This growing area is known as Predictive Maintenance.

Machine learning algorithms can learn from numerous types of sensors and data points.  Often times, the most effective data points for successfully building predictive maintenance algorithms have proven to be vibration data, learning that certain vibration profiles can predict the future failure of a machine.

Data Acquisition

The Broadsens SVT200-V is the only compact true real-time wireless vibration sensor that can monitor machine condition continuously with more than 3-year battery life in typical usage.

SVT200-V has two sampling modes: continuous low-speed sampling mode and high-speed sampling mode. It acquires x, y and z axis data in 16-bit resolution continuously. When the sensor detects a vibration event, it switches to high-speed 6.4kHz sampling rate, takes a fixed amount of data, calculates velocity RMS and acceleration RMS value, and sends the result plus temperature to the wireless gateway.

The smart algorithm inside SVT200-V adjusts the sampling mode dynamically and optimizes the energy usage. It can capture both high frequency and low frequency defects from the machine and structures.

The Broadsens wireless gateway connects and controls many sensors including the SVT200-V, SV200-A, SVT300-V, SVT300-A, SVT400-V and SVT400-A. The gateway includes 4-core ARM processor for real-time data visualization and processing. The gateway is configurable to transfer real-time sensor data to third-party systems via MQTT such as the Elipsa AI Platform.

Real time wireless vibration & temperature sensor

Broadsens real time wireless vibration & temperature sensor

The AI

Elipsa’s AI-based Predictive Maintenance seamlessly deploys across any workflow on the edge or in the cloud, increasing the availability and output of critical equipment. Elipsa’s self-training AI models and bolt-on approach enable AI deployments that are simple, fast, and flexible.

Through the use of Elipsa’s Rapid Deployment Templates, users can start intelligently monitoring critical equipment in as little as five minutes.  Elipsa’s Broadsens Vibration Analysis template takes in real-time velocity RMS data on the x, y, and z axis.

Once an SVT200-V is connected, data is streamed to Elipsa via MQTT. Elipsa’s Rapid Deployment Template automatically starts to learn the normal vibration profile of the machine that the sensor is attached to.  After a set number of data points (as defined in the template), Elipsa automatically builds a machine learning model and returns predictions back to the Broadsens gateway.

Elipsa’s innovative approach learns normal vibration of a given machine in order to detect abnormalities of any kind reported back to the user via the Broadsens software.

Case Study

In this case study, Broadsens's wireless vibration sensor SVT200-V and wireless gateway GU200S, vibration analysis software BroadVibra are used to monitor an air condenser. SVT200-V inside single screw-hole package is used with magnet mount. The sensor with magnet mount can be installed in several seconds. Data are fed to Elipsa’s AI platform continuously in real time via MQTT protocol. 24-hour data from the sensor is shown as below.

After several days, the sensor was removed to simulate accident to the air condenser. Elipsa AI algorithm detected the change with both velocity RMS and acceleration RMS value. Velocity RMS value showed more significant change, which is consistent with the industrial standard that prefers vibration velocity RMS over acceleration RMS for machine condition monitoring.

Wireless vibration sensor mounted on panel

Wireless vibration sensor mounted on panel

Vibration velocity RMS AI prediction

Vibration velocity RMS AI prediction

24-hour vibration data from the panel

24-hour vibration data from the panel

Acceleration RMS AI prediction

Acceleration RMS AI prediction

Predictive Maintenance at Scale

The combined Broadsens/Elipsa solution can easily be deployed across a range of equipment at scale. Make the promise of predictive maintenance a reality to start proactively managing critical equipment. There’s no need for a data scientist or a large capital ex spend.  This plug-and-play solution will reduce downtime, increase operating efficiency, improve scheduling of key employees, making your machines more sustainable.

IP68 Wireless Vibration and Temperature Sensors

After many testing, Broadsens updated its wireless vibration and temperature sensors' rating from IP67 to IP68. This rating could truly reflect the ability of the sensors working under tough environments. The testing were performed in different environments, including ice water submerge, deep water submerge, and long duration water submerge. The testing proved that Broadsens wireless vibration and temperature sensors are some of the best and toughest in the industry.

IP69 wireless vibration sensor

Ice water submerge testing

In this testing, Broadsens's wireless vibration and temperature sensors are submerged under iced water for more than 1 hour. There were random-selected one SVT-A series and one SVT-V series wireless vibration sensor. Both sensors took data continuously. Yes Broadsens's innovative design allow the ultra-low power wireless vibration sensors take data continuously.

SVT-A wireless vibration sensors include SVT200-A, SVT300-A and SVT400-A. They take triaxial acceleration raw data, which allows for predictive maintenance and AI-based analysis.

SVT-V wireless vibration sensors include SVT200-V, SVT300-V and SVT400-V. They take data continuously non-stop, which allows for real-time machine condition monitoring and accidents alarm in time.

Both type of sensors should be used for industrial IOT applications.

In the pictures below, the left pictures show long-duration testing. In this test, the sensors were submerge in a water bottle for more than 48 hours. There is no leak detected and the sensors are working normally after 48 hours. In the right picture, the sensors were submerged under a well water with a depth of 1.5m for more than 4 hours. The sensors are also working normally without any water damage. The wireless vibration and temperature sensors are perfect solutions for industrial IOT applications and machine condition monitoring.

IP69 wireless vibration sensor under water test

Long duration underwater test

Underwater test of wireless vibration sensor

1.5m under water test

Real-time Wireless Vibration & Temperature Sensor Upgrade

One of the best real-time wireless vibration & temperature sensors just gets better. There are four major improvements on Broadsens's popular SVT-V series real-time wireless vibration monitoring product line:

1. Broadsens calibrated the SVT200-V wireless vibration sensor based on ISO 10816 standard. Before firmware version 2.5, SVT200-V measures relative velocity, acceleration RMS and temperature. The wireless vibration sensor can monitor vibration events in real time with the combination of fast response and long-lasting battery life. No other wireless vibration sensors come close to its performance in terms of performance, physical size, weight and environment survivability. But users have to manually calculate the velocity RMS value using multiple measurements from the SVT200-V sensor, which makes it inconvenient. From firmware version 2.5 and above, SVT200-V will output velocity RMS, acceleration RMS and temperature in default. The velocity RMS value can be compared with the ISO 10816 standard to quickly tell the overall condition of a machine.

2. SVT-V series sensors can be ordered in the M6 screw package (SVT-A series package) too. It means that an SVT-V sensor can be mounted with screws, studs, epoxy, magnet bases, mounting pads. At the same time, an SVT-A sensor can be ordered in screw mount package (SVT-V series package)

SVT-V wireless vibration sensor package options

SVT-V vibration sensor in two package types

Real time vibration velocity RMS, acceleration RMS and temperature measurements

Real time vibration velocity RMS, acceleration RMS and temperature measurements

3. Real-time wireless vibration sensors SVT300-V and SVT400-V for high acceleration range applications. SVT200-V can meet the requirements for most vibration requirements. However, there are cases that need high g range. SVT300-V has a maximum range of 16g. SVT400-V has a maximum range of 64g. The default packages of SVT300-V and SVT400-V are in the M6 screw hold package (SVT-A series package). Screw mount package similar to SVT200-V can also be ordered with a longer lead time.

4. There is no need to manually remove acceleration RMS offset at the BroadVibra vibration analysis software now. SVT-V series wireless vibration sensors newly improved intelligent algorithm removed the DC offset automatically. Instead, BroadVibra software added the ISO 10816 vibration velocity reference table, which makes it more convenient to tell the vibration severity of machines. This feature makes it very convenient for machine condition monitoring.

True real-time wireless vibration monitoring

True real-time vibration monitoring

ISO 10816 vibration severity reference

ISO 10816 vibration severity reference

Wireless vibration sensors SVT200-V, SVT300-V and SVT400-V require to be used with Broadsens's wireless gateway and BroadVibra vibration monitoring software. The innovative design of Broadsens's ultra-low power communication protocol allows the system to achieve the best battery efficiency in the industry. The wireless vibration sensors, wireless gateways and vibration monitoring software provide an intelligent solution for predictive maintenance and machine condition monitoring.

Broadsens Wireless Vibration Sensors Obtained Calibration Certificate

Broadsens ultra-low power wireless vibration sensors recently obtained calibration certificate from Institute of Calibration and Technologies Co and KOLAS.

The calibration was performed using B&K 8305, Agilent 33220A arbitrary waveform generator, B&K 2692 condition amplifier and HP 34401A multimeter. The frequency range from 10Hz up to 1kHz was verified at x, y, z triaxial axes against the standard instrument. All x, y and z axes gave excellent results within 2% accuracy typically in the frequency range. The wireless vibration sensors can go up to 10kHz with up to 25.6kHz sampling rate.

wireless vibration sensor in testing

Broadsens wireless vibration sensor in testing

certified wireless vibration sensor

Sensor calibration certificate

If you are looking for ultra-compact, light-weight and high performance wireless vibration sensors with trusted result, then Broadsens has the right solution. Broadsens ultra-low power wireless vibration sensors have the highest battery efficiency in the industry. They are built for tough environments, so that you don't need to replace the broke sensors or replace batteries in industrial applications.

The wireless vibration sensors require to use Broadsens's wireless gateways for the maximum performance and long-lasting battery. There are multiple configurations of the wireless gateways for different industrial applications such as motors, pumps, engines, belts, bearings and gear box monitoring.

The system is ideal for IIOT applications, condition based maintenance and predictive maintenance.

#wireless #vibrationmonitoring #sensors #lowpower #iiot #predictivemaintenance #conditionmonitoring #conditionbasedmaintenance

Advanced Filtering for Vibration Analysis

Broadsens recently enhanced its filtering ability in the vibration analysis software BroadVibra 2.5.8. In this release, the negative edge effect is removed, which allows for more accurate time-domain and frequency domain vibration analysis. When the software is used with ultra-low power wireless vibration sensors SVT200-A, SVT300-A and SVT400-A, the system provides one of the most advanced filtering ability for machine condition monitoring and predictive maintenance. BroadVibra vibration monitoring and analysis software is installed inside the wireless gateways with life-time license. Users do not need to pay subscription fee to use the software, which can save the cost in the long run. Moreover, the software comes with 1-year free tech support and upgrade.

vibration analysis with FFT and high-pass filter

Figure 1. High pass filter with edge effect

In Figure 1, a 4th order high-pass filter is applied to the vibration signal. The vibration signal is obtained from a SVT200-A wireless vibration sensor mounted on a industrial fan. The wireless vibration system is used for industrial fan  vibration monitoring. The wireless vibration sensor takes triaxial raw acceleration data and send them to the wireless gateway. The data acquisition mode is "single DAQ" mode, in which 4,096 sample points are taken. The sampling rate is set at 3.2kHz. The data resolution is 16-bit.

At the very beginning of Figure 1, if you look closely, then you may notice that there is an edge effect of the filtering data. This is due to the reason that all filters have a transient effect, which needs a short time period to settle. The edge effect is especially obvious in z-axis in this testing.

Figure 2 removes the x and y axes, and zooms in the beginning of the z-axis curve. You can clearly see the edge effect in Figure 2. In Figure 3, the edge effect is removed automatically in the BroadVibra vibration analysis software version 2.5.8 and above. This allows more accurate time-domain and frequency domain vibration analysis.

Vibration FFT analysis edge effect

Figure 2. Zoomed in edge effect at z-axis

Vibration analysis edge effect removed

Figure 3. Edge effect automatically removed

The BroadVibra vibration analysis software allows user to select high-pass, low-pass and band-pass filtering, plus continuous adjustment of the cutoff frequency. The filtering order can be selected from 4th order, 8th order and up to 12th order. With the advanced filtering ability and FFT analysis at the edge-computing gateway, Broadsens offers some of the best wireless vibration sensors in the industry.

Posts navigation

1 2 3 4 5 6 7 10 11 12