Stwin-BX1 operating temperature and CBM implementation

[DDineshkumar]

I'm working on CBM model for predicting maintenance on Motor and trying to analyze the bearing frequencies I have few questions to develop a solution based on STWIn-BX1

1) Mounting of the Board - is it necessary to mount the board on the Motor near the bearing?

2) the operating temperature range of the board is just up to 35degc, but the accelerometer and vibratory sensor is rated for 105degC, how to use the board for extended temperature range?

3) I currently use FP-data log firmware to capture the data and do analysis with math lab to predict the bearing frequencies. is there any way i can create a model to include the list of bearing frequencies that will enable me to create failure alerts based on magnitudes related to bearing and implement a decision tree.

Regards

Dinesh Kumar 

[SimonePradolini]

Hello @DDineshkumar 

I suggest you to have a look at this video (link), which describes a demo setup for industrial anomaly detection and condition monitoring that we showcased at the latest Embedded World. I hope the video will be helpful and provide you with some insights for building your setup.

1) To achieve optimal vibration coupling, it's best to mount the board as close to the source as possible. Additionally, there are addon boards for the STWIN.box that are compatible with FP-SNS-DATALOG2 and designed specifically for your purpose: STEVAL-C34KAT1 and STEVAL-C34KAT2. I recommend creating your dataset using these boards as well.

2) Please note that ST STEVAL boards are intended for evaluation purposes only and are not guaranteed for industrial applications. You are free to conduct your experiments, but there are no warranties regarding temperature, humidity, or dust resistance.

3) FP-SNS-DATALOG2 is an excellent tool for creating your dataset. It allows you to label the data and convert the dataset using the HSDPython_SDK included in the Function Pack into CSV, TXT, or a pandas DataFrame format. Afterwards, you have the option to use your preferred open-source toolkit to build your model or to utilize NanoEdgeAI Studio and input the labeled data.

Best regards

Simone

In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.

[DDineshkumar · Accepted solution]

Hello @SimonePradolini 

Thanks for responding back!

I have mounted the evaluation board STWINBX1 near to the bearing assembly and captured the data using the vibrometer IIS3DWB using the FP-SNS-Datalog2 firmware and convert it back to csv format.

I used math lab to check the bearing frequencies which are related to the Inner race, outer race and rotating ring. Individual bearing frequencies corresponding to the motor rpm was captured and with the fft. I was able see the magnitudes on the rotating ring since the bearing was a good one, I didn't see big spike in the magnitude. in this method Individual bearing frequencies were analyzed manually by loading the data in math lab and cross validating the same.

I tried to use the Predicative monitoring dashboard application to validate the system, but I faced several issues in the connectivity I.e. while connecting the micro usb cable to STSTWINKT1B the pc is not recognizing it shows error code 43 even after Mutiple tries and fixing the driver software I was unable to connect the board to pc to use terra term for configuring. I have  STWINWFV1 mounted along with STWIN KT1B and also have a stwin box - stwin BX1. my next step is to use the aws cloud and do the fft online rather than using the math lab. the use test the NanoEdgeAI Studio to develop the model.

I would like to get your help on establishing the wifi connection to these boards which might help me to move forward on the process.

How to get the Mac address of the individual boards which helps me to get whitelisted and connect to the network? 

Best Regards

Dinesh kumar