Published July 16, 2019 © GPL3+

Capstone Project (Temperature Monitor and Anomaly Detector)

It monitors Fridge's temperature and alerts via Telegram, if the temperature falls below thresholds. It alerts if someone opens the door, too.

IntermediateProtip2.5 hours776

Capstone Project (Temperature Monitor and Anomaly Detector)

Things used in this project

Hardware components

Bolt IoT Bolt WiFi Module

Temperature Sensor

Male/Female Jumper Wires

Software apps and online services

Bolt IoT Bolt Cloud

Integromat

Story

Ever felt burdensome to keep a check on temperature of a facility or plant? Keep reporting the highs and the lows. Well, imagine it is automated. You can just sit and have a cup of tea. Let IoT do the job for you.

This project demonstrates a Refrigerator's temperature monitor and also detects anomaly if found. It alerts you via Telegram if the temperature inside falls too low or it is higher than it should be. It also alerts if someone opens the refrigerator's door. This is done using Z-Score analysis. If your temperature is critical it alerts you and you can predict the temperature that would be after a certain time, thus helping you make your decisions better. It can be implemented to any plant, facility that requires temperature monitoring. Let's dive into it.

Connections:

1 / 2 • Connecting the Temperature Monitor Circuit

Configuring a new Product on Cloud

1 / 3 • Creating a new Product

Now that you have made the connections and registered the product on cloud, it's time for taking inputs.

Connect the module to power supply using an adapter or Power Bank and place it on the refrigerator. Keep the sensor inside the refrigerator.

Connecting to Power Bank and placing the sensor in refrigerator

Now, record the readings of the sensor for 2 hours to get the gist of the temperature values in there. We'll then set the thresholds accordingly.

Plotting and Prediciton

Once you finish taking readings the graph would look somewhat like this below.

Graph of the temperature readings over time

Now play with the predicted points, coefficients and frame size and predict until you get a graph that shows similar behavior (like the one below).

Prediction using Polynomial Regression

We can see the temperature constantly (more or less) remains between 0-5 degree Celsius. So, our minimum threshold is 0 degree Celsius and maximum threshold is 5 degree Celsius.

Configuring scenario in Integromat

Now alerts are carried using Integromat.

Create a New Scenario of Webhooks and Telegram.

Scenario

Set the schedule mode to trigger.
Copy the Webhook URL to your code.
Create a new Telegram Bot.
Search 'BotFather' in telegram
Send '/newbot' and create a new bot. Choose bot name.
On successful creation a AUTH_TOKEN will be generated.
Now create a new channel in Telegram App and add your Bot to it assigning it all permissions.
Click on Telegram in Scenario and choose 'ADD' in connection
Give a name and enter the AUTH_TOKEN
Enter the chat ID of channel you've created in Chat ID
Enter the text message as below.

Turn the Scenario ON

Coding

It's a good practice to store your credentials, API, etc. in a different file.

So, we'll create two Python files. viz. conf.py and fridge_alert.py

Config File

1 / 3 • Code for computing z-score bounds and trigerring Integromat

Now the stage is set, Let's run our code and see the output.

Running the code

Telegram Messages

Simple! isn't it?

Code

import conf,json,requests,math,statistics
import time
from boltiot import Bolt

PARAMS={'status': "undefined"}

def trigger_integromat_webhook(state):
	PARAMS['status']=state
	URL = conf.INTEGROMAT_URL
	response = requests.get(URL, PARAMS)
	print (response.text)

def compute_bounds(history_data,frame_size,factor) :
	if(len(history_data)<frame_size) :
		return None
	if(len(history_data)>frame_size) :
		del history_data[0:len(history_data)-frame_size]
	Mn=statistics.mean(history_data)
	Variance=0
	for data in history_data :
		Variance += math.pow((data-Mn),2)
	Zn = factor * math.sqrt(Variance / frame_size)
	High_bound = history_data[frame_size-1]+Zn
	Low_bound = history_data[frame_size-1]-Zn
	return [High_bound,Low_bound]

mybolt = Bolt(conf.API_KEY,conf.DEVICE_ID)
history_data=[]
# these thresholds are set using the data collected from 2 Hours
max_threshold = 5
min_threshold = 0

while True:
	response = mybolt.analogRead('A0')
	data = json.loads(response)
	if data['success'] != 1:
		print("There was an error whilst retrieving the data")
		print("This is the temperature" + data['value'])
		time.sleep(10)
		continue
	try:
		sensor_value = int(data['value'])
		sensor_value = sensor_value/10.24
		print("The Temperature is ",round(sensor_value,2),"degree Celsius")
	except e:
		print("There was an error while parsing the response: ",e)
		continue

	if sensor_value > max_threshold:
		# temperature is beyond required maximum
		trigger_integromat_webhook("MAX")
	elif sensor_value < min_threshold:
		# temperature is below required minimum
		trigger_integromat_webhook("MIN")

	bound = compute_bounds(history_data,conf.FRAME_SIZE,conf.MUL_FACTOR)
	if not bound:
		required_data_count = conf.FRAME_SIZE-len(history_data)
		print("Not enough data to compute Z-Score. Need ",required_data_count, "more data points")
		history_data.append(int(data['value']))
		time.sleep(10)
		continue
	try:
		# If temperature rises abnormally --> DOOR IS OPEN
		if sensor_value > bound[0]:
			trigger_integromat_webhook("OPEN")
		history_data.append(sensor_value)
	except Exception as e:
		print("Error",e)
	time.sleep(10)

Credits

Aniruddha Mishra

1 project • 1 follower

Final Year Computer Science & Engineering Student, NIT Andhra Pradesh

Capstone Project (Temperature Monitor and Anomaly Detector)

Things used in this project

Hardware components

Software apps and online services

Story

Connections:

Configuring a new Product on Cloud

Plotting and Prediciton

Configuring scenario in Integromat

Coding

Schematics

LM35 Sensor Circuit Connection

Code

fridge_alert.py

conf.py

product_code

Credits

Aniruddha Mishra

Comments

Embed the widget on your own site

Capstone Project (Temperature Monitor and Anomaly Detector)

Capstone Project (Temperature Monitor and Anomaly Detector)

Things used in this project

Hardware components

Software apps and online services

Story

Connections:

Configuring a new Product on Cloud

Plotting and Prediciton

Configuring scenario in Integromat

Coding

Schematics

LM35 Sensor Circuit Connection

Code

fridge_alert.py

conf.py

product_code

Credits

Aniruddha Mishra

Comments

Related channels and tags