Published October 11, 2020 © GPL3+

Temperature Monitoring System with Alerts and Prediction

Dispatch SMS alerts for temperature anomalies or if readings fall below the threshold, additionally forecasting future temperature values.

IntermediateFull instructions provided733

Temperature Monitoring System with Alerts and Prediction

Things used in this project

Hardware components

RCA Female to Female Coupler, 3 Way

Temperature Sensor

Bolt IoT Bolt WiFi Module

Software apps and online services

Bolt IoT Android App

Snappy Ubuntu Core

Twilio SMS Messaging API

Story

This project centers on real-time room temperature monitoring. It proactively sends SMS alerts when there is a significant fluctuation in temperature, or if the temperature dips below a predetermined minimum. Moreover, it leverages historical data to predict future temperature trends, empowering you to take informed actions.

Due to certain medical conditions, my physician has advised me against staying in rooms with temperatures below 33 degrees. Additionally, abrupt temperature changes can have harmful effects on my skin. Consequently, I conceived the idea of constructing an IoT device capable of alerting me as soon as any of the aforementioned situations occur. This device can also forecast forthcoming temperatures, allowing me to take preventive measures as needed.

WORKING OF THE PROJECT

The project mainly encompasses three functions:

Dispatching alert SMS when the temperature falls below a particular minimum.
Issuing alert SMS when a significant temperature change occurs.
Predicting future temperatures utilizing Polynomial Regression.

SENDING ALERT SMS

Ubuntu, a Linux-based operating system, is widely used on servers.

On the other hand, Twilio is a third-party service providing SMS capabilities, enabling software developers to send and receive text messages programmatically via its web service APIs.

Upon gaining access to our Ubuntu (Linux) server, it's imperative to create a configuration file. This file will securely store all sensitive device and user keys, as demonstrated below.

SID = 'You can find SID in your Twilio Dashboard' 
AUTH_TOKEN = 'You can find  on your Twilio Dashboard' 
FROM_NUMBER = 'This is the no. generated by Twilio. You can find this on your Twilio Dashboard'
TO_NUMBER = 'This is your number. Make sure you are adding +91 in beginning'
API_KEY = 'This is your Bolt Cloud account API key'
DEVICE_ID = 'This is the ID of your Bolt device'

The initial four variables can be sourced from the Twilio dashboard, while the final two variables can be established as follows: Connect the Bolt device to the Bolt cloud to ascertain the DEVICE_ID and generate the API_KEY.

Next, create the main_code.py file. This file will house the primary code, which can be divided into the subsequent steps:

Import all necessary libraries and the configuration file.
Construct a function that provides high and low bounds.
Retrieve the sensor value from the Bolt device.
Validate the sensor value.
Verify if the sensor value has dropped below the minimum and determine if an alert message is warranted.
Determine whether the sensor value has breached the set bounds and evaluate if an alert is necessary.
Pause for 10 seconds. Then, return to step 3.

PREDICTING TEMPERATURE

Power up the device and establish a connection with the Bolt Cloud.
Proceed to cloud.boltiot.com and initiate a new product creation. During this process, select 'Input Device' as the product type and 'GPIO' as the interface type.
Upon product creation, locate and select the newly minted product, then click on the configure icon.
In the 'Hardware' tab, activate the radio button adjacent to the A0 pin. Label this pin as 'temp' and confirm the configuration using the 'Save' icon.
Transition to the 'Code' tab, designate the product code name as 'predict', and set the code type to 'js'.
Compose the following code to graph the temperature data and execute the polynomial regression algorithm on this data. Save these product configurations afterward.

setChartLibrary('google-chart');
setChartTitle('Polynomial Regression');
setChartType('predictionGraph');
setAxisName('time_stamp','temp');
mul(0.0977);
plotChart('time_stamp','temp');

Navigate to the 'Products' tab, choose the created product, and then click the link icon. In the ensuing popup, select your Bolt device and finalize by clicking the 'Done' button.
Select the 'Deploy Configuration' button, followed by the 'View this Device' icon to access the page you've configured.
Allow approximately two hours for the device to transfer sufficient data points to the Cloud. Afterwards, hit the 'Predict' button to display the prediction graph derived from the Polynomial Regression algorithm.

OUTPUT

SMS

This is a screenshot capturing the console output, the result of the code execution.

output

The console initially displays "Not enough data to compute Z-score. Need 10 more data points," due to the frame value being set at 10. As soon as this frame is filled with 10 data points in the history list, the compute_bound function begins calculating the upper and lower thresholds.

Upon activating the AC and switching to I-cool mode, a significant temperature drop from 352 to 344 occurred, thereby triggering an anomaly detection. Consequently, an SMS alert was dispatched to my number stating, "Someone switched on the I-cool mode in AC."

The preset minimum temperature limit was set at 341. Hence, when the temperature fell below this limit, another SMS alert was sent to my number. This message read, "The current temperature sensor value is 340 and in Celsius, it's 33.203125."

PREDICTION

The image below depicts a prediction graph of time versus temperature, with four points forecasted via polynomial regression.

As evidenced in this graph, a sharp temperature drop occurred around 11:00 PM, corresponding with the alert SMS I received. The calculation for temperature is as follows: Temperature = (sensor_value * 100) / 1024.

Circuit diagram

Connecting LM35 to bolt

Step 1: Hold the sensor in a manner such that you can read LM35 written on it.

Step 2: In this position, identify the pins of the sensor as VCC, Output and Gnd from your left to right.

VCC is connected to the red wire, Output is connected to the orange wire and Gnd is connected to the brown wire.

Step 3: Using male to female wire connect the 3 pins of the LM35 to the Bolt Wifi Module as follows:

VCC pin of the LM35 connects to 5v of the Bolt Wifi module.
Output pin of the LM35 connects to A0 (Analog input pin) of the Bolt Wifi module.
Gnd pin of the LM35 connects to the Gnd.

output

This is the screenshot of the console where the output of the code is shown.
Here we can see that as the frame value is 10 the console will show "Not enough data to compute Z-score. Need 10 more data points."
Now as soon as I switched on the AC and turned I-cool mode on, the temperature dropped from 352 to 344 cause of which an SMS was sent to my number informing "Someone switched on the I-cool mode in AC".
Now the minimum limit was set to 341, so, as soon as the temperature dropped beyond 341 an SMS was sent to my number informing "The current temperature sensor value is 340 and celcius33.203125"

Code

Complete code

import json, time, math, statistics  
from boltiot import Sms, Bolt
#importing configuration file which holds the confidential data 
import conf   

#function to compute bounds or Z Score Analysis

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)  #returns object of Bolt to mybolt and connects with the bolt device 
sms = Sms(conf.SSID, conf.AUTH_TOKEN, conf.TO_NUMBER, conf.FROM_NUMBER) #create a platform for the mobile networks and server to connect with each other
history_data=[] #list of the sensor values to be stored in

while True:
    response = mybolt.analogRead('A0') #reads the data from A0 pin
    data = json.loads(response) #converts the data in the python dictionary type
    if data['success'] != 1:
        print("There was an error while retriving the data.")
        print("This is the error:"+data['value'])
        time.sleep(10)
        continue

    print ("This is the value "+data['value'])
    sensor_value=0
    try:
        sensor_value = int(data['value'])
    except e:
        print("There was an error while parsing the response: ",e)
        continue

    try: 
        sensor_value = int(data['value'])
        minimum_limit = 341
        
        #alerts when the temperature goes below minimum limit-
        
        if sensor_value < minimum_limit: 
            print("Making request to Twilio to send a SMS")
            Temperature=(100*sensor_value)/1024 
            response = sms.send_sms("The Current temperature sensor value is " +str(sensor_value)+"and in celcius" +str(Temperature))
            print("Response received from Twilio is: " + str(response))
            print("Status of SMS at Twilio is :" + str(response.status))
    except Exception as e: 
        print ("Error occured: Below are the details")
        print (e)

    bound = compute_bounds(history_data,conf.FRAME_SIZE,conf.MUL_FACTOR) #calls the function and as a result it returns low and high bound 
    if not bound: #if the function returns none 
        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
    
        #alerts when there is a sudden raise or drop in temperature-
    
    try:
        if sensor_value > bound[0] : #if value greater than high bound
            print ("The Temperature level increased suddenly. Sending an SMS.")
            response = sms.send_sms("Someone switched on the I-heat mode in Heater")
            print("This is the response ",response)
        elif sensor_value < bound[1]: #if value lower than low bound
            print ("The Temperature level decreased suddenly. Sending an SMS.")
            response = sms.send_sms("Someone switched on the I-cool mode in AC")
            print("This is the response ",response)
        history_data.append(sensor_value);
    except Exception as e:
        print ("Error",e)

    
    
    time.sleep(10)

Credits

Kunal Mehta

1 project • 1 follower

Temperature Monitoring System with Alerts and Prediction

Things used in this project

Hardware components

Software apps and online services

Story

WORKING OF THE PROJECT

OUTPUT

Schematics

Circuit diagram

output

Code

Complete code

Credits

Kunal Mehta

Comments

Embed the widget on your own site

Temperature Monitoring System with Alerts and Prediction

Temperature Monitoring System with Alerts and Prediction

Things used in this project

Hardware components

Software apps and online services

Story

WORKING OF THE PROJECT

OUTPUT

Schematics

Circuit diagram

output

Code

Complete code

Credits

Kunal Mehta

Comments

Related channels and tags