IoT | TensorFlow WeatherStationは降雨強度を予測します

コード

• IoT_weather_station_neural_network.py
• ESP12E_remote_weather_station.ino
• SIM808_remote_weather_station.ino
• index.php（Webアプリケーション）
• account_verification_token.php（Webアプリケーション）

IoT_weather_station_neural_network.py Python

 ＃TensorFlowを使用して降雨強度を予測するIoT Weather Station＃Windows、Linux、またはUbuntu＃Kutluhan Aktar＃Googleスプレッドシートの気象データを照合し、TensorFlowに組み込まれたニューラルネットワークで解釈して降雨強度を予測します。 ＃詳細情報：＃https：//www.theamplituhedron.com/projects/IoT_Weather_Station_Predicting_Rainfall_Intensity_with_TensorFlowimport tensorflow as tffrom tensorflow import kerasimport matplotlib.pyplot as pltimport numpy as npimport pandas as pd＃クラスを作成してニューラルネットワークを構築する気象データのスケーリング（正規化）。classWeather_Station：def __init __（self、data）：self.df =data self.input =[] self.label =[]＃さまざまな降雨強度の予測と値のクラス名を定義します。 self.class_names =['None'、 'Light Rain'、 'Moderate Rain'、 'Heavy Rain'、 'Violent Rain']＃要求された列のグラフィックを作成します。 def graphics（self、column_1、column_2、xlabel、ylabel）：＃データセットから要求された列を表示します：plt.style.use（ "dark_background"）plt.gcf（）。canvas.set_window_title（ 'IoT Weather Station'）plt .hist2d（self.df [column_1]、self.df [column_2]）plt.colorbar（）plt.xlabel（xlabel）plt.ylabel（ylabel）plt.title（xlabel）plt.show（）＃作成する前にデータを視覚化するニューラルネットワークモデルにフィードします。 def data_visualization（self）：＃要求された列を検査して、適切にフォーマットされたデータでモデルを構築します：self.graphics（ 'WD'、 '1h_RF'、 'Wind Direction（deg）'、 'One-Hour Ra​​infall（mm）'）self .graphics（ 'Av_WS'、 '1h_RF'、 '平均風速（m / s）'、 '1時間の降雨量（mm）'）self.graphics（ 'Mx_WS'、 '1h_RF'、 '最大風速（m / s） '、' 1時間の降雨量（mm） '）self.graphics（' 24h_RF '、' 1h_RF '、' 24時間の降雨量（mm） '、' 1時間の降雨量（mm） '）self.graphics （ 'Tem'、 '1h_RF'、 'Temperature（C）'、 'One-Hour Ra​​infall（mm）'）self.graphics（ 'Hum'、 '1h_RF'、 'Humidity（％）'、 'One-Hour Ra​​infall （mm） '）self.graphics（' b_PR '、' 1h_RF '、'気圧（hPA） '、' 1時間の降雨量（mm） '）＃ニューラルネットワークモデルに応じてデータをスケーリング（正規化）します。 def scale_data（self）：＃風向と風速：wv =self.df.pop（ 'Av_WS'）max_wv =self.df.pop（ 'Mx_WS'）＃ラジアンに変換します。 wd_rad =self.df.pop（ 'WD'）* np.pi / 180＃風のx成分とy成分を計算します。 self.df ['scaled_WX'] =wv * np.cos（wd_rad）self.df ['scaled_WY'] =wv * np.sin（wd_rad）＃最大風のxおよびy成分を計算します。 self.df ['scaled_max_WX'] =max_wv * np.cos（wd_rad）self.df ['scaled_max_WY'] =max_wv * np.sin（wd_rad）＃温度：tem =self.df.pop（ 'Tem'）self .df['scaled_Tem'] =tem / 25 # Humidity:hum =self.df.pop('Hum') self.df['scaled_Hum'] =hum / 70 # Barometric Pressure:bPR =self.df.pop( 'b_PR') self.df["scaled_bPR"] =bPR / 1013 # 24 Hour Rainfall (Approx.) rain_24 =self.df.pop('24h_RF') self.df['scaled_24h_RF'] =rain_24 / 24 # Define the input and label arrays. def create_input_and_label(self):n =len(self.df) # Create the input array using the scaled variables:for i in range(n):self.input.append(np.array([self.df['scaled_WX'][i], self.df['scaled_WY'][i], self.df['scaled_max_WX'][i], self.df['scaled_max_WY'][i], self.df['scaled_Tem'][i], self.df['scaled_Hum'][i], self.df['scaled_bPR'][i]])) self.input =np.asarray(self.input) # Create the label array using the one-hour and 24-hour rainfall variables:for i in range(n):_class =0 # Evaluate the approximate rainfall rate:approx_RF_rate =(self.df['1h_RF'][i] + self.df['scaled_24h_RF'][i]) * 100 # As labels, assign classes of rainfall intensity according to the approximate rainfall rate (mm):if approx_RF_rate ==0:_class =0 elif approx_RF_rate <2.5:_class =1 elif 2.5  ", self.class_names[np.argmax(prediction[i])]) # Save the model for further usage without training steps:def save_model(self):self.model.save("E:\PYTHON\weather_station.h5") # Run Artificial Neural Network (ANN):def Neural_Network(self, save):self.scale_data() self.create_input_and_label() self.split_data() self.build_and_train_model() if save ==True:self.save_model() # Example Input and Layer:print("\nScaled Input [EXP]:\n") print(self.train_input[0]) print("\nScaled Label [EXP]:\n") print(self.train_label[0]) # Read data (Remote Weather Station.csv):csv_path ="E:\PYTHON\Remote Weather Station.csv"df =pd.read_csv(csv_path)# Define a new class object named 'station':stati on =Weather_Station(df)# Visualize data:#station.data_visualization()# Artificial Neural Network (ANN):station.Neural_Network(False)# Enter inputs for making predictions:prediction_array =np.array([ [0, 0, 0.31819805, 0.31819805, 0.6988, 0.81498571, 0.99349753], [0, -0, 0, -0, 0.8444, 1, 0.96835143], [0, 0, 0.45, 0, 0.87577, 0.95857143, 1.00128332], [-0, -0, -0, -0, 0.8224, 1.05714286, 0.99279368]])# Prediction Results:station.make_prediction(prediction_array)

ESP12E_remote_weather_station.inoArduino

 ///////////////////////////////////////////// // IoT Weather Station Predicting // // Rainfall Intensity w/ TensorFlow // // ------------------------ // // NodeMCU (ESP-12E) // // by Kutluhan Aktar // // // ///////////////////////////////////////////////// Collates weather data on Google Sheets and interprets it with a neural network built in TensorFlow to make predictions on the rainfall intensity. //// For more information:// https://www.theamplituhedron.com/projects/IoT_Weather_Station_Predicting_Rainfall_Intensity_with_TensorFlow//// Connections// NodeMCU (ESP-12E) :// Weather Station// VV --------------------------- 5V// D5 --------------------------- RX// D6 --------------------------- TX// G --------------------------- GND// Include required libraries:#include #include  #include #include #include // Define your WiFi settings.const char *ssid ="";const char *password ="";// Define weather station settings:char databuffer[35];double temp;int transferring =0;// Define the serial connection pins - RX and TX.SoftwareSerial Serial_1(D6, D5); // (Rx, Tx)void setup() { // Wait until connected. delay（1000）; // Initiate serial ports:Serial.begin(115200); Serial_1.begin(9600); // It is just for assuring if connection is alive. WiFi.mode(WIFI_OFF); delay（1000）; // This mode allows NodeMCU to connect any WiFi directly. WiFi.mode（WIFI_STA）; // Connect NodeMCU to your WiFi. WiFi.begin(ssid, password); Serial.print("\n\n"); Serial.print("Try to connect to WiFi. Please wait! "); Serial.print("\n\n"); // Halt the code until connected to WiFi. while（WiFi.status（）！=WL_CONNECTED）{delay（500）; Serial.print("*"); } // If connection is successful:Serial.print("\n\n"); Serial.print("-------------------------------------"); Serial.print("\n\n"); Serial.print("Connection is successful!"); Serial.print("\n\n"); Serial.print("Connected WiFi SSID :"); Serial.print(ssid); Serial.print("\n\n"); Serial.println("Connected IPAddress :"); Serial.println(WiFi.localIP()); Serial.print("\n\n");}void loop() { // Get data from the remote weather station:getBuffer(); // Debug the information and create the link:String weather_data ="wd=" + String(WindDirection()) + "&a_ws=" + String(WindSpeedAverage()) + "&m_ws=" + String(WindSpeedMax()) + "&1_rf=" + String(RainfallOneHour()) + "&24_rf=" + String(RainfallOneDay()) + "&tem=" + String(Temperature()) + "&hum=" + String(Humidity()) + "&b_pr=" + String(BarPressure()); String server ="http://192.168.1.24/remote_weather_station/?"; Serial.println("Weather Data => " + weather_data); Serial.println("Buffer => " + String(databuffer)); // Send data packets every 5 minutes to Raspberry Pi (or any server). transferring++; Serial.println("Time => " + String(transferring) + "s / " + String(int(5*60)) + "s\n\n"); if(transferring ==5*60){ // Create the HTTP object to make a request to the server. HTTPClient http; http.begin(server + weather_data); int httpCode =http.GET(); String payload =http.getString(); Serial.println("Data Send...\nHTTP Code => " + String(httpCode) + "\nServer Response => " + payload + "\n\n"); http.end(); transferring =0; } // Wait 1 second... delay(1000);}// WEATHER STATIONvoid getBuffer(){ int index; for (index =0;index <35;index ++){ if(Serial_1.available()){ databuffer[index] =Serial_1.read(); if (databuffer[0] !='c'){ index =-1; } } else{ index --; } }}int transCharToInt(char *_buffer, int _start, int _stop){ int _index; int result =0; int num =_stop - _start + 1; int _temp[num]; for (_index =_start;_index <=_stop;_index ++){ _temp[_index - _start] =_buffer[_index] - '0'; result =10*result + _temp[_index - _start]; } return result;}int WindDirection(){ return transCharToInt(databuffer,1,3); } // Wind Direction (deg)float WindSpeedAverage(){ temp =0.44704 * transCharToInt(databuffer,5,7);温度を返す; } // Average Air Speed (1 minute)float WindSpeedMax(){ temp =0.44704 * transCharToInt(databuffer,9,11);温度を返す; } //Max Air Speed (5 minutes)float Temperature(){ temp =(transCharToInt(databuffer,13,15) - 32.00) * 5.00 / 9.00;温度を返す; } // Temperature ("C")float RainfallOneHour(){ temp =transCharToInt(databuffer,17,19) * 25.40 * 0.01;温度を返す; } // Rainfall (1 hour)float RainfallOneDay(){ temp =transCharToInt(databuffer,21,23) * 25.40 * 0.01;温度を返す; } // Rainfall (24 hours)int Humidity(){ return transCharToInt(databuffer,25,26); } // Humidity (%)float BarPressure(){ temp =transCharToInt(databuffer,28,32);戻り温度/10.00; } // Barometric Pressure (hPA)

SIM808_remote_weather_station.inoArduino

 ///////////////////////////////////////////// // IoT Weather Station Predicting // // Rainfall Intensity w/ TensorFlow // // ------------------------ // // Arduino Uno (SIM808) // // by Kutluhan Aktar // // // ///////////////////////////////////////////////// Collates weather data on Google Sheets and interprets it with a neural network built in TensorFlow to make predictions on the rainfall intensity. //// For more information:// https://www.theamplituhedron.com/projects/IoT_Weather_Station_Predicting_Rainfall_Intensity_with_TensorFlow//// Connections// Arduino Uno:// SIM808 GPS/GPRS/GSM Shield For Arduino// D0 --------------------------- RX// D1 --------------------------- TX// D12 --------------------------- POWER // Weather Station// 5V --------------------------- 5V// D5 --------------------------- RX// D6 --------------------------- TX// GND --------------------------- GND// Include required libraries:#include #include // Define the sim808.DFRobot_SIM808 sim808(&Serial);// Define weather station settings:char databuffer[35];double temp;int transferring =0;// Define the serial connection pins - RX and TX.SoftwareSerial Serial_1(6, 5); // (Rx, Tx)void setup() { // Wait until connected. delay（1000）; // Initiate serial ports:Serial.begin(9600); Serial_1.begin(9600); //******** Initialize sim808 module ************* while(!sim808.init()) { delay(1000); Serial.print("Sim808 init error\r\n"); } delay(2000); // Continue if the SIM808 Module is working accurately. Serial.println("Sim808 init success"); delay(5000);}void loop() { // Get data from the remote weather station:getBuffer(); // Debug the information and create the link:String weather_data_1 ="wd=" + String(WindDirection()) + "&a_ws=" + String(WindSpeedAverage()) + "&m_ws=" + String(WindSpeedMax()); String weather_data_2 ="&1_rf=" + String(RainfallOneHour()) + "&24_rf=" + String(RainfallOneDay()) + "&tem=" + String(Temperature()); String weather_data_3 ="&hum=" + String(Humidity()) + "&b_pr=" + String(BarPressure()); Serial.print("Weather Data => " + weather_data_1); Serial.print(weather_data_2); Serial.println(weather_data_3); Serial.println("Buffer => " + String(databuffer)); // Send data packets every 5 minutes to the server. transferring++; Serial.println("Time => " + String(transferring) + "s / " + String(int(5*60)) + "s\n\n"); if(transferring ==5*60){ //*********** Attempt DHCP ******************* while(!sim808.join(F("cmnet"))) { Serial.println("Sim808 join network error!"); delay（2000）; } //************ Successful DHCP **************** delay(5000); Serial.println("Successful DHCP"); //*********** Establish a TCP connection ************ if(!sim808.connect(TCP,"192.168.1.24", 80)) { // Change it with your server. Serial.println("Connection Error"); }else{ Serial.println("Connection OK"); } delay(2000); //*********** Send a GET request ***************** String line ="GET /remote_weather_station/?" + weather_data_1 + weather_data_2 + weather_data_3 + " HTTP/1.0\r\n\r\n"; Serial.println(line); char buffer[512]; // Convert the line from string to char array to make an HTTP Get Request with the SIM808. char web_hook[110]; String_to_Char(line, 110, web_hook); sim808.send(web_hook, sizeof(web_hook)-1); while (true) { int ret =sim808.recv(buffer, sizeof(buffer)-1); if (ret <=0){ Serial.println("Fetch Over...");壊す; } // Uncomment to view the response in the serial monitor. /* buffer[ret] ='\0'; Serial.print("Recv:"); Serial.print(ret); Serial.print(" bytes:"); Serial.println(buffer); */ Serial.println("\nData Send");壊す; } //************* Close TCP or UDP connections ********** sim808.close(); //*** Disconnect wireless connection, Close Moving Scene ******* sim808.disconnect(); // Exit. transferring =0; } // Wait 1 second... delay(1000);}// WEATHER STATIONvoid getBuffer(){ int index; for (index =0;index <35;index ++){ if(Serial_1.available()){ databuffer[index] =Serial_1.read(); if (databuffer[0] !='c'){ index =-1; } } else{ index --; } }}int transCharToInt(char *_buffer, int _start, int _stop){ int _index; int result =0; int num =_stop - _start + 1; int _temp[num]; for (_index =_start;_index <=_stop;_index ++){ _temp[_index - _start] =_buffer[_index] - '0'; result =10*result + _temp[_index - _start]; } return result;}int WindDirection(){ return transCharToInt(databuffer,1,3); } // Wind Direction (deg)float WindSpeedAverage(){ temp =0.44704 * transCharToInt(databuffer,5,7);温度を返す; } // Average Air Speed (1 minute)float WindSpeedMax(){ temp =0.44704 * transCharToInt(databuffer,9,11);温度を返す; } //Max Air Speed (5 minutes)float Temperature(){ temp =(transCharToInt(databuffer,13,15) - 32.00) * 5.00 / 9.00;温度を返す; } // Temperature ("C")float RainfallOneHour(){ temp =transCharToInt(databuffer,17,19) * 25.40 * 0.01;温度を返す; } // Rainfall (1 hour)float RainfallOneDay(){ temp =transCharToInt(databuffer,21,23) * 25.40 * 0.01;温度を返す; } // Rainfall (24 hours)int Humidity(){ return transCharToInt(databuffer,25,26); } // Humidity (%)float BarPressure(){ temp =transCharToInt(databuffer,28,32);戻り温度/10.00; } // Barometric Pressure (hPA)void String_to_Char(String _String, int _size, char _convert[]){ for(int i=0;i<_size;i++){ _convert[i] =_String[i]; }} 

index.php (web application)PHP

 (int)$_GET['wd'], "a_ws" => (float)$_GET['a_ws'], "m_ws" => (float)$_GET['m_ws'], "1_rf" => (float)$_GET['1_rf'], "24_rf" => (float)$_GET['24_rf'], "tem" => (float)$_GET['tem'], "hum" => (int)$_GET['hum'], "b_pr" => (float)$_GET['b_pr'] ];}else{ $variables_from_module =[ "wd" => "err", "a_ws" => "err", "m_ws" => "err", "1_rf" => "err", "24_rf" => "err", "tem" => "err", "hum" => "err", "b_pr" => "err" ];}/** * Returns an authorized API client. * @return Google_Client the authorized client object */function getClient(){ $client =new Google_Client(); $client->setApplicationName('Remote Weather Station'); // Enter your application name. $client->setScopes('https://www.googleapis.com/auth/spreadsheets'); $client->setAuthConfig('credentials.json'); $client->setAccessType('offline'); $client->setPrompt('select_account consent'); // Load previously authorized token from a file, if it exists. // The file token.json stores the user's access and refresh tokens, and is // created automatically when the authorization flow completes for the first // time. $tokenPath ='token.json'; if (file_exists($tokenPath)) { $accessToken =json_decode(file_get_contents($tokenPath), true); $client->setAccessToken($accessToken); print("Token Found!"); } // If there is no previous token or it's expired. if ($client->isAccessTokenExpired()) { // Refresh the token if possible, else fetch a new one. if ($client->getRefreshToken()) { $client->fetchAccessTokenWithRefreshToken($client->getRefreshToken()); } else { // Request authorization from the user. $authUrl =$client->createAuthUrl(); // Do not forget to refresh the page after getting the verification code and entering it to the account_verification_token.php. printf("Open the following link in your browser:

%s

", $authUrl); // <=Comment print 'Do not forget to refresh the page after getting the verification code and entering it to the account_verification_token.php.

Set the verification code in the account_verification_token.php file.'; // <=Comment // Set the verification code to create the token.json. $authCode =trim($GLOBALS['account_verification_token']); // Exchange authorization code for an access token. $accessToken =$client->fetchAccessTokenWithAuthCode($authCode); $client->setAccessToken($accessToken); // Check to see if there was an error and the account_verification_token is entered. if (array_key_exists('error', $accessToken)) { throw new Exception(join(', ', $accessToken)); }else{ print("Successful! Refresh the page."); } } // Save the token to a file. if (!file_exists(dirname($tokenPath))) { mkdir(dirname($tokenPath), 0700, true); } file_put_contents($tokenPath, json_encode($client->getAccessToken())); } return $client;}// Get the API client and construct the service object.$client =getClient();$service =new Google_Service_Sheets($client);// Enter your spreadsheetId:$spreadsheetId ='';// Enter the range (the first row) under which new values will be appended (8 rows):$range ='A1:H1';// Append recent findings from the weather station to the spreadsheet.$values =[ [$variables_from_module["wd"], $variables_from_module["a_ws"], $variables_from_module["m_ws"], $variables_from_module["1_rf"], $variables_from_module["24_rf"], $variables_from_module["tem"], $variables_from_module["hum"], $variables_from_module["b_pr"]]];$body =new Google_Service_Sheets_ValueRange([ 'values' => $values]);$params =[ 'valueInputOption' => "RAW"];// Append if only requested!if(isset($_GET['wd']) &&isset($_GET['a_ws']) &&isset($_GET['m_ws']) &&isset($_GET['1_rf']) &&isset($_GET['24_rf']) &&isset($_GET['tem']) &&isset($_GET['hum']) &&isset($_GET['b_pr'])){ $result =$service->spreadsheets_values->append($spreadsheetId, $range, $body, $params); printf("

%d cells appended.", $result->getUpdates()->getUpdatedCells());}else{ print ("
Missing Data!");}

account_verification_token.php (web application)PHP

"; // Enter the verification code after authorization. ?>

カスタムパーツとエンクロージャー

回路図