Update app.py

app.py

@@ -1,50 +1,59 @@
-
 import streamlit as st
 import numpy as np
 from sklearn.linear_model import LinearRegression
 import pandas as pd
 
-# Create the Streamlit app
-st.title("Transformer Tap Changer Optimization App")
+# Title of the app
+st.title("132/11 kV Transformer Tap Changer Optimization App")
+
+# Nominal secondary voltage (11.5 kV)
+nominal_secondary_voltage = 11.5
 
 # Input fields for voltage and load
-voltage_in = st.number_input("Enter the Input Voltage (kV)", min_value=90, max_value=150, value=115)
-voltage_out = st.number_input("Enter the Output Voltage (kV)", min_value=80, max_value=130, value=100)
+voltage_in = st.number_input("Enter the Input Voltage (132 kV)", min_value=100, max_value=150, value=132)
+voltage_out = st.number_input("Enter the Output Voltage (11 kV)", min_value=10.0, max_value=15.0, value=11.0)
 load = st.number_input("Enter the Current Load (MW)", min_value=50, max_value=500, value=250)
 
-# Simple logic to determine the tap position based on voltage_out
-def optimize_tap_change(voltage_in, voltage_out, load):
-    # Example logic to decide when to change tap position
-    if voltage_out < 95:
-        return "Tap 1 (Increase voltage)"
-    elif voltage_out > 105:
-        return "Tap 5 (Decrease voltage)"
-    else:
-        return "Tap 3 (Optimal position)"
-
-# Display the recommended tap position
-recommended_tap = optimize_tap_change(voltage_in, voltage_out, load)
-
-st.write(f"**Recommended Tap Position**: {recommended_tap}")
-
-# Create a simple dataset for machine learning model training
-# Example data (features: voltage_in, load, previous_tap_change)
-data = {
-    'voltage_in': [110, 115, 120, 125],
-    'load': [250, 300, 350, 400],
-    'tap_position': [3, 4, 2, 5]  # Target variable: tap position
-}
-df = pd.DataFrame(data)
-
-X = df[['voltage_in', 'load']]  # Features
-y = df['tap_position']  # Target variable
-
-# Train the Linear Regression model
-model = LinearRegression()
-model.fit(X, y)
-
-# Predict optimal tap position based on current input
-predicted_tap = model.predict([[voltage_in, load]])
-
-st.write(f"**Predicted Tap Position using Machine Learning**: Tap {int(predicted_tap[0])}")
+# Convert secondary voltage to primary voltage using transformer ratio (132 kV / 11 kV)
+# This is the nominal transformer voltage ratio
+transformer_ratio = 132 / 11
+
+# Calculate the optimal tap position based on output voltage
+def calculate_optimal_tap(voltage_in, voltage_out, load):
+    # Desired output voltage should be 11.5 kV (nominal secondary voltage)
+    target_voltage_out = nominal_secondary_voltage
+    
+    # Calculate the required primary voltage to achieve desired secondary voltage (11.5 kV)
+    required_primary_voltage = target_voltage_out * transformer_ratio
+
+    # Calculate the voltage deviation from nominal (in primary)
+    voltage_deviation = voltage_in - required_primary_voltage
+
+    # Optimizing tap changer setting based on voltage deviation
+    # Assuming tap positions range from -13 (decreasing voltage) to +13 (increasing voltage)
+    # Tap range can be calculated based on the voltage deviation and transformer ratio
+    tap_position = round(voltage_deviation / (voltage_in / 27))  # 27 is the number of taps
+
+    # Ensure that the tap position is within the range of the 27-tap MR tap changer
+    if tap_position > 13:
+        tap_position = 13
+    elif tap_position < -13:
+        tap_position = -13
+
+    # Return the tap position recommendation
+    return tap_position
+
+# Button to get the recommended tap position
+if st.button('Get Tap Position'):
+    # Calculate the optimal tap position
+    optimal_tap = calculate_optimal_tap(voltage_in, voltage_out, load)
+    
+    # Show the recommended tap position
+    st.write(f"**Recommended Tap Position**: Tap {optimal_tap} (Adjust to maintain 11.5 kV output)")
+
+# Display additional results
+st.write(f"**Nominal Secondary Voltage**: {nominal_secondary_voltage} kV")
+st.write(f"**Input Voltage**: {voltage_in} kV")
+st.write(f"**Output Voltage**: {voltage_out} kV")
+st.write(f"**Current Load**: {load} MW")