From df093ee00a5d84b9e3a03254b72b04c4df9d0600 Mon Sep 17 00:00:00 2001
From: Jens Ahrensfeld <jens@jayfield.org>
Date: Tue, 2 Apr 2019 20:10:06 +0000
Subject: [PATCH] -added Kalman filter

git-svn-id: http://moon:8086/svn/projects/HendiControl@207 fda53097-d464-4ada-af97-ba876c37ca34
---
 Control/brewpi/kalman.py | 125 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 125 insertions(+)
 create mode 100644 Control/brewpi/kalman.py

diff --git a/Control/brewpi/kalman.py b/Control/brewpi/kalman.py
new file mode 100644
index 0000000..4e28427
--- /dev/null
+++ b/Control/brewpi/kalman.py
@@ -0,0 +1,125 @@
+import numpy as np
+from numpy.linalg import inv
+from matplotlib.pyplot import plot, figure, subplot, title, xlabel, ylabel, grid, show
+
+class Kalman():
+	def __init__(self, params={}):
+		dt = params['dt']
+		var_P = params['var_P']
+		var_Q = params['var_Q']
+		var_R = params['var_R']
+		var_Z = params['var_Z']
+		model = np.matrix([1, dt, 1/2*dt**2]).transpose()
+		N = len(model)-1
+
+		P = var_P*np.eye(N)
+		R = var_R*np.eye(N)
+		H = np.eye(N)
+
+		A = np.eye(N)
+		for row in range(0, N):
+			A[row, row:N] = model.transpose()[0, 0:N-row]
+
+		G = np.matrix(model[N:0:-1])
+		Q = G * G.transpose() * var_Q
+
+		self.P = P
+		self.Q = Q
+		self.R = R
+		self.N = N
+		self.A = A
+		self.H = H
+		self.var_Z = var_Z
+
+		X = np.matrix([0, 1.0]).transpose()
+		Xp = np.matrix([0, -1.0]).transpose()
+		self.Xp = Xp
+		self.X = X
+
+		np.set_printoptions(precision=3)
+
+	@staticmethod
+	def print(p, d):
+		print(p)
+		print(d)
+
+	def process(self):
+
+		_x1 = np.empty(0)
+		_y1 = np.empty(0)
+		_x2 = np.empty(0)
+		_y2 = np.empty(0)
+		for n in range(0, 100):
+
+			# ----------------------------
+			# State estimate
+			self.Xp = self.A * self.Xp
+
+			# ----------------------------
+			# Process ground truth
+			self.X = self.A * self.X
+
+			# ----------------------------
+			# Take noisy measurement
+			Z = self.H * self.X + self.var_Z * np.random.randn(self.N, 1)
+
+			# ----------------------------
+			# Measurement prediction
+			Zp = self.H * self.Xp
+
+			# ----------------------------
+			# Measurement residual
+			V = Z - Zp
+
+			# ----------------------------
+			# State	prediction covariance
+			self.P = self.A * self.P * self.A.transpose() + self.Q
+
+			# ----------------------------
+			# Measurement prediction covariance
+			S = self.H * self.P * self.H.transpose() + self.R
+
+			# ----------------------------
+			# Kalman gain
+			K = self.P * self.H.transpose() * inv(S)
+
+			# ----------------------------
+			# Update state estimate
+			self.Xp = self.Xp + K * V
+
+			# ----------------------------
+			# Updated state covariance
+			self.P = self.P - K * S * K
+
+			# ----------------------------
+			# Plot vars
+			_x1 = np.append(_x1, Z[0])
+			_x2 = np.append(_x2, Z[1])
+			_y1 = np.append(_y1, self.Xp[0])
+			_y2 = np.append(_y2, self.Xp[1])
+
+		n = range(0,100)
+		figure(1)
+		subplot(2, 1, 1)
+		plot(n, _x1, 'bx', n, _y1, '-r', linewidth=1)
+		grid(True)
+		subplot(2, 1, 2)
+		plot(n, _x2, 'bx', n, _y2, '-r', linewidth=1)
+		grid(True)
+		show()
+# Main
+if __name__ == '__main__':
+
+	params = {
+		'dt'	: 1,
+		'var_P'	: 1,
+		'var_Q'	: .001,
+		'var_R'	: 1,
+		'var_Z'	: 1
+	}
+	k = Kalman(params)
+
+	k.process()
+
+	print("End of program")
+