added (self.u_abc_k1 = self.u_lim * self.subactions) for calculation of u_abc from subaction state

Author: manjeetjha070

examples/model_predictive_controllers/pmsm_fcs_mpc_dq_current_control.ipynb

@@ -33,7 +33,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -42,7 +42,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -66,7 +66,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -94,7 +94,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -124,15 +124,19 @@
     "        self.p = environment.get_wrapper_attr('physical_system').electrical_motor.motor_parameter['p']\n",
     "        self.abc_to_dq = environment.get_wrapper_attr('physical_system').abc_to_dq_space\n",
     "        self.prediction_horizon = prediction_horizon  # Prediction horizon (typically 1 for FCS-MPC)\n",
+    "\n",
+    "        # limit values for the normalization\n",
+    "        self.u_lim = environment.get_wrapper_attr('physical_system').limits[env.get_wrapper_attr('state_names').index('u_sd')]\n",
     "        \n",
     "        # Get the finite set of voltage vectors from the environment\n",
     "        self.subactions = -np.power(-1, environment.get_wrapper_attr('physical_system')._converter._subactions)\n",
+    "        self.u_abc_k1  = self.u_lim * self.subactions\n",
     "        \n",
     "    def _simulate_sequence(self, i_d, i_q, epsilon_el, omega, ref_i_d, ref_i_q, depth):\n",
     "        min_cost = float('inf')\n",
     "        best_sequence = []\n",
     "\n",
-    "        for idx, (v_a, v_b, v_c) in enumerate(self.subactions):\n",
+    "        for idx, (v_a, v_b, v_c) in enumerate(self.u_abc_k1):\n",
     "            # Convert to dq             \n",
     "            v_dq = np.transpose(np.array([self.abc_to_dq(np.array([v_a, v_b, v_c]), epsilon_el + 0.5*omega*self.tau)]))\n",
     "            v_d, v_q = v_dq[0], v_dq[1]\n",
@@ -199,7 +203,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -217,7 +221,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -254,13 +258,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "47799e64eeb84ba88aaee9f1d299e191",
+       "model_id": "793190cb48db401cb57950c71587cbe5",
        "version_major": 2,
        "version_minor": 0
       },
@@ -317,14 +321,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 26,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Reward = -1430.5877421997113\n"
+      "Reward = -1041.746469033069\n"
      ]
     }
    ],