def update(self): l = self.t_current X = np.array([i for i in range(self.t_current)]).reshape(l, 1) GPRDegradationModel.update(self, X, self.HI[self.t_incipient:self.t_incipient+self.t_current])
def initialize_model(self): GPRDegradationModel.__init__(self, self.HI)
def predict(self): X = np.array([i for i in range(167)]).reshape(167, 1) Yp, Vp = GPRDegradationModel.predict(self, X) return Yp, Vp
def initialize_model(self):
GPRDegradationModel.__init__(self, self.HI[self.t_incipient])
def predict(self, next_steps):
l = self.t_current + next_steps
X = np.array([i for i in range(l)]).reshape(l, 1)
Yp, Vp = GPRDegradationModel.predict(self, X)
self.t_current += next_steps
return Yp, Vp
if (iter_ / tracker == 1.0):
continuously_deg_pts += 1
initial_deg_pts.append(strangeness)
else:
initial_deg_pts = []
continuously_deg_pts = 0
iter_ = 0
tracker = 0
flag = False
if (continuously_deg_pts >= min_continuous_deg_pts):
break
# #-----------RUL Estimation-------------------------------------
hi_raw = np.array(initial_deg_pts).reshape(len(initial_deg_pts), 1)
rul_model = GPRDegradationModel(hi_raw, failure_threshold, order=1)
for i in range(deg_start_idx + min_continuous_deg_pts, len(files)):
df = pd.read_csv(files[i],
sep='\t',
header=None,
names=(['0', '1', '2', '3']))
fea = np.reshape([td.get_rms(df[str(test_bearing_idx)]),\
td.get_kurtosis(df[str(test_bearing_idx)]),\
td.get_crestfactor(df[str(test_bearing_idx)])],(-1,3))
error = da.predict(som, fea, scaler).reshape(1, 1)
error = pd.DataFrame(error)
strangeness, _ = ad.test_cosmo(error)
hi_raw = np.concatenate((hi_raw, strangeness.reshape(-1, 1)), axis=0)
# predict next prediction_horizon intervals