Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
W
WHC-LOF
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package registry
Container registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Terms and privacy
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
WeDoWind - Fault detection and co-innovation
WHC-LOF
Commits
09ec93b4
Commit
09ec93b4
authored
3 years ago
by
Yoshiaki Sakagami
Browse files
Options
Downloads
Patches
Plain Diff
WARD_script
parent
67211178
Branches
main
No related tags found
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
Fail_ward_T07_hyd.py
+186
-0
186 additions, 0 deletions
Fail_ward_T07_hyd.py
with
186 additions
and
0 deletions
Fail_ward_T07_hyd.py
0 → 100644
+
186
−
0
View file @
09ec93b4
# #Code : Failed Detecting Wind Turbine
import
pandas
as
pd
import
matplotlib.pyplot
as
plt
import
numpy
as
np
from
sklearn.cluster
import
AgglomerativeClustering
from
sklearn.neighbors
import
kneighbors_graph
#import susi
# Load training data
df_sig
=
pd
.
read_csv
(
'
../data/wind-farm-1-signals-training.csv
'
,
sep
=
'
;
'
)
# signals
df_met
=
pd
.
read_csv
(
'
../data/wind-farm-1-metmast-training.csv
'
,
sep
=
'
;
'
)
# metmast
df_log
=
pd
.
read_csv
(
'
../data/wind-farm-1-logs-training.csv
'
,
sep
=
'
;
'
)
# logs
df_fail
=
pd
.
read_csv
(
'
../data/wind-farm-1-failures-training.csv
'
,
sep
=
'
;
'
)
# failures
#%% index time - datetime and reindex full time series , remove utc format
dt
=
pd
.
date_range
(
start
=
'
2016-01-01 00:00:00
'
,
end
=
'
2017-09-01 00:10:00
'
,
freq
=
'
10min
'
);
#complete time series
idx
=
pd
.
DatetimeIndex
(
dt
);
df_met
.
index
=
pd
.
to_datetime
(
df_met
[
'
Timestamp
'
]).
dt
.
tz_localize
(
None
)
df_fail
.
index
=
pd
.
to_datetime
(
df_fail
[
'
Timestamp
'
]).
round
(
'
10min
'
).
dt
.
tz_localize
(
None
)
# round 10 min (caution)
df_met
=
df_met
.
reindex
(
idx
)
df_fail
=
df_fail
.
reindex
(
idx
)
#%% separate time series of each wind turbine , index time and remove duplicate
turbines
=
[
'
T01
'
,
'
T06
'
,
'
T07
'
,
'
T09
'
,
'
T11
'
]
dfs
=
[
df_sig
[
df_sig
[
'
Turbine_ID
'
]
==
wt
]
for
wt
in
turbines
]
for
i
in
range
(
0
,
5
):
dfs
[
i
].
index
=
pd
.
to_datetime
(
dfs
[
i
][
'
Timestamp
'
]).
dt
.
tz_localize
(
None
)
# index datetime
dfs
[
i
]
=
dfs
[
i
].
loc
[
~
dfs
[
i
].
index
.
duplicated
(
keep
=
'
last
'
)]
# Remove duplicate data
dfs
[
i
]
=
dfs
[
i
].
reindex
(
idx
)
#reindex date
df
=
pd
.
concat
(
dfs
,
keys
=
turbines
,
names
=
[
'
Turbine
'
],
axis
=
1
)
# Concatenate 5 wind turbines (signals) - Mult-Index
#%% Plot variables of wind turbines
#df['T01'].columns # view the columns you wnat to plot
#'Nac_Temp_Avg' , 'Gen_RPM_Avg','Grd_Prod_Pwr_Avg', 'Gen_Bear_Temp_Avg'
#Hyd_Oil_Temp_Avg
dfx
=
df
.
xs
(
'
Hyd_Oil_Temp_Avg
'
,
axis
=
1
,
level
=
1
)
# cross section variable of each turbine
#dfr1=df.xs('Gen_RPM_Avg',axis=1,level=1) # cross section variable of each turbine
#dfr2=df.xs('Grd_Prod_Pwr_Avg',axis=1,level=1) # cross section variable of each turbine
#dfv=df.xs('Amb_WindSpeed_Avg',axis=1,level=1) # cross section variable of each turbine
#dfg=df.xs('Grd_Prod_Pwr_Avg',axis=1,level=1) # cross section variable of each turbine
#dfx=dfr2/dfr1
#dfx=dfx.resample('H').mean()
dfx
[
'
average
'
]
=
dfx
.
mean
(
axis
=
1
)
# average all variable
dfx
[
dfx
==
np
.
inf
]
=
np
.
nan
dfx
[
dfx
==-
np
.
inf
]
=
np
.
nan
dfwa
=
dfx
.
iloc
[:,
0
:
5
].
dropna
()
# remove nan rows
#%% self organizing map
'''
X=np.array(dfwa) # remove nan rows
som = susi.SOMClustering(n_rows=3, n_columns=4,learning_rate_start=1,random_state=50,n_iter_unsupervised=1000,verbose=1)
som.fit(X)
clusters = np.array(som.get_clusters(X))
ncol=3
df1 = pd.DataFrame(clusters)
df1.columns=[
'
linha
'
,
'
coluna
'
]
df1[
'
cluster
'
]=df1[
'
linha
'
]+df1[
'
coluna
'
]*ncol+1
df1.index=dfwa.index
dfa=pd.concat([dfa,df1[
'
cluster
'
]],axis=1)
'''
#%%
#from sklearn.preprocessing import MinMaxScaler
#scaler = MinMaxScaler()
#scaler.fit(dfwa)
#dfwaN=scaler.transform(dfwa)
# Clustering Ward method (20 clusters)
#connectivity = kneighbors_graph(dfwa, n_neighbors=20, include_self=False) default
connectivity
=
kneighbors_graph
(
dfwa
,
n_neighbors
=
20
,
include_self
=
False
)
km
=
AgglomerativeClustering
(
n_clusters
=
12
,
linkage
=
'
ward
'
,
connectivity
=
connectivity
)
dfc
=
pd
.
DataFrame
(
km
.
fit_predict
(
dfwa
)
+
1
)
dfc
.
index
=
dfwa
.
index
dfc
.
columns
=
[
'
cluster
'
]
dfa
=
pd
.
concat
([
dfx
,
dfc
[
'
cluster
'
]],
axis
=
1
)
dfa
.
to_csv
(
'
input_hyd.csv
'
)
#%%
import
matplotlib.cm
as
cm
cmap
=
cm
.
jet
n_clusters
=
13
evenly_spaced_interval
=
np
.
linspace
(
0
,
1
,
n_clusters
)
colors
=
[
cmap
(
x
)
for
x
in
evenly_spaced_interval
]
colors
[
8
]
=
(
0.0
,
0.0
,
0.0
,
1.0
)
#colors[11]=(1.0,0.0,0.0,1.0)
fig
,
ax
=
plt
.
subplots
(
1
,
1
,
figsize
=
(
8
,
6
));
clusters
=
dfa
.
iloc
[:,
0
:
5
].
groupby
(
dfa
[
'
cluster
'
]).
mean
()
clusters
[
'
average
'
]
=
clusters
.
mean
(
axis
=
1
)
clusters
=
clusters
.
sort_values
(
by
=
[
'
average
'
])
clusters
=
clusters
.
reset_index
()
for
i
in
range
(
1
,
13
):
plt
.
subplot
(
3
,
4
,
i
)
plt
.
plot
(
clusters
.
T
[
i
-
1
][
1
:
-
1
],
marker
=
'
o
'
,
c
=
colors
[
i
-
1
])
plt
.
ylim
(
20
,
60
)
plt
.
grid
()
plt
.
title
(
'
C
'
+
str
(
i
),
fontsize
=
10
)
fig
.
text
(
0.01
,
0.3
,
'
Hyd_Oil_Temp_Avg [C]
'
,
rotation
=
90
,
fontsize
=
14
)
fig
.
text
(
0.45
,
0.02
,
'
Wind Turbines
'
,
rotation
=
0
,
fontsize
=
14
)
plt
.
tight_layout
()
fig
.
subplots_adjust
(
left
=
0.08
)
fig
.
subplots_adjust
(
bottom
=
0.1
)
fig
.
subplots_adjust
(
top
=
0.9
)
#%%
dfM
=
dfa
.
pivot_table
(
index
=
[
dfa
.
index
.
year
,
dfa
.
index
.
week
],
columns
=
dfa
[
'
cluster
'
],
values
=
'
cluster
'
,
aggfunc
=
np
.
nansum
)
dfM
=
dfM
.
reset_index
(
drop
=
True
)
dfM
.
index
=
(
dfa
.
resample
(
'
W
'
).
mean
().
index
)
dfT
=
dfM
.
T
.
divide
(
dfM
.
sum
(
axis
=
1
)).
T
dfT
.
columns
=
clusters
.
sort_values
(
by
=
[
'
cluster
'
]).
index
+
1
dfT
=
dfT
.
sort_index
(
axis
=
1
)
import
matplotlib.gridspec
as
gridspec
gs
=
gridspec
.
GridSpec
(
4
,
1
)
ax1
=
plt
.
subplot
(
gs
[
0
,:])
ax2
=
plt
.
subplot
(
gs
[
1
:,:])
turbines
=
[
'
T01
'
,
'
T06
'
,
'
T07
'
,
'
T09
'
,
'
T11
'
]
cores
=
[
'
r
'
,
'
m
'
,
'
g
'
,
'
c
'
,
'
b
'
]
mk
=
[
'
o
'
,
'
d
'
,
'
P
'
,
'
s
'
,
'
^
'
]
status
=
[
'
GENERATOR
'
,
'
HYDRAULIC_GROUP
'
,
'
GENERATOR_BEARING
'
,
'
TRANSFORMER
'
,
'
GEARBOX
'
]
status_name
=
[
x
+
'
_
'
+
y
for
x
in
turbines
for
y
in
status
]
for
i
in
range
(
0
,
5
):
# plt.plot(dfa[turbines].iloc[:,i],c=cores[i],label=turbines[i])
for
j
in
range
(
0
,
5
):
ax1
.
plot
(
dfx
[
'
average
'
][(
df_fail
[
'
Component
'
]
==
status
[
j
])
&
(
df_fail
[
'
Turbine_ID
'
]
==
turbines
[
i
])],
c
=
cores
[
i
],
marker
=
mk
[
j
],
markersize
=
7
,
linestyle
=
'
None
'
,
label
=
status_name
[
j
+
i
*
5
])
ax1
.
set_xlim
(
dfT
.
index
[
0
],
dfT
.
index
[
-
2
])
ax
=
dfT
.
plot
(
kind
=
"
bar
"
,
ax
=
ax2
,
stacked
=
True
,
width
=
0.9
,
edgecolor
=
'
w
'
,
lw
=
0.3
,
color
=
colors
,
figsize
=
(
12
,
6
))
ax
.
xaxis
.
set_ticks
(
np
.
arange
(
0
,
88
,
4
))
ax
.
set_xticklabels
(
[
x
.
strftime
(
"
%y-%m-%d
"
)
for
x
in
dfT
.
index
[::
4
]],
rotation
=
90
)
ax
.
legend
(
bbox_to_anchor
=
(
1.1
,
1.7
),
ncol
=
1
)
ax1
.
set_ylabel
(
'
tp [C]
'
)
plt
.
subplots_adjust
(
left
=
0.05
)
plt
.
subplots_adjust
(
right
=
0.9
)
plt
.
subplots_adjust
(
bottom
=
0.17
)
plt
.
subplots_adjust
(
top
=
0.78
)
plt
.
subplots_adjust
(
hspace
=
0.5
)
plt
.
xlabel
(
'
UTC Time
'
,
fontsize
=
14
)
plt
.
ylabel
(
'
Occurrence [-]
'
,
fontsize
=
14
)
ax1
.
legend
(
loc
=
'
center left
'
,
bbox_to_anchor
=
(
0.01
,
2.0
),
ncol
=
5
,
fontsize
=
8
)
#%%
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment