Instrumentation & Measurement Magazine 24-9 - 51

Detection of Beam Instabilities from
Stored Data
Fig. 5. Measured normalized Beam 1 lifetime as a function of the LHC
transverse tunes. Blue dot: Nominal working point. Red dot: Lifetime-optimized
working point as computed by the surrogate model. The prediction (blue circle)
is close, but not equal, to the measured maximum lifetime (red circle), the
absolute minimum and maximum values of the beam lifetime being 1.05 h and
32.7 h, respectively (from [36]).
Several SL models were trained and compared, and the best
performance was achieved with a Gradient Boosted Decision
Tree model [44]. The extraction of the optimal machine configuration
from the trained lifetime response was made by using
an off-the-shelf simplex optimizer [45]. An important observation
is that the input data distribution is not optimal, as LHC
operation reproduces strictly a given parameter set in every
cycle to prevent performance loss due to unconventional
machine settings. Therefore, the surrogate model trained on
available data exactly represents the operational machine
configurations but features a scarce predictive power for unconventional
machine setups, as these are underrepresented,
if not absent, in the data set used to build the surrogate model.
Dedicated experimental sessions were therefore performed
to collect data representing unconventional settings of the
LHC. Machine configurations were varied and correspondingly,
tune scans were carried out [46], and the collected data
are used to test and complement the current model. It is worth
noting that beam instabilities increased the beam emittances,
thus affecting the machine performance. These instabilities are
not considered by the current model, another weakness of the
existing setup. If this issue is ignored and the goal restricted to
the problem of optimising the lifetime, agreement with the optimal
lifetime region of the measured tune diagram is found,
as seen in Fig. 5, where the maximum measured lifetime (red
circle) is shown together with the optimal value from the surrogate
model (blue circle). In particular, the model is able to
detect the optimal regions, reaching an improvement of the
lifetime of a factor of two, although it misses the maximum.
One possible reason for this is the rather large distance of the
nominal working point from the optimized working point,
showing the maximum lifetime, with the model seeing relatively
few of such configurations in the training data.
December 2021
Beam instabilities due to collective motion can generate to a severe
degradation of beam quality and to a reduction in collider
luminosity. It is therefore crucial to gain insight into the conditions
that lead to instabilities, in view of finding appropriate
mitigation measures. A few dedicated measurement devices
are installed at the LHC for this purpose, and here we focus on
the data collected through the observation box (ObsBox) of the
transverse damping system [47].
This device keeping a rolling buffer of data coming from
several BPMs. When triggered, either automatically or manually,
the ObsBox writes the entire buffer to disk. Here, the focus
is on data saved upon automatic detection of an instability. The
data saved in this manner is of very high resolution, i.e., it comprises
bunch-by-bunch, turn-by-turn, and transverse beam
position information along the machine cycle for all beam
modes and fill types, with around 4 TB of data accumulated
so far. The data set presented here was collected between Sept.
5, 2017 and Dec. 3, 2018 and includes a total of 36196 triggers.
However, no signs of beam instabilities were found in most
of the data. A procedure to identify unusual beam oscillation
patterns in the data and cluster the various types of signals together
was therefore developed to speed up the data analysis.
Before any clustering can be performed, the false triggers
need to be removed from the data. This step is equivalent to
an anomaly-detection problem with the false triggers being
the nominal samples and the instabilities the anomalies. Data
filtering is conducted by the extraction of several features present
in the data [36], on which Principal Component Analysis
(PCA) [48] is carried out. Such a PCA space can have a dimension
as low as 4, while still describing 93% of the variance of the
extracted attributes, as shown in Fig. 6.
A standard IF [31] algorithm can be applied to the PCA
space to identify the anomalous samples.
In this way, the trained IF can perform the filtering of the
false triggers from the ObsBox data. Then, more computationally
intensive algorithms can be run on the predicted
Fig. 6. Principal Component Analysis of ObsBox data collected with automatic
triggers. The histogram shows the explained variance of each PCA component,
while the curve represents the cumulative explained variance (from [36]).
IEEE Instrumentation & Measurement Magazine
51

Instrumentation & Measurement Magazine 24-9

Table of Contents for the Digital Edition of Instrumentation & Measurement Magazine 24-9

Instrumentation & Measurement Magazine 24-9 - Cover1
Instrumentation & Measurement Magazine 24-9 - Cover2
Instrumentation & Measurement Magazine 24-9 - 1
Instrumentation & Measurement Magazine 24-9 - 2
Instrumentation & Measurement Magazine 24-9 - 3
Instrumentation & Measurement Magazine 24-9 - 4
Instrumentation & Measurement Magazine 24-9 - 5
Instrumentation & Measurement Magazine 24-9 - 6
Instrumentation & Measurement Magazine 24-9 - 7
Instrumentation & Measurement Magazine 24-9 - 8
Instrumentation & Measurement Magazine 24-9 - 9
Instrumentation & Measurement Magazine 24-9 - 10
Instrumentation & Measurement Magazine 24-9 - 11
Instrumentation & Measurement Magazine 24-9 - 12
Instrumentation & Measurement Magazine 24-9 - 13
Instrumentation & Measurement Magazine 24-9 - 14
Instrumentation & Measurement Magazine 24-9 - 15
Instrumentation & Measurement Magazine 24-9 - 16
Instrumentation & Measurement Magazine 24-9 - 17
Instrumentation & Measurement Magazine 24-9 - 18
Instrumentation & Measurement Magazine 24-9 - 19
Instrumentation & Measurement Magazine 24-9 - 20
Instrumentation & Measurement Magazine 24-9 - 21
Instrumentation & Measurement Magazine 24-9 - 22
Instrumentation & Measurement Magazine 24-9 - 23
Instrumentation & Measurement Magazine 24-9 - 24
Instrumentation & Measurement Magazine 24-9 - 25
Instrumentation & Measurement Magazine 24-9 - 26
Instrumentation & Measurement Magazine 24-9 - 27
Instrumentation & Measurement Magazine 24-9 - 28
Instrumentation & Measurement Magazine 24-9 - 29
Instrumentation & Measurement Magazine 24-9 - 30
Instrumentation & Measurement Magazine 24-9 - 31
Instrumentation & Measurement Magazine 24-9 - 32
Instrumentation & Measurement Magazine 24-9 - 33
Instrumentation & Measurement Magazine 24-9 - 34
Instrumentation & Measurement Magazine 24-9 - 35
Instrumentation & Measurement Magazine 24-9 - 36
Instrumentation & Measurement Magazine 24-9 - 37
Instrumentation & Measurement Magazine 24-9 - 38
Instrumentation & Measurement Magazine 24-9 - 39
Instrumentation & Measurement Magazine 24-9 - 40
Instrumentation & Measurement Magazine 24-9 - 41
Instrumentation & Measurement Magazine 24-9 - 42
Instrumentation & Measurement Magazine 24-9 - 43
Instrumentation & Measurement Magazine 24-9 - 44
Instrumentation & Measurement Magazine 24-9 - 45
Instrumentation & Measurement Magazine 24-9 - 46
Instrumentation & Measurement Magazine 24-9 - 47
Instrumentation & Measurement Magazine 24-9 - 48
Instrumentation & Measurement Magazine 24-9 - 49
Instrumentation & Measurement Magazine 24-9 - 50
Instrumentation & Measurement Magazine 24-9 - 51
Instrumentation & Measurement Magazine 24-9 - 52
Instrumentation & Measurement Magazine 24-9 - 53
Instrumentation & Measurement Magazine 24-9 - 54
Instrumentation & Measurement Magazine 24-9 - 55
Instrumentation & Measurement Magazine 24-9 - 56
Instrumentation & Measurement Magazine 24-9 - 57
Instrumentation & Measurement Magazine 24-9 - 58
Instrumentation & Measurement Magazine 24-9 - 59
Instrumentation & Measurement Magazine 24-9 - 60
Instrumentation & Measurement Magazine 24-9 - 61
Instrumentation & Measurement Magazine 24-9 - 62
Instrumentation & Measurement Magazine 24-9 - 63
Instrumentation & Measurement Magazine 24-9 - 64
Instrumentation & Measurement Magazine 24-9 - 65
Instrumentation & Measurement Magazine 24-9 - 66
Instrumentation & Measurement Magazine 24-9 - 67
Instrumentation & Measurement Magazine 24-9 - 68
Instrumentation & Measurement Magazine 24-9 - 69
Instrumentation & Measurement Magazine 24-9 - 70
Instrumentation & Measurement Magazine 24-9 - 71
Instrumentation & Measurement Magazine 24-9 - 72
Instrumentation & Measurement Magazine 24-9 - 73
Instrumentation & Measurement Magazine 24-9 - 74
Instrumentation & Measurement Magazine 24-9 - 75
Instrumentation & Measurement Magazine 24-9 - 76
Instrumentation & Measurement Magazine 24-9 - 77
Instrumentation & Measurement Magazine 24-9 - 78
Instrumentation & Measurement Magazine 24-9 - 79
Instrumentation & Measurement Magazine 24-9 - 80
Instrumentation & Measurement Magazine 24-9 - Cover3
Instrumentation & Measurement Magazine 24-9 - Cover4
https://www.nxtbookmedia.com