Search

Particle accelerators play a crucial role in scientific research, enabling the study of fundamental physics and materials science, as well as having important medical applications. This study proposes a novel graph learning approach to classify operational beamline configurations as good or bad. By considering the relationships among beamline elements, we transform data from components into a heterogeneous graph. We propose to learn from historical, unlabeled data via our self-supervised training strategy along with fine-tuning on a smaller, labeled dataset. Additionally, we extract a low-dimensional representation from each configuration that can be visualized in two dimensions. Leveraging our ability for classification, we map out regions of the low-dimensional latent space characterized by good and bad configurations, which in turn can provide valuable feedback to operators. This research demonstrates a paradigm shift in how complex, many-dimensional data from beamlines can be analyzed and leveraged for accelerator operations.

Abstract The UK Government has endorsed the case for autonomous vehicle (AV) technology and its economic benefits in its industrial strategies since 2013. In late 2016 the Science and Technology Committee in the House of Lords (the legislature’s upper chamber) conducted an Inquiry into the policy. We conduct a content analysis of the text corpus of the Inquiry. Drawing from theories of sociotechnical change we explore how it contributes to building a vision of a future AV world embedded in a national economic and technological project. The technology is framed as a solution to societal grand challenges and the Inquiry corpus is dominated by actors committed to the project. Alternative visions, including sceptical interpretations, are present in the corpus, but rare, reflecting the selection process for contributions to the Inquiry. Predominantly, the corpus represents the public as deficient: dangerous drivers, unaware of promised benefits and unduly anxious about the unfamiliar. Their views are marginal in this Parliamentary Inquiry’s findings. AV technology is one of several possible means to pursue wider mobility policy goals of greater safety, affordability, access and sustainability. Our analysis suggests that the pursuit of an AV future risks becoming a goal in itself instead of a means to these broader societal goals.

This work investigates the efficacy of deep learning (DL) for classifying C100 superconducting radio-frequency (SRF) cavity faults in the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. CEBAF is a large, high-power continuous wave recirculating linac that utilizes 418 SRF cavities to accelerate electrons up to 12 GeV. Recent upgrades to CEBAF include installation of 11 new cryomodules (88 cavities) equipped with a low-level RF system that records RF time-series data from each cavity at the onset of an RF failure. Typically, subject matter experts (SME) analyze this data to determine the fault type and identify the cavity of origin. This information is subsequently utilized to identify failure trends and to implement corrective measures on the offending cavity. Manual inspection of large-scale, time-series data, generated by frequent system failures is tedious and time consuming, and thereby motivates the use of machine learning (ML) to automate the task. This study extends work on a previously developed system based on traditional ML methods (Tennant and Carpenter and Powers and Shabalina Solopova and Vidyaratne and Iftekharuddin, Phys. Rev. Accel. Beams, 2020, 23, 114601), and investigates the effectiveness of deep learning approaches. The transition to a DL model is driven by the goal of developing a system with sufficiently fast inference that it could be used to predict a fault event and take actionable information before the onset (on the order of a few hundred milliseconds). Because features are learned, rather than explicitly computed, DL offers a potential advantage over traditional ML. Specifically, two seminal DL architecture types are explored: deep recurrent neural networks (RNN) and deep convolutional neural networks (CNN). We provide a detailed analysis on the performance of individual models using an RF waveform dataset built from past operational runs of CEBAF. In particular, the performance of RNN models incorporating long short-term memory (LSTM) are analyzed along with the CNN performance. Furthermore, comparing these DL models with a state-of-the-art fault ML model shows that DL architectures obtain similar performance for cavity identification, do not perform quite as well for fault classification, but provide an advantage in inference speed.

We present the initial results of a proof-of-concept ‘smart alarm’ for the Continuous Electron Beam Accelerator Facility injector beamline at Jefferson Lab. To minimize machine downtime and improve operational efficiency, an autonomous alarm system able to identify and diagnose unusual machine states is needed. Our approach leverages a trained neural network capable of alerting operators (a) when an anomalous condition exists in the beamline and (b) identifying the element setting that is the root cause. The tool is based on an inverse model that maps beamline readings (diagnostic readbacks) to settings (beamline attributes operators can modify). The model takes as input readings from the machine and computes machine settings which are compared to control setpoints. Instances where predictions differ from setpoints by a user-defined threshold are flagged as anomalous. Given data corresponding to 354 anomalous injector configurations, the model can narrow the root cause of an anomalous condition to three potential candidates with 94.6% accuracy. Furthermore, compared to the current method of identifying anomalous conditions which raises an alarm when machine parameters drift outside their normal tolerances, the data-driven model can identify 83% more anomalous conditions.

Behaviour on the road is ordered by a range of norms, rules, laws, and infrastructures. The introduction of self-driving vehicles onto the road opens a debate about the rules that should govern their actions and how these should be integrated with, or lead to the modification of, existing road rules. In this paper, we analyse the current rules of the road, with a particular focus on the UK's Highway Code, in order to inform future rulemaking. We consider the full range of laws, norms, infrastructures, and technologies that govern interactions on the road and where these came from. The rules have a long history and they contribute to a social order that privileges some modes of mobility over others, reinforcing a culture of automobility that shapes lives, livelihoods and places. The introduction of self-driving vehicles, and the digital code on which they depend, could reorder the culture and concrete of our roads, by flattening the multidimensional rules of the road, hardening rules that are currently soft and standardising across diverse contexts. Future rule changes to accommodate self-driving vehicles may enable increases in safety and accessibility, but the trade-offs demand democratic debate.

Automated vehicles (AVs) have the potential to cause profound shifts across a wide range of areas of human life, including economic structures, land use, lifestyles and personal well-being. Most current social science on AVs is narrowly framed. Research on public attitudes has focused on whether people are likely to accept and use AVs. We contend that failing to anticipate a wider range of profound social implications may have serious negative consequences, and that social scientists from a range of disciplinary perspectives can provide invaluable insights. Our conclusions are the product of a workshop in London held in 2018 to discuss the place of social science research in relation to the development of AVs. This paper summarises a core selection of our concerns, interests, theoretical and substantive points of reference and aspirations for a constructive role in this field of research and development.

We report on the development of machine learning models for classifying C100 superconducting radio-frequency (SRF) cavity faults in the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. CEBAF is a continuous-wave recirculating linac utilizing 418 SRF cavities to accelerate electrons up to 12 GeV through five passes. Of these, 96 cavities (12 cryomodules) are designed with a digital low-level rf system configured such that a cavity fault triggers waveform recordings of 17 rf signals for each of the eight cavities in the cryomodule. Subject matter experts are able to analyze the collected time-series data and identify which of the eight cavities faulted first and classify the type of fault. This information is used to find trends and strategically deploy mitigations to problematic cryomodules. However, manually labeling the data is laborious and time consuming. By leveraging machine learning, near real-time—rather than postmortem—identification of the offending cavity and classification of the fault type has been implemented. We discuss performance of the machine learning models during a recent physics run. Results show the cavity identification and fault classification models have accuracies of 84.9% and 78.2%, respectively.

In this paper we demonstrate that societal psychology makes a unique contribution to the study of change through its focus on the 'contextual politics' of change, examining the different interests at stake within any social context. Societal psychology explores the contexts which promote or inhibit social and societal change and can be seen as a bridge between social and political psychology. It focuses on how the context shapes the ways in which societal change is understood, supported or resisted. To understand the intellectual rationale of societal psychology, and how it aims to foster societal change, we first consider the history of the discipline. Second, we consider what is meant by 'context', as understanding the environment of change is the hallmark of societal psychology. Third, we lay out three distinct features of a societal psychological approach to change: the politics of change; interventions and planned change; emergent change processes. Finally, the paper examines possible future developments of societal psychology and its role in understanding and creating societal change, alongside its place within the wider canon of social and political psychology.

Background. The aim was to examine the temporal relationships over 10 months between cannabis use and symptoms of psychosis and depression in people with schizophrenia and related disorders. The design was a prospective study of 101 patients with schizophrenia and related disorders who were assessed monthly over 10 months on medication compliance, cannabis and other drug use, symptoms of depression and symptoms of psychosis.Method. Linear regression methods to assess relationships between cannabis use and symptoms of psychosis and depression while adjusting for serial dependence, medication compliance and other demographic and clinical variables.Results. Cannabis use predicted a small but statistically significant increase in symptoms of psychosis, but not depression, after controlling for other differences between cannabis users and non-users. Symptoms of depression and psychosis did not predict cannabis use.Conclusion. Continued cannabis use by persons with schizophrenia predicts a small increase in psychotic symptom severity but not vice versa. [ABSTRACT FROM AUTHOR]