Assessment of reinforcement learning applications for industrial control based on complexity measures

Abstract Machine learning and particularly reinforcement learning methods may be applied to control tasks ranging from single control loops to the operation of whole production plants. However, their utilization in industrial contexts lacks understandability and requires suitable levels of operability and maintainability. In order to asses different application scenarios a simple measure for their complexity is proposed and evaluated on four examples in a simulated palette transport system of a cold rolling mill. The measure is based on the size of controller input and output space determined by different granularity levels in a hierarchical process control model. The impact of these decomposition strategies on system characteristics, especially operability and maintainability, are discussed, assuming solvability and a suitable quality of the reinforcement learning solution is provided.

Download Full-text

Beginning L2 complexity development in CLIL and non-CLIL secondary education

Instructed Second Language Acquisition ◽

10.1558/isla.38247 ◽

2019 ◽

Vol 3 (2) ◽

pp. 153-180 ◽

Cited By ~ 1

Author(s):

Bram Bulte ◽

Alex Housen

Keyword(s):

Secondary Education ◽

Secondary School ◽

Foreign Language ◽

Mixed Models ◽

Target Language ◽

Complexity Measures ◽

Linguistic Complexity ◽

Longitudinal Development ◽

The Impact

The present study analyses the impact of a bilingual Content and Language Integrated Learning (CLIL) programme vis-à-vis a regular monolingual programme on the development of different aspects of L2 learners’ linguistic (syntactic, morphological and lexical) complexity. Five pupils enrolled in a Dutch–English CLIL programme in a secondary school in the Netherlands are compared with five peers following the mainstream programme with English as a Foreign Language (EFL) teaching. The longitudinal development of these ten pupils’ linguistic complexity in L2-English is investigated by means of six complexity measures calculated for each of eleven writing tasks collected over a period spanning their first nineteen months of secondary education. Linear mixed models are used to estimate the effects of time and programme type on the pupils’ L2 complexity. The results indicate that both groups of learners significantly increase the complexity of their L2 writing over the course of the study. Surprisingly, only limited effects of programme type (CLIL vs non-CLIL) are found, despite considerable differences in the quantity and quality of instructional exposure to the target language, suggesting that for these pupils increased and more varied instructional exposure to the L2 in the CLIL programme did not lead to significantly different L2 productions in terms of linguistic complexity. Several possible explanations for these findings are considered and the implications for CLIL research are discussed.

Download Full-text

Learning to Tune a Class of Controllers with Deep Reinforcement Learning

Minerals ◽

10.3390/min11090989 ◽

2021 ◽

Vol 11 (9) ◽

pp. 989

Author(s):

William John Shipman

Keyword(s):

Reinforcement Learning ◽

Network Size ◽

Training Environment ◽

Control Loops ◽

Environment Domain ◽

The Face ◽

Minerals Processing ◽

Policy Optimization ◽

Flow Rate Control ◽

The Impact

Control systems require maintenance in the form of tuning their parameters in order to maximize their performance in the face of process changes in minerals processing circuits. This work focuses on using deep reinforcement learning to train an agent to perform this maintenance continuously. A generic simulation of a first-order process with a time delay, controlled by a proportional-integral controller, was used as the training environment. Domain randomization in this environment was used to aid in generalizing the agent to unseen conditions on a physical circuit. Proximal policy optimization was used to train the agent, and hyper-parameter optimization was performed to select the optimal agent neural network size and training algorithm parameters. Two agents were tested, examining the impact of the observation space used by the agent and concluding that the best observation consists of the parameters of an auto-regressive with exogenous input model fitted to the measurements of the controlled variable. The best trained agent was deployed at an industrial comminution circuit where it was tested on two flow rate control loops. This agent improved the performance of one of these control loops but decreased the performance of the other control loop. While deep reinforcement learning does show promise in controller tuning, several challenges and directions for further study have been identified.

Download Full-text

Self-Compassion and Quality of Life in Adults Who Stutter

American Journal of Speech-Language Pathology ◽

10.1044/2020_ajslp-20-00055 ◽

2020 ◽

Vol 29 (4) ◽

pp. 2097-2108

Author(s):

Robyn L. Croft ◽

Courtney T. Byrd

Keyword(s):

Quality Of Life ◽

Social Connectedness ◽

The Self ◽

Future Research ◽

Self Compassion ◽

Adults Who Stutter ◽

And Gender ◽

Relationship Of ◽

The Impact

Purpose The purpose of this study was to identify levels of self-compassion in adults who do and do not stutter and to determine whether self-compassion predicts the impact of stuttering on quality of life in adults who stutter. Method Participants included 140 adults who do and do not stutter matched for age and gender. All participants completed the Self-Compassion Scale. Adults who stutter also completed the Overall Assessment of the Speaker's Experience of Stuttering. Data were analyzed for self-compassion differences between and within adults who do and do not stutter and to predict self-compassion on quality of life in adults who stutter. Results Adults who do and do not stutter exhibited no significant differences in total self-compassion, regardless of participant gender. A simple linear regression of the total self-compassion score and total Overall Assessment of the Speaker's Experience of Stuttering score showed a significant, negative linear relationship of self-compassion predicting the impact of stuttering on quality of life. Conclusions Data suggest that higher levels of self-kindness, mindfulness, and social connectedness (i.e., self-compassion) are related to reduced negative reactions to stuttering, an increased participation in daily communication situations, and an improved overall quality of life. Future research should replicate current findings and identify moderators of the self-compassion–quality of life relationship.

Download Full-text

Surgery for Lung Cancer and the Consequences for the Swallow

Perspectives of the ASHA Special Interest Groups ◽

10.1044/persp1.sig13.162 ◽

2016 ◽

Vol 1 (13) ◽

pp. 162-168

Author(s):

Pippa Hales ◽

Corinne Mossey-Gaston

Keyword(s):

Lung Cancer ◽

Treatment Options ◽

Vocal Cord Palsy ◽

Subsequent Treatment ◽

Physiological Reserve ◽

Palliative Phase ◽

And Function ◽

The Impact ◽

Swallow Function

Lung cancer is one of the most commonly diagnosed cancers across Northern America and Europe. Treatment options offered are dependent on the type of cancer, the location of the tumor, the staging, and the overall health of the person. When surgery for lung cancer is offered, difficulty swallowing is a potential complication that can have several influencing factors. Surgical interaction with the recurrent laryngeal nerve (RLN) can lead to unilateral vocal cord palsy, altering swallow function and safety. Understanding whether the RLN has been preserved, damaged, or sacrificed is integral to understanding the effect on the swallow and the subsequent treatment options available. There is also the risk of post-surgical reduction of physiological reserve, which can reduce the strength and function of the swallow in addition to any surgery specific complications. As lung cancer has a limited prognosis, the clinician must also factor in the palliative phase, as this can further increase the burden of an already compromised swallow. By understanding the surgery and the implications this may have for the swallow, there is the potential to reduce the impact of post-surgical complications and so improve quality of life (QOL) for people with lung cancer.

Download Full-text