Challenges in the Development of Soft Sensors for Bioprocesses: A Critical Review

Among the greatest challenges in soft sensor development for bioprocesses are variable process lengths, multiple process phases, and erroneous model inputs due to sensor faults. This review article describes these three challenges and critically discusses the corresponding solution approaches from a data scientist’s perspective. This main part of the article is preceded by an overview of the status quo in the development and application of soft sensors. The scope of this article is mainly the upstream part of bioprocesses, although the solution approaches are in most cases also applicable to the downstream part. Variable process lengths are accounted for by data synchronization techniques such as indicator variables, curve registration, and dynamic time warping. Multiple process phases are partitioned by trajectory or correlation-based phase detection, enabling phase-adaptive modeling. Sensor faults are detected by symptom signals, pattern recognition, or by changing contributions of the corresponding sensor to a process model. According to the current state of the literature, tolerance to sensor faults remains the greatest challenge in soft sensor development, especially in the presence of variable process lengths and multiple process phases.

Download Full-text

Soft Sensor Development Based on Kernel Dynamic Time Warping and a Relevant Vector Machine for Unequal-length Batch Processes

Expert Systems with Applications ◽

10.1016/j.eswa.2021.115223 ◽

2021 ◽

pp. 115223

Author(s):

Kepeng Qiu ◽

Jianlin Wang ◽

Rutong Wang ◽

Yongqi Guo ◽

Liqiang Zhao

Keyword(s):

Dynamic Time Warping ◽

Soft Sensor ◽

Batch Processes ◽

Time Warping ◽

Sensor Development ◽

Dynamic Time ◽

Unequal Length

Download Full-text

Status of Food Security in Banten Province, Indonesia

10.31227/osf.io/fcvpm ◽

2019 ◽

Author(s):

Weksi Budiaji

Keyword(s):

Population Dynamics ◽

Food Security ◽

Arable Land ◽

Secondary Data ◽

Disaster Risk ◽

Soil Types ◽

Indicator Variables ◽

Cereal Production ◽

The Status ◽

Vast Area

This paper discusses the status of food security in Banten Province, Indonesia based on regional and city characteristics. Secondary data is used and is analyzed descriptively covering population dynamics, the population living in poverty, cereal production, disaster risk and soil types. Tangerang Region is found to have the largest population with the greatest number of people living in poverty among the regions and cities in Banten Province. Cereal production is dominated by the regions rather than the cities due to their vast area. Regarding arable land, flooding is the most threatening disaster in the major rice producing areas. In order to identify the distributions of regions and cities regarding food security, three indicator variables of food security dimensions are plotted, namely, cereal normative consumption, proportion of the population living in poverty, and proportion of malnourished babies. The three regions of Pandeglang Region, Lebak Region and Serang Region are grouped together in a less secure group.

Download Full-text

Adaptive Soft Sensor Development Based on Online Ensemble Gaussian Process Regression for Nonlinear Time-Varying Batch Processes

Industrial & Engineering Chemistry Research ◽

10.1021/acs.iecr.5b01495 ◽

2015 ◽

Vol 54 (30) ◽

pp. 7320-7345 ◽

Cited By ~ 35

Author(s):

Huaiping Jin ◽

Xiangguang Chen ◽

Li Wang ◽

Kai Yang ◽

Lei Wu

Keyword(s):

Gaussian Process ◽

Gaussian Process Regression ◽

Soft Sensor ◽

Batch Processes ◽

Time Varying ◽

Sensor Development

Download Full-text

Site controlling in infrastructure projects by digital methods

IABSE Congress, Christchurch 2021: Resilient technologies for sustainable infrastructure ◽

10.2749/christchurch.2021.0521 ◽

2021 ◽

Author(s):

Tino Walther ◽

Marianne Pieper ◽

Hans-Joachim Bargstädt

Keyword(s):

Performance Measurement ◽

Construction Industry ◽

Process Model ◽

Current Practice ◽

Early Stage ◽

Recommendations For Action ◽

Digital Planning ◽

The Status ◽

Project Controlling ◽

Digital Methods

<p>The construction industry is essentially determined by digital transformation and an increasingly complex market environment. Project controlling and monitoring is of high importance for construction site activities to achieve the project goals. Digital planning and recording methods make it possible to identify deviations at an early stage and to ensure the profitability of the project. To discuss the current practice of construction performance measurement as well as digital approaches in this domain, a qualitative study was carried out. The results of this empirical analysis examine the status quo of the construction performance measurement in civil engineering companies to illustrate the currently used methods and trends. Findings for the future use of digital planning and recording methods were obtained from the investigation. Based on empirical hypotheses, recommendations for action as well as for an improved process model are given.</p>

Download Full-text

Conceptual Approaches to Pedogenesis

Soils in Archaeological Research ◽

10.1093/oso/9780195149654.003.0006 ◽

2004 ◽

Author(s):

Vance T. Holliday

Keyword(s):

Process Model ◽

Soil Formation ◽

Site Formation ◽

Biogeochemical Processes ◽

Pedogenic Process ◽

Soil Geomorphology ◽

Multiple Process ◽

The Many ◽

Soil Forming Processes ◽

State Factor

To fully appreciate and apply pedologic principals in archaeology, some of the theoretical underpinnings of pedology and especially soil geomorphology must be outlined. Pedologists and soil geomorphologists have attempted to describe, if not model, the processes of soil formation, the factors that drive the processes, and the evolution of soils as landscapes evolve (summarized by Smeck et al., 1983; Johnson and Watson-Stegner, 1987; and Gerrard, 1992, pp. 1–50, 217–220). The task is a difficult one, however, because of the complex and variable sets of processes responsible for soil development. Several of the resulting approaches have proven useful for conceptualizing pedogenesis and, more important, for interpreting soils. In addition to understanding soil-forming processes for interpreting soil profiles, understanding soil formation is important for understanding site formation. The conceptual approaches particularly useful in soil geomorphic and geoarchaeological research are summarized below. Soil-forming processes as components of site formation are discussed more fully in chapter 10. The following discussions of conceptual approaches to pedogenesis are roughly arranged in order of increasing complexity. The “multiple-process model” is essentially a categorization of soil-forming processes. It does not explain pedogenesis but is a useful way to sort and group the many soil-forming processes. The “state factor” approach and the “K-cycle” concept do not deal directly with soil formation, but instead focus on important external factors and processes that drive or affect pedogenesis such as climate and geomorphic evolution. The “soil evolution” model and the “new global view of soils” attempt to integrate pedogenic process with landscape evolution, climate, and other factors. This section closes with discussion of two important aspects of pedogenesis and pedogenic pathways that offer caveats in the use of soils for reconstructing the past. Soils are the result of biogeochemical processes determined and driven by the ecosystem (following Buol et al., 1997). This relationship is more simply described as “internal soil-forming processes” driven by “external soil-forming factors” (fig. 3.1; after Buol et al., 1984). A useful approach to categorizing the many and varied internal soil-forming processes responsible for pedogenesis is the multiple-process model of Simonson (1959, 1978).

Download Full-text

Heterogeneous sensing in a multifunctional soft sensor for human-robot interfaces

Science Robotics ◽

10.1126/scirobotics.abc6878 ◽

2020 ◽

Vol 5 (49) ◽

pp. eabc6878 ◽

Cited By ~ 1

Author(s):

Taekyoung Kim ◽

Sudong Lee ◽

Taehwa Hong ◽

Gyowook Shin ◽

Taehwan Kim ◽

...

Keyword(s):

Form Factor ◽

Form Factors ◽

Soft Sensor ◽

Compact Form ◽

Original Form ◽

Entire Body ◽

Soft Sensors ◽

Input Stimulus ◽

Human Robot Interfaces ◽

Deformation Modes

Soft sensors have been playing a crucial role in detecting different types of physical stimuli to part or the entire body of a robot, analogous to mechanoreceptors or proprioceptors in biology. Most of the currently available soft sensors with compact form factors can detect only a single deformation mode at a time due to the limitation in combining multiple sensing mechanisms in a limited space. However, realizing multiple modalities in a soft sensor without increasing its original form factor is beneficial, because even a single input stimulus to a robot may induce a combination of multiple modes of deformation. Here, we report a multifunctional soft sensor capable of decoupling combined deformation modes of stretching, bending, and compression, as well as detecting individual deformation modes, in a compact form factor. The key enabling design feature of the proposed sensor is a combination of heterogeneous sensing mechanisms: optical, microfluidic, and piezoresistive sensing. We characterize the performance on both detection and decoupling of deformation modes, by implementing both a simple algorithm of threshold evaluation and a machine learning technique based on an artificial neural network. The proposed soft sensor is able to estimate eight different deformation modes with accuracies higher than 95%. We lastly demonstrate the potential of the proposed sensor as a method of human-robot interfaces with several application examples highlighting its multifunctionality.

Download Full-text