Embedded Files
Machine learning-based soft-sensor development for road quality classification
Machine learning-based soft-sensor development for road quality classification
Vibrations in road vehicles cause several harmful effects, health problems can occur for the passengers, and mechanical damage can occur to the vehicle components. Given the health, safety, and financial issues that arise, keeping the road network in good condition and detecting road defects as early as possible requires an extensive monitoring system. Related to this, our study presents the development of hardware and software for a low-cost, multi-sensor road quality monitoring system for passenger vehicles. The developed monitoring system can classify road sections according to their quality parameters into four classes. In order to detect vibrations in the vehicle, accelerometers and gyroscope sensors are installed at several points. Then, a machine learning-based soft-sensor development is introduced. Besides noise filtering, each data point is resampled by spatial frequency to reduce the velocity dependence. Subsequently, a decision tree-based classification model is trained using features from the power spectrum and principal component analysis. The classification algorithm is validated and tested with measurement data in a real-world environment. In addition to reviewing the accuracy of the model, we examine the correlation of the data measured in the cabin and on the suspension to see how much additional information is provided by the sensor on the axle.
Post date: 9 June 2023
Edge-Computing and Machine-Learning-Based Framework for Software Sensor Development
Edge-Computing and Machine-Learning-Based Framework for Software Sensor Development
The present research presents a framework that supports the development and operation of machine-learning (ML) algorithms to develop, maintain and manage the whole lifecycle of modeling software sensors related to complex chemical processes. Our motivation is to take advantage of ML and edge computing and offer innovative solutions to the chemical industry for difficult-to-measure laboratory variables. The purpose of software sensor models is to continuously forecast the quality of products to achieve effective quality control, maintain the stable production condition of plants, and support efficient, environmentally friendly, and harmless laboratory work. As a result of the literature review, quite a few ML models have been developed in recent years that support the quality assurance of different types of materials. However, the problems of continuous operation, maintenance and version control of these models have not yet been solved. The method uses ML algorithms and takes advantage of cloud services in an enterprise environment. Industrial 4.0 devices such as the Internet of Things (IoT), edge computing, cloud computing, ML, and artificial intelligence (AI) are core techniques. The article outlines an information system structure and the related methodology based on data from a quality-assurance laboratory. During the development, we encountered several challenges resulting from the continuous development of ML models and the tuning of their parameters. The article discusses the development, version control, validation, lifecycle, and maintenance of ML models and a case study. The developed framework can continuously monitor the performance of the models and increase the amount of data that make up the models. As a result, the most accurate, data-driven and up-to-date models are always available to quality-assurance engineers with this solution.
Published on 3rd of June 2022.
János Abonyi is the Special Issue Editor of "Soft Sensors 2021-2022"
János Abonyi is the Special Issue Editor of "Soft Sensors 2021-2022"
The Special Issue solicits papers that cover the development, validation, application, and maintenance of software sensors. The potential topics include, but are not limited to:
Data-driven modeling for soft sensor development (from classical system identification and multivariate chemometric techniques to deep learning);
Semi-mechanistic and first-principle models in soft sensor development (including grey box models);
Validation and maintenance of soft sensors;
Control-oriented soft sensor development (g., inferential control, senseless control);
Applications in fault detection and diagnosis and monitoring of complex processes;
Applications in state estimation, control, and optimization (e.g., sensorless motor control, nonlinear model predictive control);
Special applications in process analytical technology (PAT), manufacturing, chemical, bio, pharmaceutical, oil, and process engineering.
Link to the Special Issue "Soft Sensors 2021-2022"
Constrained Recursive Input Estimation of Blending and Mixing Systems
Constrained Recursive Input Estimation of Blending and Mixing Systems
Blending, mixing processes are often supported by advanced process control systems to maximise margins from available component and heat streams. Since these model-based solutions require accurate and reliable data, in weakly instrumented processes, the unknown inlet concentrations and temperatures should be estimated based on the measured outflows. This work presents a method for the reliable estimation of multiple input variables of process units. The key idea is that the input estimation problem is formulated as a constrained recursive estimation task. The applicability of the method is illustrated based on a benchmark model of a blending system. The performance of the method is compared to the moving window and Kalman Filter based solutions. The results show the superior performance of the proposed method and confirm that the apriori knowledge-based constraints improve the robustness of the estimates.
Operating regime model based multi-objective sensor placement for data reconciliation
Operating regime model based multi-objective sensor placement for data reconciliation
Although the number of sensors in chemical production plants is increasing thanks to the IoT revolution, it is still a crucial problem what to measure and how to place the sensors as such the resulted sensor network be robust and cost-effectively provide the required information. This problem is especially relevant in flexible multi-purpose, multi-product production plants when there are significant differences among the operating regions. The present work aims the development of a sensor placement methodology that utilizes the advantages of local linear models. Realizing the often conflicting nature of the key objectives of sensor placement, the problem is formulated as a multi-objective optimization task taking into consideration the cost, estimation accuracy, observability and fault detection performance of the designed networks and simultaneously seeking for the optimal solutions under multiple operating regimes. The effectiveness of the Non-dominated Sorting Genetic Algorithm-II (NSGA-II)-based solution of the defined problem is demonstrated through benchmark examples.
Soft Sensors Special Issue
Soft Sensors Special Issue
Post date: Aug 30, 2018 8:1:00 PM
Post date: Aug 30, 2018 8:1:00 PM
We are editing a special issue related to software sensors.
Please forward this link to researchers potentially interested insubmitting a paper.
Slide to promote special issue in conference
http://www.mdpi.com/journal/sensors/special_issues/Soft_Sensors
Software sensor for activity-time monitoring and fault detection in production lines
Software sensor for activity-time monitoring and fault detection in production lines
Industry 4.0-based human-in-the-loop cyber-physical production systems are transforming the industrial workforce to accommodate the ever-increasing variability of production. Real-time operator support and performance monitoring require accurate information on the activities of operators. The problem with tracing hundreds of activity times is critical due to the enormous variability and complexity of products. A software-sensor-based activity-time and performance measurement system to handle this problem is proposed.
To ensure a real-time connection between operator performance and varying product complexity, fixture sensors and an indoor positioning system (IPS) were designed and this multi sensor data merged with product-relevant information.
The proposed model-based performance monitoring system tracks the recursively estimated parameters of the activity-time estimation model. As the estimation problem can be ill-conditioned and poor raw sensor data can result in unrealistic parameter estimates, constraints were introduced into the parameter-estimation algorithm to increase the robustness of the software sensor.
The applicability of the proposed methodology is demonstrated on a well-documented benchmark problem of a wire harness manufacturing process. The fully reproducible and realistic simulation study confirms that the indoor positioning system-based integration of primary sensor signals and product-relevant information can be efficiently utilized in terms of the constrained recursive estimation of the operator activity.
The MATLAB files will be avaliable after the acceptance of the paper.
Multivariate Statistical and Computational Intelligence Techniques for Quality Monitoring of Production Systems
Multivariate Statistical and Computational Intelligence Techniques for Quality Monitoring of Production Systems
The ISO 9001:2008 quality management standard states that organizations shall plan and implement monitoring, measurement, analysis and improvement processes to demonstrate conformity to product requirements. According to the standard, detailed analysis of data is required for this purpose. The analysis of data should also provide information related to characteristics and trends of processes and products, including opportunities for preventive action. The preliminary aim of this chapter is to show how intelligent techniques can be used to design data–driven tools that are able to support the organization to continuously improve the effectiveness of their production according to the Plan—Do—Check—Act (PDCA) methodology. The chapter focuses on the application of data mining and multivariate statistical tools for process monitoring and quality control. Classical multivariate tools such as PLS and PCA are presented along with their nonlinear variants. Special attention is given to software sensors used to estimate product quality. Practical application examples taken from chemical and oil and gas industries illustrate the applicability of the discussed techniques.
Data-driven Development and Maintenance of Soft-Sensors
Data-driven Development and Maintenance of Soft-Sensors
Product quality related process variables have significant role in advanced process control (APC). Online analyzers and software sensors can provide accurate and timely information for APC systems. In this paper we give an overview of data based soft-sensor development. We show that soft-sensor models of APC require maintenance and demonstrate that statistical quality control (SQC) techniques can be effectively used to automatize the related fault detection tasks.
Statistical Process Control Based Performance Evaluation Of On-Line Analysers
Statistical Process Control Based Performance Evaluation Of On-Line Analysers
On-line analyzers can provide accurate and timely information for process control and monitoring. Statistical Process Control (SPC) techniques can be effectively utilized to support the development and maintenance of these tools. The D6299- 10 ASTM standard details how on-line analyzers should be validated. The applicability of this standard is demonstrated through the analysis of industrial data collected from an on-line gas chromatograph. The results confirm that automatized SPC can effectively improve the reliability of advanced process control systems.
Semi-mechanistic Models for State-Estimation – Soft Sensor for Polymer Melt Index Prediction
Semi-mechanistic Models for State-Estimation – Soft Sensor for Polymer Melt Index Prediction
Nonlinear state estimation is a useful approach to the monitoring of industrial (polymerization) processes. This paper investigates how this approach can be followed to the development of a soft sensor of the product quality (melt index). The bottleneck of the successful application of advanced state estimation algorithms is the identification of models that can accurately describe the process. This paper presents a semi-mechanistic modeling approach where neural networks describe the unknown phenomena of the system that cannot be formulated by prior knowledge based differential equations. Since in the presented semi-mechanistic model structure the neural network is a part of a nonlinear algebraic-differential equation set, there are no available direct input-output data to train the weights of the network. To handle this problem in this paper a simple, yet practically useful spline-smoothing based technique has been used. The results show that the developed semi-mechanistic model can be efficiently used for on-line state estimation.
Effects of Catalyst Activity Profiles on the Operating Conditions of an Industrial Polymerization Reactor
Effects of Catalyst Activity Profiles on the Operating Conditions of an Industrial Polymerization Reactor
The aim of this paper is to analyze how different catalyst activity profiles influence the operating strategies of industrial polymerization reactors. Since the catalyst activity profiles may change considerably in the range of the residence-time of the reactor, the properties of the produced polymer powder are the averages of ones produced by catalyst particles with various activities. Hence, the residence-time distribution of the polymer phase has an effect on the product properties as well. Based on these phenomena a new method proposed to transform information from laboratory reactor into a form which can be used to estimate the operation condition of industrial reactor. The whole approach is demonstrated in case of the production of high-density polyethylene.
Report abuse