Optimal RFID Deployment in a Multiple-Stage Production System Under Inventory Inaccuracy and Robust Control Policy

Invisible stock loss often occurs in inventory management systems, which is usually caused by quality deterioration, theft, and misplacement and makes inventory record inaccurate. Inaccurate inventory record will bring significant negative impact on the performance of inventory control and leads to severe stock-out. To eliminate this negative impact, in this paper, we develop a Markov decision process (MDP) model for an inventory control system with invisible stock loss, inaccurate record, and replenishment lead-time. Based on the MDP model, a robust inventory control policy is constructed by using the policy iteration technique. From numerical experiments, we find that the robust policy still has a reorder point/order-up-to level structure i.e., an (s, S) structure, and can significantly reduce the impact of inventory inaccuracy.

An analysis of Electromagnetic Interference (EMI) between a Radio Frequency Identification (RFID) device and an Implantable Cardiac Defibrillator (ICD) is presented in this paper. In particular, the analysis focuses on the effects of EMI produced by an RFID reader on ICD operation. Thus, a brief overview of both ICD and RFID devices is presented at first. Subsequently, several experimental tests are performed inside an anechoic RF chamber, which ensures an appropriate shielding against external EMI sources. As a result, the comparison among ICD operating thresholds highlights its susceptibility against the RFID device.

Certain businesses call for a high level of traceability to track high value products. This case study of City Healthcare,1 New Zealand, focuses on the complex management issues related to the initial decisions to use radio frequency identification (RFID) technology on such a product, instead of a barcode. RFID devices are effectively tiny memory storage devices that can be read and sometimes written to from a distance using radio waves through an appropriate interrogation device. RFID devices have been touted as a replacement for barcodes in supply-chain applications. Issues and challenges investigated here include the ability of RFID to replace barcodes, business benefit from technology investment, technology adoption, and the role of external regulations in the adoption process.

In recent years the acceptance of Radio Frequency I dentification (RFID) technology in business environments has been increasing rapidly due to its competitive business value. Adopting a suitable RF IDbased information system has become increasingly important for supermarkets. However, most supermarkets still use conventional barcode-based s ystems to manage their information processes, which are consistently reported as one of the most unenth usiastic aspects of supermarket shopping for both customers and management. We propose an RFID agent-based architecture that adopts intelligent agent technology with an RFID based applications. RFID provides capability to uniquely identify an object wi thin a supermarket area, while agents are able to establ ish a channel of communication which can be used to facilitate communications between a RFID device and supermarket back-end system. The proposed framework includes a design of intelligent mobile s hopping cart equipped with both RFID and agent technologies. As a result of using the proposed RFI D agent based architecture, the customer shopping experience will be improved due to ease of retrievi ng of the detailed information on items and quick checkout by scanning all items at once, thus elimin ating queues. From supermarket management point of view the proposed architecture will reduce the cost of operation e.g., decreasing cost of goods sold w hich comes in the form of labor efficiency in areas of c heckout operation, inventory management and alerting the supermarket management when a certain product is running out of stock and needs to be restocked.

The SCOR-model contains five primary management processes, namely, Plan, Source, Make, Deliver, and Return. The development of radio frequency identification (RFID) technology provides an efficient way to improve the supply chain performance. In this paper, the application of RFID technology in a SCOR-model driven enterprise production system (EPS) is introduced. The framework and architecture of the RFID-based EPS are proposed to integrate the RFID devices into the production system. Afterwards the main processes of the SCOR-model driven EPS are illustrated, problems concerning communication between the RFID devices and the EPS are discussed as well. With the application of RFID, the improvement of SCOR performance metrics is analyzed in the end.

In this work, a deep economic and technical analysis for the enhancement of e-waste hierarchy applied to the Radio Frequency Identification (RFID) tags is presented. Nowadays, the RFID technology represents a valuable solution for many applications to improve the quality and efficiency of the supply chain, as well as for enhanced people or object identification and smart devices. This leads to massive usage of such devices that could represent a threat to the environment, since they are often considered as generic waste and no specific e-waste policy has been identified for RFID. For these reasons, the paper presents a study based on the desk research technique to propose several possibilities currently available for producers of different RFID devices in order to mitigate this problem at every e-waste hierarchy stage, i.e., ecological design and prevention, reuse, recycle, and disposal. Moreover, a cost/benefit analysis has been reported in order to highlight the economic advantages related to the RFID tags reuse, as well as environmental impact reduction. Results proved that passive RFID tags represent the major candidate for the e-waste hierarchy enhancement at every level, demonstrating that it is more convenient for the producer to consider an ecologically aware design and promote a take-back system for tags in order to take advantages from the solution proposed for the RFID e-waste hierarchy.

Radio Frequency Identification (RFID) is a globally accepted technology, which has a great success in the area of supply chain management and particularly inventory management. Businesses benefit from this cost efficient opportunity to scan and track inventories. The tracking of items with RFID devices is applied in a variety of areas, such as retailing, healthcare and traffic management. Traffic congestions in metropolitan areas have developed to a major problem in many countries all over the world. They have a negative impact on the economy, the environment and the overall quality of life. The purpose of this article is to discover the use of RFID technology to manage traffic congestions and to reduce the negative impact on the economy. RFID devices would give the opportunity to control the traffic in real-time and to gather valuable information about the development and the sources of congestions. Bottlenecks could be detected early and infrastructure could be aligned accordingly. Further research is suggested to achieve a well-discovered solution, developed globally by experts.

Oilfield tubulars (typically metallic pipes) and other types of oilfield equipment are typically stored in outdoor areas and may be scattered around the field. Managing these types of inventory is challenging and costly, as it requires significant labor resources. Therefore, inventory inaccuracy is common, and data-driven decisions may not be possible in a timely manner. We propose the use of radio frequency identification (RFID) for tracking oilfield tubulars and similar, outdoor-stored, equipment. Our proposed application utilizes passive ultra-high frequency (UHF) RFID technology that enables capturing unique serial identification numbers that are attached to inventory items from a distance of several meters. Passive UHF RFID tags require no batteries to operate. Typical tag cost is low. Each tag is placed on an inventory item and corresponds to a database entry containing specific information about this item. The tag communicates its serial number using power provided by an RFID reader radio transmission. The RFID reader is securely mounted to the underside of a UAV flown over the field. Captured RFID tags are either stored locally and retrieved once the UAV lands, or are wirelessly transmitted to a constantly updating inventory database. In addition to tag ID, the captured data typically includes time and date stamp, as well as location data. This research project included the design and manufacturing of an enclosure to house a RFID reader system which includes a host computer, embedded reader, antenna, power source, and necessary components for user interface. Specialized mounts were designed and manufactured to attach the enclosure and antenna to the UAV. The project incorporated the development of "middleware", specialized software installed on the host computer to communicate with the reader. The reader handles low-level communication with the antenna. To reduce network traffic, event management and data filtering are efficiently performed. The results of several UAV flights in experimental areas are presented and discussed. Various brands of passive RFID tags for oilfield applications were tested. Particular attention was given to population density of the items, stacking configuration, vertical altitude distance between reader and tags, and time to collect inventory data for a given area of surveillance. As RFID applications are increasing in the oil, gas, solar, and other sectors of the energy production industries, UAVs can effectively be used to get important operational and inventory data. UAV use is particularly appealing in inaccessible and remote locations.

The increasing need for automated surveillance systems in indoor environments such as airports, warehouses, production plants, etc. has stimulated the development of intelligent systems based on mobile sensors. Differently from traditional non-mobile surveillance systems, those based on mobile robots are still in their initial stage of development, and many issues are currently open for investigation (Everett, 2003; DehuaI et al., 2007). The use of robots significantly expands the potential of surveillance systems, which can evolve from the traditional passive role in which the system can only detect events and trigger alarms, to active surveillance in which a robot can be used to interact with the environment, with humans or with other robots for more complex cooperative actions (Burgard et al., 2000; Vig & Adams, 2007). A major challenge in surveillance tasks using mobile robots is that of providing the robot with a suitable knowledge of the environment to both navigate safely and perform inspection tasks. Furthermore, in order to effectively exploit mobility and multifunctionality, it is important to develop integrated control systems, capable of addressing simultaneously a number of problems, such as task planning, dynamic task sequencing, resolution of conflicts for shared resources, event-based feedback control. These issues are part of our current research concerning the development of a multi-sensor Surveillance Mobile Robot (SMR). The SMR consists of a commercial mobile robot (see Fig. 1), which is equipped with various sensors including a laser rangefinder and a Radio Frequency IDentification (RFID) device, and takes advantage of a hybrid control architecture to implement both high-level functions, like mission execution monitoring, and low-level reactive control. So far, several behaviours and tasks have been implemented and experimented. In this chapter, we focus on environment mapping and exploration using RFID technology. An RFID device typically consists of radio frequency (RF) tags, a reader with one or more antennas, and software to process the tag readings. The reader interrogates the tags, receiving their ID code and other information stored in their memory. Tags can be either passive or active. Passive tags are activated by the electromagnetic field generated by the RFID antenna. Active tags, instead, are powered by an on-board battery (Finkenzeller, 2003). Applications of RFID include inventory management, industry automation, ID badges and 2

Wireless location sensing plays a critical role in the developing Internet of Things (IoT), which has been attracting increasing attention in both the academia and industry recently. Nowadays UHF Radio Frequency Identification (RFID), due to its long-range, inexpensive, multi-tag identification and batteryfree sensing capability, has been widely applied for localization especially in intelligent manufacturing factories and warehouses. Inspired by the robustness against noise and multipath distortion of synthetic aperture radar, we present a rotating synthetic aperture RFID method for robot localization in this paper. Based on this method, a robot equipped with a rotating RFID antenna perceives the position of itself, so it is a smart transporter unit in manufacturing for searching and conveying objects. The robot estimates its positions based on synthetic aperture RFID with an indistinct trajectory. Rotation and multi-frequency technique improves the resolution and location accuracy. The theoretical ambiguity analysis is also proposed. We evaluate the performance with commercial-off-the-shelf (COTS) RFID devices and build a prototype system with cm-level mean accuracy.

BackgroundRadio Frequency Identification (RFID) devices are becoming more and more essential for patient safety in hospitals. The purpose of this study was to determine patient safety, data reliability and signal loss wearing on skin RFID devices during magnetic resonance imaging (MRI) and computed tomography (CT) scanning.MethodsSixty RFID tags of the type I-Code SLI, 13.56 MHz, ISO 18000-3.1 were tested: Thirty type 1, an RFID tag with a 76 × 45 mm aluminum-etched antenna and 30 type 2, a tag with a 31 × 14 mm copper-etched antenna. The signal loss, material movement and heat tests were performed in a 1.5 T and a 3 T MR system. For data integrity, the tags were tested additionally during CT scanning. Standardized function tests were performed with all transponders before and after all imaging studies.ResultsThere was no memory loss or data alteration in the RFID tags after MRI and CT scanning. Concerning heating (a maximum of 3.6°C) and device movement (below 1 N/kg) no relevant influence was found. Concerning signal loss (artifacts 2 - 4 mm), interpretability of MR images was impaired when superficial structures such as skin, subcutaneous tissues or tendons were assessed.ConclusionsPatients wearing RFID wristbands are safe in 1.5 T and 3 T MR scanners using normal operation mode for RF-field. The findings are specific to the RFID tags that underwent testing.

<p>            Billions of passive radiofrequency tags are produced by the Radio-Frequency Identification (RFID) industry every year to identify goods remotely. New research and business applications are continuously arising, including recently localization and sensing for earth science. Indeed, the cost of tags is often several orders of magnitudes below conventional outdoor sensors used in earth science, allowing to deploy up to thousands of tags with minimal investment. Furthermore, passive wireless tags require little maintenance, which fits well for years-long monitoring. This study reviews the earth science applications that are being developed today, that use RFID devices available on the market, i.e., 900 MHz far-field tags and 125 kHz near-field tags.</p><p>            Ground displacements of centimeters to hundreds of meters can be monitored using RFID location techniques. Indeed, RFID tags were firstly used in earth science to track the displacement of riverine and coastal sediments due to bedloading. Near-field tags inserted in pebbles can be identified typically up to 0.5 m from the reading device even when buried. The tags are read either by fixed portals or by a mobile device, obtaining either high space or time resolution data, respectively. Very recently, measuring the phase difference of arrival of far-field tags allowed to estimate displacements with centimetric accuracy, with a tag-reader distance up to 50 m. That allowed measuring the ground displacements continuously relatively to a fixed reader, or to estimate tags location placed on the ground by carrying a reader over a drone using the synthetic aperture radar method. Alternatively, RFID tags can also be used for sensing the evolution over time of the temperature, moisture level, vibrations, resonant frequency or crack opening of a geologic object.</p><p>            This review presents multiple applications for monitoring unstable rock/earth structures using RFID. First, slow landslides can be monitored with accurate displacement monitoring and with soil moisture sensors. Then, prone-to-failure rock columns could be monitored by sensing crack opening or resonant frequency, using the same tags as with the concrete structure applications. Finally, sediment loading due to rapid mass movements such as floods, debris flows, tsunami or typhoons, have been studied largely using tags placed into pebbles.</p><p> </p><p>Author’s published work on the topic:</p><ul><li>Le Breton, M., Baillet, L., Larose, E., Rey, E., Benech, P., Jongmans, D., Guyoton, F., 2017. Outdoor UHF RFID: Phase Stabilization for Real-World Applications. IEEE Journal of Radio Frequency Identification 1, 279–290.</li> <li>Le Breton, M., Baillet, L., Larose, E., Rey, E., Benech, P., Jongmans, D., Guyoton, F., Jaboyedoff, M., 2019. Passive radio-frequency identification ranging, a dense and weather-robust technique for landslide displacement monitoring. Engineering Geology 250, 1–10.</li> <li>Le Breton, M., 2019. Suivi temporel d’un glissement de terrain à l’aide d’étiquettes RFID passives, couplé à l’observation de pluviométrie et de bruit sismique ambiant (PhD Thesis). Université Grenoble Alpes, ISTerre, Grenoble, France.</li> </ul>

We present a new method of learning control policies that successfully operate under unknown dynamic models. We create such policies by leveraging a large number of training examples that are generated using a physical simulator. Our system is made of two components: a Universal Policy (UP) and a function for Online System Identification (OSI). We describe our control policy as universal because it is trained over a wide array of dynamic models. These variations in the dynamic model may include differences in mass and inertia of the robots' components, variable friction coefficients, or unknown mass of an object to be manipulated. By training the Universal Policy with this variation, the control policy is prepared for a wider array of possible conditions when executed in an unknown environment. The second part of our system uses the recent state and action history of the system to predict the dynamics model parameters mu. The value of mu from the Online System Identification is then provided as input to the control policy (along with the system state). Together, UP-OSI is a robust control policy that can be used across a wide range of dynamic models, and that is also responsive to sudden changes in the environment. We have evaluated the performance of this system on a variety of tasks, including the problem of cart-pole swing-up, the double inverted pendulum, locomotion of a hopper, and block-throwing of a manipulator. UP-OSI is effective at these tasks across a wide range of dynamic models. Moreover, when tested with dynamic models outside of the training range, UP-OSI outperforms the Universal Policy alone, even when UP is given the actual value of the model dynamics. In addition to the benefits of creating more robust controllers, UP-OSI also holds out promise of narrowing the Reality Gap between simulated and real physical systems.

The development of autonomous vehicle control policies based on deep reinforcement learning is a principal technical problem for cyber-physical systems, fundamentally constrained by the high dimensionality of state spaces, inherent algorithmic instability, and a pervasive risk of policy over-specialization that severely limits generalization to real-world scenarios. The object of this investigation is the iterative process of forming a robust control policy within a simulated environment, while the subject focuses on the influence of specialized reward structures and initial training conditions on policy convergence and generalization capability. The study's aim is to develop and empirically evaluate a deep Q-learning policy optimization method that utilizes dynamic initial conditions to mitigate over-specialization and achieve stable, globally optimal adaptive control. The developed method formalizes two optimization criteria. First, the adaptive reward function serves as the safety and convergence criterion, defined hierarchically with major penalties for collision, intermediate incentives for passing checkpoints and a continuous minor penalty for elapsed time to drive efficiency. Second, the mechanism of dynamic initial conditions acts as the policy generalization criterion, designed to inject necessary stochasticity into the state distribution. The agent is modeled as a vehicle equipped with an eight-sensor system providing 360 degrees coverage, making decisions from a discrete action space of seven options. Its ten-dimensional state vector integrates normalized sensor distance readings with normalized dynamic characteristics, including speed and angular error. Empirical testing confirmed the policy's vulnerability under baseline fixed-start conditions, where the agent demonstrated over-specialization and stagnated at a traveled distance of approximately 960 conventional units after 40,000 episodes. The subsequent application of the dynamic initial conditions criterion successfully addressed this failure. By forcing the agent to rely on its generalized state mapping instead of trajectory memory, this approach successfully overcame the learning plateau, enabling the agent to achieve full, collision-free track traversal between 53,000 and 54,000 episodes. Final optimization, driven by penalty, reduced the total track completion time by nearly half. This verification confirms the method's value in producing robust, stable, and efficient control policies suitable for integration into autonomous transport cyber-physical systems.

This paper investigates the robust optimal control problem of a class of continuous-time, partially linear, interconnected systems. In addition to the dynamic uncertainties resulted from the interconnected dynamic system, unknown bounded disturbances are taken into account throughout the learning process, wherein the system’s dynamics and the disturbances are assumed unknown. These challenges lead the collected online data to be imperfect. In this scenario, traditional data-driven control techniques, such as adaptive dynamic programming (ADP) and robust ADP, encounter a challenge in approximating the optimal control policy precisely due to imperfect data and computational errors. In this paper, a novel data-driven robust policy iteration method is proposed to simultaneously solve the robust optimal control problems. Without relying on the knowledge of the system’s dynamics, the external disturbances or the complete state, the implementation of the proposed method only needs to access the input and partial state information. Based on the small-gain theorem, the notions of strong unboundedness observability and input-to-output stability, it is guaranteed that the learned robust optimal control gain is stabilizing and that the solution of the closed-loop system is uniformly ultimately bounded despite the existence of dynamic uncertainties and unknown external disturbances. The simulation results reveal the efficiency and practicality of the proposed data-driven control method. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This work is motivated by the use of reinforcement learning to improve the quality of designing adaptive optimal controllers for engineering applications. Adaptive dynamic programming methods, in particular policy iteration (PI), are widely used in solving optimal control problems. However, due to the iterative nature of PI, the approximated optimal control policy may be inaccurate and imprecise. Especially, when using imperfect system’s measurements instead of the modelling information. This can result in causing the learned control policy to deviate from the actual optimal policy. This becomes more challenging in the existence of dynamic uncertainties and unknown external disturbances which corrupt the measurements and result in imperfect data. This work investigates the conditions on the uncertainties such that the proposed novel data-driven PI algorithm is robust to system’s uncertainties, unknown external disturbances and imperfect measurements. The approximated robust optimal control policy performs robustly in the existences of imperfect data and uncertainties, and at the same time is close enough to the optimal control policy.