• Research News
Research News

Research News

2023 2022202120202019 | 2018  | 2017 | 2016 | 2015 | 2014 | 2013 | 2012 | 2011

*The information and links in the topics is current on the date of announcement, but is subject to change without prior notice.

23 Mar, 2023
TOKYO—Toshiba Corporation (TOKYO: 6502) developed a compact, high-sensitivity odor sensor that detects specific odor, for on-site maintenance and inspection of social infrastructure facilities. Using a quartz crystal resonator (QCR) *1 based compact and inexpensive sensor, and proprietary technology that evenly coats a thin film of a metal organic framework (MOF)*2, which well absorbs specific odors, Toshiba has realized high-sensitivity detection performance for the sensor, although it is less expensive and smaller than conventional analyzers with a volume ratio of less than few tenths in comparison.
Recently, Toshiba has applied this technology to musty odor that arise in drinking water sources and tap water, and succeeded to detect 2-methylisoborneol (“2-MIB”), the main cause of such odors, with a concentration of 0.2ppbv (2 parts per 10 billion) in air. This level of performance satisfies the standards for an aqueous concentration of 10ng/L and under (1g per 100 million within 1L of water), which represents the water quality standards for 2-MIB based on the Waterworks Act of Japan*3.
The detection of musty odor typically requires the installation of a large analyzer. Additionally, inspections based on sensory evaluations that depend on the experience and olfactory sense of the inspector are also conducted in great number. The utilization of this technology in odor anomaly inspections conducted at purification plants is anticipated to result in greater automation and efficiency of musty odor inspections at those plants. Additionally, coating the sensor with different types of thin film makes it possible to apply this technology in sensors for detecting non-musty off-odors, such as oily, scorched, or metallic odors. Going forward, this technology holds the promise of being applied to anomaly inspections in the areas of quality and production control at food and beverage manufacturers in addition to the maintenance and inspection of social infrastructure facilities.
Toshiba will announce the details of this technology at the 103rd CSJ Annual Meeting, which will be held on the Noda Campus of the Tokyo University of Science starting on March 22.
13 Mar, 2023
TOKYO—Toshiba Corporation (TOKYO: 6502) has developed an AI that understands specialized technical documents of factories and plants in the infrastructure sector with high efficiency and accuracy: it understands accumulated sector-specialized documents (hereinafter, “specialized data”) including technical drawings, machine specifications, and inspection/incident reports, thereby enabling more effective inspection and maintenance. Whereas efficient learning of general terms from a large general-purpose language model (teacher model) is widely available, the developed AI learns sector-specific technical terms using a separate curriculum with a limited amount of specialized data. Such efficient learning of both general and technical terms enables generation of small-scale language models (student models), thereby allowing for accurate understanding of technical documents with limited computational resources.
Specialized data that accumulates experts’ experiences and knowledge were previously difficult for an AI to understand. However, specialized data can be utilized by the developed AI in actual infrastructure maintenance. It can extract phenomena in previous incidents as well as measures to solve them with high accuracy. This AI is expected to contribute to faster corrective maintenance and to the realization of condition-based maintenance.
Toshiba will present this AI at the 29th Annual Meeting of the Association for Natural Language Processing (NLP2023, Okinawa, March 13-17, 2023), which will be held in a hybrid format.
Toshiba aims to achieve “proactive maintenance” including condition based maintenance with utilization of experts’ knowledge in future.
08 Dec, 2022
Toshiba Corporation, Tohoku University Tohoku Medical Megabank Organization (ToMMo), Tohoku University Hospital, and the National Institute of Information and Communications Technology (NICT) have demonstrated the world's first*1 personalized healthcare*2 system that stores genome data from many individuals in multiple locations and utilizes them for medical treatment and healthcare using an information theoretically secure method based on the quantum key distribution (QKD) link, the secret sharing system and personal authentication technology. This system is theoretically secure against the threat of store now and decrypt later attacks, prevents data leaks, falsification, and loss of genome data. In this system, data decryption and reconstruction*3 are performed by using personal authentication and individual consent. The system is expected to contribute to the realization and spread of personalized healthcare.
16 Nov, 2022
TOKYO—Toshiba Corporation (TOKYO: 6502) has announced its development of “Variational Autoencoder-based Deterioration Estimation (VAE-DE),” an acoustic wear-estimating AI that analyzes equipment operating sounds and detects signs of wear with high accuracy. This AI allows early detection of signs indicating equipment wear without false positives, even in the presence of ambient noise from the environment or electrical noise from circuits. To verify the effectiveness of this AI, Toshiba used simulation data based on operating sounds from cooling fans actually used in power facilities for several years and noise collected at power facility installation sites. By investigating correlations between the “estimated wear value,” a value obtained by estimating a device’s extent of deterioration based on its operating sounds, and the “deterioration trend,” which indicates the actual state of equipment wear, Toshiba has found significant improvement in the correlation coefficient, which increased from 0.144 to 0.905. Those results confirm that the developed method can estimate wear with high accuracy while suppressing false positives due to noise, a feat that has been difficult to achieve in the past. This AI makes it possible to determine the extent of equipment deterioration based on its operating sounds and to perform maintenance at appropriate times. Toshiba will present the details of this technology at the 9th International Conference on Condition Monitoring and Diagnosis 2022 (CMD2022), an international conference related to diagnostic technologies for power facilities, to be held from November 13 to 18 in a hybrid format, online and in Kitakyushu, Fukuoka Prefecture, Japan.
08 Nov, 2022
TOKYO-Toshiba Corporation (TOKYO: 6502) has developed a Sliding Sheet-Lattice Matrix (SSLM) for ultrasonic nondestructive testing in infrastructure maintenance and inspections. The developed SSLM does not require the application of a liquid couplant, such as the gel applied to human bodies for ultrasonic examinations during health checkups, and furthermore combines high performance for passing ultrasonic waves (ultrasonic propagation) with smooth device operability. Nondestructive testing is an inspection evaluating internal defect and its form or size in an object without damaging it, and ultrasound, which is harmless to the human body, is widely used in such inspections. Liquid or gel couplant are often used in ultrasonic inspections, especially when inspecting the human body, because they both provide high levels of ultrasonic propagation and smooth operations. However, in the field of infrastructure maintenance and inspection, liquids can seep into the interior of inspection targets, leading to failure or deterioration of the applied structures or equipment. Minimizing such effects requires additional work, so applications to infrastructure now also uses adhesive sheets of solid couplant, but there is generally a trade-off between ultrasonic propagation and smooth operations, leading to issues such as increased work times. Toshiba has developed SSLM comprising a proprietary soft sheet and lattice material to realize both ultrasonic wave propagation and smooth operability. The lattice material allows low-friction movement over structure and equipment surfaces when changing inspection positions, and when inspecting, applying a load to press the SSLM against the object that is the target of an inspection allows propagation of ultrasonic waves, giving it rapid response characteristics. Ultrasonic nondestructive testing requires taking measurements from many locations following the surface of the inspected object, and thus use of the developed SSLM should result in significant time reductions compared with the inspection times seen when using conventional adhesive sheets(*1). In addition, compared with conventional ultrasonic nondestructive inspection methods using a liquid couplant, SSLM eliminates the need for masking areas outside of the inspection area before the inspection and removing applied liquid couplant after inspections, thereby contributes to improved efficiency and automation of maintenance and inspections. Furthermore, it enables be applied to objects that were previously difficult to apply, due to the difficulty of removing liquids. Toshiba will present details of this development at the 43rd Symposium on Ultra Sonic Electronics (USE2022) (*2), which will be held in Kyoto from November 7.
02 Nov, 2022
Toshiba Corporation and the CiRA Foundation have begun joint research to develop methods for establishing iPS cells (induced pluripotent stem cells) using liposomes technology.
07 Oct, 2022
TOKYO—Toshiba Corporation (TOKYO: 6502) has developed large-scale production technology for the electrodes that realizes high level efficiency in Power to Gas (P2G) technology, essential know-how for advancing toward a carbon neutral society, while reducing the use of iridium, one of the world’s rarest precious metals, to 1/10*1.
27 Sep, 2022
TOKYO—Researchers at Japan’s Toshiba Corporation (TOKYO: 6502) have announced a significant advance in their work to develop an efficient, low cost and highly reliable tandem solar cell that raises the output of solar panels by layering a transparent solar cell over a standard silicon cell.
16 Sep, 2022
Researchers at Toshiba Corporation (TOKYO: 6502) have achieved a breakthrough in quantum computer architecture: the basic design for a double-transmon coupler that will improve the speed and accuracy of quantum computation in tunable couplers. The coupler is a key device in determining the performance of superconducting quantum computers.
26 Aug, 2022
TOKYO—Toshiba Corporation (TOKYO: 6502) has demonstrated the effectiveness of its grid-forming (GFM) inverter, which was developed to ensure the stability of microgrids. A microgrid is a type of distributed energy system that enables regional self-sufficiency for electric power through the use of renewable energy, rather than relying on power supply from large-scale power plants. When there is a sudden fluctuation in the output of or demand for electric power, a normally stable frequency can fluctuate drastically, possibly triggering a protection relay(*1) and cutting off power supply, leading to power outages. In particular, as the share of renewable energy increases, fluctuations in grid frequency increase. In particular, frequency fluctuations will increase with increased ratios of renewable energy, so the widespread use of microgrids will require technologies for maintaining a stable grid frequency.
12 Jul, 2022
TOKYO—Toshiba Corporation (TOKYO: 6502) has developed a technology that could analyze and visualize the internal soundness of bridge decks which cannot be seen from the exterior, and demonstrated its effectiveness for bridges at the Fukuoka-Kitakyushu Expressway Public Corporation (Fukuoka Expressway). This technology uses sensors installed at the undersurface of the deck to acquire and digitize data from weak waves generated at the road surface as vehicles cross the bridge, analyzes the data to digitize internal damage and visualize as a soundness map that cannot be recognized through conventional visual inspections. This technology will enable repair plan formulations and work task implementations according to the internal condition of bridges, and furthermore promote the digitalization of bridge aging countermeasures and contribute to more efficient bridge repair and extending the service life of social infrastructure. Toshiba has demonstrated this technology for repairs to bridge decks at Fukuoka Expressway Route 2, confirming the validity of evaluations of the internal condition of bridges. The company will continue conducting demonstration with Fukuoka Expressway, and together with its operating company, Toshiba Plant Systems & Services Corporation, aims to start providing this service to road operators in FY2024.
15 Jun, 2022
KAWASAKI--Toshiba Electronic Devices & Storage Corporation and Toshiba Corporation (collectively “Toshiba”) have together developed the world’s first 4.5-kV double-gate reverse-conducting injection-enhanced gate transistor (RC-IEGT). Toshiba confirmed a total power loss, when switching on and off (switching loss), reduction of 24% compared with the conventional single-gate structure.
25 May, 2022
TOKYO—Toshiba Corporation (TOKYO: 6502) has developed Few-Shot Object Detection AI, an image recognition-based technology capable of immediately detecting a new object with unprecedented accuracy. Simply registering a single image primes the technology to recognize new products and parts in production and logistics. The company designed the new AI to be useful in situations where new objects appear frequently, such as plants that regularly process updated and improved products and parts, and distribution centers that are constantly required to handle new merchandise. There are worldwide efforts to convert sensing data from the field into valuable information and return it to the field as feedback, thereby increasing productivity, quality, and efficiency in operations. Image recognition AI, which detects people and objects in images, is particularly valuable for analysis aiming to improve productivity, automate processes, and reduce workloads. However, one drawback of the technology is the need to prepare large amounts of image data for training to detect new objects every time they are needed in the situations where the technology is used. Toshiba’s new Few-Shot Object Detection AI is automatically pre-trained to recognize the shapes of non-target objects in the training images, a proprietary development in the training process that enables the AI to detect new objects with the registration of a single image and no retraining in the field. In an assessment of detection accuracy based on a public dataset, the technology achieved unprecedented accuracy. Companies that operate factories and plants that handle many different parts and equipment have been reluctant to incorporate AI into their processes because of the time and effort required for retraining every time something changes. Few-Shot Object Detection AI is easy to introduce and use, helping these companies digitize their operations and promote digital transformation to improve productivity, quality, and efficiency. Toshiba is scheduled to give a presentation on the details of the new technology on May 25, 2022 at ICIAP 2021, the 21st International Conference on Image Analysis and Processing.
23 May, 2022
TOKYO—Toshiba Corporation (TOKYO: 6502) has developed artificial intelligence (AI) for detecting anomalies during infrastructure inspections. With only a few reference images of inspection targets and no real-world training, the technology can accurately detect cracks and rust as well as leaks, adhesion of foreign material, detachment of parts, and other infrequent, untrained anomalies. This new AI not only reduces inspection workloads—particularly those that imperil workers or require travel, such as atop steel towers in the mountains, under elevated bridges, on slopes, and under solar panels—it also performs well in real-world situations where the scarcity of images from the field has hampered past efforts to use AI. The technology uses features from pre-trained deep learning models to compare inspection photographs against reference images, and thus does not require real-world training as in the case of conventional AI. Toshiba’s proprietary correction technology enables the new AI to detect anomalies with high accuracy even when inspection photographs are taken from different angles than in the reference images, and also limits false positives in the case of unique patterns that are actually normal. In an assessment based on a public dataset, the AI was 91.7% accurate, the highest figure ever recorded. The new technology automates inspections, reduces workloads, and expedites the discovery of anomalies, helping ensure stable long-term operation of infrastructure. Toshiba is scheduled to give a presentation on the details of this new AI on May 25, 2022 at ICIAP 2021, the 21st International Conference on Image Analysis and Processing, in Italy.
18 Mar, 2022
TOKYO—Toshiba Corporation (TOKYO: 6502) has revealed major advances in shrinking the laser projector unit of its LiDAR to one quarter the size of the previous version released in June 2021. Using two of the new projector units, the new LiDAR is just 206cm3 in volume that can fit comfortably into the palm of the hand. Its range has been pushed out to 300m, the world’s longest with an industry-leading image resolution of 1200x84 pixels. It can be configured with flexible combinations of projector units to handle a variety of long-range and wide-angle detection applications.