著者

丹下 吉雄 松井 哲郎

出版者

一般社団法人 電気学会

雑誌

電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)

巻号頁・発行日

vol.144, no.1, pp.21-27, 2024-01-01 (Released:2024-01-01)

参考文献数

25

---

In this paper, we propose a self-tuning algorithm by which we can achieve autonomous engineering including model identification and control parameter tuning on the edge-type MPC (Model Predictive Control). In the model identification algorithm, offset estimation is introduced in order to replace step response tests. We compare the control performance of the self-tuning edge-type MPC with those of PID control and offline-tuned edge-type MPC for a MIMO stir process model. As a result, the proposed self-tuning edge-type MPC achieves faster tracking performance without any pre-tuning.

著者

飯坂 達也 松井 哲郎 福山 良和

出版者

一般社団法人 電気学会

雑誌

電気学会論文誌B(電力・エネルギー部門誌) (ISSN:03854213)

巻号頁・発行日

vol.124, no.3, pp.347-354, 2004 (Released:2004-06-01)

参考文献数

22

被引用文献数

8 13

---

This paper presents a daily peak load forecasting method using an analyzable structured neural network (ASNN) in order to explain forecasting reasons. In this paper, we propose a new training method for ASNN in order to explain forecasting reason more properly than the conventional training method. ASNN consists of two types of hidden units. One type of hidden units has connecting weights between the hidden units and only one group of related input units. Another one has connecting weights between the hidden units and all input units. The former type of hidden units allows to explain forecasting reasons. The latter type of hidden units ensures the forecasting performance. The proposed training method make the former type of hidden units train only independent relations between the input factors and output, and make the latter type of hidden units train only complicated interactions between input factors. The effectiveness of the proposed neural network is shown using actual daily peak load. ASNN trained by the proposed method can explain forecasting reasons more properly than ASNN trained by the conventional method. Moreover, the proposed neural network can forecast daily peak load more accurately than conventional neural network trained by the back propagation algorithm.

著者

大熊 達義 佐藤 洋湖 湯浅 光悦 幡手 雄幸 長内 智宏 石田 正文 渡辺 孝芳 高梨 信吾 金沢 武道 小野寺 庚午 花田 勝美 方山 揚誠 工藤 一 藤田 〓 松井 哲郎 吉田 穣

出版者

The Japanese Respiratory Society

雑誌

日本胸部疾患学会雑誌 (ISSN:03011542)

巻号頁・発行日

vol.21, no.12, pp.1213-1221, 1983-12-25 (Released:2010-02-23)

参考文献数

13

---

A 32-year-old taxi driver was admitted with complaints of coughing and exanthema. The respiratory symptoms and exanthema had appeared in April, 1980 and he had been tatooed on his back and arms about a year previously. His tatoo was composed of four distinctive colours (red, yellow, green and black). Exanthema was seen in only the red, yellow and green parts. Bilateral axillar and cervical lymph nodes were palpable. Chest X-ray films revealed diffuse shadows in both lung fields. Serum and urine test were normal. a biopsy of skin tissues and a lymphotic gland showed granulomatous changes caused by the tatoo dyes. Analysis of the dyes suggested that the red coloring matter consisted of organic mercury.Pathological findings of the specimen obtained from a lung biopsy showed thickening of the alveolar wall, with infiltration of lymphocytes and epitheloid granuloma. Electron microscopy showed that the tatoo dyes were localized in his skin, lymph nodes and lung. We concluded that this was a case of diffuse, granulomatous interstitial pneumonia due to his tatoo.