JPH03177742A - Automatic control mechanism for air conditioner - Google Patents
Automatic control mechanism for air conditionerInfo
- Publication number
- JPH03177742A JPH03177742A JP1315720A JP31572089A JPH03177742A JP H03177742 A JPH03177742 A JP H03177742A JP 1315720 A JP1315720 A JP 1315720A JP 31572089 A JP31572089 A JP 31572089A JP H03177742 A JPH03177742 A JP H03177742A
- Authority
- JP
- Japan
- Prior art keywords
- control
- sensor
- learning
- air conditioner
- section
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000007613 environmental effect Effects 0.000 claims abstract description 9
- 238000013528 artificial neural network Methods 0.000 claims description 29
- 238000005259 measurement Methods 0.000 claims description 3
- 230000000717 retained effect Effects 0.000 claims 1
- 238000009434 installation Methods 0.000 abstract description 9
- 230000001537 neural effect Effects 0.000 abstract description 5
- 230000007704 transition Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 3
- 238000004378 air conditioning Methods 0.000 description 2
- 238000007664 blowing Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000009423 ventilation Methods 0.000 description 2
- 230000004931 aggregating effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Landscapes
- Air Conditioning Control Device (AREA)
Abstract
Description
【発明の詳細な説明】
〔概 要〕
空気調整機の自動制御に関し、
多様な設置環境と、比較的多数、多種の環境状態を条件
とする、空気調整機の自動制御を容易に実現できる空気
調整機自動制御機構を目的とし、センサ部、ニューラル
ネット部、空気調整機制御部、及び学習制御部を有し、
該センサ部は、所要数のセンサを有し、該センサによっ
て所要の環境状態を測定し、所定の時点ごとの該測定結
果から所定のセンサ情報を生成し、該ニューラルネント
部は、所要の構成のニューラルネットワークであって、
所与の入力信号と教師信号からなる学習パターンを学習
し、該センサ部の生成する該センサ情報を該入力信号と
して、該学習結果に基づく制御情報を出力し、該空気調
整機制御部は、入力部を有し、利用者が該入力部によっ
て入力する制御情報、及び該ニューラルネット部の出力
する該制御情報の何れによっても、所定の空気調整機を
制御する制御信号を、該制御情報に対応して出力し、該
学習制御部は、該制御情報が該入力部から発生された時
点で、該センサ情報と該制御情報とを保持し、該ニュー
ラルネット部を制御して、該保持するセンサ情報を該入
力信号とし、該制御情報を該教師信号とする学習パター
ンの学習を実行させるように構成する。[Detailed Description of the Invention] [Summary] Regarding the automatic control of air conditioners, the present invention relates to an air conditioner that can easily realize automatic control of air conditioners in various installation environments and under a relatively large number and variety of environmental conditions. Aiming at a regulator automatic control mechanism, it has a sensor section, a neural network section, an air conditioner control section, and a learning control section,
The sensor section has a required number of sensors, measures a required environmental state using the sensor, and generates predetermined sensor information from the measurement results at each predetermined time point, and the neural component section has a required configuration. A neural network,
The air conditioner control unit learns a learning pattern consisting of a given input signal and a teacher signal, uses the sensor information generated by the sensor unit as the input signal, and outputs control information based on the learning result, and the air conditioner control unit It has an input section, and uses the control information inputted by the user through the input section and the control information outputted from the neural network section to generate a control signal for controlling a predetermined air conditioner. Correspondingly, the learning controller retains the sensor information and the control information when the control information is generated from the input unit, and controls the neural network unit to retain the sensor information and the control information. The learning pattern is configured to execute learning using sensor information as the input signal and control information as the teacher signal.
本発明は、空気調整機の自動制御、待にニューラルネッ
トワークを利用して制御を行う、空気調整線自動制御機
構に関する。TECHNICAL FIELD The present invention relates to automatic control of an air conditioner, and particularly to an air adjustment line automatic control mechanism that performs control using a neural network.
〔従来の技術と発明が解決しようとする課題〕空気調整
機、いわゆるエアコン、の自動制御では、通常例えば対
象の部屋に設けた比較的少数の温度センサによって、セ
ンサ設置場所の室温を測定し、室温が設定温度より高け
れば送風を強め、設定温度より低くなれば送風を弱め、
或いは停止するというような、比較的単純な要因による
制御が行われる。[Problems to be solved by the prior art and the invention] In automatic control of air conditioners, so-called air conditioners, the room temperature at the location where the sensor is installed is usually measured using a relatively small number of temperature sensors installed in the target room. If the room temperature is higher than the set temperature, the fan will be increased; if the room temperature is lower than the set temperature, the fan will be decreased.
Or, control is performed based on relatively simple factors, such as stopping.
従って、例えば人が部屋の一隅にかたまっている場合と
、部屋全体に分散している場合とで送風状態を変えたり
、室内の人数、部屋の広さ、部屋の保温性等に応じて制
御をすることは難しい。Therefore, for example, the ventilation conditions may be changed depending on whether people are clustered in one corner of the room or spread out throughout the room, or controls may be adjusted depending on the number of people in the room, the size of the room, the heat retention of the room, etc. It's difficult to do.
そのような複雑な要因を考慮して制御することは、各種
のセンサを必要個所に設けて環境状態を測定し、それら
に基づいて制御をすれば不可能ではないが、多種多数の
環境状態値と制御のための出力との因果関係を決定して
、確定的な制御論理を組むことは容易でなく、それを多
様な設置環境に柔軟に対応できるように一般化すること
は更に難しい。It is not impossible to control such complex factors by installing various sensors at necessary locations to measure the environmental conditions and control based on them, but it is possible to control the environment by taking into account a wide variety of environmental condition values. It is not easy to determine the causal relationship between the control logic and the control output and to formulate a deterministic control logic, and it is even more difficult to generalize it so that it can flexibly correspond to a variety of installation environments.
本発明は、多様な設置環境に対応し、比較的多数個所で
検出する多種の環境状態を条件として、空気調整機の適
切な自動制御を行うことが、比較的容易に実現できる空
気調整線自動制御機構を目的とする。The present invention is compatible with various installation environments and can relatively easily realize appropriate automatic control of an air conditioner under various environmental conditions detected at a relatively large number of locations. Intended as a control mechanism.
第１図は、本発明の構成を示すブロック図である。 FIG. 1 is a block diagram showing the configuration of the present invention.
図は空気調整線自動制御機構のｔ！戒であって、センサ
部１、ニューラルネット部２、空気調整機制御部３、及
び学習制御部４を有し、センサ部１は、所要数のセンサ
５を有し、センサ５によって所要の環境状態を測定し、
センサ情報生成部６が所定の時点ごとの該測定結果から
所定のセンナ情報を生成し、ニューラルネット部２は、
所要の構成のニューラルネットワークであって、所与の
入力信号と教師信号からなる学習パターンを学習し、セ
ンサ部１の生成する該センサ情報を該入力信号として、
該学習結果に基づく制御情報を出力し、空気調整機制御
部３は、入力部７を有し、利用者が入力部７によって入
力する制御情報、及びニューラルネット部２の出力する
該制御情報の何れによっても、所定の空気調整機を制御
する制御信号を、該制御情報に対応して出力し、学習制
御部４は、該制御情報が入力部７から発生された時点で
、該センサ情報と該制御情報とを保持し、ニューラルネ
ット部２を制御して、該保持するセンサ情報を該入力信
号とし、該制御情報を該教師信号とする学習パターンの
学習を実行させる。The figure shows the air adjustment line automatic control mechanism. The sensor unit 1 has a sensor unit 1, a neural network unit 2, an air conditioner control unit 3, and a learning control unit 4. The sensor unit 1 has a required number of sensors 5, and the sensors 5 control the required environment. measure the condition,
The sensor information generation unit 6 generates predetermined sensor information from the measurement results at each predetermined time point, and the neural network unit 2
A neural network with a required configuration, which learns a learning pattern consisting of a given input signal and a teacher signal, and uses the sensor information generated by the sensor unit 1 as the input signal,
The air conditioner control unit 3 has an input unit 7 and outputs control information based on the learning result, and receives control information input by the user through the input unit 7 and the control information output from the neural network unit 2. In either case, a control signal for controlling a predetermined air conditioner is output in accordance with the control information, and the learning control unit 4 receives the sensor information and the control information at the time when the control information is generated from the input unit 7. The control information is held, and the neural network section 2 is controlled to execute learning of a learning pattern using the held sensor information as the input signal and the control information as the teacher signal.
この制御機構により、例えば典型的な制御をニューラル
ネット部２に学習させておいて、その制御機構の制御下
で空気調整機を使用し、制御が適当でない場合に利用者
が入力部７から必要な制御情報を入力して、空気調整機
を好みの状態に制御すると、利用者が制御した状態を自
動的に学習するので、設置環境に適応した自動制御へ次
第に移行することを期待できる。With this control mechanism, for example, typical control can be learned by the neural network unit 2, and the air conditioner can be used under the control of the control mechanism, and if the control is not appropriate, the user can use the input unit 7 to Once the user inputs control information and controls the air conditioner to the desired state, the system will automatically learn the state in which the user controlled it, so it can be expected that the system will gradually shift to automatic control that is adapted to the installation environment.
〔実施例〕
第１図の構成における、各センサ５は例えば空気調整を
行う部屋の中に一様に分散した測定個所に設けられ、各
測定個所に例えば温度センサ、湿度センサと、人の所在
状態を感知するための赤外線センサ等を置く。[Example] In the configuration shown in FIG. 1, each sensor 5 is installed at measuring points uniformly distributed in a room where air conditioning is performed, and each measuring point is equipped with a temperature sensor, a humidity sensor, and a sensor for detecting the location of a person. Install infrared sensors, etc. to detect the status.
センサ情報生成部６はセンサ５の測定値出力について、
ニューラルネット部２に入力するための前処理を、例え
ば一定時間間隔ごとに行って１組のセンサ情報をニュー
ラルネット部２へ出力する。Regarding the measured value output of the sensor 5, the sensor information generation unit 6
Preprocessing for inputting to the neural network unit 2 is performed, for example, at regular time intervals, and one set of sensor information is output to the neural network unit 2.
この前処理ではニューラルネット部２を効率よく利用で
きるように、測定値を集約したり、変換する演算を行う
ことができる。なお、センサ情報生成部６は、後述のよ
うに学習制御部４から要求された場合にも要求のあった
時点のセンサ情報を生成する。In this preprocessing, calculations for aggregating and converting measured values can be performed so that the neural network unit 2 can be used efficiently. Note that the sensor information generation unit 6 generates sensor information at the time of the request even when requested by the learning control unit 4 as described later.
ニューラルネット部２は、公知の学習機能を有するタイ
プのニューラルネットワークを主体に構成され、センサ
部１の出力するセンサ情報を入力信号として、それまで
の学習結果に基づいて、空気調整機制御部３に空気調整
機を所要の状態に制御する制御信号出力を要求するため
の制御情報を出力する。The neural network unit 2 is mainly composed of a type of neural network having a known learning function, and uses the sensor information output from the sensor unit 1 as an input signal to control the air conditioner control unit 3 based on the learning results up to that point. The controller outputs control information for requesting output of a control signal to control the air conditioner to a desired state.
空気調整機は部屋の状況に応じて、１台又は複数台設置
され、空気調整機制御部３は各空気調整機に対して個別
に制御信号を送るように構成し、その場合にニューラル
ネット部２からは、各個別の制御信号に対応する制御情
報が出力され、各制御情報には例えば送風の温度、強さ
等の所要値を示す値を出力するようにする。One or more air conditioners are installed depending on the situation of the room, and the air conditioner control unit 3 is configured to send control signals to each air conditioner individually. 2 outputs control information corresponding to each individual control signal, and each control information outputs a value indicating a required value such as the temperature and strength of the blowing air.
このような制御情報と同種の値は、入力部７に設けるキ
ー等の手段によって、利用者が入力できるようになって
いる。利用者の設定によって入力部７から制御情報が発
生されると、空気調整機制御部３はこの制御情報を優先
して受は取って、それに従う制御信号を出力するので、
ニューラルネット部２に記憶されている制御に関わらず
、利用者の好む制御を行うことができる。Values similar to such control information can be input by the user using means such as keys provided in the input section 7. When control information is generated from the input unit 7 according to the user's settings, the air conditioner control unit 3 receives this control information with priority and outputs a control signal in accordance with it.
Regardless of the control stored in the neural network unit 2, the user can perform the control desired by the user.
他方、入力部７の発生する制御情報は学習制御部４でも
受は取り、学習制御部４は制御情報を受は取ると、それ
を記憶すると共にセンサ情報生成部６に要求して、その
時のセンサ情報を受は取って記憶した後、ニューラルネ
ット部２に対して、記憶しているセンサ情報を入力信号
、制御情報を出力の教師信号とする学習パターンの学習
の実行を要求する。On the other hand, the control information generated by the input unit 7 is also received by the learning control unit 4. When the learning control unit 4 receives the control information, it stores it and requests it to the sensor information generation unit 6 to generate the current information. After receiving and storing the sensor information, it requests the neural network unit 2 to execute learning of a learning pattern using the stored sensor information as an input signal and control information as an output teacher signal.
そこで、ニューラルネット部２は、例えば公知のバック
プロパゲーション法による学習を実行して、その学習パ
ターンにおいて出力ができるだけ教師信号に近づくよう
に、ニューラルネットワーク内のノード間の結合の重み
を調整する。Therefore, the neural network unit 2 executes learning using, for example, a known backpropagation method, and adjusts the weights of connections between nodes in the neural network so that the output in the learning pattern is as close as possible to the teacher signal.
第２図は前記のような空気調整機態動制御機構を適用す
る例であり、第２図（ａ）は比較的小面積の部屋の例で
あって、「・」で示す位置にそれぞれ例えば前記のよう
な３Ｍ１類のセンサを設置して自動制御機構１０につな
ぎ、空気調整機１１は１個所のみに置いた例である。FIG. 2 shows an example in which the above-mentioned air conditioning maneuver control mechanism is applied, and FIG. 2(a) shows an example of a room with a relatively small area. This is an example in which a 3M1 type sensor as described above is installed and connected to the automatic control mechanism 10, and the air conditioner 11 is placed only at one location.
この場合に、例えば人が空気調整機に近いテレビの前に
集まって居る場合と、比較的遠いソファの辺りにいる場
合とを自動制？１１機横１０内のニューラルネット部で
識別して異なる制御情報を出力することにより、前者の
場合には空気調整機の近傍が適温になるように、適温の
比較的弱い送風とし、後者の場合にはソファの近傍が適
温になるように調整した温度で若干強い送風を行うとい
うような制御が容易にできる。In this case, for example, can we automatically control whether people are gathered in front of the TV near the air conditioner or relatively far away from the sofa? In the former case, the area near the air conditioner is blown at a relatively weak temperature so that the area near the air conditioner is at an appropriate temperature, and in the latter case, the neural network unit in the side 10 of the 11 aircraft identifies and outputs different control information. It is easy to control things like blowing a little stronger air at a temperature that is adjusted so that the area near the sofa is at an appropriate temperature.
又第２図（ｂ）は比較的大きな部屋に、多人数いる場合
の例で、空気調整機１１が４台設置され、自動制御機構
１２は４台の空気調整機を制御するように構成され、人
の所在位置の分布を自動制御機構１２内のニューラルネ
ット部で識別して、その状況に応じて、人の多い部分の
送風を特に強めるような制御が容易にできる。FIG. 2(b) shows an example where there are many people in a relatively large room, where four air conditioners 11 are installed and the automatic control mechanism 12 is configured to control the four air conditioners. By identifying the distribution of people's locations using the neural network section in the automatic control mechanism 12, it is easy to control the ventilation to be particularly strong in areas where there are many people, depending on the situation.
又何れの場合もニューラルネット部の初期の学習による
調整が設置場所の環境に十分適合していなくても、各種
の状況で利用者が所望の空気調整を得るように制御を行
うことにより、その制御を学習して適切な制御を自動的
に行うようになる。In any case, even if the initial learning adjustment of the neural network unit is not fully suited to the environment of the installation location, the system can be controlled so that the user can obtain the desired air adjustment in various situations. It will learn the controls and automatically perform appropriate controls.
以上の説明から明らかなように本発明によれば、空気調
整機について、多様な設置環境に対応し、比較的多数個
所で検出する多種の環境状態を条件として、空気調整機
の適切な自動制御を行うことが、経済的に可能になると
いう効果がある。As is clear from the above description, according to the present invention, the air conditioner can be appropriately automatically controlled in response to various installation environments and under various environmental conditions detected at a relatively large number of locations. This has the effect of making it economically possible to do so.
第１図は本発明の構成を示すブロック図、第２図は本発
明の機構の設置例の説明図である。
図においで、
１はセンサ部、 ２はニューラルネット部、３
は空気調整機制御部、４は学習制御部、５はセンサ、
６はセンサ情報生成部、７は入力部、
１０．１２は自動制御機構、１１は空気調整機
を示す。FIG. 1 is a block diagram showing the configuration of the present invention, and FIG. 2 is an explanatory diagram of an installation example of the mechanism of the present invention. In the figure, 1 is the sensor section, 2 is the neural network section, and 3 is the sensor section.
is an air conditioner control unit, 4 is a learning control unit, 5 is a sensor,
6 is a sensor information generation section, 7 is an input section,
10.12 shows an automatic control mechanism, and 11 shows an air conditioner.
Claims (1)
機制御部（３）、及び学習制御部（４）を有し、該セン
サ部（１）は、所要数のセンサ（５）を有し、該センサ
によって所要の環境状態を測定し、所定の時点ごとの該
測定結果から所定のセンサ情報を生成し（６）、 該ニューラルネット部（２）は、所要の構成のニューラ
ルネットワークであって、所与の入力信号と教師信号か
らなる学習パターンを学習し、該センサ部（１）の生成
する該センサ情報を該入力信号として、該学習結果に基
づく制御情報を出力し、該空気調整機制御部（３）は、
入力部（７）を有し、利用者が該入力部によって入力す
る制御１情報、及び該ニューラルネット部（２）の出力
する該制御情報の何れによっても、所定の空気調整機を
制御する制御信号を、該制御情報に対応して出力し、 該学習制御部（４）は、該制御情報が該入力部（７）か
ら発生された時点で、該センサ情報と該制御情報とを保
持し、該ニューラルネット部（２）を制御して、該保持
するセンサ情報を該入力信号とし、該制御情報を該教師
信号とする学習パターンの学習を実行させるように構成
されていることを特徴とする空気調整機自動制御機構。[Claims] It has a sensor section (1), a neural network section (2), an air conditioner control section (3), and a learning control section (4), and the sensor section (1) has a required number of The neural network unit (2) has a sensor (5) that measures a required environmental state and generates predetermined sensor information from the measurement results at each predetermined time point (6); A neural network configured to learn a learning pattern consisting of a given input signal and a teacher signal, and to generate control information based on the learning result using the sensor information generated by the sensor section (1) as the input signal. The air conditioner control unit (3) outputs the following:
control which has an input section (7) and controls a predetermined air conditioner according to either control 1 information inputted by the user through the input section and control information outputted from the neural network section (2); outputting a signal corresponding to the control information, and the learning control section (4) retains the sensor information and the control information at the time when the control information is generated from the input section (7). , characterized in that the neural network unit (2) is configured to execute learning of a learning pattern in which the retained sensor information is used as the input signal and the control information is used as the teacher signal. Air conditioner automatic control mechanism.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP1315720A JPH03177742A (en) | 1989-12-05 | 1989-12-05 | Automatic control mechanism for air conditioner |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP1315720A JPH03177742A (en) | 1989-12-05 | 1989-12-05 | Automatic control mechanism for air conditioner |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| JPH03177742A true JPH03177742A (en) | 1991-08-01 |
Family
ID=18068728
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP1315720A Pending JPH03177742A (en) | 1989-12-05 | 1989-12-05 | Automatic control mechanism for air conditioner |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPH03177742A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5727131A (en) * | 1992-10-23 | 1998-03-10 | Nippondenso Co., Ltd. | Neural network learning device |
| US8246321B2 (en) | 2008-02-14 | 2012-08-21 | Seiko Epson Corporation | Tube unit, control unit, and micropump |
| US8251954B2 (en) | 2005-04-27 | 2012-08-28 | Seiko Epson Corporation | Fluid transportation system and method of setting fluid ejection amount |
| US8303275B2 (en) | 2006-12-07 | 2012-11-06 | Seiko Epson Corporation | Micropump, tube unit, and control unit |
| US8353683B2 (en) | 2007-06-05 | 2013-01-15 | Seiko Epson Corporation | Micropump, pump module, and drive module |
| US8491286B2 (en) | 2008-12-05 | 2013-07-23 | Seiko Epson Corporation | Tube unit, control unit, and micropump |
| US8491284B2 (en) | 2008-09-29 | 2013-07-23 | Seiko Epson Corporation | Control unit, tube unit, and micropump |
| US8491283B2 (en) | 2008-08-20 | 2013-07-23 | Seiko Epson Corporation | Micropump |
| GB2530300A (en) * | 2014-09-18 | 2016-03-23 | Trollhetta As | Monitoring an environmental condition |
| CN111140986A (en) * | 2019-12-23 | 2020-05-12 | 珠海格力电器股份有限公司 | Operating state detection method and device of air conditioning system, storage medium and air conditioner |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS63108145A (en) * | 1986-10-24 | 1988-05-13 | Mitsubishi Electric Corp | Inferring control device for air conditioner |
| JPH0348301A (en) * | 1989-07-14 | 1991-03-01 | Matsushita Electric Ind Co Ltd | Optimum control device |
| JPH0391646A (en) * | 1989-09-04 | 1991-04-17 | Matsushita Electric Ind Co Ltd | Information processing device and air conditioner using same information processing device |
-
1989
- 1989-12-05 JP JP1315720A patent/JPH03177742A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS63108145A (en) * | 1986-10-24 | 1988-05-13 | Mitsubishi Electric Corp | Inferring control device for air conditioner |
| JPH0348301A (en) * | 1989-07-14 | 1991-03-01 | Matsushita Electric Ind Co Ltd | Optimum control device |
| JPH0391646A (en) * | 1989-09-04 | 1991-04-17 | Matsushita Electric Ind Co Ltd | Information processing device and air conditioner using same information processing device |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5727131A (en) * | 1992-10-23 | 1998-03-10 | Nippondenso Co., Ltd. | Neural network learning device |
| US8251954B2 (en) | 2005-04-27 | 2012-08-28 | Seiko Epson Corporation | Fluid transportation system and method of setting fluid ejection amount |
| US8303275B2 (en) | 2006-12-07 | 2012-11-06 | Seiko Epson Corporation | Micropump, tube unit, and control unit |
| US8353683B2 (en) | 2007-06-05 | 2013-01-15 | Seiko Epson Corporation | Micropump, pump module, and drive module |
| US8246321B2 (en) | 2008-02-14 | 2012-08-21 | Seiko Epson Corporation | Tube unit, control unit, and micropump |
| US8491283B2 (en) | 2008-08-20 | 2013-07-23 | Seiko Epson Corporation | Micropump |
| US9657731B2 (en) | 2008-08-20 | 2017-05-23 | Seiko Epson Corporation | Micropump |
| US8491284B2 (en) | 2008-09-29 | 2013-07-23 | Seiko Epson Corporation | Control unit, tube unit, and micropump |
| US8491286B2 (en) | 2008-12-05 | 2013-07-23 | Seiko Epson Corporation | Tube unit, control unit, and micropump |
| GB2530300A (en) * | 2014-09-18 | 2016-03-23 | Trollhetta As | Monitoring an environmental condition |
| GB2530300B (en) * | 2014-09-18 | 2021-06-30 | Trollhetta As | Monitoring an environmental condition |
| CN111140986A (en) * | 2019-12-23 | 2020-05-12 | 珠海格力电器股份有限公司 | Operating state detection method and device of air conditioning system, storage medium and air conditioner |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Teeter et al. | Application of functional link neural network to HVAC thermal dynamic system identification | |
| US5464369A (en) | Method and apparatus for estimating the rate at which a gas is generated within an enclosed space | |
| US20230251607A1 (en) | Environment controller and method for inferring via a neural network one or more commands for controlling an appliance | |
| US20230259074A1 (en) | Inference server and environment controller for inferring via a neural network one or more commands for controlling an appliance | |
| US20240069502A1 (en) | Environment controller and method for inferring one or more commands for controlling an appliance taking into account room characteristics | |
| US20120197828A1 (en) | Energy Saving Control for Data Center | |
| US11747771B2 (en) | Inference server and environment controller for inferring one or more commands for controlling an appliance taking into account room characteristics | |
| JPH03177742A (en) | Automatic control mechanism for air conditioner | |
| US10436470B2 (en) | Rule-based load shedding algorithm for building energy management | |
| EP3025099A1 (en) | Control device and method for buildings | |
| CA3035593A1 (en) | Training server and method for generating a predictive model for controlling an appliance | |
| JPH07192875A (en) | Device for automatic control of lighting and lighting system for controlling lighting condition inside house | |
| JP2000018687A (en) | Central management system for air conditioner | |
| JPH03110340A (en) | Control device for air conditioner | |
| US7325749B1 (en) | Distributed solid state programmable thermostat/power controller | |
| JPS6330902A (en) | Multi-loop control device | |
| CN209947269U (en) | VR fire escape experience room | |
| JPH0593540A (en) | Comfortable space control system | |
| JPS6129638A (en) | Controlling device of indoor environment | |
| JPH01147242A (en) | Airconditioner | |
| WO2023112074A1 (en) | Apparatus control device and apparatus control method | |
| JPH0599485A (en) | Fuzzy air-conditioning control system | |
| JPH0618073A (en) | Air conditioner | |
| Loveday et al. | Multivariate stochastic modelling of a full-scale office zone and air conditioning plant: the potential for BEMS | |
| JPH0330004A (en) | Thermo-hygrostat |