CN104875577A - All-condition double-area temperature calibration method and automobile air conditioner control system - Google Patents
All-condition double-area temperature calibration method and automobile air conditioner control system Download PDFInfo
- Publication number
- CN104875577A CN104875577A CN201410068347.XA CN201410068347A CN104875577A CN 104875577 A CN104875577 A CN 104875577A CN 201410068347 A CN201410068347 A CN 201410068347A CN 104875577 A CN104875577 A CN 104875577A
- Authority
- CN
- China
- Prior art keywords
- temperature
- network model
- formula
- neural network
- alignment method
- 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.)
- Granted
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60H—ARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
- B60H1/00—Heating, cooling or ventilating [HVAC] devices
- B60H1/00642—Control systems or circuits; Control members or indication devices for heating, cooling or ventilating devices
- B60H1/00735—Control systems or circuits characterised by their input, i.e. by the detection, measurement or calculation of particular conditions, e.g. signal treatment, dynamic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Mechanical Engineering (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Thermal Sciences (AREA)
- Air-Conditioning For Vehicles (AREA)
Abstract
The invention discloses an all-condition double-area temperature calibration method and an automobile air conditioner control system, and a BP neural network model of the temperature at a left area and a right area where human body perception positions are can be established when a temperature sensor in a car is calibrated. The method comprises determining an input signal of a network model, collecting training data of the network model in all conditions, processing the input and the output of the network model in normalization and processing the output in reverse normalization, and initializing and training the network model using a Matlab toolset. Because the input and the output of the network model are processed in normalization and the output is processed in reverse normalization, the defect that a conventional temperature calibration method depends on a control time axis can be thoroughly overcome. On the premise that all factors influencing on a temperature sensor in a car are in consideration, the accuracy of temperature calibration and the anti-interference performance are improved, accurate feedback can be provided to an in-car temperature closed loop control system, so the stability and accuracy on temperature control can be raised by adopting the automobile air conditioner control system.
Description
Technical field
The present invention relates to automobile air conditioner control system and dual-zone temperature control method field thereof, in particular a kind of full working scope dual-zone temperature alignment method utilizing BP neural net model establishing to realize the vehicle interior temperature sensor of automobile air conditioner control system on 16 micro controller systems.
Background technology
The vehicle interior temperature parameter of automobile air conditioner control system is one of most important parameter in vehicle interior temperature calibration algorithm, in actual application, what in orthodox car air-conditioned coach, the temperature correction of temperature sensor adopted is the alignment method of automatic operating, namely air-conditioner controller in automatic mode, the temperature value of human body position, two-region, left and right (the cm position, forehead front 5 of such as chaufeur and copilot) in car is gathered according to the skew of time, utilize the difference of this temperature value and vehicle interior temperature sensor temperature values to realize the temperature correction of vehicle interior temperature sensor.
But, the temperature correction method that traditional this employing difference compensates, larger to the dependence of air-conditioner control system time shaft, once time shaft is subject to non-objective interference, such as, when opening car door or vehicle window in temperature controlled processes, just destroy vehicle interior temperature balance, and then have impact on the accuracy of vehicle interior temperature pick up calibration; And traditional temperature correction method is carried out based on the temperature set in car, accurate temperature scanning cannot be realized and control, especially can only be applicable to single district temperature and control, the requirement that accurate dual-zone temperature controls cannot be met; In addition, running under the a/c system of traditional temperature correction method is in automatic mode all the time, and be not suitable for manual mode, as used situation when manual regulation inner-outer circulation, wind speed etc. instead, the requirement of vehicle interior temperature closed loop feed back cannot be met.
Therefore, prior art still haves much room for improvement and develops.
Summary of the invention
For solving the problems of the technologies described above, the invention provides a kind of vehicle interior temperature sensor full working scope dual-zone temperature alignment method based on BP neural net model establishing, accuracy and the antijamming capability of temperature correction can be improved.
Meanwhile, the present invention also provides a kind of automobile air conditioner control system based on BP neural net model establishing, and its temperature correction method used can realize dual-zone temperature calibration.
Technical scheme of the present invention is as follows: a kind of full working scope dual-zone temperature alignment method, for in automobile air conditioner control system, wherein, set up BP neural network model when calibrating vehicle interior temperature sensor to the temperature value of human body position, two-region, left and right, this alignment method comprises the following steps:
A, determine the incoming signal of described BP neural network model;
B, full working scope collection is carried out to the training data of described BP neural network model;
C, the input and output of described BP neural network model are normalized and renormalization process is carried out to its output;
D, Matlab tool box is utilized to carry out initialization and training to described BP neural network model.
Described full working scope dual-zone temperature alignment method, wherein: the incoming signal in described steps A comprises the vehicle interior temperature sensor reading that the outer temperature of car, blower speed PWM percentum, the temperature of two-region, left and right wind outlet, two-region, left and right sunlight sensor reading, automobile driving speed, inner-outer circulation AIR Proportional, air-out mode and needs compensate.
Described full working scope dual-zone temperature alignment method, wherein: the training data in described step B comprises car outer warm scan-data, two-region, left and right design temperature scan-data, wind speed scan-data, air-out mode scan-data, internal-external cycle throttle ratio scan-data and sunlight strength scan-data.
Described full working scope dual-zone temperature alignment method, wherein, the maximin of described BP neural network model input/output signal is determined when carrying out the normalized in described step C, comprise: [the max of the outer temperature of car, min]=[60 DEG C,-40 DEG C], [the max of blower speed PWM percentum, min]=[100, 0], [the max of two-region, left and right wind outlet temperature, min]=[80 DEG C, 0 DEG C], [the max of two-region, left and right sunlight sensor reading, min]=[1500 watts/sq m, 0 watt/sq m], [the max of automobile driving speed, min]=[250 kilometers/hour, 0 kilometer/hour], [the max of inner-outer circulation AIR Proportional, min]=[100, 0], [the max of air-out mode, min]=[7, 1], [the max of vehicle interior temperature sensor reading, min]=[80 DEG C, 20 DEG C], [the max of human body position temperature in car, min]=[80 DEG C, 20 DEG C].
Described full working scope dual-zone temperature alignment method, wherein: carrying out initialized Matlab statement to described BP neural network model in described step D is net=newff (minmax (Pn), [7,2], ' tansig', ' purelin'}), wherein Pn is input matrix, adopt L-M optimized algorithm during training, its Matlab statement be net.trainFcn=' trainlm'.
Described full working scope dual-zone temperature alignment method, wherein: described BP neural network model is Three Tiered Network Architecture, node in hidden layer is 7, comprises the following steps when 16 micro controller systems realize:
E, a discretization is got to excitation function tansig function;
F, by described BP neural network model floating number fixed point convert integer to, the table become by integer array is fitted to its fixed point;
G, generate the code of described BP neural network model based on Matlab instrument.
Described full working scope dual-zone temperature alignment method, wherein, described step e comprises:
E1, suppose A, B is the match point chosen, and C is the mid point of straight line AB, and D is the mid point of circular arc AB, and O is the center of circle of circular arc AB, and circular arc ADB is the curve needing matching, and the error of matching is the length of straight line DC, establishes formula 1:
(formula 1);
E2, establishment formula 2:
(formula 2);
E3, establishment formula 3:
(formula 3);
E4, establishment formula 4:
(formula 4);
E5, establishment formula 5:
(formula 5);
E6, establishment formula 6:
(formula 6);
E7, simultaneous formula 1 to 6, establish error of fitting formula 7:
(formula 7), wherein
for adjacent two match points, with this, scanning is carried out to match point and choose.
Described full working scope dual-zone temperature alignment method, wherein, described step F comprises:
F1, utilize " gensim (net) " of Matlab to order to convert the neural network net trained to siumlink block diagram;
F2, utilize " the Fixed-point Tool " of Matlab order by all floating numbers fixed point convert integer number to.
Described full working scope dual-zone temperature alignment method, wherein, described step G comprises: utilize " the Code Generation " of Matlab to order and carry out code building, using the output Output of described BP neural network NNET as temperature after the calibration of human body temperature sense organ position temperature sensor in car.
A kind of automobile air conditioner control system, comprises the temperature sensor being arranged on human body position, two-region, left and right in car, wherein: have employed when calibrating the temperature value of described temperature sensor above-mentioned according to any one of full working scope dual-zone temperature alignment method.
A kind of automobile air conditioner control system provided by the present invention and dual-zone temperature control method thereof, owing to have employed the renormalization process of normalized and the output to network model to the input and output of network model, at consideration automobile air conditioner control system on the basis of the various influence factors of vehicle interior temperature sensor, thoroughly break away from the dependence of conventional temperature calibration algorithm for period axle, improve accuracy and the antijamming capability of temperature correction, feed back exactly for vehicle interior temperature closed loop control system provides, be conducive to improving automobile air conditioner control system to temperature controlled stability and accuracy.
Accompanying drawing explanation
Fig. 1 is full working scope dual-zone temperature alignment method of the present invention error of fitting analysis chart used.
Fig. 2 is full working scope dual-zone temperature alignment method of the present invention carries out discrete approximation design sketch to excitation function tansig function.
Fig. 3 is full working scope dual-zone temperature alignment method of the present invention siumlink block diagram used.
Fig. 4 is temperature value after full working scope dual-zone temperature alignment method of the present invention calibration and the comparison diagram of vehicle interior temperature sensor reading.
Detailed description of the invention
Below with reference to accompanying drawing, described in detail the specific embodiment of the present invention and embodiment, described specific embodiment only in order to explain the present invention, is not intended to limit the specific embodiment of the present invention.
Due to the calibration of automobile air conditioner control system vehicle interior temperature sensor and the control output, car external environment operating mode etc. of automotive air-conditioning system closely bound up, therefore can calibrate vehicle interior temperature sensor time set up BP neural network model for the temperature of human body position in car.
For this reason, the invention provides a kind of full working scope dual-zone temperature alignment method, for in automobile air conditioner control system, set up BP neural network model when calibrating vehicle interior temperature sensor to the temperature value of human body position, two-region, left and right, this alignment method comprises the following steps:
Step S100, determine the incoming signal of described BP neural network model, the mode input of neural network must include to the utmost likely model is exported to the disturbing factor of (i.e. human body position temperature in car), according to the actual conditions of automobile air conditioner control system, signal as mode input can comprise: the outer temperature of car, blower speed PWM percentum is (as the evaluation quantity of air-out wind speed, if conditions permit also can directly replace with air-out wind speed), two-region, left and right wind outlet temperature (comprising the air-out air themperature of face's air outlet of chaufeur and copilot and the air-out air themperature of its foot's air outlet), two-region, left and right sunlight sensor reading, automobile driving speed, inner-outer circulation AIR Proportional, the vehicle interior temperature sensor reading etc. that air-out mode and needs compensate,
Step S200, full working scope collection is carried out to the training data of described BP neural network model; For realizing the vehicle interior temperature calibration neural net model establishing of full working scope two-region, training data also must contain all operating modes as much as possible, and therefore data acquisition system at least must be considered: the operating modes such as car outer warm scan-data, two-region, left and right design temperature scan-data, wind speed scan-data, air-out mode scan-data, internal-external cycle throttle ratio scan-data and sunlight strength scan-data;
Step S300, the input and output of described BP neural network model are normalized and are exported and carries out renormalization process, in order to realize normalized, must first will according to the maximin of each input/output signal of actual conditions Confirming model, specifically comprise: [the max of the outer temperature of car, min]=[60 DEG C,-40 DEG C], [the max of blower speed PWM percentum, min]=[100, 0], [the max of two-region, left and right wind outlet temperature, min]=[80 DEG C, 0 DEG C], [the max of two-region, left and right sunlight sensor reading, min]=[1500 watts/sq m, 0 watt/sq m], [the max of automobile driving speed, min]=[250 kilometers/hour, 0 kilometer/hour], [the max of inner-outer circulation AIR Proportional, min]=[100, 0], [the max of air-out mode, min]=[7, 1], [the max of vehicle interior temperature sensor reading, min]=[80 DEG C, 20 DEG C], [the max of human body position temperature in car, min]=[80 DEG C, 20 DEG C],
After the max min of each input/output signal of Confirming model, then according to formula
be normalized, wherein, Pn is inputing or outputing after normalized, and P is inputing or outputing before normalized, and PMin is the minimum value of P, and PMax is the maxim of P; And according to formula
carry out the renormalization process exported, wherein, T is the output after renormalization, and TNET is the direct output of neural network model, and TMax is the maxim of T, and TMin is the minimum value of T;
Step S400, Matlab tool box is utilized to carry out initialization and training to described BP neural network model; Concrete, the Matlab statement of BP netinit is: net=newff (minmax (Pn), [7,2], ' tansig', ' purelin'}), Pn is wherein input matrix; And network training can adopt L-M optimized algorithm, its Matlab statement be net.trainFcn=' trainlm'.
In the preferred implementation of full working scope dual-zone temperature alignment method of the present invention, described BP neural network model can be Three Tiered Network Architecture, and node in hidden layer preferably 7, can adopt 16 chip microcontroller; And be how to convert floating number fixed point in neural network to integer number, the particularly fixed-point problem of excitation function tansig by the greatest problem of chip microcontroller BP neural network, for this reason, BP neural network can comprise the following steps in the implementation method of micro controller system:
Step S500, a discretization is got to excitation function tansig function;
Step S600, by described BP neural network model floating number fixed point convert integer to, the table become by integer array is fitted to its fixed point;
Step S700, generate the code of described BP neural network model based on Matlab instrument.
In described step S500, as shown in Figure 1, Fig. 1 is full working scope dual-zone temperature alignment method of the present invention error of fitting analysis chart used, and suppose A, B is the match point chosen, C is the mid point of straight line AB, D is the mid point of circular arc AB, and O is the center of circle of circular arc AB, and circular arc ADB is the curve needing matching, the error of matching is the length of straight line DC, establishes formula 1:
(formula 1); Mathematical knowledge from being correlated with:
(formula 2);
(formula 3);
(formula 4);
(formula 5);
(formula 6);
Simultaneous formula 1 to 6, error of fitting formula 7 can be established:
(formula 7), wherein
for adjacent two match points, carry out scanning with this to match point and choose, the match point chosen is specially:
X = [-7 -4.8002 -3.2891 -2.6792 -2.2974 -2.0179 -1.7961 -1.6109 -1.4507 -1.3084 -1.1792 -1.0598 -0.9477 -0.8407 -0.7371 -0.6349 -0.5322 -0.4262 -0.3122 -0.1790 0.2296 0.3538 0.4642 0.5687 0.6709 0.7734 0.8780 0.9866 1.1010 1.2235 1.3569 1.5049 1.6730 1.8695 2.1085 2.4169 2.8565 3.6310 6.4870 7]；
Y = [ -1.0000 -0.9999 -0.9972 -0.9906 -0.9800 -0.9653 -0.9464 -0.9233 -0.8958 -0.8639 -0.8272 -0.7856 -0.7387 -0.6862 -0.6274 -0.5614 -0.4871 -0.4021 -0.3024 -0.1771 0.2256 0.3397 0.4335 0.5144 0.5856 0.6489 0.7054 0.7559 0.8009 0.8407 0.8757 0.9060 0.9319 0.9535 0.9709 0.9842 0.9934 0.9986 1.0000 1.0000]。
Shown in composition graphs 2, Fig. 2 is full working scope dual-zone temperature alignment method of the present invention carries out discrete approximation design sketch to excitation function tansig function, and its match point used is the above-mentioned match point chosen.
In described step S600, comprise: utilize " gensim (net) " of Matlab to order and convert the neural network net trained to siumlink block diagram, shown in composition graphs 3, Fig. 3 is full working scope dual-zone temperature alignment method of the present invention siumlink block diagram used, and utilizes " the Fixed-point Tool " of Matlab to order to convert all floating numbers fixed point to integer number.
In described step S700, utilize " the Code Generation " of Matlab to order and carry out code building, namely the output Output of BP neural network NNET can be used as temperature after the calibration of human body temperature sense organ position temperature sensor in car.
As can be seen here, the vehicle interior temperature alignment method that the present invention is based on BP neural net model establishing take into account the various influence factors of automobile air conditioner control system to vehicle interior temperature sensor as much as possible, thoroughly break away from the dependence of conventional temperature calibration algorithm for period axle, improve accuracy and the antijamming capability of temperature correction, feed back exactly for vehicle interior temperature closed loop control system provides, be conducive to improving automobile air conditioner control system to temperature controlled stability and accuracy.
Shown in composition graphs 4, Fig. 4 is temperature value after full working scope dual-zone temperature alignment method of the present invention calibration and the comparison diagram of vehicle interior temperature sensor reading, wherein: A is the thermocouple readings of human body temperature sense organ position, left district, B is the thermocouple readings of human body temperature sense organ position, right district, NET A is calibration Hou Zuo district vehicle interior temperature, NET B is calibration Hou You district vehicle interior temperature, its standard deviation is 0.7032 DEG C, as can be seen here, full working scope dual-zone temperature alignment method of the present invention can realize dual-zone temperature calibration, and this is also that conventional temperature alignment method institute is irrealizable.
Based on above-mentioned full working scope dual-zone temperature alignment method, present invention also offers a kind of automobile air conditioner control system based on BP neural net model establishing, comprise the temperature sensor being arranged on human body position, two-region, left and right in car, wherein: have employed the full working scope dual-zone temperature alignment method described in above-mentioned any one embodiment when calibrating the temperature value of described temperature sensor.
Should be understood that; the foregoing is only preferred embodiment of the present invention; be not sufficient to limit technical scheme of the present invention; for those of ordinary skills; within the spirit and principles in the present invention; can be increased and decreased according to the above description, replaced, converted or improved, and all these increases and decreases, replacement, conversion or the technical scheme after improving, all should belong to the protection domain of claims of the present invention.
Claims (10)
1. a full working scope dual-zone temperature alignment method, for in automobile air conditioner control system, it is characterized in that, set up BP neural network model when calibrating vehicle interior temperature sensor to the temperature value of human body position, two-region, left and right, this alignment method comprises the following steps:
A, determine the incoming signal of described BP neural network model;
B, full working scope collection is carried out to the training data of described BP neural network model;
C, the input and output of described BP neural network model are normalized and renormalization process is carried out to its output;
D, Matlab tool box is utilized to carry out initialization and training to described BP neural network model.
2. full working scope dual-zone temperature alignment method according to claim 1, is characterized in that: the incoming signal in described steps A comprises the vehicle interior temperature sensor reading that the outer temperature of car, blower speed PWM percentum, the temperature of two-region, left and right wind outlet, two-region, left and right sunlight sensor reading, automobile driving speed, inner-outer circulation AIR Proportional, air-out mode and needs compensate.
3. full working scope dual-zone temperature alignment method according to claim 1, is characterized in that: the training data in described step B comprises car outer warm scan-data, two-region, left and right design temperature scan-data, wind speed scan-data, air-out mode scan-data, internal-external cycle throttle ratio scan-data and sunlight strength scan-data.
4. full working scope dual-zone temperature alignment method according to claim 1, it is characterized in that, the maximin of described BP neural network model input/output signal is determined when carrying out the normalized in described step C, comprise: [the max of the outer temperature of car, min]=[60 DEG C,-40 DEG C], [the max of blower speed PWM percentum, min]=[100, 0], [the max of two-region, left and right wind outlet temperature, min]=[80 DEG C, 0 DEG C], [the max of two-region, left and right sunlight sensor reading, min]=[1500 watts/sq m, 0 watt/sq m], [the max of automobile driving speed, min]=[250 kilometers/hour, 0 kilometer/hour], [the max of inner-outer circulation AIR Proportional, min]=[100, 0], [the max of air-out mode, min]=[7, 1], [the max of vehicle interior temperature sensor reading, min]=[80 DEG C, 20 DEG C], [the max of human body position temperature in car, min]=[80 DEG C, 20 DEG C].
5. full working scope dual-zone temperature alignment method according to claim 1, it is characterized in that: carrying out initialized Matlab statement to described BP neural network model in described step D is net=newff (minmax (Pn), [7,2], ' tansig', ' purelin'}), wherein Pn is input matrix, adopt L-M optimized algorithm during training, its Matlab statement be net.trainFcn=' trainlm'.
6. full working scope dual-zone temperature alignment method according to claim 1, it is characterized in that: described BP neural network model is Three Tiered Network Architecture, node in hidden layer is 7, comprises the following steps when 16 micro controller systems realize:
E, a discretization is got to excitation function tansig function;
F, by described BP neural network model floating number fixed point convert integer to, the table become by integer array is fitted to its fixed point;
G, generate the code of described BP neural network model based on Matlab instrument.
7. full working scope dual-zone temperature alignment method according to claim 6, it is characterized in that, described step e comprises:
E1, suppose A, B is the match point chosen, and C is the mid point of straight line AB, and D is the mid point of circular arc AB, and O is the center of circle of circular arc AB, and circular arc ADB is the curve needing matching, and the error of matching is the length of straight line DC, establishes formula 1:
(formula 1);
E2, establishment formula 2:
(formula 2);
E3, establishment formula 3:
(formula 3);
E4, establishment formula 4:
(formula 4);
E5, establishment formula 5:
(formula 5);
E6, establishment formula 6:
(formula 6);
E7, simultaneous formula 1 to 6, establish error of fitting formula 7:
(formula 7), wherein
for adjacent two match points, with this, scanning is carried out to match point and choose.
8. full working scope dual-zone temperature alignment method according to claim 6, it is characterized in that, described step F comprises:
F1, utilize " gensim (net) " of Matlab to order to convert the neural network net trained to siumlink block diagram;
F2, utilize " the Fixed-point Tool " of Matlab order by all floating numbers fixed point convert integer number to.
9. full working scope dual-zone temperature alignment method according to claim 6, it is characterized in that, described step G comprises: utilize " the Code Generation " of Matlab to order and carry out code building, using the output Output of described BP neural network NNET as temperature after the calibration of human body temperature sense organ position temperature sensor in car.
10. an automobile air conditioner control system, comprising the temperature sensor being arranged on human body position, two-region, left and right in car, it is characterized in that: have employed the full working scope dual-zone temperature alignment method according to any one of claim 1 to 9 when calibrating the temperature value of described temperature sensor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410068347.XA CN104875577B (en) | 2014-02-27 | 2014-02-27 | A kind of full working scope dual-zone temperature calibration method and its automobile air conditioner control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410068347.XA CN104875577B (en) | 2014-02-27 | 2014-02-27 | A kind of full working scope dual-zone temperature calibration method and its automobile air conditioner control system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104875577A true CN104875577A (en) | 2015-09-02 |
| CN104875577B CN104875577B (en) | 2019-03-22 |
Family
ID=53943354
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410068347.XA Active CN104875577B (en) | 2014-02-27 | 2014-02-27 | A kind of full working scope dual-zone temperature calibration method and its automobile air conditioner control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104875577B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108674121A (en) * | 2018-03-30 | 2018-10-19 | 温州长江汽车电子有限公司 | A kind of the multi-temperature zone vehicle interior temperature control system and its control method of riding vehicle |
| CN109435630A (en) * | 2018-11-15 | 2019-03-08 | 无锡英捷汽车科技有限公司 | A kind of crew module's temprature control method based on artificial neural network algorithm |
| CN110070170A (en) * | 2019-05-23 | 2019-07-30 | 福州大学 | PSO-BP neural network sensor calibrating system and method based on MCU |
| CN113978202A (en) * | 2021-11-12 | 2022-01-28 | 上汽通用五菱汽车股份有限公司 | Vehicle-mounted air conditioner adjusting method, vehicle and computer-readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1191293A (en) * | 1998-03-24 | 1998-08-26 | 吴志源 | Intelligent fuzzy logic controlling method for air conditioner |
| JP2001334820A (en) * | 2000-05-29 | 2001-12-04 | Denso Corp | Vehicle air conditioner |
| CN203404890U (en) * | 2013-06-09 | 2014-01-22 | 上海荣孚科技发展有限公司 | Neural network-controlled dual-temperature-zone automobile air conditioner control system |
-
2014
- 2014-02-27 CN CN201410068347.XA patent/CN104875577B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1191293A (en) * | 1998-03-24 | 1998-08-26 | 吴志源 | Intelligent fuzzy logic controlling method for air conditioner |
| JP2001334820A (en) * | 2000-05-29 | 2001-12-04 | Denso Corp | Vehicle air conditioner |
| CN203404890U (en) * | 2013-06-09 | 2014-01-22 | 上海荣孚科技发展有限公司 | Neural network-controlled dual-temperature-zone automobile air conditioner control system |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108674121A (en) * | 2018-03-30 | 2018-10-19 | 温州长江汽车电子有限公司 | A kind of the multi-temperature zone vehicle interior temperature control system and its control method of riding vehicle |
| CN109435630A (en) * | 2018-11-15 | 2019-03-08 | 无锡英捷汽车科技有限公司 | A kind of crew module's temprature control method based on artificial neural network algorithm |
| CN109435630B (en) * | 2018-11-15 | 2020-12-29 | 无锡英捷汽车科技有限公司 | Passenger compartment temperature control method based on artificial neural network algorithm |
| CN110070170A (en) * | 2019-05-23 | 2019-07-30 | 福州大学 | PSO-BP neural network sensor calibrating system and method based on MCU |
| CN113978202A (en) * | 2021-11-12 | 2022-01-28 | 上汽通用五菱汽车股份有限公司 | Vehicle-mounted air conditioner adjusting method, vehicle and computer-readable storage medium |
| CN113978202B (en) * | 2021-11-12 | 2024-05-28 | 上汽通用五菱汽车股份有限公司 | Vehicle-mounted air conditioner adjusting method, vehicle and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104875577B (en) | 2019-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104875577A (en) | All-condition double-area temperature calibration method and automobile air conditioner control system | |
| US8364318B2 (en) | Demand control ventilation with fan speed control | |
| CN102022802B (en) | Method for controlling air conditioner | |
| US8463444B2 (en) | Environment control system | |
| CN103042895B (en) | Method for controlling outlet air temperature of automobile air conditioner | |
| TW200801402A (en) | Air conditioning controller | |
| WO2010074430A3 (en) | Air conditioner and method for controlling the same | |
| CN104990207A (en) | Dynamic self-adaptive air conditioner control system | |
| SG136834A1 (en) | A method and apparatus for maintaining air characteristics in an air ventilated facility using fan filter units | |
| KR102017534B1 (en) | Method for regulating the temperature of the interior of a motor vehicle, and associated airconditioning system | |
| CN106853759B (en) | A kind of control method and device of vehicle PTC heating system | |
| CN105022904B (en) | Vehicle ambient temperature calculation method based on Engine Inlet Temperature | |
| WO2008001227A3 (en) | Conveying temperature information in a controlled variable speed heating, ventilation, and air conditioning (hvac) system | |
| CN104589951B (en) | The control method and its control system of air conditioning for automobiles cycle throttle | |
| CN103963598A (en) | Automatic automobile air conditioner control method | |
| JPS5984614A (en) | Dual type car air-conditioner | |
| CN108674121A (en) | A kind of the multi-temperature zone vehicle interior temperature control system and its control method of riding vehicle | |
| WO2019029095A1 (en) | Built-in temperature detecting unit-based automatic vehicle air conditioning control method and controller | |
| JP2012136171A (en) | On-vehicle control system | |
| CN103963597A (en) | Automatic automobile air conditioner controller | |
| CN201779804U (en) | Car air-conditioning temperature control system | |
| CN105172520A (en) | Logic control method used for automatic automobile air conditioner | |
| CN105526679A (en) | Energy-saving control method and device for air conditioner | |
| CN102374603B (en) | Control method for intellectualization space heating air conditioner and system using same | |
| CN202002262U (en) | Automatic temperature controller of automobile air conditioner |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 516006 Guangdong province Huizhou City Zhongkai high tech Zone and five West Road No. 103 Applicant after: HUIZHOU DESAY SV AUTOMOTIVE CO., LTD. Address before: 516006 Guangdong province Huizhou City Zhongkai high tech Zone and five West Road No. 103 Applicant before: Huizhou Desay SV Auto. Electronics Co., Ltd. |
|
| COR | Change of bibliographic data | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |