CN107826027A - Refrigerator car temprature control method and system based on big data analysis - Google Patents

Refrigerator car temprature control method and system based on big data analysis Download PDF

Info

Publication number
CN107826027A
CN107826027A CN201710860576.9A CN201710860576A CN107826027A CN 107826027 A CN107826027 A CN 107826027A CN 201710860576 A CN201710860576 A CN 201710860576A CN 107826027 A CN107826027 A CN 107826027A
Authority
CN
China
Prior art keywords
refrigerator car
temperature
speed
cluster
compressor
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
Application number
CN201710860576.9A
Other languages
Chinese (zh)
Other versions
CN107826027B (en
Inventor
闫伟
魏爱荣
李国祥
王安冉
王浩
任志远
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong University
Original Assignee
Shandong University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shandong University filed Critical Shandong University
Priority to CN201710860576.9A priority Critical patent/CN107826027B/en
Publication of CN107826027A publication Critical patent/CN107826027A/en
Application granted granted Critical
Publication of CN107826027B publication Critical patent/CN107826027B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60PVEHICLES ADAPTED FOR LOAD TRANSPORTATION OR TO TRANSPORT, TO CARRY, OR TO COMPRISE SPECIAL LOADS OR OBJECTS
    • B60P3/00Vehicles adapted to transport, to carry or to comprise special loads or objects
    • B60P3/20Refrigerated goods vehicles
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60HARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
    • B60H1/00Heating, cooling or ventilating [HVAC] devices
    • B60H1/00642Control systems or circuits; Control members or indication devices for heating, cooling or ventilating devices
    • B60H1/00735Control systems or circuits characterised by their input, i.e. by the detection, measurement or calculation of particular conditions, e.g. signal treatment, dynamic models
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60HARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
    • B60H1/00Heating, cooling or ventilating [HVAC] devices
    • B60H1/32Cooling devices
    • B60H1/3204Cooling devices using compression
    • B60H1/3205Control means therefor

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Thermal Sciences (AREA)
  • Mechanical Engineering (AREA)
  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Transportation (AREA)
  • Devices That Are Associated With Refrigeration Equipment (AREA)

Abstract

The invention discloses a kind of refrigerator car temprature control method and system based on big data analysis, the described method comprises the following steps:By the measured data for testing the rotating speed for obtaining the temperature of monitoring point in refrigerator car, refrigerator car outer surface each test point temperature, environment temperature and speed, refrigeration unit compressor and blower fan;Cluster analysis is carried out to the data of acquisition, obtains multiple cluster clusters;Using the multiple cluster cluster as training sample, ellipsoidal unit neutral net is trained as output variable using compressor rotary speed and rotation speed of fan respectively;Compressor rotary speed and rotation speed of fan are controlled in real time based on the ellipsoidal unit neutral net.The present invention can realize that quantitative control, the more traditional rule of thumb regulation and control in real time of refrigerator car temperature are more reasonable.

Description

Refrigerator car temprature control method and system based on big data analysis
Technical field
The present invention relates to refrigeration control field, more particularly to a kind of refrigerator car temprature control method based on big data analysis And system.
Background technology
Biological agent occupies highly important position in people live, and most of biological agent needs low in the process of circulation Temperature refrigeration, biological agent Cold Chain Logistics market are huge.The raising required with people medical security is, it is necessary to which the biology of refrigeration is made The safety problem of agent encounters higher requirement and challenge.The unqualified event of biological agent recurred in recent years allows people Improve vigilant, the Cold Chain Logistics of biological agent are also increasingly taken seriously.Refrigerator car possesses the function of insulation and refrigeration, energy Enough meet the requirement in the short-distance Refrigerated Transport of biological agent, be the key link of its Cold Chain Logistics.Maintain in refrigerator carriage body Portion's temperature is constant, keeps carriage body various places inside to have the less temperature difference, for ensureing that the quality of biological agent in transportation rises Important effect.
In refrigerator car, air enters refrigerator car through evaporator, if the selection of speed of the compressor of refrigeration unit and blower fan It is improper, it can cause to flow through the air velocity of evaporator, temperature can not make the Temperature Distribution in refrigerator car meet to require, influence in-car The quality of biological agent.Therefore, the rotating speed of refrigeration unit compressor and blower fan how is rationally controlled, ensures the temperature in refrigerator car It is the technical problem that those skilled in the art urgently solve at present within the scope of being distributed in reasonably.
The content of the invention
In order to solve the above problems, the present invention provides a kind of refrigerator car temprature control method and system, by each monitoring point temperature Difference, refrigerator car outer surface each point temperature, environment temperature and speed carry out cluster point to a large amount of measured datas as input variable Analysis, it is divided into three kinds of worst hot case, high and cold operating mode and normal temperature operating mode cluster clusters, then using three kinds of cluster clusters as ellipsoidal unit The input of neutral net, using the rotating speed of compressor of air conditioner and blower fan as output variable, ellipsoidal unit neutral net is trained, is obtained The Controlling model of compressor and rotation speed of fan, with this rational control evaporator outlet temperature and wind speed.
To achieve these goals, the present invention adopts the following technical scheme that:
A kind of refrigerator car temprature control method, comprises the following steps:
Step 1:The temperature of monitoring point, each test point temperature in refrigerator car outer surface, environment in refrigerator car are obtained by testing The measured data of the rotating speed of temperature and speed, refrigeration unit compressor and blower fan;
Step 2:Cluster analysis is carried out to the data of acquisition, obtains n cluster cluster;
Step 3:Using n cluster cluster as training sample, become respectively using compressor rotary speed and rotation speed of fan as output Amount training ellipsoidal unit neutral net;
Step 4:Compressor rotary speed and rotation speed of fan are controlled in real time based on the ellipsoidal unit neutral net.
Further, the step 2 is clustered using c-means clustering algorithms, obtain worst hot case, high and cold operating mode and Three kinds of cluster clusters of normal temperature operating mode.
Further, the step 4 includes:With the temperature of monitoring point, each monitoring point temperature difference, refrigerator car appearance in refrigerator car Face each point temperature, environment temperature and speed are real-time input variable, based on the ellipsoidal unit neutral net, calculate compressor and The rotating speed of blower fan is controlled refrigerator car temperature in real time.
Further, the ellipsoidal unit neutral net is made up of an input layer, a hidden layer and an output layer. Input layer is determined according to the number of input parameter, and hidden layer has 7 implicit nodes, and output layer has 1 output node.Input Node and 7 implicit nodes are all attached and connection weight is 1, deviation 0, imply node also by the side connected entirely Formula is connected with output node.
Further, any one input variable x ∈ RdGaussian probability-density function form be expressed asWherein πkFor hybrid weight, and meet πk=1 and πk >=0, ckAnd ΣkRespectively d dimension gaussian densities p (x | θk) center vector and full covariance matrix, parameter set θ={ π1,…πk, c1,…ck1,…,Σk}。
According to another object of the present invention, present invention also offers a kind of refrigerator car temperature control system, including:Data are adopted Acquisition means, computing device and controller, the computing device include memory, processor and storage on a memory and can be The computer program run on processor, it is characterised in that realize following steps during the computing device described program:
Receive temperature, each test point temperature in refrigerator car outer surface, the environment temperature of monitoring point in the refrigerator car that experiment obtains With the measured data of the rotating speed of speed, refrigeration unit compressor and blower fan;
Cluster analysis is carried out to the data of acquisition, obtains multiple cluster clusters;
Using the multiple cluster cluster as training sample, output variable is used as using compressor rotary speed and rotation speed of fan respectively Train ellipsoidal unit neutral net;
Receive outside the temperature, each monitoring point temperature difference, refrigerator car of monitoring point in the refrigerator car that data acquisition device obtains in real time Surface each point temperature, environment temperature and speed, as real-time input variable, based on the ellipsoidal unit neutral net, calculate pressure The rotating speed of contracting machine and blower fan is simultaneously sent to controller;
The controller is controlled refrigerator car temperature in real time based on the compressor and the rotating speed of blower fan received.
Further, the data acquisition device includes being laid in multiple temperature sensors inside and outside refrigerator car.
The step 2 is clustered using c-means clustering algorithms, obtains worst hot case, high and cold operating mode and normal temperature operating mode Three kinds of cluster clusters.
Further, the ellipsoidal unit neutral net is made up of an input layer, a hidden layer and an output layer; Input layer is determined according to the number of input parameter, and hidden layer has 7 implicit nodes, and output layer has 1 output node.Input Node and 7 implicit nodes are all attached and connection weight is 1, deviation 0, imply node also by the side connected entirely Formula is connected with output node.
Further, any one input variable x ∈ RdGaussian probability-density function form be expressed asWherein πkFor hybrid weight, and meet πk=1 and πk >=0, ckAnd ΣkRespectively d dimension gaussian densities p (x | θk) center vector and full covariance matrix, parameter set θ={ π1,…πk, c1,…ck1,…,Σk}。
Beneficial effects of the present invention:
1st, the present invention is from compressor and rotation speed of fan control refrigerator car temperature, by it with refrigerator car surfaces externally and internally temperature, Environment temperature and speed founding mathematical models, can be according to data such as the refrigerator car internal and external temperature obtained in real time and speeds, to temperature Degree carries out quantitative real-time control, and on the one hand more traditional rule of thumb regulation and control are more reasonable, reduce and cause because lacking experience Improperly situation, another aspect, real-time auto-control save manual labor for control.
2nd, the present invention is in the temperature acquisition to refrigerator car, in addition to the temperature inside and outside collection refrigerator car, also goods in the car The diverse location arrangement temperature sensor of thing, to the deployment scenarios of goods in reaction cabin so that the control of temperature is more reasonable.
3rd, the present invention neural network model training before carried out cluster analysis first, using the result of cluster analysis as The training data of neural network model, improve neural metwork training efficiency.
Brief description of the drawings
Fig. 1 is the flow chart of refrigerator car temprature control method of the present invention;
Fig. 2 arranges for observation station of the present invention, wherein point layout when 2 (a) is empty wagons;On goods when 2 (b) is loading Point layout;
Fig. 3 is the schematic diagram that the present invention trains ellipsoidal unit neutral net using compressor rotary speed as output variable;
Fig. 4 is the schematic diagram that the present invention trains ellipsoidal unit neutral net using rotation speed of fan as output variable.
Embodiment
The invention will be further described with embodiment below in conjunction with the accompanying drawings.
It is noted that described further below is all exemplary, it is intended to provides further instruction to the application.It is unless another Indicate, all technologies used herein and scientific terminology are with usual with the application person of an ordinary skill in the technical field The identical meanings of understanding.
It should be noted that term used herein above is merely to describe embodiment, and be not intended to restricted root According to the illustrative embodiments of the application.As used herein, unless the context clearly indicates otherwise, otherwise singulative It is also intended to include plural form, additionally, it should be understood that, when in this manual using term "comprising" and/or " bag Include " when, it indicates existing characteristics, step, operation, device, component and/or combinations thereof.
In the case where not conflicting, the feature in embodiment and embodiment in the application can be mutually combined.
Embodiment one
The purpose of the present embodiment is to provide a kind of refrigerator car temprature control method.
Based on above-mentioned purpose, a kind of refrigerator car temprature control method is present embodiments provided, as shown in figure 1, including following Step:
Step 1:Obtain and the temperature of monitoring point in refrigerator car, refrigerator car outer surface each point temperature, environment are obtained by experiment A large amount of measured datas of the rotating speed of temperature and speed, refrigeration unit compressor and blower fan.
The temperature of monitoring point, refrigerator car outer surface each point temperature and environment temperature are gathered by temperature sensor in refrigerator car Obtained data, and upload in deposit portable computer.
The arrangement of temperature sensor is as shown in Fig. 2 wherein, such as Fig. 2 (a) is arranged in the inside and outside monitoring point of refrigerator car, cold When hiding arrangement of goods on car, on goods shown in arrangement such as Fig. 2 (b) of monitoring point, by entering trip temperature to each position of goods Monitoring, to react the deployment scenarios of goods.Each monitoring point temperature difference is refrigerator car inner sensor maximum temperature point and minimum temperature point The temperature difference;Environment temperature is measured by car temperature outside sensor.
Step 2:Cluster analysis is carried out to the data of acquisition, obtains multiple cluster clusters.
Cluster analysis is a kind of by physics or abstract object, the side for making a distinction and classifying according to the similitude between object Method.People can determine " core " (i.e. cluster centre) first, then arrive the object " attraction " of surrounding when implementing cluster behavior Should be around " core ", the characteristics of so as to complete cluster process.
The present embodiment is using c-means clustering algorithms to each monitoring point temperature, each monitoring point temperature difference, refrigerator car in refrigerator car Outer surface each point temperature, environment temperature and speed are clustered, and obtain three kinds of worst hot case, high and cold operating mode and normal temperature operating mode clusters Cluster.
Before cluster, because the unit of use is different, differs greatly, first had to at data between the order of magnitude Reason, makes its standardization, specific standardized method is:Subtract the minimum value of codomain, then divided by codomain section.
Determine data setC cluster centre ck(k=1,2 ..., K), passes throughCalculate c-th of cluster DkCovariance matrix, this control strategy c=3.
Step 3:Using the multiple cluster cluster as training sample, become using compressor rotary speed and rotation speed of fan as output Amount training ellipsoidal unit neutral net.
By the measured datas of worst hot case, high and cold operating mode and three kinds of normal temperature operating mode cluster cluster, as neutral net Training sample.That is, with the temperature of monitoring point, each monitoring point temperature difference, refrigerator car outer surface each point temperature, environment temperature in refrigerator car Degree and speed are input variable, are respectively trained using compressor rotary speed and rotation speed of fan and are used as the ellipsoidal unit nerve net of output variable Network model.
Temperature Distribution in refrigerator car is mainly influenceed by the temperature and speed of the cold air for entering refrigerator car, and is entered cold The temperature and speed for hiding the cold air of car are determined that refrigeration unit includes refrigeration compressor, cold by the rotating speed of refrigeration unit and blower fan The parts such as condenser, choke valve (or expansion valve) and evaporator, therefore the present embodiment is using the rotating speed of compressor and blower fan as output Variable, by controlling the rotating speed of compressor and blower fan to control refrigeration vehicle interior temperature.Fig. 3 is to be used as output variable using compressor rotary speed Train the schematic diagram of ellipsoidal unit neutral net;Fig. 4 is that ellipsoidal unit neutral net is trained using rotation speed of fan as output variable Schematic diagram.
Ellipsoidal unit network mode is a kind of feedforward neural network, and the three-layer network of ellipsoidal unit is used by hidden node Network is formed, and each input node to each implicit node is connected by two weights, represents super ellipsoids unit respectively in the input space Center and semi-major axis in each dimension, but each hidden node is not shared for all output nodes, and only with corresponding pattern class Other output node connection.If pattern to be sorted similar to singlet Gaussian Profile or approximate Gaussian distribution, network can only by Input layer and output layer are formed, and output layer uses ellipsoidal unit.
The ellipsoidal unit neutral net of the present embodiment is made up of an input layer, a hidden layer and an output layer.It is defeated Enter node layer number to be determined according to the number of input parameter, hidden layer there are 7 implicit nodes, and output layer has 1 output section Point.Input node is all attached with 7 implicit nodes and connection weight is 1, deviation 0, implies node also by complete The mode of connection is connected with output node.
Using kernel function of the Gaussian probability-density function as ellipsoidal unit neutral net.Any one input variable x ∈ RdGaussian probability-density function form be expressed as Wherein πkFor hybrid weight, and meet πk=1 and πk>=0, ckAnd ΣkRespectively d dimension gaussian densities p (x | θk) center vector and Full covariance matrix, parameter set θ={ π1,…πk,c1,…ck1,…,Σk}。
Step 4:Compressor rotary speed and rotation speed of fan are controlled in real time based on the ellipsoidal unit neutral net.
With the temperature of monitoring point, each monitoring point temperature difference, refrigerator car outer surface each point temperature, environment temperature and car in refrigerator car Speed is real-time input variable, by the ellipsoidal unit neuron models of training, calculates the rotating speed of compressor and blower fan, realizes cold Hide the temperature control of car.
Embodiment two
The purpose of the present embodiment is to provide a kind of refrigerator car temperature control system.
Based on object above, a kind of refrigerator car temperature control system is present embodiments provided, including:Data acquisition device, Computing device and controller, the computing device include memory, processor and storage on a memory and can be in processors The computer program of upper operation, it is characterised in that realize following steps during the computing device described program:
Receive temperature, each test point temperature in refrigerator car outer surface, the environment temperature of monitoring point in the refrigerator car that experiment obtains With the measured data of the rotating speed of speed, refrigeration unit compressor and blower fan;
Cluster analysis is carried out to the data of acquisition, obtains multiple cluster clusters;
Using the multiple cluster cluster as training sample, output variable is used as using compressor rotary speed and rotation speed of fan respectively Train ellipsoidal unit neutral net;
Receive outside the temperature, each monitoring point temperature difference, refrigerator car of monitoring point in the refrigerator car that data acquisition device obtains in real time Surface each point temperature, environment temperature and speed, as real-time input variable, based on the ellipsoidal unit neutral net, calculate pressure The rotating speed of contracting machine and blower fan is simultaneously sent to controller;
The controller is controlled refrigerator car temperature in real time based on the compressor and the rotating speed of blower fan received.
Wherein, the data acquisition device includes being laid in multiple temperature sensors inside and outside refrigerator car.
The step 2 is clustered using c-means clustering algorithms, obtains worst hot case, high and cold operating mode and normal temperature operating mode Three kinds of cluster clusters.
The ellipsoidal unit neutral net is made up of an input layer, a hidden layer and an output layer;Input layer root It is determined according to the number of input parameter, hidden layer there are 7 implicit nodes, and output layer has 1 output node.Input node and 7 Individual implicit node is all attached and connection weight is 1, deviation 0, and implicit node is also by the mode that connects entirely and defeated Egress is connected.
Any one input variable x ∈ RdGaussian probability-density function form be expressed asWherein πkFor hybrid weight, and meet πk=1 and πk >=0, ckAnd ΣkRespectively d dimension gaussian densities p (x | θk) center vector and full covariance matrix, parameter set θ={ π1,…πk, c1,…ck1,…,Σk}。
The present invention is from compressor and rotation speed of fan control refrigerator car temperature, by itself and refrigerator car surfaces externally and internally temperature, ring Border temperature and speed founding mathematical models, can be according to data such as the refrigerator car internal and external temperature obtained in real time and speeds, to temperature Quantitative real-time control is carried out, on the one hand more traditional rule of thumb regulation and control are more reasonable, reduce and cause control because lacking experience Improperly situation, another aspect, real-time auto-control save manual labor to system.
It will be understood by those skilled in the art that above-mentioned each module of the invention or each step can use general computer Device realizes that alternatively, they can be realized with the program code that computing device can perform, it is thus possible to they are deposited Storage performed in the storage device by computing device, either they are fabricated to respectively each integrated circuit modules or by it In multiple modules or step be fabricated to single integrated circuit module to realize.The present invention is not restricted to any specific hardware With the combination of software.
Although above-mentioned the embodiment of the present invention is described with reference to accompanying drawing, model not is protected to the present invention The limitation enclosed, one of ordinary skill in the art should be understood that on the basis of technical scheme those skilled in the art are not Need to pay various modifications or deformation that creative work can make still within protection scope of the present invention.

Claims (10)

1. a kind of refrigerator car temprature control method, it is characterised in that comprise the following steps:
Step 1:Temperature, each test point temperature in refrigerator car outer surface, the environment temperature of monitoring point in refrigerator car are obtained by testing With the measured data of the rotating speed of speed, refrigeration unit compressor and blower fan;
Step 2:Cluster analysis is carried out to the data of acquisition, obtains multiple cluster clusters;
Step 3:Using the multiple cluster cluster as training sample, become respectively using compressor rotary speed and rotation speed of fan as output Amount training ellipsoidal unit neutral net;
Step 4:Compressor rotary speed and rotation speed of fan are controlled in real time based on the ellipsoidal unit neutral net.
2. a kind of refrigerator car temprature control method as claimed in claim 1, it is characterised in that the step 2 uses c-means Clustering algorithm is clustered, and obtains three kinds of worst hot case, high and cold operating mode and normal temperature operating mode cluster clusters.
3. a kind of refrigerator car temprature control method as claimed in claim 1, it is characterised in that the step 4 includes:With refrigeration The temperature of in-car monitoring point, each monitoring point temperature difference, refrigerator car outer surface each point temperature, environment temperature and speed become for input in real time Amount, based on the ellipsoidal unit neutral net, the rotating speed for calculating compressor and blower fan is controlled refrigerator car temperature in real time.
A kind of 4. refrigerator car temprature control method as claimed in claim 1, it is characterised in that the ellipsoidal unit neutral net It is made up of an input layer, a hidden layer and an output layer;Input layer is determined according to the number of input parameter, is implied Layer has 7 implicit nodes, and output layer has 1 output node;Input node is all attached with 7 implicit nodes and connection weight It is 1 again, deviation 0, implicit node is connected also by the mode connected entirely with output node.
A kind of 5. refrigerator car temprature control method as claimed in claim 1, it is characterised in that any one input variable x ∈ Rd Gaussian probability-density function form be expressed asIts Middle πkFor hybrid weight, and meet πk=1 and πk>=0, ckAnd ΣkRespectively d dimension gaussian densities p (x | θk) center vector and complete Covariance matrix, parameter set θ={ π1,…πk,c1,…ck1,…,Σk}。
A kind of 6. refrigerator car temperature control system, it is characterised in that including:Data acquisition device, computing device and controller, institute The computer program that computing device includes memory, processor and storage on a memory and can run on a processor is stated, Characterized in that, realize following steps during the computing device described program:
Receive temperature, refrigerator car outer surface each test point temperature, environment temperature and the car of monitoring point in the refrigerator car that experiment obtains The measured data of the rotating speed of speed, refrigeration unit compressor and blower fan;
Cluster analysis is carried out to the data of acquisition, obtains multiple cluster clusters;
Using the multiple cluster cluster as training sample, trained respectively using compressor rotary speed and rotation speed of fan as output variable Ellipsoidal unit neutral net;
Receive the temperature, each monitoring point temperature difference, refrigerator car outer surface of monitoring point in the refrigerator car that data acquisition device obtains in real time Each point temperature, environment temperature and speed, as real-time input variable, based on the ellipsoidal unit neutral net, calculate compressor With the rotating speed of blower fan and send to controller;
The controller is controlled refrigerator car temperature in real time based on the compressor and the rotating speed of blower fan received.
7. a kind of refrigerator car temperature control system as claimed in claim 5, it is characterised in that the data acquisition device includes The multiple temperature sensors being laid in inside and outside refrigerator car.
8. a kind of refrigerator car temprature control method as claimed in claim 5, it is characterised in that the step 2 uses c-means Clustering algorithm is clustered, and obtains three kinds of worst hot case, high and cold operating mode and normal temperature operating mode cluster clusters.
A kind of 9. refrigerator car temprature control method as claimed in claim 5, it is characterised in that the ellipsoidal unit neutral net It is made up of an input layer, a hidden layer and an output layer;Input layer is determined according to the number of input parameter, is implied Layer has 7 implicit nodes, and output layer has 1 output node;Input node is all attached with 7 implicit nodes and connection weight It is 1 again, deviation 0, implicit node is connected also by the mode connected entirely with output node.
A kind of 10. refrigerator car temprature control method as claimed in claim 5, it is characterised in that any one input variable x ∈ RdGaussian probability-density function form be expressed as Wherein πkFor hybrid weight, and meet πk=1 and πk>=0, ckAnd ΣkRespectively d dimension gaussian densities p (x | θk) center vector and Full covariance matrix, parameter set θ={ π1,…πk,c1,…ck1,…,Σk}。
CN201710860576.9A 2017-09-21 2017-09-21 Refrigerator car temprature control method and system based on big data analysis Active CN107826027B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710860576.9A CN107826027B (en) 2017-09-21 2017-09-21 Refrigerator car temprature control method and system based on big data analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710860576.9A CN107826027B (en) 2017-09-21 2017-09-21 Refrigerator car temprature control method and system based on big data analysis

Publications (2)

Publication Number Publication Date
CN107826027A true CN107826027A (en) 2018-03-23
CN107826027B CN107826027B (en) 2019-09-03

Family

ID=61643946

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710860576.9A Active CN107826027B (en) 2017-09-21 2017-09-21 Refrigerator car temprature control method and system based on big data analysis

Country Status (1)

Country Link
CN (1) CN107826027B (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108773315A (en) * 2018-05-25 2018-11-09 天津商业大学 Intelligent temperature control refrigerator car based on real-time weather information
CN109050200A (en) * 2018-08-22 2018-12-21 吉林大学 A kind of control method of automobile heat pump air conditioner
CN110481412A (en) * 2019-08-26 2019-11-22 山东大学 A kind of refrigerator carriage and refrigerator car with temperature field dynamic regulation function
CN111196119A (en) * 2018-11-16 2020-05-26 比亚迪股份有限公司 Method and device for controlling air conditioner on vehicle
CN111207498A (en) * 2019-12-27 2020-05-29 广东美的白色家电技术创新中心有限公司 Air conditioner, control method thereof, server, and computer-readable storage medium
CN111660755A (en) * 2019-12-04 2020-09-15 摩登汽车有限公司 Control method and device of automobile air conditioner, vehicle control unit and automobile
CN114996661A (en) * 2022-08-04 2022-09-02 山东佳力通汽车有限公司 Refrigerator car temperature monitoring method and system
KR102471478B1 (en) * 2022-07-27 2022-11-28 주식회사 로드맵 How to reserve the operation of the freezer of the delivery vehicle for cold chain

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH11294923A (en) * 1998-04-08 1999-10-29 Mitsubishi Heavy Ind Ltd Refrigeration vehicle operation control system and refrigeration vehicle
CN103197538A (en) * 2013-04-24 2013-07-10 中南林业科技大学 Brooder temperature control method based on process neural network
CN104374053A (en) * 2014-11-25 2015-02-25 珠海格力电器股份有限公司 Intelligent control method, device and system
CN105787271A (en) * 2016-02-26 2016-07-20 江苏方天电力技术有限公司 Heat supply unit adjustable power output range evaluation method based on big data analysis technology
CN205853810U (en) * 2016-06-24 2017-01-04 中原工学院 A kind of refrigerator car control system utilizing phase-change material

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH11294923A (en) * 1998-04-08 1999-10-29 Mitsubishi Heavy Ind Ltd Refrigeration vehicle operation control system and refrigeration vehicle
CN103197538A (en) * 2013-04-24 2013-07-10 中南林业科技大学 Brooder temperature control method based on process neural network
CN104374053A (en) * 2014-11-25 2015-02-25 珠海格力电器股份有限公司 Intelligent control method, device and system
CN105787271A (en) * 2016-02-26 2016-07-20 江苏方天电力技术有限公司 Heat supply unit adjustable power output range evaluation method based on big data analysis technology
CN205853810U (en) * 2016-06-24 2017-01-04 中原工学院 A kind of refrigerator car control system utilizing phase-change material

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108773315A (en) * 2018-05-25 2018-11-09 天津商业大学 Intelligent temperature control refrigerator car based on real-time weather information
CN109050200A (en) * 2018-08-22 2018-12-21 吉林大学 A kind of control method of automobile heat pump air conditioner
CN109050200B (en) * 2018-08-22 2020-02-18 吉林大学 Control method of automobile heat pump air conditioner
CN111196119A (en) * 2018-11-16 2020-05-26 比亚迪股份有限公司 Method and device for controlling air conditioner on vehicle
CN110481412A (en) * 2019-08-26 2019-11-22 山东大学 A kind of refrigerator carriage and refrigerator car with temperature field dynamic regulation function
CN111660755A (en) * 2019-12-04 2020-09-15 摩登汽车有限公司 Control method and device of automobile air conditioner, vehicle control unit and automobile
CN111207498A (en) * 2019-12-27 2020-05-29 广东美的白色家电技术创新中心有限公司 Air conditioner, control method thereof, server, and computer-readable storage medium
KR102471478B1 (en) * 2022-07-27 2022-11-28 주식회사 로드맵 How to reserve the operation of the freezer of the delivery vehicle for cold chain
CN114996661A (en) * 2022-08-04 2022-09-02 山东佳力通汽车有限公司 Refrigerator car temperature monitoring method and system

Also Published As

Publication number Publication date
CN107826027B (en) 2019-09-03

Similar Documents

Publication Publication Date Title
CN107826027B (en) Refrigerator car temprature control method and system based on big data analysis
Li et al. Thermal error modeling of machine tool spindle based on the improved algorithm optimized BP neural network
CN105378391B (en) For the on-line optimization scheme of HVAC demand responses
CN109508035B (en) Multi-region hierarchical unmanned aerial vehicle formation path planning method based on distributed control
CN112015174B (en) Multi-AGV motion planning method, device and system
CN109804206A (en) For the controller of operating air conditioning system and the control method of air-conditioning system
CN110866592B (en) Model training method, device, energy efficiency prediction method, device and storage medium
Liu et al. Inverse design of the thermal environment in an airliner cabin by use of the CFD-based adjoint method
CN113791634A (en) Multi-aircraft air combat decision method based on multi-agent reinforcement learning
CN107704875A (en) Based on the building load Forecasting Methodology and device for improving IHCMAC neutral nets
Zeng et al. Modeling for UAV resource scheduling under mission synchronization
CN106499656B (en) A kind of fan wind speed intelligent control method
CN113326651A (en) Refrigerating station load and energy efficiency ratio dynamic modeling method based on T-S fuzzy model
CN106708065A (en) Unmanned aerial vehicle landing control method, device and unmanned aerial vehicle
CN114662201B (en) Optimizing method for intelligent regulation and control of natural ventilation
CN109191049B (en) Logistics transportation supervision system and method based on cloud computing
CN110470033A (en) For controlling the method, apparatus and air-conditioning of air-conditioning
CN109885082A (en) The method that a kind of lower unmanned aerial vehicle flight path of task based access control driving is planned
Cao et al. Autonomous maneuver decision of UCAV air combat based on double deep Q network algorithm and stochastic game theory
CN114444201A (en) Autonomous capability evaluation method of ground attack unmanned aerial vehicle based on Bayesian network
CN105550437A (en) Reverse design method for indoor environment based on genetic algorithm
CN117634295A (en) Aircraft track prediction method based on deep learning
CN113821903A (en) Temperature control method and device, modular data center and storage medium
CN111881993B (en) Operation mode multilayer hierarchical matching optimization method for copper matte converting process
Agarwal et al. Improving energy efficiency in UAV attitude control using deep reinforcement learning

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant