CN103912966A - Optimal control method for ground source heat pump refrigerating system - Google Patents
Optimal control method for ground source heat pump refrigerating system Download PDFInfo
- Publication number
- CN103912966A CN103912966A CN201410125301.7A CN201410125301A CN103912966A CN 103912966 A CN103912966 A CN 103912966A CN 201410125301 A CN201410125301 A CN 201410125301A CN 103912966 A CN103912966 A CN 103912966A
- Authority
- CN
- China
- Prior art keywords
- load
- cooling water
- prediction
- refrigeration
- chilled
- 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
Landscapes
- Air Conditioning Control Device (AREA)
Abstract
The invention relates to an optimal control method for a ground source heat pump refrigerating system and belongs to the field of energy-saving optimal control for air conditioning systems of buildings. Multiple models are optimally combined, as along as a prediction model contains contrasting information of the system, the prediction model can be combined with multiple good prediction models for predicting even if the prediction model is poor in effect, and a predicting character of the system can still be improved; in order to improve final predicting precision, a control system operates a combined predicting method to comprehensively utilize information provided by various methods, loss of useful information caused by a single prediction module is avoided, randomness is reduced, and predicting precision is increased. The optimal value provided by the optimal control method is ensured to meet tail end load requirements and capable of minimizing energy consumption of the system. After the optimal set value is determined, a central refrigerating system of the ground source heat pump refrigerating system is controlled to operate in an optimal set working status.
Description
Technical field
The present invention relates to a kind of earth source heat pump refrigeration system energy conservation optimizing method, belong to the energy saving optimizing control field of air conditioning system.
Background technology
National economy energy resource consumption formation mainly contains industrial energy consumption, traffic energy consumption and building energy consumption, along with moving forward steadily of well-off society of China, the paces of Process of Urbanization Construction also can not be ignored continuing to increase the building energy consumption problem of bringing in this, and building energy consumption 2/3rds be air-conditioning system power consumption, account at building energy consumption under the ever-increasing present situation of ratio of whole energy resource consumption, the air conditioner system energy saving in building has become emphasis and the focus in energy-saving field.In the today of advocating energetically green low-carbon life, the dynamics that strengthens air conditioner energy saving has huge practical significance undoubtedly to saving the energy, ground source heat pump technology is the energy-saving building technology that country widelys popularize in recent decades, replace cooling tower equipment with underground pipe compared with traditional air-conditioning system, can make full use of geothermal energy resources, realizing and get heat-obtaining in cold winter summer, is a kind of real green air conditioner technology.
Along with application and the development of building automation system and variable-frequency control technique, automatic control technology is promoted and is come at field of heating ventilation air conditioning gradually, but central air conditioner system be one have time lag, time become, the complication system of non-linear and large inertia, its complexity causes central air conditioner system to be difficult to accurately Mathematical Modeling or method are described, this realizes accurately and controls and bring no small difficulty to control system, still depends on to a great extent labor management in Practical Project; Simultaneously owing to lacking advanced control technology means and equipment, central air conditioner system still adopts traditional labor management mode and easy switching control device mostly, can not realize air conditioner refrigerating and follow the variation of end load and dynamic adjustments, in the time of operation at part load, cause energy waste very large, make energy for building inefficiency, air-conditioning system automaticity is not high, directly has influence on HVAC managerial skills.
On the other hand, realizing refrigeration system running operating point is vital with mating of refrigerating capacity for control system, accomplishes this point, requires control system must take a set of practicable control algolithm as guidance, but in most cases HVAC control system is to utilize certain experience or semiempirical formula to regulate, this method is only the thought based on data fitting, further consider and can find that the coefficient that only utilizes curvilinear regression to obtain refrigeration system Energy Efficiency Ratio and each influence factor is one group of static parameter, in fact refrigeration system Energy Efficiency Ratio not only with some relating to parameters also with other relating to parameters, therefore in fact the parameter in matching relational expression is not changeless but one group of slow time-varying coefficient, under different running statuses, coefficient is different, from the angle of Self Adaptive Control, the semiempirical formula of matching is not also suitable for the inline diagnosis of control system.In addition, whether this empirical equation can disclose the mechanism of action that affects heat pump Energy Efficiency Ratio well, its degree of accuracy not yet have science according to being verified, therefore in actual motion there is very large roughening in the adjusting of heat pump, if system can not be moved under a good operating point, must cause its Energy Efficiency Ratio to be had a greatly reduced quality, be unfavorable for energy-conservation.
In sum, due to central air conditioner system time become behavioral characteristics, traditional Energy Saving Control strategy can not be real-time in refrigeration system running online accumulation and comprehensive relevant information, carry out the control parameter of instant correction or regulating system, more can not make air-conditioning system all the time in optimum or approach optimum duty.
one, the definite background of air-conditioning Real-time Load
The prerequisite that realizes the optimization operation of earth-source hot-pump system is the air conditioner load that control system can be predicted to degree of precision next moment building, quantitatively equates for cold-peace load is cold with assurance system, synchronous on the time.But building air-conditioning load variations has the typical non linear feature of the stochastic behaviours such as dynamic, time variation, the amount of disturbing, uncertainty more, move in advance for ease of control system, must obtain the prediction load value of next moment building, so seek a kind of load forecasting method effectively accurately, the optimization operation and control of air-conditioning system is significant.In actual motion, if the air-conditioning method that load calculates during according to lectotype selection by time load determine, must waste larger manpower and materials, therefore in Engineering Operation, be not used.At present, definite method that is actually a kind of " remedying " of air conditioner load, there is no building enclosure and indoor heat gain from building, the angle of personnel's moisture dispersed amount is considered, but consider from low-temperature receiver side refrigerating capacity, control system by Temperature Humidity Sensor record indoor by time humiture, because the humiture of air-conditioned room has certain allowable fluctuation range, as long as indoor actual humiture is little with setting humiture deviation, just can think that refrigerating capacity meets the air conditioner load in this moment substantially, then the adjusting refrigerating capacity such as compressor that control system acts on pump and main frame makes refrigerating capacity meet room conditioning load, although this means to save the situation meets the requirement of engineering to a certain extent, but the existence of stickiness when this, do not get rid of a certain moment because cold station refrigerating capacity can not meet the phenomenon existence that air conditioner load causes indoor temperature and humidity to fluctuate larger, so or the too high requirement that can not meet comfort level of indoor temperature, the too low waste energy of temperature, be unfavorable for building energy conservation.Further considering, in fact also there is the defect of following 3 aspects in this remedial measure:
1), the accuracy of refrigeration capacity test
Existing cold station refrigerating capacity determines that employing following formula calculates:
if but a certain moment need to open a pump or stop a pump, cause flow to strengthen suddenly or reduce suddenly a lot, must cause temperature to have larger fluctuation, if the moment of temperature test is in the scope of this larger fluctuation, the larger error of the unreasonable existence of calculating that must cause cold, flow sensor reliability for temperature sensor is also poor in addition, and it is very large that the load that profit is calculated in this way may depart from actual value under certain conditions.
2), the equilibrium problem of the refrigerating capacity of cold machine and the chilling requirement of end
Even if the result of cold test is more accurate, the refrigerating capacity of cold machine and mating of chilling requirement are also very large problems: if supply water temperature fixes on setting value, chilled-water flow is enough large, this just shows that current refrigerating capacity can meet the requirement of building end, therefore the actual cold of measuring is chilling requirement, when supply water temperature higher than setting value or supply backwater temperature difference bigger than normal, when flow is lower, the very possible current cold providing is lower than the cold of needs, building does not reach the operating mode needing, but may be also that system is in suitable running status, how differentiation is enough and inadequate, only be often difficult to judge according to water temperature and the flow of the test of cold station.
3), " remedy " adjusting and lack theoretical foundation
Control system, by test indoor temperature and humidity, determines increasing or the minimizing of cold, current owing to lacking certain adjusting foundation, often human factor is larger, regulate by the unlatching of hand control pump or the start and stop of main frame etc., because control algolithm is indefinite, control ratio is more coarse.
two, the background that refrigeration system optimization of operating parameters regulates
Central refrigerating system comprises three subsystems, i.e. refrigerator system, the cooling water system chilled water system of unifying.These three subsystems all consume certain energy in the time of operation, between them, influence each other, and interact.Conventionally in the time that the energy consumption of a subsystem reduces, the energy consumption of another subsystem will increase.And the recruitment of a sub-system energy consumption is also not equal to the reduction of another subsystem energy consumption conventionally.Relation between the two constantly changes with the variation of operating condition.Therefore, the target that whole central refrigerating system is optimized is not to make the wherein power consumption minimum of some single subsystems, but makes the total power consumption minimum of whole system.In the time adopting system optimization method, the operation of whole central refrigerating system must be regarded as to an overall coordination process.The basic thought of system optimization is meeting under given operating mode (prerequisite of all end workload demands) exactly, makes the total energy consumption minimum of above-mentioned three subsystems,
In actual applications, subsystems is carried out to Performance Evaluation more difficult.This be because subsystems be coupling rather than independently, the task of therefore refrigeration system operational factor being optimized to control comprise following some:
1), determine building refrigeration duty and associated external environment;
2), determine the performance of refrigeration unit;
3), the optimal setting of identification and definite control variables, these optimal settings should make the energy consumption minimum of whole system;
4), control system and subsystem operate in the adjusting of Optimal Setting value;
For a certain specific system, the main task of carrying out system optimization comprises and finds optimum cooling water to enter coolant-temperature gage, chilled water temperature, the load sharing rate of cooling water flow, chilled-water flow, conveying equipment etc.These optimal values are being guaranteed to meet under the prerequisite of end workload demand, make the energy consumption minimum of system.After optimal setting is determined, control system central refrigerating system operates in optimum setting operating mode.
Should be noted that, these optimal settings are not invariable, but along with the variation of building load and operating condition (as performance of outdoor temperature humidity and each subsystem etc.) and realize Optimized Matching.All of these factors taken together will make on-line optimization control become in practice more difficult.
In addition because whole refrigeration system intercouples, refrigeration system is optimized just must be by whole system closed-Loop Analysis, some subsystems can not be departed to entirety analyzes separately, this close coupling makes the first step of optimal control work be difficult to find breach just, thereby has brought very large difficulty to the optimal control of refrigeration system.But in refrigeration system, the power consumption of unit accounts for the overwhelming majority, the correlation maximum of the Energy Efficiency Ratio of cold source system and unit, therefore the operational energy efficiency of unit ratio reaches optimum, and it is optimum that the Energy Efficiency Ratio of whole system also reaches substantially, therefore can be from refrigeration unit, the breach of the work that is optimized.
Summary of the invention
The deficiency existing for existing refrigeration system energy-saving control method, the present invention proposes a kind of intelligent optimized control method for earth source heat pump refrigeration system.Basic thought of the present invention is, on automatic building control system Lon-works platform, carry out secondary development and realize the integrated of single-chip microcomputer Lon-works, Single-chip Controlling language adopts MATLAB to write, single-chip microcomputer is as one-level control module, comprise that Air-conditioning Load Prediction module and refrigeration system optimization of operating parameters arrange module, Lon-works realizes the real-time control of the collection of refrigeration system real-time running state data and the transmission of one-level control signal and refrigeration system related hardware equipment as secondary control module, assurance system quantitatively equates for cold-peace load is cold on the one hand, synchronous on time, make on the other hand control system to carry out dynamic adjustments to each parametric variable of refrigeration system in advance, guarantee that refrigeration system is all the time in optimum or approach optimum duty.
Realizing refrigeration system optimum control is given with air conditioner load in the situation that, and it is system operation optimum operating condition point that control system provides one group of optimized parameter, and under this group parameter, the Energy Efficiency Ratio COP value of system operation is maximum.In actual motion, because the thermal inertia of building, the factor such as variation aperiodic and solar radiation of outside air temperature are not to occur immediately, but lag behind a period of time, therefore the humiture for guaranteeing that air-conditioning system requires, thermal source (low-temperature receiver) by time heat supply (cold) amount be a kind of amount of dynamic change, in order to realize better heat (cold) as required, must be by dynamic methods analyst thermodynamic status, and cold supply system is carried out to dynamic adjustments by the method for Prediction Parameters.Therefore, control system realize the prerequisite of optimum control be prediction air conditioner load so that inline diagnosis.Then the optimization that completes refrigeration system running state parameter regulates.
Aspect Air-conditioning Load Prediction, due to the variation of air conditioner load and external environment, in disturb and the factor analysis such as the thermal inertia of building, but being difficult to find affects mechanism.Building load Forecasting Methodology is a lot, and the condition of each self application is different with feature, in one period, building load has the feature of this kind of model sometimes, sometimes there is the feature of another kind of model, sometimes both have both, so just several models can be optimized to combination, even the forecast model of a poor effect, as long as it is containing systematic opposition information, when itself and one and several good forecast models carry out after associated prediction, still can improve the prediction characteristic of system, for improving final precision of prediction, the information that control system uses combination forecasting method comprehensive utilization the whole bag of tricks to provide, avoid Individual forecast model to lose Useful Information, reduce randomness, improve precision of prediction.Based on the pluses and minuses of various forecast models, select Intelligent Forecasting: grey forecasting model, GRNN neural network prediction and LSSVM prediction, finally use method-grey data integration technology of Optimal Combination Forecasting to merge predicting the outcome of these four kinds of forecast models and obtain final Air-conditioning Load Prediction value.
Aspect the adjusting of refrigeration system optimization of operating parameters, because the factor of refrigeration system running performance parameters mainly contains following 6: the refrigerating capacity of handpiece Water Chilling Units, chilled water outlet temperature, cooling water inlet temperature, cooling water flow, chilled-water flow, the load sharing rate of equipment group, for the whole refrigeration system of earth source heat pump, the equipment group here, except unit, also has cooling water pump, the equipment such as chilled water pump, load sharing rate determine and the sample properties curve of equipment has very large associated, for unit, the meaning of sharing of load is in overall refrigerating effect one its total power consumption minimum of timing, for water pump, due to they be responsible for be the conveying of the water yield, and the factor that affects their power consumption is this factor of flow, so, the total flow sizes that obtain conveying to the prerequisite of these equipment optimization controls, after flow is determined, can determine according to the sample curve of equipment the load sharing rate of each equipment, realization complete certain flow carry task and equipment total power consumption minimum.
Therefore in the time that whole refrigeration system is optimized, can carry out in two steps:
, according to air-conditioning total load, determine corresponding cooling water (chilled water) flow and (cooling water inlet, chilled water outlet) temperature meeting under the optimum COP prerequisite of refrigeration unit, complete first step optimization.
, complete the load sharing rate of refrigeration unit according to total refrigerating capacity, determine its load sharing rate according to total flow by water pump curve, and then the final optimization of completion system.
Technical scheme of the present invention is: a kind of earth source heat pump refrigeration system optimal control method, and specific implementation step is as follows:
The first step, along with the operation of refrigeration system, Lon-works control platform constantly gathers the operational factor of refrigeration unit, the dimensionless number adopting according to Jitian's function model is according to processing form, refrigeration unit Energy Efficiency Ratio, refrigerating capacity, cooling water flow, chilled-water flow, cooling water inlet temperature, chilled water outlet temperature are carried out respectively to nondimensionalization processing, constantly expand refrigeration unit runtime database;
Second step, use three kinds of Intelligent Forecastings: air conditioner load is predicted respectively in gray scale prediction, generalized regression nerve networks prediction, least square method supporting vector machine prediction, for the mutual supplement with each other's advantages feature of three kinds of forecast models, use grey data Fusion Model to integrate predicting the outcome of three kinds of models and obtain the predicted value of air conditioner load, reach the object of the relatively accurate prediction of air conditioner load.
The 3rd step, the least square method that utilization is forgotten with index is carried out the auto-adapted fitting of coefficient to the refrigeration unit Energy Efficiency Ratio empirical equation based on Jitian's function model, realize the object that empirical equation coefficient is dynamically adjusted, the principle equating in synchronous number in time according to refrigerating capacity and air conditioner load, refrigerating capacity in Jitian's function model is substituted with the air conditioner load of prediction, to the relation of accurate description refrigeration unit Energy Efficiency Ratio and cooling water flow, chilled-water flow, cooling water inlet temperature, 4 parameters of chilled water outlet temperature under certain refrigerating capacity.
The 4th step, utilize extremum principle, Jitian's function model is carried out to partial derivative calculating to 4 parameters (cooling water flow, chilled-water flow, cooling water inlet temperature, chilled water outlet temperature), and 4 equation group that simultaneous obtains obtain next moment refrigeration unit and approach 4 optimum operational factor operating points.
The 5th step, use simplex method to carry out the optimal combinatorial search of 4 parameters of refrigeration unit, the generalized regression nerve networks for evaluation function (GRNN) adopting in simplex method is calculated, (cooling water flow and cooling water inlet temperature are merged into a main gene to three main genes that are input as of GRNN neutral net, chilled-water flow is a main gene, chilled water outlet temperature is a main gene), neutral net is output as refrigeration unit Energy Efficiency Ratio.
The 6th step, carries out the optimization of other operational factors of refrigeration system: the unlatching number of units of refrigeration unit, cooling water pump and cooling water pump and rate of load condensate are distributed.
The 7th step, according to the optimized operation parameter combinations of next moment refrigeration system, controls in advance to each parametric variable, and when guaranteeing that moment to be measured arrives, refrigeration system is in optimum duty.
Accompanying drawing explanation
Fig. 1 is Lon-works and the integrated control principle drawing of single-chip microcomputer in earth source heat pump refrigeration system;
Fig. 2 is the data acquisition of Lon-works monitor supervision platform and control signal transmission system figure;
Fig. 3 is earth source heat pump refrigeration system control flow chart;
Fig. 4 be earth-source hot-pump system flow Single-chip Controlling basic circuit diagram (this caption: if the flow after optimizing be greater than measured discharge flow indicator for red, and strengthen total water current amount; Otherwise be green, reduce total water current amount);
Fig. 5 is that earth-source hot-pump system load rate of plant distributes single-chip microcomputer control principle circuit diagram (this caption: the equipment group here refers to main frame and cooling water pump, chilled water pump.What in the time that equipment is water pump, relay drove is the water knockout drum between main frame and water pump; In the time that equipment is main frame, what relay drove is the compressor of main frame);
Fig. 6 is based on GRNN neutral net Air-conditioning Load Prediction schematic diagram (this caption: in a hour, sampling time interval is 10 minutes, relevant parameter sequence is 6);
Fig. 7 is four operational factor principal component analysis flow charts of refrigeration unit;
Fig. 8 is based on GRNN neural computing refrigeration unit Energy Efficiency Ratio schematic diagram;
Fig. 9 is 4 the optimization of operating parameters flow charts of refrigeration unit based on simplex method;
Figure 10 is principle of genetic algorithm figure;
Figure 11 is genetic algorithm chromosome coding mode;
Figure 12 is the genetic algorithm chromosome code segment data region of search;
Figure 13 is that refrigeration plant operation number of units and the rate of load condensate based on Genetic Simulated Annealing Algorithm distributed global optimization flow chart.
The specific embodiment
Below in conjunction with accompanying drawing, the specific embodiment of the present invention being carried out to system explains.
With reference to accompanying drawing 1, a kind of earth source heat pump refrigeration system optimal control method of the present invention mainly comprises following step:
Step 1, along with the operation of refrigeration system, Lon-works controls platform and constantly gathers the operational factor of refrigeration unit: refrigeration unit Energy Efficiency Ratio, refrigerating capacity, cooling water flow, chilled-water flow, cooling water inlet temperature, chilled water outlet temperature, refrigeration unit open number of units and rate of load condensate, chilled water pump are opened number of units and rate of load condensate, cooling water pump are opened number of units and rate of load condensate.
Refrigeration unit Energy Efficiency Ratio, refrigerating capacity, cooling water flow, chilled-water flow, cooling water inlet temperature, chilled water outlet temperature are carried out respectively to nondimensionalization processing, constantly expand refrigeration unit runtime database;
，
，
，
，
chilled water outlet temperature,
cooling water inlet temperature;
chilled-water flow;
refrigeration duty,
cooling water flow, subscript
value while representing this parameter declared working condition;
Step 2, three kinds of Intelligent Forecastings of utilization: air conditioner load is predicted respectively in gray scale prediction, generalized regression nerve networks prediction, least square method supporting vector machine prediction, finally use grey data Fusion Model to integrate predicting the outcome of three kinds of models and obtain the predicted value of air conditioner load, reach the object of relatively accurate prediction air conditioner load.
(1), adopt generalized regression nerve networks (GRNN) carry out Air-conditioning Load Prediction as shown in Figure 6, be described as follows:
1), GRNN neural network structure is input layer, mode layer, summation layer, output layer:
2), the ground floor of network is input layer, neuron number equals the dimension 8 of the input vector of learning sample, each neuron is simple distribution unit, directly input variable is passed to mode layer.
3), input parameter
for upper one hour Indoor Temperature, humidity sequence, upper one hour outdoor temperature humidity sequence, upper one hour occupancy sequence, this time be engraved in time numbering in one day, season type, what day totally 8 parameter, its output
for the air conditioner load in prediction moment, computing formula is:
4), in order to eliminate the inconsistency of different parameters physics dimension, all parameters are all normalized.
5), the second layer of network is mode layer, neuron number equals number of training (the present invention is taken as 500), the weight function of this layer be Euclidean distance function (
), its effect is the weights of computing network input and ground floor
between distance,
for mode layer threshold value.The transfer function of mode layer is RBF
as the transfer function of network,
for the smooth factor.
6), the smooth factor
definite method be: make parameter
with increment
in certain limit
interior incremental variations, here:
Wherein
for each input between sample in learning sample
the minimum of a value of distance;
for calculating the minimum positive number of function identification.In learning sample, remove a sample, by remaining sample architecture generalized regression nerve networks, this sample is estimated, obtain the error between estimated value and sample value; Each sample is repeated to this process, obtains error sequence, the mean-square value by error sequence:
As the evaluation index of network performance, smoothing parameter corresponding minimum error is used for to last GRNN neutral net.
7), the 3rd layer of network be summation layer, the neuron that comprises two types in summation layer, wherein a kind of neuron computes formula
denominator, to all mode layers, arithmetic summation is carried out in neuronic output, the each neuron of mode layer is 1 with these neuronic weights that are connected, its transfer function is:
The molecule neuronic transfer function of suing for peace is
Its weight function is standardization dot product weight function, the vector of computing network
, its each element is by vector
and weight matrix
in the dot product of every row element again divided by vector
each element sum obtain,
8), last one deck of network is linear output layer, by result
offer linear transfer function
, the output of computing network.
9), GRNN neutral net training sample number is determined method:
Training sample number tentatively determines that method is:
Here
for total number of samples, after tentatively determining training sample number, next exist
near value, search for, for each
value is determined training sample number according to the minimum of a value of BIC criterion evaluation index after determining smoothing parameter:
10), GRNN network connects the correction employing BP algorithm of weights.
11), completed after GRNN neural metwork training and just can utilize the ripe neutral net of training to carry out the prediction of air conditioner load.
(2), adopt the concrete grammar of gray scale prediction to be:
1), gray scale prediction adopts gray system theory GM(1,1) forecast model, get the air conditioner load time series (sampling should be carried out every 10 minutes totally 6 groups of data) in last hour of moment of prediction:
, and cumulative time series:
, cumulative time series element
;
2), prediction moment air conditioner load is obtained by following formula:
Wherein, parameter vector
,
,
(3), adopt the concrete grammar of least square method supporting vector machine prediction to be:
1), get the air conditioner load time series (sampling should be carried out every 10 minutes totally 6 groups of data) in last hour of moment of prediction:
,
2), solve following matrix equation:
3), kernel function is taken as Gaussian kernel:
4), least square method supporting vector machine Air-conditioning Load Prediction computing formula is:
Here
for nuclear parameter is taken as 1,
for penalty factor is taken as 50,
for the time numbering of air conditioner load sampling instant in last hour in one day,
during for prediction, be engraved in the time numbering in a day.
(4), the implementation method of grey data fusion method is:
1),
for the air conditioner load value in prediction moment of being obtained by above-mentioned 3 forecast models, define distance between any two values as follows:
，
2), the support function between two data of structure:
；
3), try to achieve matrix
eigenvalue of maximum
, the special syndrome vector corresponding with it
,
Get:
, after fusion, obtain:
be grey data fusion forecasting value.
The least square method that step 3, utilization are forgotten with index is carried out the auto-adapted fitting of coefficient to the refrigeration unit Energy Efficiency Ratio empirical equation based on Jitian's function model.
(1), Jitian's function be one have good recurrence characteristic for describing the empirical model of refrigeration unit Energy Efficiency Ratio COP and refrigerating capacity, cooling water flow, chilled-water flow, cooling water inlet temperature, chilled water outlet temperature, its expression formula is:
Wherein,
for fitting constant.
(2), the definition of the least square method based on forgeing with index residual error
for:
Wherein, forgetting factor is taken as 0.75,
for the actual Energy Efficiency Ratio size of refrigeration unit of nondimensionalization,
for using the actual Energy Efficiency Ratio of refrigeration unit of nondimensionalization of Jitian function model matching.
(3), pass through residual error
right
carrying out respectively partial derivative calculating just can determine not in the same time
, 14 fitting constants in Jitian's function model:
Step 4, to predict that moment air conditioner load is as refrigerant system capacity substitution Jitian function model, according to extremum principle, by Jitian's function model, 4 parameters (cooling water flow, chilled-water flow, cooling water inlet temperature, chilled water outlet temperature) are carried out to partial derivative calculating:
4 equation group that simultaneous obtains obtain 4 operational factor operating points of next moment refrigeration unit near-optimization:
Step 5, uses simplex method to carry out the optimal combinatorial search of 4 parameters of refrigeration unit;
Specifically comprise:
(1), use principal component analytical method to analyze and find main gene 4 parameters (cooling water flow, chilled-water flow, cooling water inlet temperature, chilled water outlet temperature);
In the present invention, 4 parameters relevant to refrigeration unit Energy Efficiency Ratio are carried out to principal component analysis, obtain main gene, with reference to accompanying drawing 7, the concrete grammar of principal component analysis is:
1), 4 parameters (cooling water flow, chilled-water flow, cooling water inlet temperature, chilled water outlet temperature) sample is carried out to standardization, computing formula is:
,
for total sample number;
2), to the sample variable matrix after standardization
carry out again correspondent transform:
By row summation
, by row summation
, summation
.
According to above-mentioned calculating, obtain new matrix after correspondent transform
in element:
In formula,
for the element in raw data matrix;
for the element in the new matrix after conversion;
3), compute matrix
covariance matrix
, matrix in formula
in element
=
.
4), determine characteristic value and the characteristic of correspondence vector thereof of matrix R
The characteristic value of trying to achieve by Jacobi algorithm and characteristic vector, characteristic value is arranged by descending order:
, its characteristic of correspondence vector is
5), calculated factor loading matrix
First calculate the accumulation contribution rate of principal component, when cumulative percentage is greater than 85%, get above
individual composition is principal component, being calculated as follows of accumulation contribution rate:
Calculate thus
type factor loading matrix;
Each row in matrix are exactly corresponding characteristic vector and the subduplicate product of characteristic value.
6), mapping classification:
Choose
the maximum of type and time two large characteristic values
and corresponding characteristic vector
,
in space with
construct respectively two reference axis, and be designated as
with
.Like this, each factor of influence is in plane
a upper corresponding point, is classified as a class by contiguous factor of influence, represents that they can merge into a combined influence factor.
7), the present invention utilizes engineering project measured data, 4 parameters are carried out to principal component analysis, obtain first three main gene and be 94% information of soluble total data sample, first principal component has mainly reflected the information of chilled-water flow, Second principal component, has mainly reflected the information of chilled water outlet temperature, and the 3rd principal component has reflected the relation of cooling water flow, cooling water inlet temperature.
8), the explanation of these 4 parameters in three main genes believed than being reset to:
, the conclusion drawing according to principal component analysis, using the explain information amount of these 4 parameters in main gene as the weight of dimensionless number separately, obtains three main genes
,
,
computing formula:
| Main gene | |||
| Calculating formula |
(2), the detailed process of simplex search;
1), the structure of initial simplex
Construct a simplex that has 4 summits, initial point:
, all the other 3 points are elected as:
,
, wherein choose:
,
for the length of side of simplex, the step-length while being set as searching for.Then calculate one by one at search variables and be
evaluation function
, and compare.
2), initial point:
computing formula be:
，
，
Wherein
.
3), the length of side of simplex
definite method be:
4), evaluation function
adopt generalized regression nerve networks:
Topological structure as shown in Figure 8 for generalized regression nerve networks (GRNN neutral net), (cooling water flow and cooling water inlet temperature are merged into a main gene to 3 main genes that are input as of neutral net, chilled-water flow is a main gene, chilled water outlet temperature is a main gene), be output as corresponding refrigeration unit Energy Efficiency Ratio COP, all the other explanations are identical with the GRNN neutral net of carrying out Air-conditioning Load Prediction employing, repeat no more.
5), the iterative process of simplex method
Its flow process as shown in Figure 9, comprises following operation:
, reflection
Ask worst point
pip, even
, wherein
to remove in the summit of simplex
the leg-of-mutton center of gravity of 3 summits composition is in addition:
So
be
about the centre of form
pip, the functional value of this point is
.Wherein
for given reflectance factor is taken as 0.3.
, extend
Comparison function value
with
if,
, the pip that represents new choosing is the most better not worse than original, can in the original direction of search, suitably extend to find better point again, is about to
extend:
Wherein
for given lengthening coefficient, be taken as 1.5, if
with
replace
, otherwise with
replace
.
, shrink
If for all worst point of removing
other points in addition (
) on desired value have
or
(
second largest value in functional value, is time bad value point), illustrate that selected pip is not so good, vector is shunk, can make:
Wherein
for given constriction coefficient, be taken as 0.8,
situation under, with
replace
after shrink again.When
time, with
replace
.
, compress whole simplex
If
even, illustrating and done after above-mentioned contraction, target function value does not improve, and original simplex can be dwindled to half to best point, by all vectors
reduce half, order:
，
, obtain new simplex, constantly repeat above-mentioned iterative process, until meet certain finish condition:
the precision of setting is taken as 0.001.
Step 6, carry out the optimization of other operational factors of refrigeration system: the unlatching number of units of refrigeration unit, cooling water pump and cooling water pump and rate of load condensate are distributed, and mainly comprise following content:
(1), in the situation that air-conditioning total load is certain, the rate of load condensate that obtains unit in whole refrigeration system makes all unit total power consumption minimums:
Because refrigeration unit performance map is generally the sample curve of Energy Efficiency Ratio with rate of load condensate
, when one timing of air-conditioning total load can determine that the load sharing rate of unit makes its power consumption minimum according to its sample properties curve.If overall refrigerating effect is
, the specified refrigerating capacity of separate unit refrigeration unit is
, in system, refrigeration unit number of units amounts to
platform, the mathematical description of its load sharing rate is:
(2), the power consumption of given pump is with the sample curve of rate of load condensate
, when total flow one timing determines that according to its sample properties curve the load sharing rate of conveying equipment makes its power consumption minimum:
Total flow is
, the metered flow of single pump is
, in system, pump number of units amounts to
platform, the optimization of conveying equipment is under certain flow, and the power consumption of pump is minimum, and its mathematical description is:
(3), the unlatching number of units of refrigeration unit and cooling water pump, chilled water pump and the double optimization method of rate of load condensate:
The SECO of the equipment (unit and water pump) of refrigeration system comprises the number of units of unlatching and opens the distribution of the rate of load condensate of number of units, the nonlinear programming problem in (1) and (2) is completed by double optimization.
1), a suboptimization is that unit and water pump all adopt the optimization method based on performance map, for refrigeration unit (conveying equipment), at overall refrigerating effect for the number of units of definite start and stop
(total flow
) in certain situation, (for refrigeration unit, maximal efficiency is Energy Efficiency Ratio COP maximum to obtain maximal efficiency by refrigeration unit (water pump) performance curve; For conveying equipment, maximal efficiency is feed flow and the ratio maximum of power consumption) the lower corresponding refrigerating capacity of operation
(flow
), in a suboptimization, consider refrigerating capacity (flow) mean allocation, the unlatching number of units of refrigeration unit (water pump)
tentatively be defined as:
2), double optimization is to distribute in order to complete final optimization, after obtaining preferably opening number of units by a suboptimization, double optimization is a constrained nonlinear programming problem,
, for refrigeration unit, have:
For constrained planning problem being converted into without constraint planning, consider majorized function:
, for pump, without constraint plan optimization function be:
Wherein
for opening number of units,
that weight factor is taken as
,
be rate of load condensate allocation vector (
dimension), number of units
be taken as respectively
carry out
the contrast of value.
3), in order to determine final optimum results, rate of load condensate
the genetic algorithm of definite employing based on simulated annealing as accompanying drawing 13, wherein the genetic algorithm based on simulated annealing mainly comprises following key technology:
, chromosome coding, as accompanying drawing 11, adopts binary coding mode, and chromosome is common
section (the unlatching number of units of the refrigeration unit (water pump) in refrigeration system).
, as accompanying drawing 12,
the region of search be defined as:
, wherein
For refrigeration unit
For water pump
, the structure of fitness function,
The principle of genetic algorithm optimizing is as accompanying drawing 10, and its target finds most suitable exactly
individual parameter combinations, but when evolving in early days, genetic algorithm easily occurs that population precocity is absorbed in the situation of local optimum, based on simulated annealing Metropolis criterion, in filial generation group, choose at random individuality for fear of this situation
with
, individuality
competition enters follow-on selected probability and is:
Wherein
for annealing temperature,
.
, the setting in annealing temperature interval:
As the fitness function of structure in three, annealing temperature interval is taken as here
, each circulating temperature is changed to
.
, the setting of every generation population number and evolutionary generation in genetic algorithm:
Every generation population at individual is made as 500, and evolutionary generation was made as for 200 generations.
, 3 circulations in genetic algorithm, as accompanying drawing 13:
Ground floor circulation (in one deck circulation) is the searching process between every generation population at individual, and second layer circulation is simulated annealing process, and this one deck circulation is accompanied by the continuous reduction of simulated annealing temperature, and the 3rd layer of circulation is to change chromosome length
(be number of units
be taken as respectively
), realize the process of further optimizing between the optimum individual having after the Evolution of Population of coloured differently body length.
Step 7, according to the optimized operation parameter combinations of next moment refrigeration system, with reference to accompanying drawing 3, control system is controlled in advance to each parametric variable, and when guaranteeing that moment to be measured arrives, refrigeration system is in optimum duty.
The present invention carries out secondary development and realizes the integrated of single-chip microcomputer Lon-works on automatic building control system Lon-works platform, single-chip microcomputer is as one-level control module, comprise that Air-conditioning Load Prediction module and refrigeration system optimization of operating parameters arrange module, Lon-works realizes the real-time control of the collection of refrigeration system real-time running state data and the transmission of one-level control signal and refrigeration system related hardware equipment as secondary control module, assurance system quantitatively equates for cold-peace load is cold on the one hand, synchronous on time, make on the other hand control system to carry out dynamic adjustments to each parametric variable of refrigeration system in advance, guarantee that refrigeration system is all the time in optimum or approach optimum duty.
Claims (4)
1. an earth source heat pump refrigeration system optimal control method, comprises the following steps:
The operational factor of step 1, collection refrigeration unit, comprises that refrigeration unit Energy Efficiency Ratio, refrigerating capacity, cooling water flow, chilled-water flow, cooling water inlet temperature, chilled water outlet temperature, refrigeration unit are opened number of units and rate of load condensate, chilled water pump are opened number of units and rate of load condensate, cooling water pump are opened number of units and rate of load condensate;
Step 2, three kinds of Intelligent Forecastings of utilization: air conditioner load is predicted respectively in gray scale prediction, generalized regression nerve networks prediction, least square method supporting vector machine prediction, finally use grey data Fusion Model to integrate predicting the outcome of three kinds of models and obtain the predicted value of air conditioner load;
The least square method that step 3, utilization are forgotten with index is carried out the auto-adapted fitting of coefficient to the refrigeration unit Energy Efficiency Ratio empirical equation based on Jitian's function model;
Step 4, to predict that moment air conditioner load is as refrigerant system capacity substitution Jitian function model, according to extremum principle, by Jitian's function model, cooling water flow, chilled-water flow, cooling water inlet temperature, 4 parameters of chilled water outlet temperature are carried out to partial derivative calculating, obtain 4 operational factor operating points of next moment refrigeration unit near-optimization;
Step 5, uses simplex method to carry out the optimal combinatorial search of refrigeration unit cooling water flow, chilled-water flow, cooling water inlet temperature, 4 parameters of chilled water outlet temperature;
Step 6, carries out the optimization of other operational factors of refrigeration system, comprises unlatching number of units and the rate of load condensate distribution of refrigeration unit, cooling water pump and cooling water pump;
Step 7, according to the optimized operation parameter combinations of next moment refrigeration system, control system is controlled in advance to each parametric variable, and when guaranteeing that moment to be measured arrives, refrigeration system is in optimum duty.
2. earth source heat pump refrigeration system optimal control method as claimed in claim 1, is characterized in that: in described step 2, the neural network structure of generalized regression nerve networks prediction is input layer, mode layer, summation layer, output layer.
3. earth source heat pump refrigeration system optimal control method as claimed in claim 1, is characterized in that: the implementation method of described grey data fusion method is:
A) predict the air conditioner load value in the prediction moment that these 3 forecast models obtain for gray scale prediction, generalized regression nerve networks prediction, least square method supporting vector machine, define distance between any two values as follows:
,
B), the support function between two data of structure:
;
C), try to achieve matrix
eigenvalue of maximum
, the special syndrome vector corresponding with it
,
Get:
, after fusion, obtain:
be grey data fusion forecasting value.
4. earth source heat pump refrigeration system optimal control method as claimed in claim 1, is characterized in that: the Optimization Steps of described step 6 is:
A), in the situation that air-conditioning total load is certain, the rate of load condensate that obtains unit in whole refrigeration system makes all unit total power consumption minimums:
B), the power consumption of given pump is with the sample curve of rate of load condensate, when total flow one timing determines that according to its sample properties curve the load sharing rate of conveying equipment makes its power consumption minimum:
C), the unlatching number of units of refrigeration unit and cooling water pump, chilled water pump and the double optimization method of rate of load condensate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410125301.7A CN103912966B (en) | 2014-03-31 | 2014-03-31 | A kind of earth source heat pump refrigeration system optimal control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410125301.7A CN103912966B (en) | 2014-03-31 | 2014-03-31 | A kind of earth source heat pump refrigeration system optimal control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103912966A true CN103912966A (en) | 2014-07-09 |
| CN103912966B CN103912966B (en) | 2016-07-06 |
Family
ID=51038845
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410125301.7A Expired - Fee Related CN103912966B (en) | 2014-03-31 | 2014-03-31 | A kind of earth source heat pump refrigeration system optimal control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103912966B (en) |
Cited By (38)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105156327A (en) * | 2015-09-30 | 2015-12-16 | 深圳德尔科机电环保科技有限公司 | Energy-saving control method for compressed air industrial screw-type air compressor group control system |
| CN105259752A (en) * | 2015-11-13 | 2016-01-20 | 北京博锐尚格节能技术股份有限公司 | Load distribution method, device and system for device cluster |
| CN105937823A (en) * | 2016-03-31 | 2016-09-14 | 中国农业大学 | Control method and system for ground source heat pump |
| CN105987486A (en) * | 2014-10-15 | 2016-10-05 | 欧姆龙株式会社 | Heat demand estimation device and method, facility control device, method and system |
| CN104654690B (en) * | 2014-11-18 | 2017-01-11 | 深圳职业技术学院 | Method and system for controlling water chilling unit |
| CN106440188A (en) * | 2016-06-21 | 2017-02-22 | 中华电信股份有限公司 | Automatic air conditioner operation capacity adjusting system and method |
| CN107143981A (en) * | 2017-05-24 | 2017-09-08 | 山东师范大学 | A kind of controlling system of central air conditioner and method |
| CN107429930A (en) * | 2015-04-01 | 2017-12-01 | 三菱电机株式会社 | Air-conditioning system control device |
| CN107543345A (en) * | 2016-06-27 | 2018-01-05 | 荏原冷热***株式会社 | Heat source system and its control method |
| CN107816828A (en) * | 2017-10-19 | 2018-03-20 | 英特尔产品（成都）有限公司 | Method, apparatus and system for the temperature set-point of the refrigeration machine that determines refrigeration system |
| CN109033595A (en) * | 2018-07-16 | 2018-12-18 | 清华大学 | Build Green performance sunykatuib analysis new method and device |
| CN109323425A (en) * | 2018-11-15 | 2019-02-12 | 广东美的制冷设备有限公司 | Control method, device and the readable storage medium storing program for executing of air-conditioning |
| CN109634121A (en) * | 2018-12-28 | 2019-04-16 | 浙江工业大学 | More parent genetic algorithm air source heat pump multiobjective optimization control methods based on radial basis function neural network |
| CN109726896A (en) * | 2018-12-05 | 2019-05-07 | 新奥数能科技有限公司 | The calculation method and device of energy efficiency, storage medium, electronic device |
| CN109816166A (en) * | 2019-01-17 | 2019-05-28 | 山东大学 | A kind of ground-source heat pump system performance prediction method |
| CN110057045A (en) * | 2019-03-20 | 2019-07-26 | 青岛海尔空调器有限总公司 | Control method for air conditioner |
| CN110110388A (en) * | 2019-04-12 | 2019-08-09 | 天津大学 | Building air conditioning load forecasting method based on data pre-processing and wavelet decomposition |
| CN110118382A (en) * | 2019-04-15 | 2019-08-13 | 天津大学 | General operation regulation strategy identification and evaluation method for heat exchange station |
| CN110239721A (en) * | 2019-06-23 | 2019-09-17 | 北京航空航天大学 | For the optimum design method of electric air cycle refrigeration system |
| CN110288164A (en) * | 2019-07-02 | 2019-09-27 | 广州市特沃能源管理有限公司 | A kind of building air conditioning refrigeration station system forecast Control Algorithm |
| CN110598923A (en) * | 2019-09-03 | 2019-12-20 | 深圳市得益节能科技股份有限公司 | Air conditioner load prediction method based on support vector regression optimization and error correction |
| CN111043720A (en) * | 2019-10-21 | 2020-04-21 | 天津大学 | Low-cost robustness adjustment strategy making method of refrigeration system under load uncertainty |
| CN111158264A (en) * | 2020-01-09 | 2020-05-15 | 吉林大学 | Model prediction control rapid solving method for vehicle-mounted application |
| CN111256294A (en) * | 2020-01-17 | 2020-06-09 | 深圳市得益节能科技股份有限公司 | Model prediction-based optimization control method for combined operation of water chilling unit |
| CN111442480A (en) * | 2020-04-08 | 2020-07-24 | 广东美的暖通设备有限公司 | Operation control method and system for air conditioning equipment, air conditioning equipment and storage medium |
| CN111598224A (en) * | 2020-05-15 | 2020-08-28 | 西安建筑科技大学 | Air conditioner cold load prediction method for optimizing BP neural network based on simulated annealing algorithm |
| CN111767682A (en) * | 2020-06-09 | 2020-10-13 | 上海电力大学 | Heat pump energy storage system design control co-optimization method based on dynamic coupling model |
| CN111798045A (en) * | 2020-06-30 | 2020-10-20 | 西安建筑科技大学 | Energy-saving optimization method for chilled water system of central air conditioner |
| CN111854015A (en) * | 2020-08-07 | 2020-10-30 | 广州市设计院 | Air-conditioning refrigeration machine room system and control method thereof |
| CN113051737A (en) * | 2021-03-16 | 2021-06-29 | 天津大学 | Ground source heat pump data driving modeling method considering thermal measurement data abnormity |
| CN113255223A (en) * | 2021-06-02 | 2021-08-13 | 西安建筑科技大学 | Short-term prediction method and system for air conditioner load |
| CN113821902A (en) * | 2021-06-17 | 2021-12-21 | 李壮举 | Active disturbance rejection control system for static optimization of central air-conditioning refrigeration station |
| CN113959071A (en) * | 2021-07-21 | 2022-01-21 | 北京金茂绿建科技有限公司 | Machine learning assistance-based operation control optimization method for centralized water chilling unit air conditioning system |
| CN114174722A (en) * | 2019-01-10 | 2022-03-11 | 威廉姆斯炉业公司 | Dynamic regulating heater |
| CN114383299A (en) * | 2021-12-22 | 2022-04-22 | 武汉理工大学 | Central air-conditioning system operation strategy optimization method based on big data and dynamic simulation |
| CN114971090A (en) * | 2022-07-27 | 2022-08-30 | 中国电力科学研究院有限公司 | Electric heating load prediction method, system, equipment and medium |
| CN116822709A (en) * | 2023-05-22 | 2023-09-29 | 深圳市中电电力技术股份有限公司 | Parallel water chilling unit load distribution optimization method, system and storage medium |
| CN117330507A (en) * | 2023-10-12 | 2024-01-02 | 苏州星帆华镭光电科技有限公司 | Remote test control method for handheld laser instrument |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5579993A (en) * | 1995-01-06 | 1996-12-03 | Landis & Gyr Powers, Inc. | HVAC distribution system identification |
| CN101251291A (en) * | 2008-04-03 | 2008-08-27 | 上海交通大学 | Central air conditioning system global optimization energy-saving control method and device based on model |
| CN103234256A (en) * | 2013-04-17 | 2013-08-07 | 上海达希能源科技有限公司 | Dynamic load tracking central air conditioner cold source global optimum energy-saving control method |
| CN103453623A (en) * | 2013-09-13 | 2013-12-18 | 天津大学建筑设计研究院 | Water source heat pump air-conditioning system operating parameter optimization control method |
-
2014
- 2014-03-31 CN CN201410125301.7A patent/CN103912966B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5579993A (en) * | 1995-01-06 | 1996-12-03 | Landis & Gyr Powers, Inc. | HVAC distribution system identification |
| CN101251291A (en) * | 2008-04-03 | 2008-08-27 | 上海交通大学 | Central air conditioning system global optimization energy-saving control method and device based on model |
| CN103234256A (en) * | 2013-04-17 | 2013-08-07 | 上海达希能源科技有限公司 | Dynamic load tracking central air conditioner cold source global optimum energy-saving control method |
| CN103453623A (en) * | 2013-09-13 | 2013-12-18 | 天津大学建筑设计研究院 | Water source heat pump air-conditioning system operating parameter optimization control method |
Cited By (60)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105987486A (en) * | 2014-10-15 | 2016-10-05 | 欧姆龙株式会社 | Heat demand estimation device and method, facility control device, method and system |
| CN104654690B (en) * | 2014-11-18 | 2017-01-11 | 深圳职业技术学院 | Method and system for controlling water chilling unit |
| CN107429930A (en) * | 2015-04-01 | 2017-12-01 | 三菱电机株式会社 | Air-conditioning system control device |
| CN107429930B (en) * | 2015-04-01 | 2019-12-20 | 三菱电机株式会社 | Air conditioning system control device |
| CN105156327A (en) * | 2015-09-30 | 2015-12-16 | 深圳德尔科机电环保科技有限公司 | Energy-saving control method for compressed air industrial screw-type air compressor group control system |
| CN105259752B (en) * | 2015-11-13 | 2018-08-03 | 北京博锐尚格节能技术股份有限公司 | Load distribution method, device and system for equipment group |
| CN105259752A (en) * | 2015-11-13 | 2016-01-20 | 北京博锐尚格节能技术股份有限公司 | Load distribution method, device and system for device cluster |
| CN105937823A (en) * | 2016-03-31 | 2016-09-14 | 中国农业大学 | Control method and system for ground source heat pump |
| CN106440188A (en) * | 2016-06-21 | 2017-02-22 | 中华电信股份有限公司 | Automatic air conditioner operation capacity adjusting system and method |
| CN106440188B (en) * | 2016-06-21 | 2020-07-31 | 中华电信股份有限公司 | Automatic air conditioner operation capacity adjusting system and method |
| CN107543345A (en) * | 2016-06-27 | 2018-01-05 | 荏原冷热***株式会社 | Heat source system and its control method |
| CN107143981B (en) * | 2017-05-24 | 2019-06-28 | 山东师范大学 | A kind of controlling system of central air conditioner and method |
| CN107143981A (en) * | 2017-05-24 | 2017-09-08 | 山东师范大学 | A kind of controlling system of central air conditioner and method |
| CN107816828A (en) * | 2017-10-19 | 2018-03-20 | 英特尔产品（成都）有限公司 | Method, apparatus and system for the temperature set-point of the refrigeration machine that determines refrigeration system |
| CN107816828B (en) * | 2017-10-19 | 2018-12-04 | 英特尔产品（成都）有限公司 | For determining the method, apparatus and system of the temperature set-point of the refrigeration machine of refrigeration system |
| CN109033595A (en) * | 2018-07-16 | 2018-12-18 | 清华大学 | Build Green performance sunykatuib analysis new method and device |
| CN109033595B (en) * | 2018-07-16 | 2024-03-29 | 清华大学 | New method and device for building green performance simulation analysis |
| CN109323425A (en) * | 2018-11-15 | 2019-02-12 | 广东美的制冷设备有限公司 | Control method, device and the readable storage medium storing program for executing of air-conditioning |
| CN109323425B (en) * | 2018-11-15 | 2021-05-25 | 广东美的制冷设备有限公司 | Control method and device of air conditioner and readable storage medium |
| CN109726896A (en) * | 2018-12-05 | 2019-05-07 | 新奥数能科技有限公司 | The calculation method and device of energy efficiency, storage medium, electronic device |
| CN109634121A (en) * | 2018-12-28 | 2019-04-16 | 浙江工业大学 | More parent genetic algorithm air source heat pump multiobjective optimization control methods based on radial basis function neural network |
| CN109634121B (en) * | 2018-12-28 | 2021-08-03 | 浙江工业大学 | Multi-parent genetic algorithm air source heat pump multi-objective optimization control method based on radial basis function neural network |
| CN114174722A (en) * | 2019-01-10 | 2022-03-11 | 威廉姆斯炉业公司 | Dynamic regulating heater |
| CN109816166B (en) * | 2019-01-17 | 2022-11-29 | 山东大学 | Ground source heat pump system performance prediction method |
| CN109816166A (en) * | 2019-01-17 | 2019-05-28 | 山东大学 | A kind of ground-source heat pump system performance prediction method |
| CN110057045A (en) * | 2019-03-20 | 2019-07-26 | 青岛海尔空调器有限总公司 | Control method for air conditioner |
| CN110057045B (en) * | 2019-03-20 | 2021-10-29 | 青岛海尔空调器有限总公司 | Control method for air conditioner |
| CN110110388A (en) * | 2019-04-12 | 2019-08-09 | 天津大学 | Building air conditioning load forecasting method based on data pre-processing and wavelet decomposition |
| CN110118382B (en) * | 2019-04-15 | 2020-12-29 | 天津大学 | General operation regulation strategy identification and evaluation method for heat exchange station |
| CN110118382A (en) * | 2019-04-15 | 2019-08-13 | 天津大学 | General operation regulation strategy identification and evaluation method for heat exchange station |
| CN110239721A (en) * | 2019-06-23 | 2019-09-17 | 北京航空航天大学 | For the optimum design method of electric air cycle refrigeration system |
| CN110288164B (en) * | 2019-07-02 | 2022-12-02 | 广州市特沃能源管理有限公司 | Predictive control method for building air-conditioning refrigeration station system |
| CN110288164A (en) * | 2019-07-02 | 2019-09-27 | 广州市特沃能源管理有限公司 | A kind of building air conditioning refrigeration station system forecast Control Algorithm |
| CN110598923A (en) * | 2019-09-03 | 2019-12-20 | 深圳市得益节能科技股份有限公司 | Air conditioner load prediction method based on support vector regression optimization and error correction |
| CN111043720A (en) * | 2019-10-21 | 2020-04-21 | 天津大学 | Low-cost robustness adjustment strategy making method of refrigeration system under load uncertainty |
| CN111043720B (en) * | 2019-10-21 | 2021-05-14 | 天津大学 | Low-cost robustness adjustment strategy making method of refrigeration system under load uncertainty |
| CN111158264A (en) * | 2020-01-09 | 2020-05-15 | 吉林大学 | Model prediction control rapid solving method for vehicle-mounted application |
| CN111256294A (en) * | 2020-01-17 | 2020-06-09 | 深圳市得益节能科技股份有限公司 | Model prediction-based optimization control method for combined operation of water chilling unit |
| CN111256294B (en) * | 2020-01-17 | 2021-01-05 | 深圳市得益节能科技股份有限公司 | Model prediction-based optimization control method for combined operation of water chilling unit |
| CN111442480A (en) * | 2020-04-08 | 2020-07-24 | 广东美的暖通设备有限公司 | Operation control method and system for air conditioning equipment, air conditioning equipment and storage medium |
| CN111598224A (en) * | 2020-05-15 | 2020-08-28 | 西安建筑科技大学 | Air conditioner cold load prediction method for optimizing BP neural network based on simulated annealing algorithm |
| CN111598224B (en) * | 2020-05-15 | 2023-05-02 | 西安建筑科技大学 | Air conditioner cold load prediction method for optimizing BP neural network based on simulated annealing algorithm |
| CN111767682A (en) * | 2020-06-09 | 2020-10-13 | 上海电力大学 | Heat pump energy storage system design control co-optimization method based on dynamic coupling model |
| CN111767682B (en) * | 2020-06-09 | 2024-02-27 | 上海电力大学 | Heat pump energy storage system design control co-optimization method based on dynamic coupling model |
| CN111798045B (en) * | 2020-06-30 | 2023-05-26 | 西安建筑科技大学 | Energy-saving optimization method for chilled water system of central air conditioner |
| CN111798045A (en) * | 2020-06-30 | 2020-10-20 | 西安建筑科技大学 | Energy-saving optimization method for chilled water system of central air conditioner |
| CN111854015A (en) * | 2020-08-07 | 2020-10-30 | 广州市设计院 | Air-conditioning refrigeration machine room system and control method thereof |
| CN111854015B (en) * | 2020-08-07 | 2024-06-11 | 广州市设计院集团有限公司 | Air conditioner refrigerating machine room system and control method thereof |
| CN113051737A (en) * | 2021-03-16 | 2021-06-29 | 天津大学 | Ground source heat pump data driving modeling method considering thermal measurement data abnormity |
| CN113051737B (en) * | 2021-03-16 | 2022-05-20 | 天津大学 | Ground source heat pump data driving modeling method considering thermal measurement data abnormity |
| CN113255223B (en) * | 2021-06-02 | 2023-04-28 | 西安建筑科技大学 | Short-term prediction method and system for air conditioner load |
| CN113255223A (en) * | 2021-06-02 | 2021-08-13 | 西安建筑科技大学 | Short-term prediction method and system for air conditioner load |
| CN113821902A (en) * | 2021-06-17 | 2021-12-21 | 李壮举 | Active disturbance rejection control system for static optimization of central air-conditioning refrigeration station |
| CN113959071A (en) * | 2021-07-21 | 2022-01-21 | 北京金茂绿建科技有限公司 | Machine learning assistance-based operation control optimization method for centralized water chilling unit air conditioning system |
| CN114383299A (en) * | 2021-12-22 | 2022-04-22 | 武汉理工大学 | Central air-conditioning system operation strategy optimization method based on big data and dynamic simulation |
| CN114971090A (en) * | 2022-07-27 | 2022-08-30 | 中国电力科学研究院有限公司 | Electric heating load prediction method, system, equipment and medium |
| CN116822709B (en) * | 2023-05-22 | 2024-03-22 | 深圳市中电电力技术股份有限公司 | Parallel water chilling unit load distribution optimization method, system and storage medium |
| CN116822709A (en) * | 2023-05-22 | 2023-09-29 | 深圳市中电电力技术股份有限公司 | Parallel water chilling unit load distribution optimization method, system and storage medium |
| CN117330507A (en) * | 2023-10-12 | 2024-01-02 | 苏州星帆华镭光电科技有限公司 | Remote test control method for handheld laser instrument |
| CN117330507B (en) * | 2023-10-12 | 2024-04-05 | 苏州星帆华镭光电科技有限公司 | Remote test control method for handheld laser instrument |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103912966B (en) | 2016-07-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103912966B (en) | A kind of earth source heat pump refrigeration system optimal control method | |
| CN106920006B (en) | Subway station air conditioning system energy consumption prediction method based on ISOA-LSSVM | |
| CN105719028B (en) | A kind of air conditioner load dynamic prediction method based on multifactor chaos support vector machines | |
| Xikai et al. | Comparison of regression models for estimation of carbon emissions during building's lifecycle using designing factors: a case study of residential buildings in Tianjin, China | |
| CN102003772B (en) | Energy-saving optimized control method of water source heat pump | |
| CN107860102B (en) | Method and device for controlling central air conditioner | |
| CN107704875A (en) | Based on the building load Forecasting Methodology and device for improving IHCMAC neutral nets | |
| Hwang et al. | Using deep learning approaches with variable selection process to predict the energy performance of a heating and cooling system | |
| CN109932896A (en) | A kind of control method and system of building energy consumption | |
| CN113240184B (en) | Building space unit cold load prediction method and system based on federal learning | |
| CN107276069A (en) | Approximate the polymerization modeling method and system of a kind of area power grid resident temperature control load | |
| CN114383299A (en) | Central air-conditioning system operation strategy optimization method based on big data and dynamic simulation | |
| CN111649457A (en) | Dynamic predictive machine learning type air conditioner energy-saving control method | |
| KR20180138371A (en) | Method for evaluating data based models and conducting predictive control of capsule type ice thermal storage system using the same | |
| CN114046593A (en) | Dynamic predictive machine learning type air conditioner energy-saving control method and system | |
| CN114200839B (en) | Intelligent office building energy consumption control model for dynamic monitoring of coupling environment behaviors | |
| Zhao et al. | Prediction of functional zones cooling load for shopping mall using dual attention based LSTM: A case study | |
| Sha et al. | A control strategy of heating system based on adaptive model predictive control | |
| CN113432247B (en) | Water chilling unit energy consumption prediction method and system based on graph neural network and storage medium | |
| Shao et al. | A practical application-oriented model predictive control algorithm for direct expansion (DX) air-conditioning (A/C) systems that balances thermal comfort and energy consumption | |
| CN113028610B (en) | Method and device for global optimization and energy-saving control of dynamic load of central air conditioner | |
| Zhao et al. | Building cooling load prediction based on lightgbm | |
| CN113757922A (en) | Deep learning-based air conditioning system energy-saving control method, device and equipment and computer medium | |
| CN113449909A (en) | Cold load prediction method of cold accumulation air conditioner based on improved long-term and short-term memory network | |
| Wang et al. | A global optimization method for data center air conditioning water systems based on predictive optimization control |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160706 Termination date: 20170331 |