CN108563877B - Integral modeling and optimal control integrated method for solar lithium bromide refrigerating unit - Google Patents

Integral modeling and optimal control integrated method for solar lithium bromide refrigerating unit Download PDF

Info

Publication number
CN108563877B
CN108563877B CN201810353958.7A CN201810353958A CN108563877B CN 108563877 B CN108563877 B CN 108563877B CN 201810353958 A CN201810353958 A CN 201810353958A CN 108563877 B CN108563877 B CN 108563877B
Authority
CN
China
Prior art keywords
lithium bromide
unit
solar
value
variable
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.)
Active
Application number
CN201810353958.7A
Other languages
Chinese (zh)
Other versions
CN108563877A (en
Inventor
赵峰
张广渊
潘为刚
王常顺
黄欣
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 Jiaotong University
Original Assignee
Shandong Jiaotong 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 Jiaotong University filed Critical Shandong Jiaotong University
Priority to CN201810353958.7A priority Critical patent/CN108563877B/en
Publication of CN108563877A publication Critical patent/CN108563877A/en
Application granted granted Critical
Publication of CN108563877B publication Critical patent/CN108563877B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
    • F25B—REFRIGERATION MACHINES, PLANTS OR SYSTEMS; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS
    • F25B15/00—Sorption machines, plants or systems, operating continuously, e.g. absorption type
    • F25B15/02—Sorption machines, plants or systems, operating continuously, e.g. absorption type without inert gas
    • F25B15/06—Sorption machines, plants or systems, operating continuously, e.g. absorption type without inert gas the refrigerant being water vapour evaporated from a salt solution, e.g. lithium bromide
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
    • F25B—REFRIGERATION MACHINES, PLANTS OR SYSTEMS; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS
    • F25B49/00—Arrangement or mounting of control or safety devices
    • F25B49/04—Arrangement or mounting of control or safety devices for sorption type machines, plants or systems
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A30/00—Adapting or protecting infrastructure or their operation
    • Y02A30/27—Relating to heating, ventilation or air conditioning [HVAC] technologies
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
    • Y02B30/62—Absorption based systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mechanical Engineering (AREA)
  • Theoretical Computer Science (AREA)
  • Thermal Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Automation & Control Theory (AREA)
  • Chemical & Material Sciences (AREA)
  • Materials Engineering (AREA)
  • Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Medical Informatics (AREA)
  • Feedback Control In General (AREA)

Abstract

The invention discloses an integrated modeling and optimal control method of a solar lithium bromide refrigerating unit, which comprises the following steps: determining an input variable; reconstructing the input variables; determining an output variable of the overall modeling; determining an internal operation parameter optimization variable and an external process control variable; determining an optimized objective function of internal operation parameters and external process control variables of the solar lithium bromide refrigerating unit; and issuing the optimal internal operation parameters to a control system of the solar lithium bromide refrigerating unit and operating, issuing the optimal external process variable to controllers of two control loops, and quickly tracking the optimal external process variable value by the controllers by adopting a data-driven PID algorithm. The technical problems that the solar lithium bromide refrigerating unit is difficult to model, optimize and control are effectively solved, the solar lithium bromide refrigerating unit can operate in optimal parameters and efficient areas under different working conditions and loads, and the refrigerating efficiency and the safety and the stability of the solar lithium bromide refrigerating unit are effectively improved.

Description

Integral modeling and optimal control integrated method for solar lithium bromide refrigerating unit
Technical Field
The invention relates to the technical field of solar lithium bromide refrigeration, in particular to an integrated modeling and optimal control method of a solar lithium bromide refrigeration unit.
Background
Energy shortage, environmental pollution and climate change are important factors for restricting the sustainable development of economy and society in the world at present, and energy and environmental problems become important strategic problems with high concern at home and abroad. The solar energy is green, clean, and can be continuously utilized, is easy to obtain, and is safe and reliable. The solar lithium bromide refrigerating unit converts solar energy into heat energy by utilizing a solar heat collection technology, and drives the lithium bromide refrigerating unit to refrigerate by utilizing the heat energy, so that the low-carbon environment-friendly operation of a building is realized, the operation cost is low, the solar lithium bromide refrigerating unit is an important direction for the development of green buildings, and the solar lithium bromide refrigerating unit has a good development prospect.
However, the solar lithium bromide refrigerating unit is a typical complex energy conversion system with multi-energy flow input, multi-energy flow output, multi-level information flow and multi-equipment coupling, and has the characteristics of strong nonlinearity, parameter time variation, large inertia, large delay and multivariable coupling. Due to the multi-equipment coupling of the solar lithium bromide refrigerating unit, the whole operation model of the lithium bromide refrigerating unit is difficult to establish so as to accurately describe the regular operation characteristics of the unit. Meanwhile, the solar lithium bromide refrigerating unit has complex working conditions, the difference between the efficiency parameter and the operation parameter of the lithium bromide refrigerating unit is large under different working conditions and loads, but the existing products are operated under fixed operation parameters and are not optimized in real time. Therefore, optimizing the optimal internal operation parameters and external process variables of the lithium bromide unit in real time under different working conditions and loads is also a key factor influencing the efficient operation of the unit. On the basis of the target value of the optimal operation parameter, the control system adopting the advanced control algorithm is a decisive factor for the efficient and stable operation of the unit to quickly and accurately track the target value of the external process variable. However, at present, domestic and foreign documents and products do not relate to an integrated design method for integral modeling, parameter optimization and optimal control of the solar lithium bromide refrigerating unit.
Disclosure of Invention
The invention aims to solve the problems, provides an integrated modeling and optimal control method of a solar lithium bromide refrigerating unit, and provides the integrated modeling method and the real-time operation parameter optimization method of the solar lithium bromide refrigerating unit, which are used for quickly tracking an optimal external control variable target value by using a data-driven PID algorithm on the basis of optimal internal operation parameters and external control variables so as to realize the efficient, safe and stable operation of the solar lithium bromide under different working conditions and loads.
In order to achieve the purpose, the invention adopts the following technical scheme:
the integral modeling method of the solar lithium bromide refrigerating unit comprises the following steps:
the method comprises the following steps: determining input variable R of integral modeling of solar lithium bromide refrigerating uniti；
Step two: reconstructing the input variable R by C-C method phase spacei；
Step three: determining output variable S of integral modeling of solar lithium bromide refrigerating uniti；
Step four: an integral model of the solar lithium bromide refrigerating unit is established based on a deep learning method.
The input variable R in the step oneiComprises the following steps:
Ri＝[TTYN-C,TTYN-J,LTYN,TKTS-C,TKTS-J,LKTS,TLQS-C,TLQS-J,LLQS,TFSQ,WFSQ,TXSQ,WXSQ,TZLJ,LZLJ, TXHL,LXHL,NXHL,TZFQ,YZFQ]；
wherein: t isTYN-CTemperature value T of lithium bromide unit for solar hot water outletTYN-JTemperature value L of solar hot water entering lithium bromide unitTYNFlow value, T, for solar hot water to lithium bromide unitKTS-CTemperature value, T, of cold water discharged from lithium bromide unit for air conditioningKTS-JTemperature value L of air conditioner refrigerating water entering lithium bromide unitKTSFlow value, T, of cold water out of lithium bromide unit for air conditioningLQS-CTemperature value, T, for the cooling water leaving the lithium bromide unitLQS-JTemperature value L of cooling water entering lithium bromide unitLQSFlow value, T, for cooling water entering lithium bromide unitFSQIs the temperature value, W, in the generator of the lithium bromide unitFSQFor the level value, T, in the generator of the lithium bromide unitXSQIs the temperature value, W, in the lithium bromide unit absorberXSQFor the level value, T, in the absorber of the lithium bromide unitZLJIs the temperature value, L, of the refrigerantZLJIs the flow rate of the refrigerantValue, TXHLIs the temperature value, L, of the lithium bromide solutionXHLIs the flow value, N, of the lithium bromide solutionXHLIs the concentration value of the lithium bromide solution, TZFQIs the temperature value, Y, in the evaporator of the lithium bromide unitZFQThe pressure value of the evaporator of the lithium bromide unit is shown.
In the second step, the C-C method is adopted to reconstruct the input variable time sequence R of the overall modeling of the solar lithium bromide refrigerating unit in a phase space manneriSet R toiDelay time t ofiAnd embedding dimension miInput variable R of integral modeling of solar lithium bromide refrigerating unitiIs uniformly expressed as ri＝[ri(t),ri(t-ti),…,ri(t-(mi-1)ti)](ii) a R is to beiThe characteristic data is expressed as 20 XmiIs input variable time series vector ri。
In the third step, the output variable S of the integral modeling of the solar lithium bromide refrigerating unitiComprises the following steps:
Si＝[COP,PKTS,PTYN,PLQS]；
wherein: COP is the efficiency parameter value, P, of the solar lithium bromide unitKTSProduction of air conditioner cold water power value, P, for solar lithium bromide unitTYNFor solar hot water power input to solar lithium bromide units, PLQSThe power of the cooling water of the solar lithium bromide unit.
The concrete method of the fourth step is as follows:
step 4.1, constructing a 5-layer DBN based on the RBM, wherein the DBN comprises 1 input layer, 3 hidden layers and 1 decision layer;
step 4.2, the number of input layer nodes of the DBN is specified to be 20 multiplied by 3600; the number of nodes of the first hidden layer is 500; the number of nodes of the second hidden layer is 500; the number of nodes of the third hidden layer is 1000; the number of nodes of the decision layer is 4;
4.3, training 5 layers of the DBN layer by using a contrast divergence CD algorithm, and calculating output values of 3 hidden layers and 1 decision layer and weight values and offsets among the layers;
step (ii) of4.4, adjusting the whole DBN by using a BP algorithm, optimizing DBN parameters and finishing the global training of the DBN; the trained optimal weight and bias are used for obtaining the integral model parameter M of the solar lithium bromide uniti。
An optimal control integration method based on an integral modeling method of a solar lithium bromide refrigerating unit comprises the following steps:
step 1, determining an internal operation parameter optimization variable E of a solar lithium bromide refrigerating unitiAnd an external process control variable Ci；
Step 2, determining a real-time optimized objective function of the solar lithium bromide refrigerating unit;
step 3, solving the optimal internal operation parameter value of the solar lithium bromide refrigerating unit by adopting a self-adaptive chaotic particle swarm optimization algorithm
Figure GDA0001663912000000031
And external process control variable values
Figure GDA0001663912000000032
Step 4, mixing
Figure GDA0001663912000000033
The optimal internal operation parameters are issued to a control system of the solar lithium bromide refrigerating unit and operated, and the optimal external process variable is obtained
Figure GDA0001663912000000034
And the data is transmitted to controllers of the two control loops, and the controllers adopt a data-driven PID algorithm to quickly track the optimal external process variable value.
In the step 1, the internal operation parameter optimization variable E of the solar lithium bromide refrigerating unitiAnd an external process control variable CiThe method specifically comprises the following steps:
Ei＝[YZFQ,TTYN-J,LTYN,LKTS,LLQS,TLQS-J,LXHL,TXHL,LZLJ,TZLJ]；
Ci＝[TKTS-C,NXHL]；
wherein: y isZFQIs the pressure value, T, of the evaporator of the lithium bromide unitTYN-JTemperature value L of solar hot water entering lithium bromide unitTYNFlow value, T, for solar hot water to lithium bromide unitKTS-CTemperature value L of cold water discharged from lithium bromide unit for air conditioningKTSFlow value L of cold water discharged from lithium bromide unit for air conditioningLQSFlow value, T, for cooling water entering lithium bromide unitLQS-JTemperature value L of cooling water entering lithium bromide unitXHLIs the flow value, T, of the lithium bromide solutionXHLIs the temperature value, N, of the lithium bromide solutionXHLIs the concentration value of the lithium bromide solution, LZLJIs the flow rate value, T, of the refrigerantZLJIs the temperature value of the refrigerant.
The objective function in the step 2 is that the running cost NPV is lowest, Min NPVBR＝RCbr+Com+CeIn the formula: NPVBRThe annual running cost of the combined cooling heating and power system is unit; r is the coefficient of investment recovery,
Figure GDA0001663912000000041
wherein l is the annual rate and m is the service life of the equipment; cbrThe method is characterized in that the method comprises the following steps: yuan, ComFor the maintenance and management expense of solar energy lithium bromide refrigerating unit, including equipment maintenance and maintenance expense, managers expense, unit: element;
Ce＝Je(PZKB+PKTSB+PLQSB+PXHLB+PZLJB+PLQFS)
in the formula, CeThe unit is the electricity consumption cost of the solar lithium bromide refrigerating unit: element; j. the design is a squareeFor electricity price, unit: yuan/kWh; pZKBFor lithium bromide unit evacuation pump power consumption, unit: kWh; pKTSBFor lithium bromide unit air conditioner water pump power consumption, unit: kWh; pLQSBFor lithium bromide unit cooling water pump power consumption, unit: kWh; pXHLBFor lithium bromide unit bromineLithium pump power consumption, unit: kWh; pZLJBThe unit is the power consumption of the lithium bromide unit refrigerant pump: kWh; pLQFSFor cooling tower cooling fan power consumption, unit: kWh.
The step 3 is specifically as follows:
step 3.1, initializing a particle swarm, and randomly setting an initial position x and an initial speed v of the particles within an allowable range, wherein i belongs to [1, n ], and n is the number of the particles;
step 3.2 p of the ith particlebestSet to the current position of the particle, gbestSetting to be the optimal particle position in the initial population;
step 3.3 will update the position and speed of the example according to equation (4), equation (5) and equation (6);
x(t+1)＝x(t)+v(t+1) (4)
v(t+1)＝ωv(t)+c1r1(pbest(t)-x(t))+c2r2(gbest(t)-x(t)) (5)
Figure GDA0001663912000000042
wherein t is the current evolution algebra; c. C1、c2For learning factor, set c1＝c2＝2；r1、r2Is distributed in [0,1 ]]A random number within; p is a radical ofbestThe optimal solution of the particle individual is obtained; gbestA global optimal solution for the entire particle swarm; omega is an inertia coefficient; omegamax、ωminMaximum and minimum coefficients of inertia, respectively; t ismaxIs the maximum iteration number; τ is a weight coefficient, and is set to be 30;
step 3.4 calculate the fitness f (x) of the particle ii)，i∈[1,n]，f(xi) Is a fitness function;
step 3.5 if the fitness f (x) of the particle ii) Is superior to the self individual extreme value pbestFitness f (p) ofbest) Using the current position x of the particleiSubstitution of pbest；
Step 3.6 if the fitness f (x) of the particle ii) Superior foodAt the current global extreme gbestFitness f (g)best) Using the current position x of the particleiReplacement global extremum gbest；
Step 3.7 calculating the population fitness variance σ according to equation (7)2；
Figure GDA0001663912000000051
Wherein f isiIs the fitness function value of the ith particle, favgThe current average fitness function value of the particle swarm is taken as the current average fitness function value;
step 3.8, judging whether the algorithm meets the convergence condition, if so, turning to step 6.10, otherwise, turning to step 6.9;
3.9 chaotic searching is carried out according to the formulas (8) and (9), one particle is randomly replaced by the best feasible point which is searched, and then the step 3.3 is carried out;
Zi+1＝μZi(1-Zi),μ∈(2,4] (8)
x(t+1)＝xmin+Zi+1(xmax-xmin) (9)
wherein Z isi+1The variable is a chaotic variable, mu is a control parameter and is set to be 4; x is the number ofmaxIs the maximum value of the current position variable; x is the number ofminIs the minimum value of the current position variable;
step 3.10 output Global optimal solution gbestAnd the corresponding objective function value is obtained, and the algorithm is finished.
The specific method of the step 4 comprises the following steps:
Figure GDA0001663912000000052
and
Figure GDA0001663912000000053
respectively as follows:
Figure GDA0001663912000000054
Figure GDA0001663912000000055
decoupling a solar lithium bromide refrigerating unit into two independent control loops of solar water heating flow, air conditioner water temperature and lithium bromide concentration by an inverse decoupler, and designing a two-degree-of-freedom data driving PID controller for control;
step (2) using phi (j) to represent input and output values and PID parameter values stored in a database;
Figure GDA0001663912000000069
wherein N is the number of information variables in the database;
φ(j)＝[y(j-1),y(j-2),...,y(j-ny),u(j-1),u(j-2),...,u(j-nu)]as information variable, y (j-n)y) And u (j-n)u) Respectively the output and control input of the system, nyAnd nuThe order of system output and control input, respectively;
Figure GDA0001663912000000061
Tp(j) proportional parameters of PID; t isi(j) Is an integral parameter of the PID; t isd(j) Is a differential parameter of the PID;
Figure GDA0001663912000000062
is PID parameter corresponding to phi (j);
step (3) calculating the Distance d between the t moment phi (t) and the information vector phi (j) in the database by using an Euclidean Distance methodtj：
Figure GDA0001663912000000063
The distance size metric phi (t) calculated by the equation (11) measures the similarity between each information vector phi (j) stored in the database; at all lettersSelect k d in the information vectortjThe information vector corresponding to the minimum;
step (4) calculating PID parameters
Figure GDA0001663912000000064
Operating the k information vectors selected in the step (3), and obtaining the predicted estimated values of the parameters according to the k PID parameter values corresponding to the selected information vectors by using a linear weighted average method
Figure GDA0001663912000000065
Figure GDA0001663912000000066
Wherein, ω isiIs the weight of the ith information vector phi (i);
and (5) optimizing PID parameters by adopting a steepest descent method:
Figure GDA0001663912000000067
η＝diag{ηP,ηI,ηD} (14)
Figure GDA0001663912000000068
e(t)＝r(t)-y(t) (16)
where η is the learning rate, ηP、ηI、ηDLearning rates of proportion, integral and differential respectively; j (t) is an error criterion;
Figure GDA0001663912000000071
the deviation is calculated for the error criterion,
Figure GDA0001663912000000072
the PID parameter of the previous iteration cycle,
Figure GDA0001663912000000073
is the latest PID parameter of the current iteration cycle.
And (6) updating the database and deleting redundant data.
The specific method of the step (6) is as follows:
step (6.1), excluding the k information vectors selected in the step (3) from redundant data to be deleted, and extracting other distances d from the current input point from the databasetj≤σ1The information vector of (2);
step (6.2), deleting redundant data of the database by using the similar criterion among PID parameters corresponding to the information vector in the formula (17);
Figure GDA0001663912000000074
wherein, Tl(i) The stored PID parameters for the database are,
Figure GDA0001663912000000075
is the PID parameter, σ, of the current iteration cycle1And σ2Suppression coefficients for extracting deleted data from the redundant data, respectively; setting sigma1＝σ2＝0.5。
The invention has the beneficial effects that:
the invention determines an integrated method of integral modeling, parameter optimization and optimal control of a solar lithium bromide refrigerating unit, provides an integral modeling method of the solar lithium bromide refrigerating unit based on deep learning, a real-time optimization method of internal operation parameters and external operation variables based on a self-adaptive chaotic particle swarm optimization algorithm is provided on the basis of an integral model, and the optimal external control variable target value is quickly tracked by using a data-driven PID control algorithm, so that the internal operation parameters and the external operation parameters of the solar lithium bromide refrigerating unit are optimized in real time under different working conditions and loads, the technical problems of difficult modeling, difficult optimization and difficult control of the solar lithium bromide refrigerating unit are effectively solved, the method can ensure that the solar lithium bromide refrigerating unit can operate in the optimal parameter and high-efficiency area under different working conditions and loads, and effectively improves the refrigerating efficiency and the safety and the stability of the solar lithium bromide refrigerating unit.
Drawings
FIG. 1 is a design diagram of an integrated modeling and optimal control method of a solar lithium bromide refrigerating unit;
FIG. 2 is a flow chart of a data driven PID control method.
Detailed Description
The invention is further described with reference to the following figures and examples.
The invention comprises the following steps: the overall design diagram of the method is shown in fig. 1, and the method comprises an overall modeling method of a solar lithium bromide refrigerating unit based on deep learning, an internal operation parameter and external process variable optimization method of the solar lithium bromide refrigerating unit based on a self-adaptive chaotic particle swarm optimization algorithm, and an external process variable optimal control method of the solar lithium bromide refrigerating unit based on a data-driven PID control algorithm.
The method for integrating the integral modeling and the optimal control of the solar lithium bromide refrigerating unit comprises the following steps:
the method comprises the following steps: determining input variables of the overall modeling of the solar lithium bromide refrigerating unit, including;
step 1.1 selecting input variable R of integral modeling of solar lithium bromide refrigerating uniti:
Ri＝[TTYN-C,TTYN-J,LTYN,TKTS-C,TKTS-J,LKTS,TLQS-C,TLQS-J,LLQS,TFSQ,WFSQ,TXSQ,WXSQ,TZLJ,LZLJ, TXHL,LXHL,NXHL,TZFQ,YZFQ]；
Wherein: t isTYN-CThe temperature value (DEG C) of the solar hot water lithium bromide discharging unit and TTYN-JThe temperature value (DEG C) and L of the solar hot water entering the lithium bromide unitTYNFlow value (m) of solar hot water entering lithium bromide unit3/h)，TKTS-CThe temperature value (DEG C) of the lithium bromide unit for air conditioning cold water outlet, TKTS-JRefrigerating water for air conditionerTemperature value (DEG C) and L of lithium bromide feeding unitKTSFlow value (m) of cold water discharged from lithium bromide unit for air conditioning3/h)，TLQS-CThe temperature value (DEG C) of the cooling water out of the lithium bromide unit, TLQS-JThe temperature value (DEG C) of cooling water entering the lithium bromide unit and LLQSFlow value (m) of cooling water entering lithium bromide unit3/h)，TFSQIs the temperature value (DEG C) in the generator of the lithium bromide unit, WFSQFor the level value (m), T in the generator of the lithium bromide unitXSQIs the temperature value (DEG C) in the lithium bromide unit absorber, WXSQIs the level value (m), T in the absorber of the lithium bromide unitZLJThe temperature value (DEG C) of the refrigerant, LZLJIs the flow rate value (m) of the refrigerant3/h)，TXHLThe temperature value (. degree. C.) of the lithium bromide solution, LXHLIs the flow value (m) of the lithium bromide solution3/h)，NXHLConcentration value (%) of lithium bromide solution, TZFQIs the temperature value (DEG C) and Y in the evaporator of the lithium bromide unitZFQThe pressure value (kPa) of the evaporator of the lithium bromide unit is obtained;
step 1.2 reconstruction of input variable R by C-C method phase spacei：
Input variable time sequence R for reconstructing integral modeling of solar lithium bromide refrigerating unit by adopting C-C method phase spaceiSetting RiDelay time t ofiAnd embedding dimension miInput variable R of integral modeling of solar lithium bromide refrigerating unitiIs uniformly expressed as ri＝[ri(t),ri(t-ti),…,ri(t-(mi-1)ti)](ii) a R is to beiThe characteristic data is expressed as 20 XmiIs input variable time series vector ri；
Step two: determining output variable S of integral modeling of solar lithium bromide refrigerating unitiThe method comprises the following steps:
Si＝[COP,PKTS,PTYN,PLQS]；
wherein: COP is the efficiency parameter value, P, of the solar lithium bromide unitKTSAir conditioner cold water work for solar lithium bromide unit productionSpecific value (kW), PTYNFor inputting solar hot water power (kW), P of solar lithium bromide unitLQSCooling water power (kW) for the solar lithium bromide unit;
step three: the invention establishes an integral model of a solar lithium bromide refrigerating unit by a deep learning method, which mainly comprises the following steps:
step 3.1, constructing a Deep Belief Network (DBN), and specifically comprising the following steps:
step 3.1.1, constructing a 5-layer DBN based on the RBM, wherein the DBN comprises 1 input layer, 3 hidden layers and 1 decision layer;
step 3.1.2 specifies that the number of input layer nodes of the DBN is 20 multiplied by 3600; the number of nodes of the first hidden layer is 500; the number of nodes of the second hidden layer is 500; the number of nodes of the third hidden layer is 1000; the number of nodes in the decision layer is 4.
Step 3.2, the DBN training specifically comprises the following steps:
step 3.2.1, training 5 layers of the DBN layer by using a contrast divergence CD algorithm, and calculating output values of 3 hidden layers and 1 decision layer and weight values and offsets among the layers;
and 3.2.2, adjusting the whole DBN by using a BP algorithm, optimizing DBN parameters and finishing the global training of the DBN.
3.3, obtaining an integral model of the solar lithium bromide unit by using the optimal weight and the bias trained in the step 3.2;
step four: determining internal operation parameter optimization variable E of solar lithium bromide refrigerating unitiAnd an external process control variable Ci：
Ei＝[YZFQ,TTYN-J,LTYN,LKTS,LLQS,TLQS-J,LXHL,TXHL,LZLJ,TZLJ]；
Ci＝[TKTS-C,NXHL]；
Wherein: y isZFQIs the pressure value (kPa), T of the lithium bromide unit evaporatorTYN-JThe temperature value (DEG C) and L of the solar hot water entering the lithium bromide unitTYNFlow value of solar hot water entering lithium bromide unit(m3/h)，TKTS-CThe temperature value (DEG C) and L of the lithium bromide unit for air conditioning cold waterKTSFlow value (m) of cold water discharged from lithium bromide unit for air conditioning3/h)，LLQSFlow value (m3/h) of cooling water entering lithium bromide unit, TLQS-JThe temperature value (DEG C) of cooling water entering the lithium bromide unit and LXHLIs the flow value (m) of the lithium bromide solution3/h)， TXHLTemperature value (. degree. C.) of lithium bromide solution, NXHLConcentration value (%) of lithium bromide solution, LZLJIs the flow rate value (m) of the refrigerant3 /h)，TZLJIs the temperature value (deg.C) of the refrigerant;
step five: determining an optimized objective function of internal operation parameters and external process control variables of the solar lithium bromide refrigerating unit:
the objective function of the invention is: the operating cost NPV is lowest:
Min NPVBR＝RCbr+Com+Ce (1)
in formula (1): NPVBRThe annual running cost of the combined cooling heating and power system is unit; r is the coefficient of investment recovery,
Figure GDA0001663912000000101
wherein l is the annual rate and m is the service life of the equipment; cbrThe method is characterized in that the method comprises the following steps: yuan, ComFor the maintenance and management expense of solar energy lithium bromide refrigerating unit, including equipment maintenance and maintenance expense, managers expense, unit: element;
Ce＝Je(PZKB+PKTSB+PLQSB+PXHLB+PZLJB+PLQFS) (3)
in the formula (3), CeThe unit is the electricity consumption cost of the solar lithium bromide refrigerating unit: element; j. the design is a squareeFor electricity price, unit: yuan/kWh; pZKBFor lithium bromide unit evacuation pump power consumption, unit: kWh; pKTSBFor lithium bromide unit air conditioner water pump power consumptionsAmount, unit: kWh; pLQSBFor lithium bromide unit cooling water pump power consumption, unit: kWh; pXHLBThe unit is the power consumption of a lithium bromide pump of a lithium bromide unit: kWh; pZLJBThe unit is the power consumption of the lithium bromide unit refrigerant pump: kWh; pLQFSFor cooling tower cooling fan power consumption, unit: kWh;
step six: the invention adopts a self-adaptive chaotic particle swarm optimization algorithm to solve the optimal internal operation parameters and the external process control variables of a solar lithium bromide refrigerating unit, and the main steps comprise:
step 6.1, initializing a particle swarm, and randomly setting an initial position x and an initial speed v of the particles within an allowable range, wherein i belongs to [1, n ], and n is the number of the particles;
step 6.2 p of the i-th particlebestSet to the current position of the particle, gbestSetting to be the optimal particle position in the initial population;
step 6.3, updating the position and the speed of the example according to the formula (4), the formula (5) and the formula (6);
x(t+1)＝x(t)+v(t+1) (4)
v(t+1)＝ωv(t)+c1r1(pbest(t)-x(t))+c2r2(gbest(t)-x(t)) (5)
Figure GDA0001663912000000102
wherein t is the current evolution algebra; c. C1、c2For learning factor, set c1＝c2＝2；r1、r2Is distributed in [0,1 ]]A random number within; p is a radical ofbestThe optimal solution of the particle individual is obtained; gbestA global optimal solution for the entire particle swarm; omega is an inertia coefficient; omegamax、ωminMaximum and minimum coefficients of inertia, respectively; t ismaxIs the maximum iteration number; τ is a weight coefficient, and is set to be 30;
step 6.4 calculate the fitness f (x) of the particle ii)，i∈[1,n]，f(xi) Is a fitness function;
step 6.5 if the fitness f (x) of the particle ii) Is superior to self individual extremum pbestFitness f (p) ofbest) Using the current position x of the particleiSubstitution of pbest；
Step 6.6 if the fitness f (x) of the particle ii) Is superior to the current global extreme gbestFitness f (g)best) Using the current position x of the particleiReplacement global extremum gbest；
Step 6.7 calculating the population fitness variance σ according to equation (7)2；
Figure GDA0001663912000000111
Wherein f isiIs the fitness function value of the ith particle, favgThe current average fitness function value of the particle swarm is taken as the current average fitness function value;
step 6.8, judging whether the algorithm meets the convergence condition, if so, turning to step 6.10, otherwise, turning to step 6.9;
6.9, performing chaotic search according to the formulas (8) and (9), randomly replacing a particle with the best searched feasible point, and then turning to the step 6.3;
Zi+1＝μZi(1-Zi),μ∈(2,4] (8)
x(t+1)＝xmin+Zi+1(xmax-xmin) (9)
wherein Z isi+1The variable is a chaotic variable, mu is a control parameter and is set to be 4; x is the number ofmaxIs the maximum value of the current position variable; x is the number ofminIs the minimum value of the current position variable;
step 6.10 output Global optimal solution gbestAnd the corresponding objective function value is obtained, and the algorithm is finished.
Step seven: solving the optimal operation parameter target value according to the sixth step
Figure GDA0001663912000000112
And external process variables
Figure GDA0001663912000000113
Figure GDA0001663912000000114
Figure GDA0001663912000000115
Will be provided with
Figure GDA0001663912000000116
The optimal internal operation parameters are issued to a control system of the solar lithium bromide refrigerating unit and operated, and the optimal external process variable is obtained
Figure GDA0001663912000000121
And the data driving PID algorithm is adopted by the controller to quickly track the target value of the external process variable, and a flow chart of the data driving PID control method is shown in figure 2.
And 7.1, decoupling the solar lithium bromide refrigerating unit into two independent control loops of L (solar water heating flow) -T (air conditioner water temperature) and W (air conditioner water temperature) -D (lithium bromide concentration) through an inverse decoupler, and controlling a two-degree-of-freedom data drive PID controller.
Step 7.2, using phi (j) to represent the input and output values and PID parameter values stored in the database;
Figure GDA0001663912000000128
wherein N is the number of information variables in the database;
φ(j)＝[y(j-1),y(j-2),...,y(j-ny),u(j-1),u(j-2),...,u(j-nu)]as information variable, y (j-n)y) And u (j-n)u) Respectively the output and control input of the system, nyAnd nuThe order of system output and control input, respectively;
Figure GDA0001663912000000122
Tp(j) proportional parameters of PID; t isi(j) Is an integral parameter of the PID; t isd(j) Is a differential parameter of the PID;
Figure GDA0001663912000000123
is PID parameter corresponding to phi (j);
step 7.3 calculate the Distance d between time t phi (t) and the information vector phi (j) in the database using Euclidean Distance methodtj：
Figure GDA0001663912000000124
The distance size metric phi (t) calculated by the equation (11) measures the similarity between each information vector phi (j) stored in the database; select k d in all information vectorstjThe information vector corresponding to the minimum;
step 7.4 calculating PID parameters
Figure GDA0001663912000000125
And 7.3, operating the k information vectors selected in the step 7.3, and obtaining the predicted estimated values of the parameters according to the k PID parameter values corresponding to the selected information vectors by using a Linear Weighted Average (LWA) method
Figure GDA0001663912000000126
Figure GDA0001663912000000127
Wherein, ω isiIs the weight of the ith information vector phi (i).
And 7.5, optimizing PID parameters by adopting a steepest descent method:
Figure GDA0001663912000000131
η＝diag{ηP,ηI,ηD} (14)
Figure GDA0001663912000000132
e(t)＝r(t)-y(t) (16)
where η is the learning rate, ηP、ηI、ηDLearning rates of proportion, integral and differential respectively; j (t) is an error criterion;
Figure GDA0001663912000000133
the deviation is calculated for the error criterion,
Figure GDA0001663912000000134
the PID parameter of the previous iteration cycle,
Figure GDA0001663912000000135
is the latest PID parameter of the current iteration cycle.
Step 7.6, updating the database and deleting redundant data;
firstly, k information vectors selected in the step 7.5 are excluded from redundant data to be deleted, and other distances d from the current input point are extracted from a databasetj≤σ1The information vector of (2); deleting redundant data of the database by using the similar criterion among PID parameters corresponding to the information vector in the formula (17);
Figure GDA0001663912000000136
wherein, Tl(i) The stored PID parameters for the database are,
Figure GDA0001663912000000137
is the PID parameter, σ, of the current iteration cycle1And σ2Respectively extracting suppression coefficients of deleted data from redundant data; setting sigma1＝σ2＝0.5。
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.

Claims (8)

1. The optimal control integration method of the overall modeling method of the solar lithium bromide refrigerating unit is characterized by comprising the following steps of:
the method comprises the following steps: determining input variable R of integral modeling of solar lithium bromide refrigerating uniti；
Step two: reconstructing the input variable R by C-C method phase spacei；
Step three: determining output variable S of integral modeling of solar lithium bromide refrigerating uniti；
Step four: establishing an integral model of the solar lithium bromide refrigerating unit based on a deep learning method;
step 1, determining an operation parameter optimization variable E of a solar lithium bromide refrigerating unitiAnd control target variable Ci(ii) a In the step 1, the operation parameter optimization variable E of the solar lithium bromide refrigerating unitiAnd control target variable CiThe method specifically comprises the following steps:
Ei＝[YZFQ,TTYN-J,LTYN,LKTS,LLQS,TLQS-J,LXHL,TXHL,LZLJ,TZLJ]；
Ci＝[TKTS-C,NXHL]；
wherein: y isZFQIs the pressure value, T, of the evaporator of the lithium bromide unitTYN-JThe temperature value L of the solar hot water entering lithium bromide unitTYNFlow value, T, for solar hot water to lithium bromide unitKTS-CTemperature value L of cold water discharged from lithium bromide unit for air conditioningKTSFlow value L of cold water discharged from lithium bromide unit for air conditioningLQSFlow value, T, for cooling water entering lithium bromide unitLQS-JTemperature value L of cooling water entering lithium bromide unitXHLIs the flow value, T, of the lithium bromide solutionXHLIs the temperature value, N, of the lithium bromide solutionXHLIs the concentration value of the lithium bromide solution, LZLJIs the flow rate value, T, of the refrigerantZLJIs the temperature value of the refrigerant;
step 2, determining an objective function for optimizing the operation parameters of the solar lithium bromide refrigerating unit;
step 3, solving the optimal operation parameter target value of the solar lithium bromide refrigerating unit by adopting a self-adaptive chaotic particle swarm optimization algorithm
Figure FDA0003514466510000011
And optimal external process variables
Figure FDA0003514466510000012
Step 4, mixing
Figure FDA0003514466510000013
The optimal internal operation parameters are issued to a control system of the solar lithium bromide refrigerating unit and operated, and the optimal external process variable is obtained
Figure FDA0003514466510000014
And the data is transmitted to controllers of the two control loops, and the controllers adopt a data-driven PID algorithm to quickly track the optimal external process variable value.
2. The method of claim 1, wherein the input variable R is an input variable in the step oneiComprises the following steps:
Ri＝[TTYN-C,TTYN-J,LTYN,TKTS-C,TKTS-J,LKTS,TLQS-C,TLQS-J,LLQS,TFSQ,WFSQ,TXSQ,WXSQ,TZLJ,LZLJ,TXHL,LXHL,NXHL,TZFQ,YZFQ]；
wherein: t isTYN-CTemperature value T of lithium bromide unit for solar hot water outletTYN-JTemperature value L of solar hot water entering lithium bromide unitTYNFlow value, T, for solar hot water to lithium bromide unitKTS-CTemperature value, T, of cold water discharged from lithium bromide unit for air conditioningKTS-JTemperature value L of air conditioner refrigerating water entering lithium bromide unitKTSFlow value, T, of cold water out of lithium bromide unit for air conditioningLQS-CTemperature value, T, for the cooling water leaving the lithium bromide unitLQS-JTemperature value L of cooling water entering lithium bromide unitLQSFlow value, T, for cooling water entering lithium bromide unitFSQIs the temperature value, W, in the generator of the lithium bromide unitFSQFor the level value, T, in the generator of the lithium bromide unitXSQIs the temperature value, W, in the lithium bromide unit absorberXSQFor the level value, T, in the absorber of the lithium bromide unitZLJIs the temperature value, L, of the refrigerantZLJIs the flow rate value, T, of the refrigerantXHLIs the temperature value, L, of the lithium bromide solutionXHLIs the flow rate value, N, of the lithium bromide solutionXHLAs concentration value of lithium bromide solution, TZFQIs the temperature value, Y, in the evaporator of the lithium bromide unitZFQThe pressure value of the evaporator of the lithium bromide unit is shown.
3. The optimal control integration method for the integration modeling method of the solar lithium bromide refrigerator set as claimed in claim 1 or 2, wherein in the second step, the phase space of the C-C method is adopted to reconstruct the input variable time series R of the integration modeling of the solar lithium bromide refrigerator setiSetting RiDelay time t ofiAnd embedding dimension miInput variable R of integral modeling of solar lithium bromide refrigerating unitiIs uniformly expressed as ri＝[ri(t),ri(t-ti),···,ri(t-(mi-1)ti)](ii) a R is to beiThe characteristic data is expressed as 20 XmiIs input variable time series vector ri。
4. The method as claimed in claim 1, wherein the step three is an output variable S of the overall modeling of the solar lithium bromide refrigerator setiComprises the following steps:
Si＝[COP,PKTS,PTYN,PLQS]；
wherein: COP is the efficiency parameter value, P, of the solar lithium bromide unitKTSProduction of air conditioner cold water power value, P, for solar lithium bromide unitTYNFor solar hot water power input to solar lithium bromide units, PLQSThe power of the cooling water of the solar lithium bromide unit.
5. The optimal control integration method of the overall modeling method of the solar lithium bromide refrigerating unit as claimed in claim 1, wherein the concrete method of the fourth step is as follows:
step 4.1, constructing a 5-layer DBN based on the RBM, wherein the DBN comprises 1 input layer, 3 hidden layers and 1 decision layer;
step 4.2, the number of input layer nodes of the DBN is specified to be 20 multiplied by 3600; the number of nodes of the first hidden layer is 500; the number of nodes of the second hidden layer is 500; the number of the nodes of the third hidden layer is 1000; the number of nodes of the decision layer is 4;
4.3, training 5 layers of the DBN layer by using a contrast divergence CD algorithm, and calculating output values of 3 hidden layers and 1 decision layer and weight values and offsets among the layers;
4.4, adjusting the whole DBN by using a BP algorithm, optimizing DBN parameters and finishing the global training of the DBN; the trained optimal weight and bias are used for obtaining the integral model parameter M of the solar lithium bromide uniti。
6. The method of claim 1, wherein the objective function in step 2 is the lowest operating cost NPV, Min NPVBR＝RCbr+Com+CeIn the formula: NPVBRIs cold and hotThe annual running cost of the power combined supply system is unit; r is the coefficient of investment recovery,
Figure FDA0003514466510000031
wherein l is the annual rate and m is the service life of the equipment; cbrThe method is characterized in that the method comprises the following steps: yuan, ComFor the maintenance and management expense of solar energy lithium bromide refrigerating unit, including equipment maintenance and maintenance expense, managers expense, unit: element;
Ce＝Je(PZKB+PKTSB+PLQSB+PXHLB+PZLJB+PLQFS)
in the formula, CeThe unit is the electricity consumption cost of the solar lithium bromide refrigerating unit: element; j. the design is a squareeFor electricity price, unit: yuan/kWh; pZKBFor lithium bromide unit evacuation pump power consumption, unit: kWh; pKTSBFor lithium bromide unit air conditioner water pump power consumption, unit: kWh; pLQSBFor lithium bromide unit cooling water pump power consumption, unit: kWh; pXHLBThe unit is the power consumption of a lithium bromide pump of a lithium bromide unit: kWh; pZLJBThe unit is the power consumption of the lithium bromide unit refrigerant pump: kWh; p isLQFSFor cooling tower cooling fan power consumption, unit: kWh.
7. The optimal control integration method for the overall modeling method of the solar lithium bromide refrigerating unit as claimed in claim 1, wherein the concrete method of the step 4 is as follows:
Figure FDA0003514466510000032
and
Figure FDA0003514466510000033
respectively as follows:
Figure FDA0003514466510000034
Figure FDA0003514466510000035
decoupling a solar lithium bromide refrigerating unit into two independent control loops of solar water heating flow, air conditioner water temperature and lithium bromide concentration by an inverse decoupler, and designing a two-degree-of-freedom data driving PID controller for control;
step (2) using phi (j) to represent input and output values and PID parameter values stored in a database;
Figure FDA0003514466510000041
wherein N is the number of information variables in the database;
φ(j)＝[y(j-1),y(j-2),...,y(j-ny),u(j-1),u(j-2),...,u(j-nu)]as information variable, y (j-n)y) And u (j-n)u) Respectively the output and control input of the system, nyAnd nuThe order of system output and control input, respectively;
Figure FDA0003514466510000042
Tp(j) proportional parameters of PID; t isi(j) Is an integral parameter of the PID; t isd(j) Is a differential parameter of the PID;
Figure FDA0003514466510000043
is PID parameter corresponding to phi (j);
step (3) calculating the distance d between phi (t) at the t moment and an information vector phi (j) in the database by using an Euclidean distance methodtj：
Figure FDA0003514466510000044
Distance size measurement calculated by equation (11)Similarity between phi (t) and each information vector phi (j) stored in the database; select k d in all information vectorstjThe information vector corresponding to the minimum;
step (4) calculating PID parameters
Figure FDA0003514466510000045
Operating the k information vectors selected in the step (3), and obtaining the predicted estimated values of the parameters according to the k PID parameter values corresponding to the selected information vectors by using a linear weighted average method
Figure FDA0003514466510000046
Figure FDA0003514466510000047
Wherein, ω isiIs the weight of the ith information vector phi (i);
and (5) optimizing PID parameters by adopting a steepest descent method:
Figure FDA0003514466510000048
η＝diag{ηP,ηI,ηD}
Figure FDA0003514466510000049
e(t)＝r(t)-y(t)
where η is the learning rate, ηP、ηI、ηDLearning rates of proportion, integral and differential respectively; j (t) is an error criterion;
Figure FDA0003514466510000051
the deviation is calculated for the error criterion,
Figure FDA0003514466510000052
the former oneThe PID parameters of the iteration cycle are,
Figure FDA0003514466510000053
the latest PID parameter of the current iteration cycle;
and (6) updating the database and deleting redundant data.
8. The optimal control integration method for the overall modeling method of the solar lithium bromide refrigerating unit as claimed in claim 7, wherein the concrete method of the step (6) is as follows:
step (6.1), excluding the k information vectors selected in the step (3) from redundant data to be deleted, and extracting other distances d from the current input point from the databasetj≤σ1The information vector of (2);
step (6.2), deleting redundant data of the database by using the similar criterion among PID parameters corresponding to the information vector in the formula (17);
Figure FDA0003514466510000054
wherein, Tl(i) For storing PID parameters, T, in the databasel new(t) is the PID parameter, σ, of the current iteration cycle1And σ2Suppression coefficients for extracting deleted data from the redundant data, respectively; setting sigma1＝σ2＝0.5。
CN201810353958.7A 2018-04-19 2018-04-19 Integral modeling and optimal control integrated method for solar lithium bromide refrigerating unit Active CN108563877B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810353958.7A CN108563877B (en) 2018-04-19 2018-04-19 Integral modeling and optimal control integrated method for solar lithium bromide refrigerating unit

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810353958.7A CN108563877B (en) 2018-04-19 2018-04-19 Integral modeling and optimal control integrated method for solar lithium bromide refrigerating unit

Publications (2)

Publication Number Publication Date
CN108563877A CN108563877A (en) 2018-09-21
CN108563877B true CN108563877B (en) 2022-05-17

Family

ID=63535903

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810353958.7A Active CN108563877B (en) 2018-04-19 2018-04-19 Integral modeling and optimal control integrated method for solar lithium bromide refrigerating unit

Country Status (1)

Country Link
CN (1) CN108563877B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109375896B (en) * 2018-10-29 2023-01-24 广东电网有限责任公司 Similar integration method and device
CN109858163B (en) * 2018-12-28 2021-04-06 清华大学 Active disturbance rejection feedforward control method of lithium bromide absorption refrigerator
CN109949180A (en) * 2019-03-19 2019-06-28 山东交通学院 A kind of the cool and thermal power load forecasting method and system of ship cooling heating and power generation system
CN110543702B (en) * 2019-08-16 2022-12-16 上海电力大学 Modeling method of internal combustion engine-lithium bromide combined cooling, heating and power system
CN113719929B (en) * 2021-08-05 2023-11-28 西安交通大学 Method and system for optimizing and controlling integrity of lithium bromide air conditioning system

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4327555A (en) * 1979-09-10 1982-05-04 Dimon Donald F Solar air conditioning system
CN104792079A (en) * 2015-04-10 2015-07-22 柳州职业技术学院 Temperature closed-loop control method for steam type lithium bromide absorption water chilling unit
CN106126906A (en) * 2016-06-22 2016-11-16 重庆科技学院 Short-term wind speed forecasting method based on C C Yu ELM

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015116362A1 (en) * 2014-01-09 2015-08-06 University Of Florida Research Foundation, Inc. Open absorption cycle for dehumidification, water heating, and evaporative cooling

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4327555A (en) * 1979-09-10 1982-05-04 Dimon Donald F Solar air conditioning system
CN104792079A (en) * 2015-04-10 2015-07-22 柳州职业技术学院 Temperature closed-loop control method for steam type lithium bromide absorption water chilling unit
CN106126906A (en) * 2016-06-22 2016-11-16 重庆科技学院 Short-term wind speed forecasting method based on C C Yu ELM

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
吸收式制冷机组逆神经网络设定优化;王亚昆;《西安交通大学学报》;20180131(第1期);第123-128页，第142页 *
基于深度置信网络的时间序列预测方法及其;张国辉;《中国优秀硕士学位论文全文数据库》;20180215(第02期);第16-39页 *

Also Published As

Publication number Publication date
CN108563877A (en) 2018-09-21

Similar Documents

Publication Publication Date Title
CN108563877B (en) Integral modeling and optimal control integrated method for solar lithium bromide refrigerating unit
CN110288164B (en) Predictive control method for building air-conditioning refrigeration station system
CN104566868B (en) A kind of central air conditioning system and its control method
CN103020481B (en) A kind of method based on energy-conservation determination air source heat pump floor heating optimal operating condition
CN111723456A (en) Central air-conditioning system energy efficiency optimization method based on NSGA-II algorithm
CN101782261B (en) Nonlinear self-adapting energy-saving control method for heating ventilation air-conditioning system
CN109945402A (en) A kind of central air conditioning water system power-economizing method
CN108990383A (en) A kind of data center's air-conditioning system forecast Control Algorithm
CN114383299B (en) Central air-conditioning system operation strategy optimization method based on big data and dynamic simulation
CN105303247A (en) Garden type hot and cold energy mixed application energy network regulation method and system
CN116398994B (en) Water chilling unit group control optimization method based on load prediction
CN109472413A (en) Consider the garden integrated energy system Optimization Scheduling of hot pipe network transmission characteristic
KR20180138371A (en) Method for evaluating data based models and conducting predictive control of capsule type ice thermal storage system using the same
Zhao et al. An online predictive control method with the temperature based multivariable linear regression model for a typical chiller plant system
Liu et al. Optimization of intelligent heating ventilation air conditioning system in urban building based on BIM and artificial intelligence technology
CN103761385A (en) Optimized design method for mult-heat-source annular pipe network
Irshad et al. Novel optimized hybrid neuro-fuzzy approach for analysis of cold thermal storage system-assisted air conditioning system performance
CN111473480A (en) Central air conditioner energy-saving control method based on decision tree classification
CN116499023A (en) Intelligent control method and system for geothermal coupling solar heating station
CN116777154A (en) Comprehensive energy system scheduling method based on distributed near-end strategy gradient algorithm
CN115577828A (en) Air conditioner refrigerating station system group control method based on data-driven modeling and optimization
Mei et al. Energy efficiency prediction of screw chillers on BP neural network optimized by improved genetic algorithm
Li et al. Thermal comfort control based on MEC algorithm for HVAC systems
Zhang et al. Optimization of ice-storage air conditioning system With ASAGA
CN110595008A (en) Multi-equipment collaborative optimization method and system for ground source heat pump air conditioning system

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
CP02 Change in the address of a patent holder
CP02 Change in the address of a patent holder

Address after: 250023 No. 5 Jiao Tong Road, Tianqiao District, Shandong, Ji'nan

Patentee after: SHANDONG JIAOTONG University

Address before: No. 5001, Haitang Road, Science Park, Changqing University, Changqing District, Jinan City, Shandong Province

Patentee before: SHANDONG JIAOTONG University