Control method and device of water chilling unit, storage medium and air conditioning system

Abstract

The invention discloses a control method and device of a water chilling unit, a storage medium and an air conditioning system.The control method of the water chilling unit comprises the steps that data of the water chilling unit at the current moment are obtained, and the load change condition of the air conditioning system at the next moment is determined according to the data of the water chilling unit; and if the load of the air conditioning system changes at the next moment, the target compressor rotating speed and the target inlet guide vane opening degree are determined according to the water chilling unit data through the particle swarm optimization method, and the water chilling unit is controlled according to the target compressor rotating speed and the target inlet guide vane opening degree. According to the control method of the water chilling unit, a particle swarm optimization method is used for achieving the optimizing process during variable load adjustment of the water chilling unit, so that an air conditioning system is in the optimal operation state meeting the load requirement and the lowest energy consumption, and the method is suitable for different types of water chilling units; and meanwhile, the method is suitable for two different processes of loading or unloading of the same type of water chilling units, and has good universality.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning, and in particular to a control method, device, storage medium and air conditioning system for a chiller. Background Art

[0002] Building energy consumption accounts for about one-third of my country's total social energy consumption, of which HVAC systems account for more than two-thirds of building energy consumption. In summer, chillers account for the highest proportion of HVAC energy consumption, exceeding 50%. Therefore, improving the operating efficiency of chillers is an important means of energy conservation and emission reduction, and is one of the effective ways for my country to achieve its carbon neutrality goal.

[0003] In the related art, a single-head variable frequency centrifugal chiller usually uses water temperature as the control target, and performs PID (Proportion Integral Derivative) control based on the difference between the actual water temperature and the target water temperature, so as to adjust the operating speed of the compressor and the opening of the inlet guide vane. However, the load rate of the actual process changes faster, and the variable frequency adjustment of the centrifugal compressor often deviates from its optimal operating point. Therefore, the centrifugal chiller is in a low energy efficiency zone during operation. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems in the related art to a certain extent. To this end, one purpose of the present invention is to propose a control method, device, storage medium and air-conditioning system for a chiller, and to use a particle swarm optimization method to realize the optimization process of the chiller during variable load adjustment. The algorithm can be used on the edge side of the device and can also be uploaded to the cloud. The air-conditioning system is in the best operating state that meets both the load demand and the minimum energy consumption by performing real-time optimization through detection data. The method is applicable to different types of chillers, and is also applicable to two different processes of loading or unloading of the same type of chiller, and has good versatility.

[0005] To achieve the above-mentioned purpose, the first aspect of the present invention proposes a control method for a chiller, the method comprising: obtaining chiller data at the current moment, and determining the load change of the air-conditioning system at the next moment based on the chiller data; if the load of the air-conditioning system changes at the next moment, using a particle swarm optimization method to determine the target compressor speed and the target inlet guide vane opening based on the chiller data, and controlling the chiller based on the target compressor speed and the target inlet guide vane opening.

[0006] In addition, the control method of the chiller proposed in the above embodiment of the present invention may also have the following additional technical features:

[0007] According to one embodiment of the present invention, the chiller data includes unit-side data and user-side data, the user-side data includes real-time load and load demand, and determining the load change of the air-conditioning system at the next moment based on the chiller data includes: calculating the cooling capacity of the unit based on the unit-side data, and determining the load change of the air-conditioning system at the next moment based on the cooling capacity of the unit and the load demand.

[0008] According to one embodiment of the present invention, the unit side data includes a chilled water inlet water temperature, a cooling water inlet water temperature, a compressor speed and an inlet guide vane opening, and the unit cooling capacity is calculated based on the unit side data, and the load change of the air-conditioning system at the next moment is determined based on the unit cooling capacity and the load demand, including: calculating the unit cooling capacity based on the chilled water inlet water temperature, the cooling water inlet water temperature, the compressor speed and the inlet guide vane opening, and calculating the difference between the unit cooling capacity and the load demand; if the difference is greater than a preset difference threshold, determining the load change of the air-conditioning system at the next moment, otherwise determining that the load of the air-conditioning system at the next moment remains unchanged.

[0009] According to one embodiment of the present invention, the method of using a particle swarm optimization to determine a target compressor speed and a target inlet guide vane opening according to the chiller data includes: initializing a particle swarm, the particle swarm includes N particles, each of the particles includes a set of compressor speeds and inlet guide vane openings; in each iteration, inputting each of the particles in the current particle swarm into a preset unit capacity model and a preset unit power model, respectively, to obtain the load capacity and power of each of the particles; calculating the fitness of each of the particles according to the load capacity and power of each of the particles, and obtaining the target compressor speed and the target inlet guide vane opening according to the fitness and the current number of iterations.

[0010] According to one embodiment of the present invention, the target compressor speed and the target inlet guide vane opening are obtained according to the fitness and the current number of iterations, including: obtaining the global optimal fitness and the local optimal fitness of each particle up to the current iteration according to the fitness; judging whether the current number of iterations is greater than or equal to the preset number of iterations; if the current number of iterations is greater than or equal to the preset number of iterations, judging whether the load capacity corresponding to the global optimal fitness meets the load requirement; if the load requirement is met, the compressor speed and inlet guide vane opening corresponding to the global optimal fitness are used as the target compressor speed and the target inlet guide vane opening respectively; if the current number of iterations is less than the preset number of iterations, updating the current particle group according to the local optimal fitness and the global optimal fitness for the next iteration.

[0011] According to an embodiment of the present invention, the fitness function used to calculate the fitness includes a constraint function and an objective function, the constraint function is constructed according to the load capacity and the load demand, and the objective function is constructed according to the power.

[0012] According to an embodiment of the present invention, the constraint function is a function that makes the difference between the load capacity and the load demand zero, and the objective function is a function that minimizes the power.

[0013] According to one embodiment of the present invention, the preset unit capacity model and the preset unit power model are established by the following method: obtaining sample data and preprocessing the sample data, wherein the sample data includes chiller operation data and / or chiller simulation data, and the preprocessing includes physical logic screening and / or abnormal point cleaning; performing parameter importance analysis on the preprocessed sample data, and determining the fitting function form based on the analysis results, wherein the fitting function form includes the class and number of terms of the fitting function; training the model constructed by the fitting function, and determining whether the accuracy of the trained model meets the preset accuracy requirements; if the model accuracy meets the preset accuracy requirements, outputting the trained model, otherwise, returning to the step of preprocessing the sample data.

[0014] According to an embodiment of the present invention, the method further includes: if the load capacity corresponding to the global optimal fitness does not meet the load requirement, returning to the step of initializing the particle swarm.

[0015] According to an embodiment of the present invention, the method further includes: if the load of the air conditioning system remains unchanged at the next moment, determining the current compressor speed as the target compressor speed, and determining the current inlet guide vane opening as the target inlet guide vane opening.

[0016] The control method of the chiller of the embodiment of the present invention first obtains the data of the chiller, and judges the load change of the air-conditioning system at the next moment according to the data of the chiller, as long as the load of the air-conditioning system at the next moment changes. Whether loading or unloading, the particle swarm optimization method is used to search for the combination array of the compressor speed and the inlet guide vane opening that meets the current load demand and has the lowest power consumption, and the particle swarm optimization method is used to realize the optimization process during the variable load adjustment of the chiller, so that the air-conditioning system is in the best operating state that meets both the load demand and the lowest energy consumption. The method is applicable to different types of chillers, and is also applicable to the two different processes of loading or unloading of the same type of chillers, and has good versatility. In addition, the particle swarm optimization method is used to directly obtain the optimal compressor speed and the optimal inlet guide vane opening, and the compressor speed and the inlet guide vane opening are directly controlled, eliminating the compressor PID controller, and also eliminating the personalized configuration of the unit operating environment such as parameter setting, thereby improving the deployment and debugging efficiency. The proposed chiller control method has obvious intelligent characteristics and can improve product competitiveness.

[0017] To achieve the above objectives, a second aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the control method of the chiller as described above is implemented.

[0018] To achieve the above-mentioned purpose, the third aspect of the present invention proposes a control device for a chiller, which includes: an acquisition module, used to acquire the chiller data at the current moment, and determine the load change of the air-conditioning system at the next moment based on the chiller data; a control module, used to determine the target compressor speed and the target inlet guide vane opening according to the chiller data using a particle swarm optimization method when the load of the air-conditioning system changes at the next moment, and control the chiller according to the target compressor speed and the target inlet guide vane opening.

[0019] To achieve the above-mentioned object, a fourth aspect of the present invention provides an air-conditioning system, including a chiller and a control device for the chiller as described above.

[0020] The control method, device, storage medium and air-conditioning system of the chiller according to the embodiment of the present invention realize the method + advantage.

[0021] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a flow chart of a method for controlling a chiller according to an embodiment of the present invention;

[0023] Figure 2 is a flow chart of determining the load change of the air conditioning system at the next moment according to an embodiment of the present invention;

[0024] Figure 3 is a flow chart of determining a target compressor speed and a target inlet guide vane opening by using a particle swarm optimization method according to an embodiment of the present invention;

[0025] Figure 4 is a flow chart of determining a target compressor speed and a target inlet guide vane opening according to fitness and the current number of iterations according to an embodiment of the present invention;

[0026] Figure 5 is a flow chart of a chiller operation control method according to an embodiment of the present invention;

[0027] Figure 6 is a flow chart of establishing a preset unit capability model and a preset unit power model according to an embodiment of the present invention;

[0028] Figure 7 is a schematic diagram of a chiller capacity model and energy consumption model training process according to an embodiment of the present invention;

[0029] Figure 8 is a schematic diagram of a control device for a chiller according to an embodiment of the present invention;

[0030] Fig. 9 Schematic diagram of an air conditioning system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0032] The control method, device, storage medium and air-conditioning system of the chiller according to the embodiment of the present invention will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0033] Figure 1 The present invention is a flowchart of a method for controlling a chiller according to an embodiment of the present invention.

[0034] In one embodiment of the present invention, Figure 1 As shown, the control method of the chiller includes:

[0035] S1, obtaining the chiller data at the current moment, and determining the load change of the air-conditioning system at the next moment according to the chiller data.

[0036] Specifically, the control method of the chiller proposed in the present invention uses the idea of ​​real-time optimization to reduce the energy consumption of the chiller compressor so that the system is in the real-time energy efficiency optimization during operation. To achieve real-time optimization, it is first necessary to collect the chiller data in real time, and judge the load change of the air-conditioning system at the next moment through the collected operating parameters of the chiller. If the load of the air-conditioning system increases at the next moment, the chiller will go through a loading process; if the load of the air-conditioning system decreases at the next moment, the chiller will go through a load reduction process. The optimization algorithm of the chiller proposed in the present invention can be applied to both the situation of chiller loading and the situation of chiller load reduction.

[0037] Specifically, the chiller data can be divided into unit-side data and user-side data according to the different data application scopes, wherein the unit-side data includes parameters such as the chilled water inlet temperature, the cooling water inlet temperature, the compressor speed, and the inlet guide vane opening, and the user-side data includes real-time load and load demand. The real-time load and load demand in the user-side data can be used to determine whether the real-time load meets the load demand. If the real-time load does not meet the load demand, the load of the air-conditioning system at the next moment should be increased. If the real-time load exceeds the load demand, the load of the air-conditioning system at the next moment should be reduced.

[0038] In addition to judging the load change of the air-conditioning system at the next moment by the difference between the real-time load and the load demand, the load change of the air-conditioning system at the next moment can also be judged by the difference between the cooling capacity of the unit calculated by the data on the chiller side and the load demand.

[0039] In one embodiment of the present invention, the chiller data includes unit-side data and user-side data, the user-side data includes real-time load and load demand, and the load change of the air-conditioning system at the next moment is determined based on the chiller data, including: calculating the cooling capacity of the unit based on the unit-side data, and determining the load change of the air-conditioning system at the next moment based on the cooling capacity and load demand of the unit.

[0040] Specifically, the unit cooling capacity can be calculated based on the unit side data, and then the load change of the air-conditioning system at the next moment can be determined based on the unit cooling capacity and load demand. If the unit cooling capacity is greater than the load demand, in order to make the air-conditioning system in the minimum energy consumption operating state, the load of the air-conditioning system at the next moment needs to be reduced. If the unit cooling capacity is less than the load demand, the load of the air-conditioning system at the next moment needs to be increased. Only when the unit cooling capacity is equal to the load demand, the air-conditioning system is in the best operating state.

[0041] In one embodiment of the present invention, Figure 2As shown, the unit side data includes the chilled water inlet temperature, the cooling water inlet temperature, the compressor speed and the inlet guide vane opening. The unit cooling capacity is calculated based on the unit side data, and the load change of the air conditioning system at the next moment is determined based on the unit cooling capacity and load demand, including:

[0042] S101, calculating the cooling capacity of the group according to the chilled water inlet temperature, the cooling water inlet temperature, the compressor speed and the inlet guide vane opening, and calculating the difference between the cooling capacity of the group and the load demand.

[0043] S102: If the difference is greater than a preset difference threshold, determining a load change of the air-conditioning system at the next moment; otherwise, determining that the load of the air-conditioning system at the next moment remains unchanged.

[0044] Specifically, the unit side data is collected in real time, wherein the unit side data includes parameters such as the chilled water inlet water temperature, the cooling water inlet water temperature, the compressor speed and the inlet guide vane opening, and the unit cooling capacity under the current situation is calculated according to the currently collected chilled water inlet water temperature, the cooling water inlet water temperature, the compressor speed and the inlet guide vane opening, and the difference between the unit cooling capacity and the load demand is calculated. The difference is an absolute value. If the difference is greater than the preset difference threshold, the load change of the air-conditioning system at the next moment may be a load increase or a load decrease. The preset difference threshold is 0 in an ideal state, that is, in reality, it is difficult for the unit cooling capacity of the air-conditioning system to fully track the load demand. The preset difference threshold can be set to a value close to 0. The smaller the preset difference threshold is set, the more accurate it is. If the difference between the unit cooling capacity and the load demand is less than or equal to the preset difference threshold, it is determined that the load of the air-conditioning system at the next moment remains unchanged, and there is no need to perform optimal control on the air-conditioning system.

[0045] The present invention uniformly processes the two changes of loading or unloading of the air-conditioning system at the next moment, that is, when the load of the air-conditioning system changes at the next moment, the air-conditioning system is processed by an optimization algorithm. The present invention uses a particle swarm optimization method to search for a combination array of compressor speed and inlet guide vane opening that meets the current load demand and has the lowest power consumption.

[0046] S2, if the load of the air-conditioning system changes at the next moment, the target compressor speed and the target inlet guide vane opening are determined according to the chiller data using the particle swarm optimization method, and the chiller is controlled according to the target compressor speed and the target inlet guide vane opening.

[0047] Among them, the target compressor speed and the target inlet guide vane opening are the compressor speed and the inlet guide vane opening that meet the current load demand of the air-conditioning system and minimize the power consumption, and the chiller is controlled according to the target compressor speed and the target inlet guide vane opening to put the air-conditioning system in the best operating state. In addition, the present invention proposes a method for directly adjusting the compressor speed and the inlet guide vane opening, without the need to use PID control, eliminating the need for parameter setting and personalized configuration, and improving the deployment and debugging efficiency.

[0048] In one embodiment of the present invention, Figure 3 As shown in FIG. 1 , the target compressor speed and the target inlet guide vane opening are determined according to the chiller data using the particle swarm optimization method, including:

[0049] S21, initializing a particle swarm, the particle swarm includes N particles, each particle includes a set of compressor speed and inlet guide vane opening.

[0050] S22, in each iteration, each particle in the current particle group is input into a preset unit capacity model and a preset unit power model respectively to obtain the load capacity and power of each particle.

[0051] S23, calculating the fitness of each particle according to the load capacity and power of each particle, and obtaining the target compressor speed and the target inlet guide vane opening according to the fitness and the current number of iterations.

[0052] Specifically, the particle swarm optimization method is used to search for a combination array of compressor speed and inlet guide vane opening that meets the current load demand and has the lowest power consumption. A particle swarm of size N is established based on the above-collected unit-side data and initialized. Each particle includes a set of compressor speed and inlet guide vane opening. For example, let each particle be numbered j, the current iteration step be i, and the compressor speed be spd j,i , the inlet guide vane opening is igv j,i , j = 1, 2, 3 ... N, with the compressor speed as spd j,i and the inlet guide vane opening is igv j,i Combined data as a particle, N groups of compressor speeds are spd j,i and the inlet guide vane opening is igv j,i The combined data constitutes a particle swarm.

[0053] Each particle in the current particle swarm is input into the established preset unit capacity model and preset unit power model to obtain the load capacity and power of each particle, and then the fitness of each particle is calculated according to the load capacity and power of each particle, and the target compressor speed and target inlet guide vane opening are obtained according to the fitness and the current number of iterations.

[0054] In one embodiment of the present invention, Figure 4 As shown, the target compressor speed and the target inlet guide vane opening are obtained according to the fitness and the current number of iterations, including:

[0055] S231, obtaining the global optimal fitness up to the current iteration and the local optimal fitness of each particle according to the fitness.

[0056] S232, determining whether the current number of iterations is greater than or equal to a preset number of iterations.

[0057] S233: If the current number of iterations is greater than or equal to the preset number of iterations, it is determined whether the load capacity corresponding to the global optimal fitness meets the load demand.

[0058] S234: If the load demand is met, the compressor speed and inlet guide vane opening corresponding to the global optimal fitness are used as the target compressor speed and the target inlet guide vane opening, respectively.

[0059] S235: If the current number of iterations is less than the preset number of iterations, the current particle swarm is updated according to the local optimal fitness and the global optimal fitness to perform the next iteration.

[0060] Specifically, the established particles are input into the preset unit capacity model and the preset unit power model to obtain the load capacity and power of each particle, and the fitness of each particle is calculated according to the load capacity and power of each particle. Then, the global optimal fitness at the current iteration and the local optimal fitness of each particle are calculated according to the fitness of each particle, wherein the global optimal fitness at the current iteration corresponds to a set of compressor speeds and inlet guide vane openings, and the local optimal fitness of each particle corresponds to a set of compressor speeds and inlet guide vane openings of each particle.

[0061] Specifically, it is determined whether the current number of iterations is greater than or equal to the preset number of iterations. If the current number of iterations is greater than or equal to the preset number of iterations, it means that the number of iterations has reached the preset number of iterations. The preset number of iterations can be configured. After the number of iterations is satisfied, it does not necessarily mean that the load capacity corresponding to the global optimal fitness at this time meets the load demand. It is also necessary to judge the load capacity corresponding to the global optimal fitness at this time. If the load capacity corresponding to the global optimal fitness at this time meets the load demand, the compressor speed and inlet guide vane opening corresponding to the global optimal fitness are used as the target compressor speed and target inlet guide vane opening respectively, and the target compressor speed and target inlet guide vane opening are used to control the chiller. If the current number of iterations is less than the preset number of iterations, the current particle swarm is updated according to the local optimal fitness and the global optimal fitness for the next iteration.

[0062] Among them, the compressor speed and inlet guide vane opening corresponding to the global optimal fitness can be recorded as the global optimal compressor speed and the global optimal inlet guide vane opening, and the local optimal fitness of each particle can be recorded as the local optimal compressor speed and the local optimal inlet guide vane opening corresponding to each particle. The current particle swarm is updated according to the local optimal fitness and the global optimal fitness, including: updating the compressor speed in the particle swarm according to the local optimal compressor speed and the global optimal compressor speed of each particle, updating the inlet guide vane opening in the particle swarm according to the local optimal inlet guide vane opening and the global optimal inlet guide vane opening of each particle, obtaining a new particle swarm, inputting each particle in the current particle swarm into the preset unit capacity model and the preset unit power model, respectively, obtaining the load capacity and power of each particle, and performing the next iteration until the current number of iterations is greater than or equal to the preset number of iterations.

[0063] In one embodiment of the present invention, the control method of the chiller further includes: if the load capacity corresponding to the global optimal fitness does not meet the load demand, returning to the step of initializing the particle swarm.

[0064] Specifically, if the current iteration number of the particle swarm is greater than or equal to the preset iteration number, the load capacity corresponding to the global optimal fitness at this time is judged. If the load capacity corresponding to the global optimal fitness at this time does not meet the load requirement, the step of initializing the particle swarm is returned.

[0065] Figure 5 FIG. 1 is a flow chart of a chiller operation control method according to an embodiment of the present invention. Figure 5 As shown, first collect the unit side data and user side data. The unit side data includes the chilled water inlet water temperature Tin_eva and the cooling water inlet water temperature Tin_con, the compressor speed spd and the inlet guide vane opening igv. The user side data includes the real-time load Q and the load demand Qn. The load change of the air-conditioning system at the next moment is judged according to the collected chiller data. This method has been described above and will not be repeated here. If the load of the air-conditioning system changes at the next moment, the particle swarm optimization method is used to search for the combination array of the compressor speed and the inlet guide vane opening that meets the current load demand and has the lowest power consumption. The details are as follows: Initialize (the current iteration step i=1 at the time of initialization) a particle swarm of size N, and each particle (numbered j) takes the compressor speed as spd j,i and the inlet guide vane opening is igv j,i The combined data is used as its position parameter, and the combined array is used to input the established unit capacity model and unit power model to obtain the load capacity Q of each particle. j,i , the power P of each particle j,i , and then calculate the fitness f of each particle separately j,i(j=1,2,…,N), further calculate the local optimal fitness f of each particle from the start of the search to the current iteration step i j,best And record the corresponding local optimal compressor speed spd j,best and the local optimal inlet guide vane opening igv j,best , and calculate the global optimal fitness f of all particles best , and record the corresponding global optimal compressor speed spd best and the global optimal inlet guide vane opening igv best , determine whether the current iteration step is less than the preset number of iterations. If so, update the position parameters of each particle according to the global optimal position parameters and the local optimal position parameters until the optimization is completed. Finally, determine the global optimal position parameters output by the algorithm, that is, the global optimal compressor speed spd best and the global optimal inlet guide vane opening igv best Whether the corresponding load capacity meets the load demand, if so, it will be used as the adjustment target value of the operating speed and inlet guide vane opening at the next moment. At this time, the unit operates according to the input compressor parameters and can achieve low power consumption; if the global optimal compressor speed spd best and the global optimal inlet guide vane opening igv best If the unit capacity model calculated by the combined array cannot meet the real-time load demand, the optimization is re-searched.

[0066] In one embodiment of the present invention, Figure 5 As shown, the control method of the chiller also includes: if the load of the air-conditioning system remains unchanged at the next moment, determining the current compressor speed as the target compressor speed, and determining the current inlet guide vane opening as the target inlet guide vane opening.

[0067] Specifically, if, when judging the load addition and reduction of the air-conditioning system, it is determined that the load of the air-conditioning system remains unchanged at the next moment, the current compressor speed and the current inlet guide vane opening are already the compressor speed and the current inlet guide vane opening in the optimal state, the current compressor speed is determined as the target compressor speed, the current inlet guide vane opening is determined as the target inlet guide vane opening, and the chiller is controlled according to the target compressor speed and the target inlet guide vane opening.

[0068] In one embodiment of the present invention, the fitness function used to calculate the fitness includes a constraint function and an objective function, the constraint function is constructed according to the load capacity and the load demand, and the objective function is constructed according to the power.

[0069] Specifically, the compressor speed is spd j,i and the inlet guide vane opening is igv j,iCombine the data input into the established unit capacity model and unit power model to obtain the load capacity Q of each particle j,i , the power P of each particle j,i , according to the load capacity Q of each particle j,i and load demand Q n Construct a fitness function, where the fitness function may include a constraint function and an objective function, according to the load capacity Q of each particle j,i and load demand Q n Construct a constraint function based on the power P of each particle j,i Construct the objective function, integrate the constraint function and the objective function as the fitness function, and calculate the fitness f of each particle separately j,i (j=1,2,…,N).

[0070] In one embodiment of the present invention, the constraint function is a function that makes the difference between the load capacity and the load demand zero, and the objective function is a function that minimizes the power.

[0071] Specifically, according to the load capacity Q of each particle j,i and load demand Q n Construct a constraint function that can transform the load capacity Q of each particle j,i and load demand Q n The difference between them is used as a constraint condition, and the constraint function can be load capacity Q j,i and load demand Q n The difference between the two functions is zero, that is, Q j,i -Q n = 0. According to the power P of each particle j,i Construct the objective function, which can be to make the power P j,i The smallest function, that is, min(P j,i ).

[0072] Each particle in the particle swarm is input into the preset unit capacity model and the preset unit power model to obtain the load capacity Q of each particle. j,i and power P j,i , and the preset unit capability model and the preset unit power model are pre-trained models. The method of the present invention using the pre-trained unit capability model and the unit power model can perform parameter identification on the measured data of the actual unit, and has good applicability.

[0073] In one embodiment of the present invention, Figure 6 As shown, the preset unit capability model and the preset unit power model are established by the following method:

[0074] S301, acquiring sample data and preprocessing the sample data, wherein the sample data includes chiller operation data and / or chiller simulation data, and the preprocessing includes physical logic screening and / or abnormal point cleaning;

[0075] S302, performing parameter importance analysis on the preprocessed sample data, and determining a fitting function form according to the analysis result, wherein the fitting function form includes the class and number of terms of the fitting function;

[0076] S303, training the model formed by the fitting function, and determining whether the accuracy of the trained model meets the preset accuracy requirement;

[0077] S304: If the model accuracy meets the preset accuracy requirement, the trained model is output; otherwise, the process returns to the step of preprocessing the sample data.

[0078] Specifically, to train the preset unit capacity model and the preset unit power model, it is first necessary to obtain a training set, i.e., sample data, which includes chiller operation data and / or chiller simulation data. The sample data is preprocessed, and the preprocessing may include physical logic screening and / or abnormal point cleaning. The preprocessed sample data is subjected to parameter importance analysis, and the fitting function form is determined according to the analysis results, wherein the fitting function form includes the class and number of terms of the fitting function.

[0079] As an example, the unit capacity model Q = f (spd, igv, EWT_con, EWT_eva) and the unit power model P = f (spd, igv, EWT_con, EWT_eva) can be established, where Q is the unit cooling capacity, spd is the compressor operating speed, igv is the inlet guide vane opening, EWT_con is the condenser inlet water temperature, EWT_eva is the evaporator inlet water temperature, and P is the compressor power. The compressor operating speed spd ranges from 9000rpm to 18000rpm; the inlet guide vane opening igv ranges from 0 to 100; the evaporator inlet water temperature EWT_eva ranges from 8 to 12°C; the condenser inlet water temperature EWT_con ranges from 20 to 40°C.

[0080] The unit capability model and the unit power model can be cubic polynomial fitting models, and the unit capability model Q fitting polynomial is as follows:

[0081] Q=a0+a1spd+a2igv+a3EWT_con+a4EWT_eva+a5spd*EWT_con+a6spd*EWT_eva+a7EWT_con*EWT_eva+a8spd*igv+a9spd 2 +a 10 spd 3

[0082] Among them, a0, a1, …, a 10 is the coefficient of the fitting model of the unit capability model Q.

[0083] The unit power model P polynomial is as follows:

[0084] P=b0+b1spd+b2igv+b3EWT_con+b4EWT_eva+b5spd*EWT_con+b6spd*EWT_eva+b7EWT_con*EWT_eva+b8spd*igv+b9spd 2 +b 10 spd 3

[0085] Among them, b0, b1, …, b 10 is the coefficient of the fitting model of the unit power model P.

[0086] After the fitting polynomial is established, the fitting function is trained, and it is determined whether the model accuracy after training meets the preset accuracy requirement. The preset accuracy requirement can be an accuracy requirement. When the accuracy of the model accuracy reaches the preset accuracy, it is determined that the model accuracy after training meets the preset accuracy requirement. The model that meets the preset accuracy requirement is the trained model, otherwise the sample data is returned to the preprocessing step, and the sample data is continued to be trained until the model accuracy meets the preset accuracy requirement.

[0087] like Figure 7 An example of training a unit capability and power model is shown. In order to obtain a higher-precision unit capability model and unit power model and reduce the impact of abnormal data on the model, it is necessary to filter and clean the real-time data collected during the unit operation. The method for improving the model calculation accuracy mentioned in this embodiment can be used for both real-time operation data and generated data for system simulation. Specific process: The obtained data (operation / simulation) is cleaned through physical logic screening and anomaly detection algorithm, and then the cleaned data set is used to perform parameter importance analysis to determine the fitting function form (order and number of terms), and then the model is trained, and then it is determined whether the model accuracy meets the set value. If not, continue to perform anomaly detection and regenerate the data set training model until the model accuracy meets the requirements.

[0088] In addition, for scenarios with severe load fluctuations, a combination of traditional PID regulation and the optimization control proposed in the present invention can be adopted, that is, the real-time load regulation of the unit is mainly based on traditional PID regulation, and optimization control is performed regularly to improve the stability of unit control.

[0089] The control method of the chiller of the embodiment of the present invention first obtains the data of the chiller, and judges the load change of the air-conditioning system at the next moment according to the data of the chiller, as long as the load of the air-conditioning system at the next moment changes. Whether loading or unloading, the particle swarm optimization method is used to search for the combination array of the compressor speed and the inlet guide vane opening that meets the current load demand and has the lowest power consumption, and the particle swarm optimization method is used to realize the optimization process during the variable load adjustment of the chiller, so that the air-conditioning system is in the best operating state that meets both the load demand and the lowest energy consumption. The method is applicable to different types of chillers, and is also applicable to the two different processes of loading or unloading of the same type of chillers, and has good versatility. In addition, the particle swarm optimization method is used to directly obtain the optimal compressor speed and the optimal inlet guide vane opening, and the compressor speed and the inlet guide vane opening are directly controlled, eliminating the compressor PID controller, and also eliminating the personalized configuration of the unit operating environment such as parameter setting, thereby improving the deployment and debugging efficiency. The proposed chiller control method has obvious intelligent characteristics and can improve product competitiveness.

[0090] The present invention also provides a computer-readable storage medium.

[0091] In one embodiment of the present invention, a computer program is stored on a computer-readable storage medium, and when the computer program is executed by a processor, the control method of the chiller as described above is implemented.

[0092] The invention also provides a control device for the chiller.

[0093] In one embodiment of the present invention, Figure 8 As shown, the control device 100 of the chiller includes: an acquisition module 10, which is used to acquire the chiller data at the current moment, and determine the load change of the air-conditioning system at the next moment according to the chiller data; a control module 20, which is used to determine the target compressor speed and the target inlet guide vane opening according to the chiller data by using a particle swarm optimization method when the load of the air-conditioning system changes at the next moment, and control the chiller according to the target compressor speed and the target inlet guide vane opening.

[0094] The invention also provides an air conditioning system.

[0095] In one embodiment of the present invention, Fig. 9 As shown, the air conditioning system 1000 includes a chiller 200 and the above-mentioned chiller control device 100.

[0096] The computer-readable storage medium, the control device of the chiller and the air-conditioning system of the embodiment of the present invention use the control method of the chiller to search for the combination array of the compressor speed and the inlet guide vane opening that meets the current load demand and has the lowest power consumption by using the particle swarm optimization method, so that the air-conditioning system is in the best operating state that meets both the load demand and the lowest energy consumption, and the method is applicable to different types of chillers, and is also applicable to the two different processes of loading or unloading of the same type of chillers, and has good versatility. In addition, the particle swarm optimization method is used to directly obtain the optimal compressor speed and the optimal inlet guide vane opening, and the compressor speed and the inlet guide vane opening are directly controlled, eliminating the compressor PID controller, and also eliminating the personalized configuration of the unit operating environment such as parameter setting, thereby improving the deployment and debugging efficiency. The proposed chiller control method has obvious intelligent characteristics and can improve the competitiveness of the product.

[0097] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0098] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0099] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0100] In the description of the present invention, it is to be understood that the terms “center”, “longitudinal”, “lateral”, “length”, “width”, “thickness”, “up”, “down”, “front”, “back”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, “clockwise”, “counterclockwise”, “axial”, “radial”, “circumferential”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0101] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0102] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0103] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0104] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A control method for a chiller, characterized in that: The method comprises: Acquire the chiller data at the current moment, and determine the load change of the air-conditioning system at the next moment according to the chiller data; If the load of the air-conditioning system changes at the next moment, the target compressor speed and the target inlet guide vane opening are determined according to the chiller data using a particle swarm optimization method, and the chiller is controlled according to the target compressor speed and the target inlet guide vane opening.

2. The method according to claim 1, characterized in that The chiller data includes chiller side data and user side data, the user side data includes real-time load and load demand, and the load change of the air-conditioning system at the next moment is determined according to the chiller data, including: The unit cooling capacity is calculated according to the unit side data, and the load change of the air conditioning system at the next moment is determined according to the unit cooling capacity and the load demand.

3. The method according to claim 2, characterized in that The unit side data includes chilled water inlet water temperature, cooling water inlet water temperature, compressor speed and inlet guide vane opening, and the unit refrigeration capacity is calculated based on the unit side data, and the load change of the air conditioning system at the next moment is determined based on the unit refrigeration capacity and the load demand, including: Calculating the cooling capacity of the unit according to the chilled water inlet temperature, the cooling water inlet temperature, the compressor speed and the inlet guide vane opening, and calculating the difference between the cooling capacity of the unit and the load demand; If the difference is greater than a preset difference threshold, a load change of the air-conditioning system at the next moment is determined; otherwise, the load of the air-conditioning system at the next moment is determined to be unchanged.

4. The method according to claim 3, characterized in that The method of using a particle swarm optimization method to determine a target compressor speed and a target inlet guide vane opening according to the chiller data includes: Initializing a particle group, the particle group includes N particles, each of the particles includes a set of compressor speed and inlet guide vane opening; In each iteration, each particle in the current particle group is input into a preset unit capacity model and a preset unit power model to obtain the load capacity and power of each particle; The fitness of each particle is calculated according to the load capacity and power of each particle, and the target compressor speed and the target inlet guide vane opening are obtained according to the fitness and the current iteration number.

5. The method according to claim 4, characterized in that The obtaining the target compressor speed and the target inlet guide vane opening according to the fitness and the current number of iterations includes: According to the fitness, a global optimal fitness up to the current iteration and a local optimal fitness of each particle are obtained; Determine whether the current number of iterations is greater than or equal to the preset number of iterations; If the current number of iterations is greater than or equal to the preset number of iterations, determining whether the load capacity corresponding to the global optimal fitness meets the load requirement; If the load demand is met, the compressor speed and inlet guide vane opening corresponding to the global optimal fitness are used as the target compressor speed and the target inlet guide vane opening respectively; If the current number of iterations is less than the preset number of iterations, the current particle swarm is updated according to the local optimal fitness and the global optimal fitness to perform the next iteration.

6. The method according to claim 4, characterized in that The fitness function used to calculate the fitness includes a constraint function and an objective function, the constraint function is constructed according to the load capacity and the load demand, and the objective function is constructed according to the power.

7. The method according to claim 6, characterized in that The constraint function is a function that makes the difference between the load capacity and the load demand zero, and the objective function is a function that minimizes the power.

8. The method according to claim 4, characterized in that The preset unit capability model and the preset unit power model are established by the following method: Acquire sample data, and preprocess the sample data, wherein the sample data includes chiller operation data and / or chiller simulation data, and the preprocessing includes physical logic screening and / or abnormal point cleaning; Performing parameter importance analysis on the preprocessed sample data, and determining the fitting function form according to the analysis result, wherein the fitting function form includes the class and number of terms of the fitting function; Training the model formed by the fitting function, and determining whether the accuracy of the trained model meets the preset accuracy requirements; If the model accuracy meets the preset accuracy requirement, the trained model is output; otherwise, the process returns to the step of preprocessing the sample data.

9. The method according to claim 5, characterized in that The method further comprises: If the load capacity corresponding to the global optimal fitness does not meet the load requirement, return to the step of initializing the particle swarm.

10. The method according to claim 3, characterized in that The method further comprises: If the load of the air-conditioning system remains unchanged at the next moment, the current compressor speed is determined to be the target compressor speed, and the current inlet guide vane opening is determined to be the target inlet guide vane opening.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the control method of the chiller according to any one of claims 1 to 10 is implemented.

12. A control device for a chiller, characterized in that: The device comprises: An acquisition module, used to acquire the chiller data at the current moment, and determine the load change of the air-conditioning system at the next moment according to the chiller data; A control module is used to determine a target compressor speed and a target inlet guide vane opening according to the chiller data by using a particle swarm optimization method when the load of the air-conditioning system changes at the next moment, and control the chiller according to the target compressor speed and the target inlet guide vane opening.

13. An air conditioning system, characterized in that: It comprises a water chiller and a control device for the water chiller as claimed in claim 12.

Images