Energy-saving control method for centrifugal water chiller

Abstract

The present application belongs to the technical field of refrigeration equipment control, and discloses an energy-saving control method for a centrifugal water chiller. The method comprises the following steps: acquiring the running state parameters and environmental state parameters of the water chiller in real time, dynamically predicting the surge boundary, calculating the running safety margin, generating an energy-saving optimization control vector, and realizing the collaborative adjustment of the compressor speed and the guide vane opening. First, the compressor speed, guide vane opening, condenser pressure, evaporator pressure and other running parameters, as well as the environmental temperature, cooling water temperature and other environmental parameters are collected, and the surge boundary is accurately predicted based on the pressure ratio, running condition vector and environmental correction coefficient. Then, the change trend of the surge boundary and the running state fluctuation characteristics are analyzed to determine the safety margin. Further, the main characteristic components of the running state are extracted through feature decomposition, and the optimization control vector is generated by balancing the energy-saving and safety requirements in combination with the dynamic weighting factor. The present application can reduce energy consumption while effectively preventing surge risk, and is suitable for complex and variable operating environments.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of refrigeration equipment control, and more particularly to an energy-saving control method for a centrifugal water chiller. BACKGROUND

[0002] As the core refrigeration equipment for large commercial buildings, industrial facilities and data centers, centrifugal water chillers are widely used due to their high efficiency, large capacity and stable performance. Currently, centrifugal water chillers account for an increasing proportion of building energy consumption, and their operating efficiency directly affects overall energy consumption and operating costs.

[0003] However, the existing centrifugal water chiller control technology has certain defects in actual application, especially in variable load and variable working condition environments. Traditional control systems generally use fixed surge boundaries as safety control benchmarks, which cannot adapt to complex external conditions such as cooling water temperature fluctuations and environmental temperature changes, resulting in the system frequently entering a protection state or a significant decrease in efficiency during extreme weather such as high summer temperatures or low winter temperatures. In actual engineering, to avoid surge risks, maintenance personnel are often forced to set overly conservative safety margins, causing the unit to run at a working point far from the high-efficiency region for a long time, resulting in a large amount of energy waste, especially in large commercial buildings and industrial cooling systems. At the same time, the existing control strategy lacks a coordinated optimization mechanism for compressor speed and guide vane opening, and exhibits a significant decrease in energy efficiency during partial load operation, making it difficult to accurately respond to dynamic load changes such as office building peak and valley periods. More seriously, when the system encounters sudden load fluctuations, due to insufficient prediction accuracy, the control system either overreacts, causing energy waste, or underreacts, resulting in unstable refrigeration effect, or even in extreme cases, causing surges and endangering equipment safety. This passive balance between energy saving and safety seriously restricts the improvement of building energy efficiency and the reduction of operating costs.

[0004] In view of this, the present application proposes an energy-saving control method for a centrifugal water chiller to solve the above problems. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned purpose, the present application provides the following technical solution: an energy-saving control method for a centrifugal water chiller, comprising:

[0006] obtaining operating state parameters and environmental state parameters of the centrifugal water chiller during operation, the operating state parameters including compressor speed, guide vane opening, condenser pressure, and evaporator pressure, and the environmental state parameters including environmental temperature and cooling water temperature;

[0007] obtaining a surge boundary prediction value of the centrifugal water chiller at each time instant according to the operating state parameters and the environmental state parameters;

[0008] Based on the change trend of the surge boundary prediction value in the analysis period of each time and the fluctuation characteristics of the operating state parameter, an operating safety margin of the centrifugal cold water unit at each time is obtained;

[0009] According to the operating safety margin at each time and the dynamic distribution characteristics of the operating state parameter, an energy-saving optimization control vector of the centrifugal cold water unit at each time is obtained; and the compressor speed and the guide vane opening are adjusted based on the energy-saving optimization control vector, so that the energy-saving operation of the centrifugal cold water unit is realized.

[0010] Further, the surge boundary prediction value of the centrifugal cold water unit at each time is obtained, including:

[0011] According to the condenser pressure and the evaporator pressure, a pressure ratio of the centrifugal cold water unit at each time is calculated;

[0012] According to the pressure ratio, the compressor speed and the guide vane opening, an operating condition vector of the centrifugal cold water unit at each time is constructed;

[0013] Based on the operating condition vector and a preset surge boundary model, an initial surge boundary value of the centrifugal cold water unit at the current time is obtained;

[0014] According to the ambient temperature and the cooling water temperature, an ambient correction coefficient of the centrifugal cold water unit at each time is calculated;

[0015] The initial surge boundary value is corrected by using the ambient correction coefficient, so as to obtain the surge boundary prediction value of the centrifugal cold water unit at each time.

[0016] Further, the operating safety margin of the centrifugal cold water unit at each time is obtained, including:

[0017] The change rate of the surge boundary prediction value in the analysis period of each time is counted, which is recorded as a surge boundary change trend value;

[0018] The fluctuation variance of the operating state parameter in the analysis period of each time is calculated, which is recorded as an operating state fluctuation value;

[0019] According to the surge boundary change trend value and the operating state fluctuation value, an operating risk feature vector of the centrifugal cold water unit at each time is constructed;

[0020] The operating risk feature vector is normalized, and combined with a preset safety margin weight, so as to obtain the operating safety margin of the centrifugal cold water unit at each time.

[0021] Further, the obtaining the energy-saving optimization control vector of the centrifugal water chiller at each time comprises:

[0022] According to the operation safety margin, an operation safety boundary of the centrifugal water chiller at each time is determined;

[0023] Based on the operation safety boundary and the dynamic distribution characteristics of the operation state parameter, an operation state feature matrix of the centrifugal water chiller at each time is constructed;

[0024] The operation state feature matrix is subjected to feature decomposition, and a main feature component is extracted, so as to obtain an energy-saving optimization direction of the centrifugal water chiller at each time;

[0025] According to the energy-saving optimization direction and the operation safety margin, an energy-saving optimization control vector of the centrifugal water chiller at each time is generated, and the energy-saving optimization control vector comprises a compressor speed adjustment amount and a guide vane opening adjustment amount.

[0026] Further, the adjusting the compressor speed and the guide vane opening based on the energy-saving optimization control vector comprises:

[0027] An actual operation condition parameter of the centrifugal water chiller at a current time is obtained;

[0028] According to the energy-saving optimization control vector, a compressor speed target value and a guide vane opening target value of the centrifugal water chiller at a next time are calculated;

[0029] Based on the actual operation condition parameter and the compressor speed target value and the guide vane opening target value, a control instruction of the centrifugal water chiller is generated;

[0030] The compressor speed and the guide vane opening of the centrifugal water chiller are adjusted through the control instruction.

[0031] Further, the obtaining method of the preset surge boundary model comprises:

[0032] Historical operation data of the centrifugal water chiller under different operation conditions are collected, and the historical operation data comprises a compressor speed, a guide vane opening, a condenser pressure, an evaporator pressure and a surge occurrence state;

[0033] According to the historical operation data, an operation condition sample set of the centrifugal water chiller is constructed;

[0034] The operation condition sample set is trained by using a machine learning algorithm, so as to obtain the preset surge boundary model, and the surge boundary model is used to represent a mapping relationship between an operation condition vector and a surge boundary value.

[0035] Further, the method for calculating the fluctuation variance of the operation state parameter comprises:

[0036] statistically analyzing time series data of the compressor rotating speed, the guide vane opening, the condenser pressure and the evaporator pressure in an analysis period of each time point;

[0037] standardizing the time series data to obtain a standardized operation parameter sequence;

[0038] calculating the variance of the standardized operation parameter sequence to obtain the operation state fluctuation value.

[0039] Further, the method for constructing the operation state feature matrix comprises:

[0040] extracting operation state distribution features of the centrifugal water chiller at each time point according to the dynamic distribution characteristics of the operation state parameter, wherein the operation state distribution features comprise joint distribution probability of the compressor rotating speed and the guide vane opening;

[0041] determining safe operation constraint conditions of the centrifugal water chiller at each time point according to the operation safety boundary;

[0042] matrixing the operation state distribution features and the safe operation constraint conditions to obtain the operation state feature matrix.

[0043] Further, the machine learning algorithm is a support vector machine algorithm or a deep neural network algorithm.

[0044] Further, the method for calculating the compressor rotating speed target value and the guide vane opening target value of the centrifugal water chiller at the next time point according to the energy-saving optimization control vector comprises:

[0045] obtaining actual operation condition parameters of the centrifugal water chiller at the current time point and the energy-saving optimization control vector;

[0046] predicting an operation condition trend vector of the centrifugal water chiller at the next time point according to the actual operation condition parameters, wherein the operation condition trend vector comprises a compressor rotating speed change trend and a guide vane opening change trend;

[0047] calculating initial compressor rotating speed target values and initial guide vane opening target values of the centrifugal water chiller at the next time point according to the operation condition trend vector and the energy-saving optimization control vector;

[0048] determining a dynamic weighting factor of the centrifugal water chiller at the next time point based on the operation safety margin and the environmental state parameter, wherein the dynamic weighting factor is used to represent the priority between energy-saving optimization and operation safety;

[0049] According to the deviation of the actual operation condition parameter and the historical operation data, a predicted deviation correction value of the centrifugal water chiller unit at the next moment is obtained;

[0050] The initial compressor speed target value and the initial guide vane opening target value are weighted and adjusted by using the dynamic weighting factor, and are corrected in combination with the predicted deviation correction value, so that a compressor speed target value and a guide vane opening target value of the centrifugal water chiller unit at the next moment are obtained.

[0051] The technical effect and advantages of the energy-saving control method of the centrifugal water chiller unit are as follows:

[0052] The present application can make the unit safely operate in the high-efficiency area closer to the surge boundary by accurately grasping the dynamically changing surge critical point, and tap the deep energy-saving potential that the traditional control method cannot reach. The present application no longer relies on the conservative static safety boundary, but perceives and accurately predicts the surge risk in real time, significantly reduces the energy waste caused by excessive protection, and effectively reduces the risk of equipment damage caused by surge, solving the traditional contradiction between energy saving and safety. In terms of energy efficiency, through accurate coordinated regulation of the compressor speed and the guide vane opening, the system is always maintained in the best energy efficiency ratio operating condition, and high-efficiency operation can be maintained even under severe conditions of external environment fluctuation, realizing significant reduction of energy consumption. This adaptive optimization control strategy makes the cold water chiller more sensitive and accurate in responding to load fluctuations, avoiding excessive regulation and energy loss in traditional control. From the long-term operation, the present application greatly reduces the frequency of system surge events, significantly prolongs the service life of key components, reduces maintenance costs and unplanned downtime, and realizes continuous optimization of energy consumption. BRIEF DESCRIPTION OF DRAWINGS

[0053] Figure 1 The flow chart of the steps of the energy-saving control method of the centrifugal water chiller unit. DETAILED DESCRIPTION

[0054] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0056] The specific scheme of the energy-saving control method of the centrifugal water chiller unit provided by the present application will be specifically described below with reference to the drawings.

[0057] The application provides an energy-saving control method of a centrifugal water chilling unit. Figure 1 It shows a step flow chart of an energy-saving control method of a centrifugal water chilling unit provided by an embodiment of the application, and the method comprises the following steps.

[0058] Step S1: obtaining running state parameters and environmental state parameters of the centrifugal water chilling unit in a running process, wherein the running state parameters comprise compressor rotating speed, guide vane opening degree, condenser pressure and evaporator pressure, and the environmental state parameters comprise environmental temperature and cooling water temperature.

[0059] In the running process of the centrifugal water chilling unit, the running state parameters and the environmental state parameters are collected in real time by sensors installed on the centrifugal water chilling unit. The running state parameters comprise compressor rotating speed, guide vane opening degree, condenser pressure and evaporator pressure, and the environmental state parameters comprise environmental temperature and cooling water temperature. The sensors are used to continuously collect the running state parameters and the environmental state parameters of the centrifugal water chilling unit at each moment, and the collected running state parameters and environmental state parameters are subjected to denoising and data standardization processing.

[0060] It should be noted that the sensors installed on the centrifugal water chilling unit include but are not limited to rotating speed sensors, pressure sensors and temperature sensors, which can ensure the collection requirements of the running state parameters and the environmental state parameters. The sampling frequency of the running state parameters and the environmental state parameters is the same.

[0061] In an implementation manner of the embodiment of the application, the sampling frequency is set to once per second.

[0062] In an implementation manner of the embodiment of the application, the Kalman filtering algorithm is selected for denoising processing, and the Z-score standardization method is used for data standardization processing. The specific method of the above preprocessing is not introduced here, and is a technical means familiar to those skilled in the art. Other data collection devices and data preprocessing algorithms can also be selected, which are not limited here.

[0063] The following steps are analyzed using the preprocessed running state parameters and environmental state parameters.

[0064] Step S2: obtaining a surge boundary prediction value of the centrifugal water chilling unit at each moment according to the running state parameters and the environmental state parameters.

[0065] The accurate prediction of the surge boundary is crucial for energy-saving operation and operation safety of the centrifugal water chiller during operation. However, the dynamic change of the surge boundary will be caused by the change of the environmental state parameters such as the environmental temperature and the cooling water temperature. The traditional control method is usually based on the fixed surge boundary, and it is difficult to adapt to the complex and changeable environmental conditions, thereby affecting the energy-saving effect and the operation stability. Since the prediction of the surge boundary needs to comprehensively consider the dynamic influence of the operation state parameters and the environmental state parameters, the multi-dimensional analysis based on the operation state parameters and the environmental state parameters is used to determine the predicted value of the surge boundary of the centrifugal water chiller at each time, thereby improving the accuracy of the energy-saving control in the complex and changeable environment.

[0066] Preferably, in some possible implementation manners of the embodiment of the present application, the predicted value of the surge boundary of the centrifugal water chiller at each time is obtained, including: calculating the pressure ratio of the centrifugal water chiller at each time according to the condenser pressure and the evaporator pressure; constructing the operation condition vector of the centrifugal water chiller at each time according to the pressure ratio, the compressor speed and the guide vane opening; obtaining the initial surge boundary value of the centrifugal water chiller at the current time based on the operation condition vector and the preset surge boundary model; calculating the environmental correction coefficient of the centrifugal water chiller at each time according to the environmental temperature and the cooling water temperature; and correcting the initial surge boundary value by using the environmental correction coefficient to obtain the predicted value of the surge boundary of the centrifugal water chiller at each time.

[0067] The pressure ratio reflects the pressure relationship between the condenser and the evaporator during the operation of the centrifugal water chiller, and is an important index for judging the surge boundary. The compressor speed and the guide vane opening directly affect the operation condition of the centrifugal water chiller, and the operation condition vector can comprehensively represent the operation state of the centrifugal water chiller by constructing the operation condition vector. The preset surge boundary model is used to represent the mapping relationship between the operation condition vector and the surge boundary value. The change of the environmental temperature and the cooling water temperature will affect the thermodynamic performance of the centrifugal water chiller, and the environmental correction coefficient can be introduced to dynamically adjust the initial surge boundary value, thereby improving the accuracy of the prediction.

[0068] In the embodiment of the present application, the pressure ratio PR is expressed by the formula:

[0069] In the formula, P_c is the condenser pressure, and P_e is the evaporator pressure.

[0070] In the embodiment of the present application, the operation condition vector V is expressed by the formula:

[0071] In the formula, PR is the pressure ratio, N is the compressor speed, and θ is the guide vane opening.

[0072] In the embodiment of the present application, the environmental correction coefficient α is expressed by the formula:

[0073] wherein T_env is the ambient temperature, T_ref is the reference ambient temperature, T_cw is the cooling water temperature, T_cw_ref is the reference cooling water temperature, and k1 and k2 are preset correction weights.

[0074] In one possible implementation of the embodiment of the present application, the reference ambient temperature T_ref is set to 25 degrees Celsius, the reference cooling water temperature T_cw_ref is set to 30 degrees Celsius, the correction weight k1 is set to 0.02, and the correction weight k2 is set to 0.03.

[0075] In the embodiment of the present application, the surge margin prediction value S_pred is expressed by the formula:

[0076] wherein S_init is the initial surge margin value, and a is the ambient correction coefficient.

[0077] Step S3: Obtain the running safety margin of the centrifugal water chiller at each time point based on the change trend of the surge margin prediction value and the fluctuation characteristics of the running state parameter in the analysis period.

[0078] Since the running safety of the centrifugal water chiller needs to be balanced between energy saving optimization and surge risk, accurate evaluation of the running safety margin is crucial to the control strategy. The conventional control method is usually based on a fixed safety margin, which is difficult to adapt to the dynamic changes of the surge margin prediction value and the fluctuation characteristics of the running state parameter, thereby leading to overly conservative or overly aggressive operation. Therefore, according to the change trend of the surge margin prediction value and the fluctuation characteristics of the running state parameter in the analysis period, the running risk of the centrifugal water chiller is analyzed to obtain the running safety margin, which is used to guide the energy saving optimization control.

[0079] Preferably, in some possible implementation manners of the embodiment of the present application, the running safety margin of the centrifugal water chiller at each time point is obtained by: calculating the change rate of the surge margin prediction value in the analysis period at each time point, denoted as the surge margin change trend value; calculating the fluctuation variance of the running state parameter in the analysis period at each time point, denoted as the running state fluctuation value; constructing the running risk feature vector of the centrifugal water chiller at each time point according to the surge margin change trend value and the running state fluctuation value; and performing normalization processing on the running risk feature vector and combining a preset safety margin weight to obtain the running safety margin of the centrifugal water chiller at each time point.

[0080] The change rate of the surge margin prediction value reflects a dynamic change trend of the surge margin, if the change rate is greater, the stability of the surge margin is lower, and the operation risk is higher; the fluctuation variance of the operation state parameter reflects the stability of the operation state, if the fluctuation variance is greater, the uncertainty of the operation state is higher, and the operation risk is higher; the operation risk feature vector comprehensively reflects the change trend of the surge margin and the fluctuation characteristic of the operation state, and through normalization processing and in combination with the safety margin weight, the size of the operation safety margin can be quantified.

[0081] In the embodiment of the application, the surge margin change trend value ΔS is expressed by a formula as follows:

[0082] In the formula, S_pred(t) is the surge margin prediction value at the current time t, S_pred(t-1) is the surge margin prediction value at the last time before the current time t, and Δt is the time interval.

[0083] In the embodiment of the application, the operation state fluctuation value σ is expressed by a formula as follows:

[0084] In the formula, X_i is the operation state parameter value at the i-th time in the analysis period, μ is the mean value of the operation state parameter in the analysis period, and n is the number of times in the analysis period.

[0085] In the embodiment of the application, the operation risk feature vector R is expressed by a formula as follows:

[0086] ;

[0087] In the embodiment of the application, the operation safety margin M is expressed by a formula as follows:

[0088] In the formula, ΔS is the surge margin change trend value, σ is the operation state fluctuation value, w1 and w2 are preset safety margin weights, and Norm is a normalization function. It should be noted that the normalization processing is used to map the operation risk feature vector to the interval [0, 1] to quantify the size of the operation safety margin.

[0089] In one implementation manner of the embodiment of the application, the analysis period contains 10 times, and each time is the last time in the analysis period.

[0090] In one implementation manner of the embodiment of the application, the preset safety margin weight w1 is set to 0.6, and w2 is set to 0.4.

[0091] It should be noted that the running risk feature vector is normalized by using the Norm function in the embodiment of the application, and other normalization methods can also be selected in the embodiment of the application, for example, maximum and minimum normalization, Z-score standardization and other normalization methods, which are not limited herein.

[0092] Step S4: obtaining an energy-saving optimization control vector of the centrifugal water chiller at each moment according to the running safety margin and the dynamic distribution characteristics of the running state parameters; and adjusting the compressor speed and the guide vane opening degree based on the energy-saving optimization control vector to realize the energy-saving operation of the centrifugal water chiller.

[0093] Since the energy-saving operation of the centrifugal water chiller needs to balance between the running safety and the energy consumption optimization, the accurate generation of the energy-saving optimization control vector is crucial to the control strategy. The conventional control method is usually based on a fixed running safety boundary or a single optimization target, and it is difficult to adapt to the dynamic changes of the running safety margin and the complex distribution characteristics of the running state parameters, thereby leading to insufficient energy-saving effect or increased running risk. Therefore, the energy-saving optimization direction of the centrifugal water chiller is analyzed according to the dynamic distribution characteristics of the running safety margin and the running state parameters, the energy-saving optimization control vector is generated, and the energy-saving operation is realized by adjusting the compressor speed and the guide vane opening degree.

[0094] Preferably, in some possible implementation manners of the embodiment of the application, the energy-saving optimization control vector of the centrifugal water chiller at each moment is obtained, including: determining a running safety boundary of the centrifugal water chiller at each moment according to the running safety margin; constructing a running state feature matrix of the centrifugal water chiller at each moment based on the running safety boundary and the dynamic distribution characteristics of the running state parameters; performing feature decomposition on the running state feature matrix, extracting main feature components, and obtaining an energy-saving optimization direction of the centrifugal water chiller at each moment; and generating an energy-saving optimization control vector of the centrifugal water chiller at each moment according to the energy-saving optimization direction and the running safety margin, the energy-saving optimization control vector including a compressor speed adjustment amount and a guide vane opening degree adjustment amount.

[0095] The running safety margin reflects the running risk level of the centrifugal water chiller at the current moment, and by determining the running safety boundary, a constraint condition can be provided for energy-saving optimization; the dynamic distribution characteristics of the running state parameters reflect the joint distribution law of the compressor speed, the guide vane opening degree and other parameters, and by constructing the running state feature matrix, the multi-dimensional characteristics of the running state can be comprehensively represented; the feature decomposition is used to extract the main feature components of the running state feature matrix, so as to determine the energy-saving optimization direction; and the energy-saving optimization control vector combines the energy-saving optimization direction and the running safety margin, so as to realize the collaborative adjustment of the compressor speed and the guide vane opening degree.

[0096] In the embodiment of the application, the running safety boundary B is expressed by a formula as follows:

[0097] ; wherein S_pred is a surge margin prediction value, and M is a running safety margin.

[0098] In the embodiment of the present application, the construction method of the running state feature matrix A will be further described in the following steps.

[0099] In the embodiment of the present application, the energy-saving optimization control vector C is expressed by the formula:

[0100] ; wherein ΔN is a compressor speed adjustment amount, and Δθ is a guide vane opening adjustment amount.

[0101] In one implementation manner of the embodiment of the present application, the feature decomposition extracts the main feature components by using the singular value decomposition (SVD) method, and other feature decomposition methods such as principal component analysis (PCA) can also be used, which is not limited herein.

[0102] The compressor speed and the guide vane opening are adjusted based on the energy-saving optimization control vector, including: acquiring actual running condition parameters of the centrifugal water chiller at a current time; calculating a compressor speed target value and a guide vane opening target value of the centrifugal water chiller at a next time according to the energy-saving optimization control vector; generating a control instruction of the centrifugal water chiller based on the actual running condition parameters and the compressor speed target value and the guide vane opening target value; and adjusting the compressor speed and the guide vane opening of the centrifugal water chiller through the control instruction to realize energy-saving running.

[0103] The actual running condition parameters reflect the actual running state of the centrifugal water chiller at the current time, and the compressor speed target value and the guide vane opening target value at the next time can be accurately calculated by combining the energy-saving optimization control vector; the control instruction is used to convert the calculation result into an executable control signal, so as to realize energy-saving running.

[0104] In the embodiment of the present application, the actual running condition parameters include the compressor speed, the guide vane opening, the condenser pressure, and the evaporator pressure.

[0105] In the embodiment of the present application, the generation method of the control instruction will be further described in the following steps.

[0106] Step S5: acquiring a preset surge margin model.

[0107] Preferably, in some possible implementation manners of the embodiment of the present application, the method for obtaining the preset surge boundary model comprises: collecting historical operation data of the centrifugal water chiller under different operation conditions, the historical operation data comprising a compressor rotating speed, a guide vane opening degree, a condenser pressure, an evaporator pressure and a surge occurrence state; constructing an operation condition sample set of the centrifugal water chiller according to the historical operation data; and training the operation condition sample set by using a machine learning algorithm to obtain the preset surge boundary model, the surge boundary model being used to represent a mapping relationship between an operation condition vector and a surge boundary value.

[0108] The historical operation data reflects actual performance of the centrifugal water chiller under different operation conditions, and by constructing the operation condition sample set, training data can be provided for the machine learning algorithm; the preset surge boundary model can dynamically predict the surge boundary value in the operation process by learning the mapping relationship between the operation condition vector and the surge boundary value.

[0109] In the embodiment of the present application, the operation condition sample set D is expressed by a formula as follows:

[0110] In the formula, V_i is the i th operation condition vector, S_i is the corresponding surge boundary value, and n is the sample number.

[0111] In one implementation manner of the embodiment of the present application, the machine learning algorithm is a support vector machine algorithm or a deep neural network algorithm.

[0112] In one implementation manner of the embodiment of the present application, the collected historical operation data covers at least 1000 hours of operation time and contains at least 10 different operation conditions.

[0113] Step S6: calculation of fluctuation variance of the operation state parameter.

[0114] Preferably, in some possible implementation manners of the embodiment of the present application, the method for calculating the fluctuation variance of the operation state parameter comprises: collecting time series data of the compressor rotating speed, the guide vane opening degree, the condenser pressure and the evaporator pressure in an analysis period of each time; performing standardization processing on the time series data to obtain a standardized operation parameter sequence; and calculating variance of the standardized operation parameter sequence to obtain an operation state fluctuation value.

[0115] The time series data reflects dynamic changes of the operation state parameter in the analysis period, and by the standardization processing, influence of different parameter dimensions can be eliminated; the fluctuation variance is used to quantify instability of the operation state parameter and is an important index for evaluating the operation safety margin.

[0116] In the embodiment of the present application, the standardized operation parameter sequence X_std is expressed by a formula as follows:

[0117] ; wherein, X is time series data, μ is mean of time series data, σ is standard deviation of time series data.

[0118] In the embodiment of the present application, the running state fluctuation value σ is expressed by the formula:

[0119] ; wherein, X_std_i is the i th value of the standardized running parameter sequence, and n is the number of time points in the analysis period.

[0120] In one implementation manner of the embodiment of the present application, the standardization processing adopts the Z-score standardization method, and other standardization methods such as maximum-minimum normalization can also be adopted, which is not limited here.

[0121] Step S7: Construction of the running state feature matrix.

[0122] Preferably, in some possible implementation manners of the embodiment of the present application, the construction method of the running state feature matrix comprises: extracting a running state distribution feature of the centrifugal water chiller at each time point according to a dynamic distribution characteristic of the running state parameter, the running state distribution feature comprising a joint distribution probability of the compressor speed and the guide vane opening degree; determining a safe running constraint condition of the centrifugal water chiller at each time point according to a running safety boundary; and performing matrix representation on the running state distribution feature and the safe running constraint condition to obtain the running state feature matrix.

[0123] The dynamic distribution characteristic of the running state parameter reflects the joint variation law of the compressor speed, the guide vane opening degree and other parameters in the running process of the centrifugal water chiller, and through the extraction of the running state distribution feature, the multi-dimensional characteristics of the running state can be comprehensively characterized; the running safety boundary provides a constraint condition for energy saving optimization, and through the determination of the safe running constraint condition, the energy saving optimization can be ensured to be performed within a safe range; the running state feature matrix integrates the running state distribution feature and the safe running constraint condition through matrix representation, thereby providing a data basis for subsequent feature decomposition.

[0124] In the embodiment of the present application, the running state distribution feature P is expressed by the formula:

[0125] ; wherein, P(N) is the probability distribution of the compressor speed, and P(θ|N) is the conditional probability distribution of the guide vane opening degree given the compressor speed.

[0126] In the embodiment of the present application, the safe running constraint condition is expressed by the formula:

[0127] ; wherein, S_pred is a surge boundary prediction value, and B is a running safety boundary.

[0128] In the embodiment of the present application, the running state feature matrix A is expressed by the formula:

[0129] In the formula, P(N, θ) is the running state distribution feature, and S_pred-B is the safe running constraint condition.

[0130] In one implementation of the embodiment of the present application, the probability distribution of the running state distribution feature is calculated by a kernel density estimation (KDE) method, and other probability distribution estimation methods such as histogram estimation can also be used, which are not limited herein.

[0131] Step S8: According to the energy-saving optimization control vector, the compressor speed target value and the guide vane opening target value of the centrifugal water chiller at the next moment are calculated.

[0132] Preferably, in some possible implementations of the embodiment of the present application, according to the energy-saving optimization control vector, the compressor speed target value and the guide vane opening target value of the centrifugal water chiller at the next moment are calculated, including: obtaining the actual running condition parameters of the centrifugal water chiller at the current moment and the energy-saving optimization control vector; according to the actual running condition parameters, predicting the running condition trend vector of the centrifugal water chiller at the next moment, the running condition trend vector including the compressor speed change trend and the guide vane opening change trend; according to the running condition trend vector and the energy-saving optimization control vector, calculating the initial compressor speed target value and the initial guide vane opening target value of the centrifugal water chiller at the next moment; based on the running safety margin and the environmental state parameters, determining the dynamic weighting factor of the centrifugal water chiller at the next moment, the dynamic weighting factor being used to represent the priority between energy-saving optimization and running safety; according to the deviation of the actual running condition parameters and the historical running data, obtaining the predicted deviation correction value of the centrifugal water chiller at the next moment; using the dynamic weighting factor to weight and adjust the initial compressor speed target value and the initial guide vane opening target value, and combining the predicted deviation correction value to correct, to obtain the compressor speed target value and the guide vane opening target value of the centrifugal water chiller at the next moment.

[0133] The actual operating condition parameter reflects the actual operating state of the centrifugal water chiller at the current time, and the predicted operating condition trend vector can consider the dynamic change trend of the operating state, thereby improving the adaptability of the target value calculation; the energy-saving optimization control vector provides an adjustment direction for energy-saving optimization, and by combining the operating condition trend vector, the initial compressor speed target value and the initial guide vane opening target value can be calculated; the change of the operating safety margin and the environmental state parameter will affect the priority between energy-saving optimization and operating safety, and by introducing the dynamic weighting factor, the adaptive balance between the two can be realized; the deviation of the actual operating condition parameter and the historical operating data reflects the error of the prediction model, and by introducing the prediction deviation correction value, the accuracy of the target value calculation can be further improved.

[0134] In the embodiment of the present application, the operating condition trend vector T is expressed by the formula:

[0135] In the formula, ΔN_trend is the compressor speed change trend, and Δθ_trend is the guide vane opening change trend.

[0136] In the embodiment of the present application, the compressor speed change trend ΔN_trend and the guide vane opening change trend Δθ_trend are predicted by a linear regression method, and other prediction methods such as time series analysis can also be used, which are not limited herein.

[0137] In the embodiment of the present application, the initial compressor speed target value N_init and the initial guide vane opening target value θ_init are expressed by the formula:

[0138] ;

[0139] ;

[0140] In the formula, N_curr is the compressor speed at the current time, θ_curr is the guide vane opening at the current time, ΔN is the compressor speed adjustment amount in the energy-saving optimization control vector, and Δθ is the guide vane opening adjustment amount in the energy-saving optimization control vector.

[0141] In the embodiment of the present application, the dynamic weighting factor β is expressed by the formula:

[0142] ; wherein, M is a running safety margin, T_env is an environment temperature, T_ref is a reference environment temperature, T_cw is a cooling water temperature, T_cw_ref is a reference cooling water temperature, k3 and k4 are preset correction weights, and exp is an exponential function with a natural constant as a base number. It should be noted that the dynamic weighting factor β is used to represent the priority between energy saving optimization and running safety, when the running safety margin M is small, the priority is inclined to running safety, and when the environment temperature or the cooling water temperature deviates from the reference value by a large margin, the priority is adjusted to adapt to the environment change.

[0143] In an implementation manner of the embodiment of the present application, the reference environment temperature T_ref is set to 25 degrees Celsius, the reference cooling water temperature T_cw_ref is set to 30 degrees Celsius, the correction weight k3 is set to 0.01, and the correction weight k4 is set to 0.02.

[0144] In the embodiment of the present application, the prediction deviation correction value E is expressed by a formula as follows:

[0145] ; wherein, E_N is a prediction deviation correction value of the compressor speed, and E_θ is a prediction deviation correction value of the guide vane opening degree. The prediction deviation correction value is obtained by calculating the deviation between the actual running condition parameter and the historical running data, and the specific method is as follows:

[0146] ;

[0147] ;

[0148] ; wherein, N_act_i is the actual compressor speed at the i th historical moment, N_pred_i is the predicted compressor speed at the i th historical moment, θ_act_i is the actual guide vane opening degree at the i th historical moment, θ_pred_i is the predicted guide vane opening degree at the i th historical moment, and m is the number of historical moments.

[0149] In the embodiment of the present application, the compressor speed target value N_target and the guide vane opening degree target value θ_target are expressed by a formula as follows:

[0150] ;

[0151] ; wherein, N_safe is a safe compressor speed corresponding to a running safety boundary, θ_safe is a safe guide vane opening degree corresponding to the running safety boundary, β is a dynamic weighting factor, E_N is a prediction deviation correction value of the compressor speed, and E_θ is a prediction deviation correction value of the guide vane opening degree.

[0152] In one implementation of the embodiment of the present application, the safe compressor speed N_safe and the safe guide vane opening θ_safe are calculated by reverse mapping of the operation safety boundary B, or are obtained by querying a preset safe operation table, which is not limited herein.

[0153] It should be noted that the control instruction is generated as follows:

[0154] The control instruction adopts a structured data format, including a unique identifier, a time stamp, a target execution device, an instruction type, and a parameter, etc. The parameter part contains a compressor speed set value, a guide vane opening set value, a change rate limit, and an execution priority. A check sum is attached at the end of the control instruction for data integrity verification.

[0155] The control instruction generation first calculates the difference between the target value and the current value to obtain the compressor speed adjustment amount and the guide vane opening adjustment amount, respectively. To prevent the device from being subjected to a large impact, the system will limit the single adjustment amplitude, and when the calculated adjustment amount exceeds the maximum allowed value, it will be limited within the maximum allowed range. According to the limited adjustment amount, a new set value is calculated. At the same time, the change rate limit is determined based on the operation safety margin, and the smaller the safety margin, the lower the change rate, to ensure system stability.

[0156] The change rate limit is calculated based on the basic change rate and the operation safety margin. An exponential decay function is used to make the change rate and the operation safety margin have a nonlinear relationship. When the operation safety margin is small, the change rate is close to zero, realizing slow adjustment; when the operation safety margin is large, the change rate is close to the basic change rate, allowing faster adjustment. The basic change rate is usually set to 10 hertz per second (compressor speed) and 1% per second (guide vane opening).

[0157] The execution priority is determined according to the emergency degree of the running state, which is divided into four levels: emergency, high, ordinary, and low. When the pressure ratio exceeds the critical value or the evaporation temperature is lower than the minimum safety value, it is set as the emergency priority; when the operation safety margin is lower than the threshold value, it is set as the high priority; when the current energy efficiency ratio is lower than 90% of the target energy efficiency ratio, it is set as the ordinary priority; and in other cases, it is set as the low priority. The priority determines the execution order and resource allocation of the control instruction in the control system.

[0158] The control instruction is transmitted to the control unit of the centrifugal water chiller through an industrial field bus (such as Modbus, Profibus, or BACnet). A standard master-slave architecture is adopted, with the control system as the master station and the centrifugal water chiller as the slave station. The transmission process includes control instruction encoding, data packet transmission, instruction decoding, check sum verification, return confirmation information, and state update, etc. The transmission protocol ensures reliable transmission and correct execution of the control instruction.

[0159] Through the control instruction generation method, the centrifugal water chiller compressor rotating speed and guide vane opening degree can be accurately adjusted, and energy saving operation can be realized under the premise of ensuring operation safety.

[0160] Thus far, the present application is completed.

[0161] The above only describes preferred embodiments of the present application and is not intended to limit the present application, and although the foregoing embodiments of the present application are described in detail, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or equivalently replace some technical features thereof. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0162] It should be noted that in this document, the terms "comprise", "comprise", or any other variant thereof are intended to cover non-exclusive inclusion, so that processes, methods, articles, or devices that include a series of elements not only include those elements, but also include other elements not explicitly listed, or include elements inherent to such processes, methods, articles, or devices. Without more limitations, the element defined by the statement "comprises a" does not exclude the presence of additional identical elements in the process, method, article, or device that includes the element.

[0163] In the description of the present application, it should be understood that the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0164] In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0165] In the description of the present application, the meaning of "several" is one or more, and the meaning of "a large number" is two or more.

[0166] In the description of the present application, the description referring to the terms "one embodiment", "some embodiments", "example", "specific example", 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 application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0167] The formula of the present specification is a value calculated by de-dimensioning, the formula is obtained by collecting a large amount of data to simulate a formula of the most recent real situation, and preset parameters and threshold values in the formula are set by a person skilled in the art according to actual conditions.

[0168] Although the embodiments of the present application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the claims and their equivalents.

Claims

1. An energy saving control method of a centrifugal water chiller, characterized by, The application relates to a centrifugal water chiller energy-saving optimization control method. The method comprises the following steps: acquiring running state parameters and environment state parameters of a centrifugal water chiller during operation, wherein the running state parameters comprise compressor rotating speed, guide vane opening degree, condenser pressure and evaporator pressure, and the environment state parameters comprise environment temperature and cooling water temperature; acquiring a surge boundary prediction value of the centrifugal water chiller at each moment according to the running state parameters and the environment state parameters; acquiring a running safety margin of the centrifugal water chiller at each moment based on the change trend of the surge boundary prediction value and the fluctuation characteristics of the running state parameters within an analysis period of each moment; acquiring an energy-saving optimization control vector of the centrifugal water chiller at each moment according to the running safety margin and the dynamic distribution characteristics of the running state parameters, and adjusting the compressor rotating speed and the guide vane opening degree based on the energy-saving optimization control vector to realize energy-saving operation of the centrifugal water chiller; the acquiring of the surge boundary prediction value of the centrifugal water chiller at each moment comprises the following steps: calculating a pressure ratio of the centrifugal water chiller at each moment according to the condenser pressure and the evaporator pressure; constructing an operation condition vector of the centrifugal water chiller at each moment according to the pressure ratio, the compressor rotating speed and the guide vane opening degree; acquiring an initial surge boundary value of the centrifugal water chiller at the current moment based on the operation condition vector and a preset surge boundary model; calculating an environment correction coefficient of the centrifugal water chiller at each moment according to the environment temperature and the cooling water temperature; 2. The energy saving control method of a centrifugal type water chiller according to claim 1, wherein correcting the initial surge boundary value by using the environment correction coefficient to obtain the surge boundary prediction value of the centrifugal water chiller at each moment. the acquiring of the running safety margin of the centrifugal water chiller at each moment comprises the following steps: statistically acquiring a change rate of the surge boundary prediction value within an analysis period of each moment, which is recorded as a surge boundary change trend value; calculating a fluctuation variance of the running state parameters within an analysis period of each moment, which is recorded as a running state fluctuation value; constructing a running risk feature vector of the centrifugal water chiller at each moment according to the surge boundary change trend value and the running state fluctuation value; 3. The energy saving control method of a centrifugal type water chiller according to claim 1, wherein normalizing the running risk feature vector and combining a preset safety margin weight to obtain the running safety margin of the centrifugal water chiller at each moment. the acquiring of the energy-saving optimization control vector of the centrifugal water chiller at each moment comprises the following steps: determining a running safety boundary of the centrifugal water chiller at each moment according to the running safety margin; constructing a running state feature matrix of the centrifugal water chiller at each moment based on the running safety boundary and the dynamic distribution characteristics of the running state parameters; performing feature decomposition on the running state feature matrix, extracting main feature components and acquiring an energy-saving optimization direction of the centrifugal water chiller at each moment; generating an energy-saving optimization control vector of the centrifugal water chiller at each moment according to the energy-saving optimization direction and the running safety margin, wherein the energy-saving optimization control vector comprises a compressor rotating speed adjustment amount and a guide vane opening degree adjustment amount.

4. The energy saving control method of a centrifugal type water chiller according to claim 1, wherein The adjusting the compressor rotating speed and the guide vane opening degree based on the energy-saving optimization control vector comprises: Obtaining actual operation condition parameters of the centrifugal water chiller at the current time; According to the energy-saving optimization control vector, calculating a compressor rotating speed target value and a guide vane opening degree target value of the centrifugal water chiller at the next time; Based on the actual operation condition parameters and the compressor rotating speed target value and the guide vane opening degree target value, generating a control instruction of the centrifugal water chiller; Adjusting the compressor rotating speed and the guide vane opening degree of the centrifugal water chiller through the control instruction.

5. The energy saving control method of a centrifugal type water chiller according to claim 1, wherein The method for obtaining the preset surge boundary model comprises: Collecting historical operation data of the centrifugal water chiller under different operation conditions, wherein the historical operation data comprises a compressor rotating speed, a guide vane opening degree, a condenser pressure, an evaporator pressure and a surge occurrence state; According to the historical operation data, constructing an operation condition sample set of the centrifugal water chiller; Using a machine learning algorithm to train the operation condition sample set to obtain the preset surge boundary model, wherein the surge boundary model is used to represent a mapping relationship between an operation condition vector and a surge boundary value.

6. The energy saving control method of a centrifugal type cold water chiller according to claim 2, wherein The method for calculating the fluctuation variance of the operation state parameter comprises: Statistically counting time series data of the compressor rotating speed, the guide vane opening degree, the condenser pressure and the evaporator pressure in an analysis period of each time; Performing standardization processing on the time series data to obtain a standardized operation parameter sequence; Calculating the variance of the standardized operation parameter sequence to obtain the operation state fluctuation value.

7. The energy saving control method of a centrifugal type cold water chiller unit according to claim 3, wherein The method for constructing the operation state feature matrix comprises: According to the dynamic distribution characteristics of the operation state parameter, extracting an operation state distribution feature of the centrifugal water chiller at each time, wherein the operation state distribution feature comprises a joint distribution probability of the compressor rotating speed and the guide vane opening degree; According to the operation safety boundary, determining a safe operation constraint condition of the centrifugal water chiller at each time; Matrixing the operation state distribution feature and the safe operation constraint condition to obtain the operation state feature matrix.

8. The energy saving control method of a centrifugal type water chiller according to claim 5, wherein The machine learning algorithm is a support vector machine algorithm or a deep neural network algorithm.

9. The energy saving control method of a centrifugal type cold water chiller unit according to claim 4, wherein The method for calculating the compressor rotating speed target value and the guide vane opening degree target value of the centrifugal water chiller at the next time according to the energy-saving optimization control vector comprises: Obtaining actual operation condition parameters of the centrifugal water chiller at the current time and the energy-saving optimization control vector; According to the actual operation condition parameters, predicting an operation condition trend vector of the centrifugal water chiller at the next time, wherein the operation condition trend vector comprises a compressor rotating speed change trend and a guide vane opening degree change trend; According to the operation condition trend vector and the energy-saving optimization control vector, calculating an initial compressor rotating speed target value and an initial guide vane opening degree target value of the centrifugal water chiller at the next time; Based on the operation safety margin and the environmental state parameter, determining a dynamic weighting factor of the centrifugal water chiller at the next time, wherein the dynamic weighting factor is used to represent a priority between energy-saving optimization and operation safety. According to the deviation of the actual operation condition parameter and the historical operation data, a predicted deviation correction value of the centrifugal water chiller at a next time is obtained; The initial compressor rotating speed target value and the initial guide vane opening target value are weighted and adjusted by using the dynamic weighting factor, and are corrected in combination with the predicted deviation correction value, so that a compressor rotating speed target value and a guide vane opening target value of the centrifugal water chiller at the next time are obtained.

Images