Calibration method for benchmark value of sub-item energy consumption based on HVAC equipment

Abstract

The present invention discloses a method for calibrating the sub-item energy consumption benchmark value based on HVAC equipment, which relates to the field of building energy conservation technology. The method for calibrating the sub-item energy consumption benchmark value based on HVAC equipment includes: judging abnormality of energy consumption benchmark value, preliminary calibration of energy consumption benchmark value and optimization calibration of energy consumption benchmark value. The present invention realizes the refined management of energy consumption of HVAC equipment through serialized analysis of different sub-item energy consumption, which helps to identify energy consumption abnormalities more accurately; through energy consumption correlation analysis, it helps to monitor energy consumption in real time and quickly feedback abnormal situations, and can accurately identify abnormal target HVAC equipment sub-item energy consumption; by considering environmental information, climate information and equipment status information, it helps to understand the reasons for energy consumption changes more comprehensively; by dynamically adjusting the energy consumption benchmark value according to real-time data and influencing factors, the adaptability and accuracy of the benchmark value are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of building energy conservation, and in particular to a method for calibrating reference values ​​of sub-item energy consumption based on heating, ventilation and air-conditioning equipment. Background Art

[0002] With the increase in global energy consumption and growing awareness of environmental protection, improving energy efficiency has become particularly important. As one of the largest energy consumers in a building, the energy efficiency of HVAC equipment directly affects the energy efficiency of the entire building. Traditional HVAC equipment energy consumption benchmarks are typically set based on historical data, but this approach may have limitations. Due to the complexity and diversity of building operating conditions, a simple energy consumption benchmark may not accurately reflect actual energy consumption. Due to the constant changes in the environment and the equipment's own status, fixed energy consumption benchmarks may not be able to adapt to these changes, necessitating calibration of the HVAC equipment's individual energy consumption benchmarks. Summary of the Invention

[0003] The present invention aims to provide a method for calibrating the reference value of sub-item energy consumption based on HVAC equipment, and calibrates the reference value of sub-item energy consumption in combination with multiple targets.

[0004] The calibration method for the benchmark value of energy consumption of HVAC equipment includes:

[0005] S1. Determine abnormality of energy consumption baseline value;

[0006] Obtain the actual energy consumption sequence of different items within the preset time range and obtain the energy consumption sequence to be analyzed X n , X n =[X n（1） , X n（2） ,…,X n（I） ]; N is the number of energy consumption categories of target HVAC equipment, X n（i） Represents the energy consumption sequence X to be analyzed n The energy consumption of the i-th target HVAC equipment in the set, n=1, 2, ..., N; I represents the energy consumption sequence X to be analyzed within the preset time range n The actual energy consumption value number in, i=1, 2, ..., I; based on the energy consumption sequence to be analyzed X n and the current energy consumption benchmark value D n Perform correlation analysis to obtain the correlation Z of sub-item energy consumption n ; If the correlation degree of sub-item energy consumption Z n If the energy consumption associated threshold is reached, the energy consumption abnormality result is normal, and the current sub-item energy consumption baseline value D is retained. n Otherwise, the energy consumption abnormality result is abnormal, and the correlation degree Z of the sub-item energy consumption is recorded. n Corresponding target HVAC equipment energy consumption X n（i）For abnormal target HVAC equipment energy consumption, proceed to step S2;

[0007] S2. Preliminary calibration of energy consumption baseline values;

[0008] Acquire environmental information and climate information within a preset time range to obtain environmental information and climate information to be analyzed; obtain current status information of the target HVAC equipment to obtain status information to be analyzed; input the status information to be analyzed, the environmental information to be analyzed, the climate information to be analyzed, and the abnormal sub-item energy consumption of the target HVAC equipment into the energy consumption influencing factor judgment model for analysis to obtain the energy consumption baseline value influencing factor;

[0009] S3. Optimization and calibration of energy consumption benchmark values;

[0010] Based on the energy consumption benchmark value influencing factors, the energy consumption of abnormal target HVAC equipment is optimized and calculated to obtain the optimized energy consumption benchmark value D. n ';Optimize the energy consumption benchmark value D of each item n 'Evaluate, if the benchmark value evaluation result is passed, the sub-item energy consumption benchmark value D will be optimized n 'As the current energy consumption benchmark value D n Otherwise, continue to optimize the energy consumption benchmark value D n 'Optimize until it meets the current energy consumption benchmark value D n The calibration results.

[0011] As a preferred technical solution of the present invention, the calculation of the item energy consumption correlation Z in step S1 is as follows: n The specific steps include:

[0012] Energy consumption of target HVAC equipment X n（i） Perform the calculation:

[0013] Q1. Calculate the correlation coefficient G of sub-item energy consumption n（i） ;

[0014] Using the formula

[0015]

[0016] Calculate the correlation coefficient G of the sub-item energy consumption n（i） , correlation coefficient of sub-item energy consumption G n（i） Represents the energy consumption sequence X to be analyzed n Medium X n（i） The correlation coefficient R A（n） Indicates the minimum difference between the two levels, R A（n） =minminY n（i） ; R B（n） Indicates the maximum difference between the two levels, R B（n）=maxmaxY n（i） ; Y n（i） Indicates the current energy consumption benchmark value D n With X n（i） The absolute value of the difference, Y n（i） =|D n -X n（i） |; E is the resolution coefficient, which is determined by the target HVAC equipment energy consumption X n（i） Make confirmation;

[0017] Q2. Determine the weight W of the correlation coefficient of sub-item energy consumption n ;

[0018] The nine-level scale method is used to calculate the energy consumption of all target HVAC equipment. n（i） Establish a sub-item energy consumption evaluation matrix; calculate the eigenvalue of the sub-item energy consumption evaluation matrix to obtain the maximum eigenvalue of the sub-item energy consumption evaluation matrix; calculate the eigenvector using the sub-item energy consumption evaluation matrix and the maximum eigenvalue of the sub-item energy consumption evaluation matrix to obtain the eigenvector of the sub-item energy consumption evaluation matrix; normalize the eigenvector of the sub-item energy consumption evaluation matrix to obtain the eigenvector of the pre-processed sub-item energy consumption evaluation matrix; the nth item in the eigenvector of the pre-processed sub-item energy consumption evaluation matrix is ​​the weight W of the sub-item energy consumption correlation coefficient n ;

[0019] Q3. Calculate the correlation Z of energy consumption items n ;

[0020] Using the formula

[0021]

[0022] Calculate the correlation Z of sub-item energy consumption n .

[0023] As a preferred technical solution of the present invention, based on the target HVAC equipment energy consumption X n（i） The specific steps for determining the resolution coefficient E include:

[0024] Energy consumption of target HVAC equipment X n（i） and target HVAC equipment energy consumption by item X n’（i） , using the formula

[0025] Calculate the resolution coefficient E （n，n’） , resolution coefficient E （n，n’） Represents the energy consumption of different target HVAC equipment items X at the same time n（i） and target HVAC equipment energy consumption by item X n’（i） The impact of time; target HVAC equipment energy consumption X n（i） and target HVAC equipment energy consumption by item Xn’（i） Represents the energy consumption of any two target HVAC equipment items X n（i） The resolution coefficient is calculated in combination to indicate the degree of energy consumption deviation between the sub-item energy consumption of target HVAC equipment in different sub-item energy consumption categories at the same time;

[0026] R B（n，n’） Represents R B（n） and R B（n’） The maximum value between the two groups; a total of n*(n-1) / 2 groups of resolution coefficients E are obtained. （n，n’） ;

[0027] Calculate all resolution coefficients E （n，n’） The resolution coefficient E is determined based on the interval where the mean value lies.

[0028] As a preferred technical solution of the present invention, the energy consumption impact factor judgment model in step S2 includes a feature extraction layer, an internal feature analysis layer, an external feature analysis layer and a result output layer;

[0029] The feature extraction layer is used to extract features of the environmental information to be analyzed and the climate information to be analyzed, and obtain features of the environmental information and climate information; and to extract features of the state information to be analyzed, and obtain features of the state information;

[0030] The external feature analysis layer is used to fuse the environmental information features and climate information features to obtain external fusion features; and to perform feature analysis on the external fusion features to obtain external energy consumption influencing factors;

[0031] The internal feature analysis layer is used to perform feature analysis on the state information features to obtain the internal energy consumption influencing factors;

[0032] The result output layer is used to match the corresponding influencing factor weights in the sub-item energy consumption factor influence library according to the abnormal target HVAC equipment sub-item energy consumption to obtain the target influencing factor weights; according to the target influencing factor weights, the external energy consumption influencing factors and the internal energy consumption influencing factors are weightedly calculated to obtain the energy consumption baseline value influencing factors.

[0033] As a preferred technical solution of the present invention, the specific steps of training the external feature analysis layer include:

[0034] Collecting several groups of external feature analysis training samples, each group of external feature analysis training samples contains an external fusion feature and a corresponding labeled external influencing factor value; combining the several groups of external feature analysis training samples to obtain an external feature analysis training set;

[0035] The external feature analysis training set is input into the energy consumption influencing factor judgment model to train the external feature analysis layer with the corresponding marked external influencing factor value as the target to obtain the initial external feature analysis layer; the initial external feature analysis layer is model evaluated to obtain the initial external feature analysis layer model evaluation result; if the initial external feature analysis layer model evaluation result is passed, the initial external feature analysis layer is used as the external feature analysis layer in the energy consumption influencing factor judgment model; otherwise, the external feature analysis training set is used to continue model training.

[0036] As a preferred technical solution of the present invention, the specific steps of training the internal feature analysis layer include:

[0037] Collecting several groups of internal feature analysis training samples, each group of internal feature analysis training samples contains an internal state feature and a corresponding labeled internal influence factor value; combining the several groups of internal feature analysis training samples to obtain an internal feature analysis training set;

[0038] The internal feature analysis training set is input into the energy consumption impact factor judgment model to train the internal feature analysis layer with the corresponding marked internal impact factor value as the target to obtain the initial internal feature analysis layer; the initial internal feature analysis layer is model evaluated to obtain the initial internal feature analysis layer model evaluation result; if the initial internal feature analysis layer model evaluation result is passed, the initial internal feature analysis layer is used as the internal feature analysis layer in the energy consumption impact factor judgment model; otherwise, the internal feature analysis training set is used to continue model training.

[0039] As a preferred technical solution of the present invention, the specific steps of optimizing the energy consumption of abnormal target HVAC equipment items based on the energy consumption baseline value influencing factor include:

[0040] Obtain the energy consumption sequence X to be analyzed corresponding to the abnormal target HVAC equipment sub-item energy consumption n , get the abnormal energy consumption sequence; make abnormal judgment on the abnormal energy consumption sequence and get the optimal screening energy consumption sequence; construct K optimized individual energy consumption benchmark values ​​H k ;Each optimized sub-item energy consumption benchmark value individual H k It contains a set of energy consumption benchmark values ​​D based on the current sub-item n The energy consumption benchmark value to be optimized is established by the energy consumption benchmark value influencing factor; the K optimized sub-item energy consumption benchmark values ​​are individually H k Combine and obtain the optimized sub-item energy consumption benchmark value iterative population; set the maximum number of iterations T, and set the current number of iterations to t;

[0041] For the optimized sub-item energy consumption benchmark value, the optimized sub-item energy consumption benchmark value individual H in the iterative population is kPerform simulation calculations, conduct predictive analysis based on the optimal screened energy consumption sequence to obtain the predicted energy consumption sequence; perform regression analysis based on the predicted energy consumption sequence to obtain the optimal predicted energy consumption mean value; calculate the Euclidean distance between the optimal predicted energy consumption mean value and the individual H of the optimized sub-item energy consumption benchmark value to be optimized, and obtain the energy consumption benchmark difference C k ; Take the reciprocal of the energy consumption benchmark difference C k as the fitness S of the individual H of the optimized sub-item energy consumption benchmark value k ; k ; k ;

[0042] During the population iteration process, iteratively update the iterative population of the optimized sub-item energy consumption benchmark value;

[0043] When the maximum iteration number is reached, output the individual H of the optimized sub-item energy consumption benchmark value corresponding to the maximum fitness k , which is the optimal individual of the optimized sub-item energy consumption benchmark value; take the energy consumption benchmark value to be optimized in the optimal individual of the optimized sub-item energy consumption benchmark value as the optimized sub-item energy consumption benchmark value D n ’.

[0044] As a preferred technical solution of the present invention, the specific steps for iteratively updating the iterative population of the optimized sub-item energy consumption benchmark value include:

[0045] Divide the iterative population of the optimized sub-item energy consumption benchmark value into two parts to obtain the first iterative population of the optimized sub-item energy consumption benchmark value and the second iterative population of the optimized sub-item energy consumption benchmark value;

[0046] Set the iteration parameter U, U = exp(-t / T); exp() is the natural exponential function; set the iteration factor V, V = exp((t - T) / T) / 2;

[0047] When V < L1, randomly exchange and update the first iterative population of the optimized sub-item energy consumption benchmark value and the second iterative population of the optimized sub-item energy consumption benchmark value;

[0048] When U < L2, update the first iterative population of the optimized sub-item energy consumption benchmark value and the second iterative population of the optimized sub-item energy consumption benchmark value to the individual of the optimized sub-item energy consumption benchmark value with a larger fitness;

[0049] When V > L1 and U > L2, select the individual of the optimized sub-item energy consumption benchmark value with a larger fitness in the first iterative population of the optimized sub-item energy consumption benchmark value and the second iterative population of the optimized sub-item energy consumption benchmark value for mutation to obtain a new iterative population of the optimized sub-item energy consumption benchmark value.

[0050] The present invention has the following advantages:

[0051] 1. The present invention realizes the refined management of HVAC equipment energy consumption through serialized analysis of different sub-items of energy consumption, which helps to more accurately identify energy consumption anomalies; through energy consumption correlation analysis, it helps to monitor energy consumption in real time and quickly feedback abnormal situations, which can accurately identify abnormal target HVAC equipment sub-item energy consumption; by considering environmental information, climate information and equipment status information, it helps to more comprehensively understand the reasons for energy consumption changes; by dynamically adjusting the energy consumption baseline value according to real-time data and influencing factors, the adaptability and accuracy of the baseline value are improved.

[0052] 2. The present invention can accurately evaluate the degree of correlation between each energy consumption data point and the benchmark value by calculating the correlation coefficient of sub-item energy consumption, providing a quantitative basis for judging energy consumption anomalies; the nine-layer scaling method and eigenvector are used to calculate the weight of the correlation coefficient of sub-item energy consumption, ensuring the reasonable weight distribution of different energy consumption factors in the comprehensive evaluation; by comprehensively considering the correlation coefficient and weight of sub-item energy consumption, the calculated sub-item energy consumption correlation can more scientifically reflect the consistency between the energy consumption sequence and the benchmark value; by calculating the impact between different sub-item energy consumption, the resolution coefficient is dynamically determined, so that the model can adapt to the characteristics of different energy consumption data, and improve the adaptability and accuracy of correlation analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 This is a structural diagram of a method for calibrating reference values ​​of sub-item energy consumption based on HVAC equipment adopted in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0055] Based on the calibration method of the energy consumption benchmark value of HVAC equipment, see Figure 1 Shown, including:

[0056] S1. Determine abnormality of energy consumption baseline value;

[0057] Obtain the actual energy consumption sequence of different items within the preset time range and obtain the energy consumption sequence to be analyzed X n , X n =[X n（1） , X n（2） ,…,X n（I） ]; N is the number of energy consumption categories of target HVAC equipment, X n（i） Represents the energy consumption sequence X to be analyzed n The energy consumption of the i-th target HVAC equipment in the set, n=1, 2, ..., N; I represents the energy consumption sequence X to be analyzed within the preset time range nThe actual energy consumption value number in, i=1, 2, ..., I; based on the energy consumption sequence to be analyzed X n and the current energy consumption benchmark value D n Perform correlation analysis to obtain the correlation Z of sub-item energy consumption n ; If the correlation degree of sub-item energy consumption Z n If the energy consumption associated threshold is reached, the energy consumption abnormality result is normal, and the current sub-item energy consumption baseline value D is retained. n Otherwise, the energy consumption abnormality result is abnormal, and the correlation degree Z of the sub-item energy consumption is recorded. n Corresponding target HVAC equipment energy consumption X n（i） For abnormal target HVAC equipment energy consumption, proceed to step S2;

[0058] The preset time range is set by professional technicians based on actual conditions and can be the time range during which abnormal signals are continuously received; the energy consumption correlation threshold is set by professional technicians based on actual conditions and reflects the degree of correlation of energy consumption values;

[0059] In step S1, the correlation degree Z of the energy consumption of each item is calculated. n The specific steps include:

[0060] Energy consumption of target HVAC equipment X n（i） Perform the calculation:

[0061] Q1. Calculate the correlation coefficient G of sub-item energy consumption n（i） ;

[0062] Using the formula

[0063]

[0064] Calculate the correlation coefficient G of the sub-item energy consumption n（i） , correlation coefficient of sub-item energy consumption G n（i） Represents the energy consumption sequence X to be analyzed n Medium X n（i） The correlation coefficient R A（n） Indicates the minimum difference between the two levels, R A（n） =minminY n（i） ; R B（n） Indicates the maximum difference between the two levels, R B（n） =maxmaxY n（i） ; Y n（i） Indicates the current energy consumption benchmark value D n With X n（i） The absolute value of the difference, Y n（i） =|D n -X n（i） |; E is the resolution coefficient, which is determined by the target HVAC equipment energy consumption X n（i）Confirm; the resolution coefficient E is an adjustment parameter used to control the sensitivity of gray relational degree calculation, which corresponds to the resolution coefficient in the standard gray relational degree calculation formula;

[0065] X n（i） represents the energy consumption of the nth sub-item energy consumption category at the i-th moment, which is the actual collected energy consumption data, that is, the sub-item energy consumption of the target HVAC equipment; D n is the baseline value of the nth energy consumption category, usually derived from historical operating data or equipment description; n（i） =|D n -X n（i） |, so R A（n） =minminY n（i） , represents a point closest to the reference value; and R B（n） =maxmaxY n（i） Indicates the point that deviates most from the reference value;

[0066] Correlation coefficient of sub-item energy consumption G n（i） The formula comes from a form of gray correlation degree calculation formula in the gray correlation analysis method. This method is often used to measure the similarity between different data series. This formula essentially measures the similarity between the actual energy consumption series and the benchmark value. This formula is one of the standard forms of gray correlation degree calculation, where R A（n） and R B（n） They represent the minimum difference between the two levels and the maximum difference between the two levels respectively. E is the resolution coefficient, which is used to adjust the sensitivity of the correlation. The formula calculates the correlation coefficient of each data point by comparing the absolute difference between the actual energy consumption and the benchmark value with the range.

[0067] Q2. Determine the weight W of the correlation coefficient of sub-item energy consumption n ;

[0068] The nine-level scale method is used to calculate the energy consumption of all target HVAC equipment. n（i） Establish a sub-item energy consumption evaluation matrix; calculate the eigenvalue of the sub-item energy consumption evaluation matrix to obtain the maximum eigenvalue of the sub-item energy consumption evaluation matrix; calculate the eigenvector using the sub-item energy consumption evaluation matrix and the maximum eigenvalue of the sub-item energy consumption evaluation matrix to obtain the eigenvector of the sub-item energy consumption evaluation matrix; normalize the eigenvector of the sub-item energy consumption evaluation matrix to obtain the eigenvector of the pre-processed sub-item energy consumption evaluation matrix; the nth item in the eigenvector of the pre-processed sub-item energy consumption evaluation matrix is ​​the weight W of the sub-item energy consumption correlation coefficient n ;

[0069] Q3. Calculate the correlation Z of energy consumption items n ;

[0070] Using the formula

[0071]

[0072] Calculate the correlation Z of sub-item energy consumption n ; This formula is a weighted average of the correlation coefficient, where W n It is the weight calculated by the nine-layer scaling method and the eigenvector method, and is used to reflect the importance of different energy consumption items.

[0073] Grey correlation analysis is particularly suitable for systems with small samples and incomplete information, and the energy consumption data of HVAC equipment is often uncertain and dynamic. Therefore, this method is very suitable for calibrating energy consumption benchmark values. By calculating the correlation, the consistency between actual energy consumption and the benchmark value can be quantified, thereby determining whether calibration is needed. The nine-layer scaling method and the eigenvector method are used to calculate weights, ensuring the reasonable weight distribution of different energy consumption items in the comprehensive evaluation. This method combines expert experience and mathematical modeling, avoids subjective arbitrariness, and improves the objectivity and scientificity of weight distribution. By introducing the resolution coefficient E, the formula can dynamically adjust the sensitivity of the correlation calculation according to the characteristics of the actual data, thereby adapting to the energy consumption analysis needs in different scenarios.

[0074] The purpose of the formula is to judge abnormal energy consumption. By calculating the correlation between sub-item energy consumption, the deviation between the actual energy consumption sequence and the benchmark value can be quantified. If the correlation between sub-item energy consumption Z n If the value is lower than the energy consumption correlation threshold, it is judged as abnormal and triggers the subsequent calibration process; this formula can accurately evaluate the correlation of each energy consumption data point, provide a quantitative basis for energy consumption management, and realize the refined management of HVAC equipment energy consumption; through correlation analysis, it can identify deviations from the baseline value caused by factors such as environmental changes and equipment aging, thereby providing data support for dynamic calibration.

[0075] Based on the target HVAC equipment energy consumption X n（i） The specific steps for determining the resolution coefficient E include:

[0076] Energy consumption of target HVAC equipment X n（i） and target HVAC equipment energy consumption by item X n’（i） , using the formula

[0077] Calculate the resolution coefficient E （n，n’） , resolution coefficient E （n，n’） Represents the energy consumption of different target HVAC equipment items X at the same time n（i） and target HVAC equipment energy consumption by item X n’（i） The impact of time; target HVAC equipment energy consumption X n（i） and target HVAC equipment energy consumption by item X n’（i） Represents the energy consumption of any two target HVAC equipment items Xn（i） The resolution coefficient is calculated in combination to indicate the degree of energy consumption deviation between the sub-item energy consumption of target HVAC equipment of different sub-item energy consumption categories at the same time. The core idea of ​​this formula is to calculate an adaptive resolution coefficient by analyzing the mutual influence between different sub-item energy consumption. In traditional grey correlation analysis, the resolution coefficient is usually a fixed value (such as 0.5), but in actual applications, the characteristics of different sub-item energy consumption may vary greatly. By calculating the mutual influence between sub-items, the value of the resolution coefficient is dynamically determined, so that it can adapt to the characteristics of different energy consumption data and improve the accuracy of correlation analysis. The mathematical rigor of the calculation is ensured by constructing the absolute difference and range of sub-item energy consumption. The normalization process further eliminates the interference of different sub-items on the resolution coefficient, making the result more universal.

[0078] In the formula, the numerator and It is the sum of the absolute differences between the two sub-items of energy consumption and the benchmark value. The product form is used to quantify the synergistic effect of the overall deviation degree of the two sub-item energy consumption series. The denominator is used to eliminate the influence of the data volume on the calculation results. The cumulative sum in the denominator increases with the increase of I. Dividing by I can ensure that the resolution coefficient is not directly affected by the number of data points. The deviation product in the denominator is standardized to the same dimension as the range to avoid distortion of the resolution coefficient caused by absolute numerical differences. The coefficient 2 is used to control the value range of the resolution coefficient and is set through expert experience.

[0079] The dynamic resolution coefficient can more accurately reflect the relationship between actual energy consumption data and the baseline value, avoiding the problems of insufficient or excessive sensitivity caused by fixed coefficients. By calculating the resolution coefficients between different sub-items, the mutual influence of multiple sub-items of energy consumption can be comprehensively analyzed, providing a basis for the global calibration of energy consumption baseline values.

[0080] R B（n，n’） Represents R B（n） and R B（n’） The maximum value between the two groups; a total of n*(n-1) / 2 groups of resolution coefficients E are obtained. （n，n’） ;

[0081] Calculate all resolution coefficients E （n，n’） The resolution coefficient E is determined based on the mean of the mean interval. This formula reflects the impact of different sub-items on the resolution coefficient. By calculating the resolution coefficient for every two sub-items and averaging all the resolution coefficients, the impact of different energy consumption sub-items on the correlation calculation can be eliminated.

[0082] In the formula, Y n（i） =|D n -X n（i） |, Y n’（i） =|D n’ -Xn’（i） |, R B（n） =maxmaxY n（i） , R B（n’） =maxmaxY n’（i） , the specific value is determined by X n（i） The energy consumption sequence X to be analyzed corresponding to the nth sub-item energy consumption category n and X n’（i） The energy consumption sequence X to be analyzed corresponding to the n'th sub-item energy consumption category n’ Make a determination; n≠n';

[0083] The specific steps for determining the resolution coefficient E based on the interval of the mean are:

[0084] Normalization is performed based on the calculated result of the mean so that the normalized mean is within the range of (0, 1). The interval is determined based on the normalized mean, and the final resolution coefficient E is selected. For example, when the normalized mean is within the first interval, E=0.3 can be set; when the normalized mean is within the second interval, E=0.4 can be set; when the normalized mean is within the third interval, E=0.5 can be set; when the normalized mean is within the fourth interval, E=0.6 can be set; when the normalized mean is within the fifth interval, E=0.7 can be set. The above values ​​only provide one setting method, and the specific values ​​are manually set by professional and technical personnel.

[0085] By calculating the correlation coefficient of sub-item energy consumption, the degree of correlation between each energy consumption data point and the benchmark value can be accurately evaluated, providing a quantitative basis for judging energy consumption anomalies; the nine-layer scaling method and eigenvector are used to calculate the weight of the sub-item energy consumption correlation coefficient, ensuring the reasonable weight distribution of different energy consumption factors in the comprehensive evaluation; by comprehensively considering the sub-item energy consumption correlation coefficient and weight, the calculated sub-item energy consumption correlation can more scientifically reflect the consistency between the energy consumption sequence and the benchmark value; by calculating the impact between different sub-item energy consumption, the resolution coefficient is dynamically determined, so that the model can adapt to the characteristics of different energy consumption data, and improve the adaptability and accuracy of correlation analysis; through sub-item correlation analysis, the rationality of the sub-item energy consumption benchmark value can be directly reflected through the data. If it is judged that there is an abnormal sub-item energy consumption correlation, it means that there is a problem in the setting of the sub-item energy consumption benchmark value, such as not being updated with climate change, or energy consumption offset due to problems such as equipment aging, and the sub-item energy consumption benchmark value needs to be calibrated;

[0086] S2. Preliminary calibration of energy consumption baseline values;

[0087] Acquire environmental information and climate information within a preset time range to obtain environmental information and climate information to be analyzed; obtain current status information of the target HVAC equipment to obtain status information to be analyzed; input the status information to be analyzed, the environmental information to be analyzed, the climate information to be analyzed, and the abnormal sub-item energy consumption of the target HVAC equipment into the energy consumption influencing factor judgment model for analysis to obtain the energy consumption baseline value influencing factor;

[0088] The energy consumption influencing factor judgment model in step S2 includes a feature extraction layer, an internal feature analysis layer, an external feature analysis layer and a result output layer;

[0089] The feature extraction layer is used to extract features of the environmental information to be analyzed and the climate information to be analyzed, and obtain features of the environmental information and climate information; and to extract features of the state information to be analyzed, and obtain features of the state information;

[0090] The external feature analysis layer is used to fuse the environmental information features and climate information features to obtain external fusion features; and to perform feature analysis on the external fusion features to obtain external energy consumption influencing factors;

[0091] The internal feature analysis layer is used to perform feature analysis on the state information features to obtain the internal energy consumption influencing factors;

[0092] The result output layer is used to match the corresponding impact factor weights in the sub-item energy consumption factor impact library according to the abnormal target HVAC equipment sub-item energy consumption to obtain the target impact factor weights; based on the target impact factor weights, the external energy consumption impact factors and internal energy consumption impact factors are weighted and calculated to obtain the energy consumption baseline impact factors;

[0093] The specific steps for training the external feature analysis layer include:

[0094] Collecting several groups of external feature analysis training samples, each group of external feature analysis training samples contains an external fusion feature and a corresponding labeled external influencing factor value; combining the several groups of external feature analysis training samples to obtain an external feature analysis training set;

[0095] The external feature analysis training set is input into the energy consumption impact factor judgment model to train the external feature analysis layer with the corresponding marked external impact factor value as the target to obtain an initial external feature analysis layer; the initial external feature analysis layer is model evaluated to obtain an initial external feature analysis layer model evaluation result; if the initial external feature analysis layer model evaluation result is passed, the initial external feature analysis layer is used as the external feature analysis layer in the energy consumption impact factor judgment model; otherwise, the external feature analysis training set is used to continue model training;

[0096] The specific steps for training the internal feature analysis layer include:

[0097] Collecting several groups of internal feature analysis training samples, each group of internal feature analysis training samples contains an internal state feature and a corresponding labeled internal influence factor value; combining the several groups of internal feature analysis training samples to obtain an internal feature analysis training set;

[0098] Input the internal feature analysis training set into the energy consumption impact factor judgment model to train the internal feature analysis layer with the corresponding marked internal impact factor value as the target to obtain an initial internal feature analysis layer; perform model evaluation on the initial internal feature analysis layer to obtain an initial internal feature analysis layer model evaluation result; if the initial internal feature analysis layer model evaluation result is passed, the initial internal feature analysis layer is used as the internal feature analysis layer in the energy consumption impact factor judgment model; otherwise, continue model training using the internal feature analysis training set;

[0099] By simultaneously considering environmental, climate, and equipment status information, a multi-dimensional analysis of factors influencing energy consumption is achieved, improving the accuracy of energy consumption prediction and analysis. The introduction of external and internal feature analysis layers enables the model to comprehensively consider features from different sources and conduct in-depth analysis, enhancing the rationality of energy consumption baseline calibration. The automated collection of training samples and construction of training sets reduces the complexity of manual operations and improves the efficiency of model training. The model evaluation and iterative training process ensures the accuracy and effectiveness of the feature analysis layer. Through continuous evaluation and optimization, the performance of the energy consumption influencing factor judgment model is improved. Through precise feature analysis and weight matching, a more accurate energy consumption baseline influencing factor is obtained, providing a reliable basis for energy consumption baseline calibration.

[0100] S3. Optimization and calibration of energy consumption benchmark values;

[0101] Based on the energy consumption benchmark value influencing factors, the energy consumption of abnormal target HVAC equipment is optimized and calculated to obtain the optimized energy consumption benchmark value D. n ';Optimize the energy consumption benchmark value D of each item n 'Evaluate, if the benchmark value evaluation result is passed, the sub-item energy consumption benchmark value D will be optimized n 'As the current energy consumption benchmark value D n Otherwise, continue to optimize the energy consumption benchmark value D n 'Optimize until it meets the current energy consumption benchmark value D n The calibration results;

[0102] The specific steps for optimizing the energy consumption of abnormal target HVAC equipment items based on the energy consumption baseline impact factors include:

[0103] Obtain the energy consumption sequence X to be analyzed corresponding to the abnormal target HVAC equipment sub-item energy consumption n , get the abnormal energy consumption sequence; make abnormal judgment on the abnormal energy consumption sequence and get the optimal screening energy consumption sequence; construct K optimized individual energy consumption benchmark values ​​H k ;Each optimized sub-item energy consumption benchmark value individual H k It contains a set of energy consumption benchmark values ​​D based on the current sub-item n The energy consumption benchmark value to be optimized is established by the energy consumption benchmark value influencing factor; the K optimized sub-item energy consumption benchmark values ​​are individually H k Combine and obtain the optimized sub-item energy consumption benchmark value iteration population; set the maximum number of iterations T, and set the current number of iterations to t; the maximum number of iterations T is set by professional technicians according to actual conditions;

[0104] Abnormal judgment is to manually screen out the energy consumption with real abnormalities and retain the energy consumption values ​​that are misjudged due to the error of the baseline value; the generation of the initial individual uses the influencing factor to calculate the current sub-item energy consumption baseline value D n Perform calculations, define the data fluctuation range, and randomly generate the energy consumption benchmark value to be optimized within the data fluctuation range;

[0105] For the optimized sub-item energy consumption benchmark value, the optimized sub-item energy consumption benchmark value individual H in the iterative population is k Perform simulation calculations, perform forecast analysis based on the optimal screening energy consumption sequence, and obtain the forecast energy consumption sequence; perform regression analysis based on the forecast energy consumption sequence to obtain the optimal forecast energy consumption mean; calculate the optimal forecast energy consumption mean and the individual H of the optimized sub-item energy consumption benchmark value k The Euclidean distance of the energy consumption benchmark value to be optimized is used to obtain the energy consumption benchmark difference C k ; Set the energy consumption benchmark difference C k The reciprocal of is used as the benchmark value for optimizing individual energy consumption k The fitness S k ;

[0106] During the population iteration process, the optimized sub-item energy consumption benchmark value iteration population is iteratively updated;

[0107] The specific steps for iteratively updating the optimized sub-item energy consumption benchmark value iterative population include:

[0108] Dividing the optimized sub-item energy consumption benchmark value iteration population into two parts to obtain a first optimized sub-item energy consumption benchmark value iteration population and a second optimized sub-item energy consumption benchmark value iteration population;

[0109] Set the iteration parameter U, U = exp (-t / T); exp () is a natural exponential function; set the iteration factor V, V = exp ((tT) / T) / 2;

[0110] When V < L1, the first optimized sub - item energy consumption benchmark value iteration population and the second optimized sub - item energy consumption benchmark value iteration population are randomly exchanged and updated;

[0111] When U < L2, the first optimized sub - item energy consumption benchmark value iteration population and the second optimized sub - item energy consumption benchmark value iteration population are updated towards the optimized sub - item energy consumption benchmark value individuals with larger fitness;

[0112] When V > L1 and U > L2, select the optimized sub - item energy consumption benchmark value individuals with larger fitness in the first optimized sub - item energy consumption benchmark value iteration population and the second optimized sub - item energy consumption benchmark value iteration population for mutation to obtain a new optimized sub - item energy consumption benchmark value iteration population;

[0113] The specific values of L1 and L2 are set by professional technicians according to the actual situation. For example, L1 is taken as 0.3 and L2 is taken as 0.7;

[0114] Using two parameters to iteratively update the population can divide the iterative process into different stages. Referring to the foraging, feeding, and mating stages of the snake group to update the iterative population, approaching the optimal solution in a reasonable update manner, avoiding falling into the local optimal solution in the early stage, and at the same time improving the convergence speed;

[0115] When the maximum number of iterations is reached, output the optimized sub - item energy consumption benchmark value individual H k , which is the optimal optimized sub - item energy consumption benchmark value individual; take the energy consumption benchmark value to be optimized in the optimal optimized sub - item energy consumption benchmark value individual as the optimized sub - item energy consumption benchmark value D n ’;

[0116] Through optimization calculations, it is ensured that the energy use of HVAC equipment reaches the highest efficiency, reducing unnecessary energy waste, realizing the dynamic management and continuous optimization of the energy consumption benchmark value; by optimizing the abnormal energy consumption sequence, it can more accurately reflect the actual energy consumption status of HVAC equipment. The optimized sub - item energy consumption benchmark value helps to identify energy consumption abnormal points, thereby taking measures to reduce energy consumption; adopting an automated iterative optimization method reduces the need for manual intervention and improves work efficiency.

[0117] It should be understood that for those of ordinary skill in the art, improvements or transformations can be made according to the above description, and all such improvements and transformations should fall within the protection scope of the appended claims of this invention. The parts not described in detail in this specification belong to the prior art well - known to those of ordinary skill in the art.

Claims

1. A method for calibrating the reference value of energy consumption of HVAC equipment, characterized in that: include: S1. Determine abnormality of energy consumption baseline value; Obtain the actual energy consumption sequence of different items within the preset time range and obtain the energy consumption sequence to be analyzed X n , X n =[X n（1） , X n（2） ,…,X n（I） ]; N is the number of energy consumption categories of target HVAC equipment, X n（i） Represents the energy consumption sequence X to be analyzed n The energy consumption of the i-th target HVAC equipment in the set, n=1, 2, ..., N; I represents the energy consumption sequence X to be analyzed within the preset time range n The number of actual energy consumption values ​​in , i=1, 2, …, I; Based on the energy consumption sequence X to be analyzed n and the current energy consumption benchmark value D n Perform correlation analysis to obtain the correlation Z of sub-item energy consumption n ; If the correlation degree of sub-item energy consumption Z n If the energy consumption associated threshold is reached, the energy consumption abnormality result is normal, and the current sub-item energy consumption baseline value D is retained. n Otherwise, the energy consumption abnormality result is abnormal, and the correlation degree Z of the sub-item energy consumption is recorded. n Corresponding target HVAC equipment energy consumption X n（i） For abnormal target HVAC equipment energy consumption, proceed to step S2; S2. Preliminary calibration of energy consumption baseline values; Obtain environmental information and climate information within a preset time range, and obtain the environmental information to be analyzed and the climate information to be analyzed; Obtain the current status information of the target HVAC equipment to obtain the status information to be analyzed; input the status information to be analyzed, the environmental information to be analyzed, the climate information to be analyzed, and the abnormal sub-item energy consumption of the target HVAC equipment into the energy consumption impact factor judgment model for analysis to obtain the energy consumption baseline value impact factor; S3. Optimization and calibration of energy consumption benchmark values; Based on the energy consumption benchmark value influencing factors, the energy consumption of abnormal target HVAC equipment is optimized and calculated to obtain the optimized energy consumption benchmark value D. n ';Optimize the energy consumption benchmark value D of each item n 'Evaluate, if the benchmark value evaluation result is passed, the sub-item energy consumption benchmark value D will be optimized n 'As the current energy consumption benchmark value D n Otherwise, continue to optimize the energy consumption benchmark value D n 'Optimize until it meets the current energy consumption benchmark value D n The calibration results; The specific steps for optimizing the energy consumption of abnormal target HVAC equipment items based on the energy consumption baseline impact factors include: Obtain the energy consumption sequence X to be analyzed corresponding to the abnormal target HVAC equipment sub-item energy consumption n , get the abnormal energy consumption sequence; make abnormal judgment on the abnormal energy consumption sequence and get the optimal screening energy consumption sequence; construct K optimized individual energy consumption benchmark values ​​H k ;Each optimized sub-item energy consumption benchmark value individual H k It contains a set of energy consumption benchmark values ​​D based on the current sub-item n The energy consumption benchmark value to be optimized is established by the energy consumption benchmark value influencing factor; the K optimized sub-item energy consumption benchmark values ​​are individually H k Combination, to obtain the iterative population of optimized sub-item energy consumption benchmark values; Set the maximum number of iterations T and set the current number of iterations to t; For the optimized sub-item energy consumption benchmark value, the optimized sub-item energy consumption benchmark value individual H in the iterative population is k Perform simulation calculations, perform forecast analysis based on the optimal screening energy consumption sequence, and obtain the forecast energy consumption sequence; perform regression analysis based on the forecast energy consumption sequence to obtain the optimal forecast energy consumption mean; calculate the optimal forecast energy consumption mean and the individual H of the optimized sub-item energy consumption benchmark value k The Euclidean distance of the energy consumption benchmark value to be optimized is used to obtain the energy consumption benchmark difference C k ; Set the energy consumption benchmark difference C k The reciprocal of is used as the benchmark value for optimizing individual energy consumption k The fitness S k ; During the population iteration process, the optimized sub-item energy consumption benchmark value iteration population is iteratively updated; When the maximum number of iterations is reached, the output of the optimal sub-item energy consumption benchmark value H corresponding to the maximum fitness is k , which is the optimal optimization sub-item energy consumption benchmark value individual; the energy consumption benchmark value to be optimized in the optimal optimization sub-item energy consumption benchmark value individual is used as the optimized sub-item energy consumption benchmark value D n '.

2. The method for calibrating the reference value of energy consumption of HVAC equipment according to claim 1, characterized in that: In step S1, the correlation degree Z of the energy consumption of each item is calculated. n The specific steps include: Energy consumption of target HVAC equipment X n（i） Perform the calculation: Q1. Calculate the correlation coefficient G of sub-item energy consumption n（i） ; Using the formula Calculate the correlation coefficient G of the sub-item energy consumption n（i） , correlation coefficient of sub-item energy consumption G n（i） Represents the energy consumption sequence X to be analyzed n Medium X n（i） The correlation coefficient R A（n） Indicates the minimum difference between the two levels, R A（n） =minminY n（i） ; R B（n） Indicates the maximum difference between the two levels, R B（n） =maxmaxY n（i） ; Y n（i） Indicates the current energy consumption benchmark value D n With X n（i） The absolute value of the difference, Y n（i） =|D n -X n（i） |; E is the resolution coefficient, which is determined by the target HVAC equipment energy consumption X n（i） Make confirmation; Q2. Determine the weight W of the correlation coefficient of sub-item energy consumption n ; The nine-level scale method is used to calculate the energy consumption of all target HVAC equipment. n（i） Establish a sub-item energy consumption evaluation matrix; calculate the eigenvalue of the sub-item energy consumption evaluation matrix to obtain the maximum eigenvalue of the sub-item energy consumption evaluation matrix; calculate the eigenvector using the sub-item energy consumption evaluation matrix and the maximum eigenvalue of the sub-item energy consumption evaluation matrix to obtain the eigenvector of the sub-item energy consumption evaluation matrix; normalize the eigenvector of the sub-item energy consumption evaluation matrix to obtain the eigenvector of the pre-processed sub-item energy consumption evaluation matrix; the nth item in the eigenvector of the pre-processed sub-item energy consumption evaluation matrix is ​​the weight W of the sub-item energy consumption correlation coefficient n ; Q3. Calculate the correlation Z of energy consumption items n ; Using the formula Calculate the correlation Z of sub-item energy consumption n .

3. The method for calibrating the reference value of energy consumption of HVAC equipment according to claim 2, characterized in that: Based on the target HVAC equipment energy consumption X n（i） The specific steps for determining the resolution coefficient E include: Energy consumption of target HVAC equipment X n（i） and target HVAC equipment energy consumption by item X n’（i） , using the formula Calculate the resolution coefficient E （n，n’） , resolution coefficient E （n，n’） Represents the energy consumption of different target HVAC equipment items X at the same time n（i） and target HVAC equipment energy consumption by item X n’（i） The impact of time; target HVAC equipment energy consumption X n（i） and target HVAC equipment energy consumption by item X n’（i） Represents the energy consumption of any two target HVAC equipment items X n（i） The resolution coefficient is calculated in combination to indicate the degree of energy consumption deviation between the sub-item energy consumption of target HVAC equipment in different sub-item energy consumption categories at the same time; R B（n，n’） Represents R B（n） and R B（n’） The maximum value between the two groups; a total of n*(n-1) / 2 groups of resolution coefficients E are obtained. （n，n’） ; Calculate all resolution coefficients E （n，n’） The resolution coefficient E is determined based on the interval where the mean value lies.

4. The method for calibrating the reference value of energy consumption of HVAC equipment according to claim 3, characterized in that: The energy consumption influencing factor judgment model in step S2 includes a feature extraction layer, an internal feature analysis layer, an external feature analysis layer and a result output layer; The feature extraction layer is used to extract features of the environmental information to be analyzed and the climate information to be analyzed, and obtain the features of the environmental information and the climate information; Perform feature extraction on the state information to be analyzed to obtain state information features; The external feature analysis layer is used to fuse the environmental information features and climate information features to obtain external fusion features; and to perform feature analysis on the external fusion features to obtain external energy consumption influencing factors; The internal feature analysis layer is used to perform feature analysis on the state information features to obtain the internal energy consumption influencing factors; The result output layer is used to match the corresponding impact factor weights in the sub-item energy consumption factor impact library according to the abnormal target HVAC equipment sub-item energy consumption, and obtain the target impact factor weights; The external energy consumption influencing factors and the internal energy consumption influencing factors are weighted and calculated according to the target influencing factor weights to obtain the energy consumption baseline value influencing factors.

5. The method for calibrating the reference value of energy consumption of HVAC equipment according to claim 4, characterized in that: The specific steps for training the external feature analysis layer include: Collecting several groups of external feature analysis training samples, each group of external feature analysis training samples contains an external fusion feature and a corresponding labeled external influencing factor value; combining the several groups of external feature analysis training samples to obtain an external feature analysis training set; The external feature analysis training set is input into the energy consumption influencing factor judgment model to train the external feature analysis layer with the corresponding marked external influencing factor value as the target to obtain the initial external feature analysis layer; the initial external feature analysis layer is model evaluated to obtain the initial external feature analysis layer model evaluation result; if the initial external feature analysis layer model evaluation result is passed, the initial external feature analysis layer is used as the external feature analysis layer in the energy consumption influencing factor judgment model; otherwise, the external feature analysis training set is used to continue model training.

6. The method for calibrating the reference value of energy consumption of HVAC equipment according to claim 5, characterized in that: The specific steps for training the internal feature analysis layer include: Collecting several groups of internal feature analysis training samples, each group of internal feature analysis training samples contains an internal state feature and a corresponding labeled internal influence factor value; combining the several groups of internal feature analysis training samples to obtain an internal feature analysis training set; Input the internal feature analysis training set into the energy consumption impact factor judgment model to train the internal feature analysis layer with the internal impact factor values corresponding to the tags as the target, and obtain the initial internal feature analysis layer; conduct model evaluation on the initial internal feature analysis layer to obtain the model evaluation result of the initial internal feature analysis layer; if the model evaluation result of the initial internal feature analysis layer is passed, use the initial internal feature analysis layer as the internal feature analysis layer in the energy consumption impact factor judgment model; otherwise, continue model training using the internal feature analysis training set.

7. The method for calibrating the reference value of energy consumption of HVAC equipment according to claim 6, characterized in that: The specific steps for iteratively updating the optimized sub-item energy consumption baseline value iteration population include: Divide the optimized sub-item energy consumption baseline value iteration population into two parts to obtain the first optimized sub-item energy consumption baseline value iteration population and the second optimized sub-item energy consumption baseline value iteration population; Set the iteration parameter U, U = exp(-t / T); exp() is the natural exponential function; set the iteration factor V, V = exp((t - T) / T) / 2; When V < L1, the first optimized sub-item energy consumption baseline value iteration population and the second optimized sub-item energy consumption baseline value iteration population are randomly exchanged and updated; When U < L2, the first optimized sub-item energy consumption baseline value iteration population and the second optimized sub-item energy consumption baseline value iteration population are updated to the optimized sub-item energy consumption baseline value individuals with larger fitness; When V > L1 and U > L2, select the optimized sub-item energy consumption baseline value individuals with larger fitness in the first optimized sub-item energy consumption baseline value iteration population and the second optimized sub-item energy consumption baseline value iteration population for mutation to obtain a new optimized sub-item energy consumption baseline value iteration population.

Images