Method, system and storage medium for processing energy consumption data of building electromechanical equipment operation

Abstract

The present invention relates to a method, system and storage medium for processing the operating energy consumption data of building electromechanical equipment, including: obtaining the operating energy consumption data of all electromechanical equipment at preset time intervals throughout the year and processing to obtain a daily energy consumption curve set; preprocessing the daily energy consumption curve set to obtain a preprocessed daily energy consumption curve set; obtaining the daily total energy consumption of each daily energy consumption curve; determining flexible operating equipment and rigid operating equipment; performing feature analysis on the daily energy consumption curve to obtain the daily operating characteristics of the flexible operating equipment and the rigid operating equipment; using a box plot method to process the abnormal points of the daily operating characteristics of the flexible operating equipment and the rigid operating equipment to obtain a once-processed daily energy consumption curve of the flexible operating equipment and the rigid operating equipment; and using a random forest method to process to obtain a de-isolated daily energy consumption curve. The present invention realizes the recognition of abnormal equipment operating energy consumption, solves the drawbacks of the traditional single-point fixed threshold monitoring of abnormal points, realizes in-depth data preprocessing, has low cost, strong versatility, and improves the level of intelligence.

Description

Technical Field

[0001] The present invention relates to the technical field of processing the energy consumption data of building electromechanical equipment operation, and more specifically, to a method, system and storage medium for processing the energy consumption data of building electromechanical equipment operation. Background Art

[0002] Building energy consumption currently accounts for about 30% of the total energy consumption of social activities. With the construction of informatization, a large amount of energy consumption data of building mechanical and electrical equipment has been accumulated. However, the effective use of these energy consumption data is not enough at present. The utilization value is more limited to energy consumption monitoring, and the value of the energy platform has not been fully utilized. One of the important reasons is that the energy consumption data monitored by building mechanical and electrical equipment is not comprehensive enough and there are data quality problems. Secondly, it is impossible to remove the daily energy consumption data with implicit and non-obvious features, which affects the accuracy of energy consumption data mining and analysis.

[0003] For the operation of system electromechanical equipment, the daily operation characteristics that appear during the operation process can often be identified from the perspective of energy consumption. In engineering applications, it is usually necessary to monitor whether the energy consumption time point exceeds the threshold to determine whether there is an abnormal time point. However, most energy-consuming equipment today has incorrect energy consumption data not only because of equipment failures, but more because of abnormal operation strategies. It is necessary to observe the daily energy consumption for data preprocessing. Since the actual operating characteristics of the building itself and the electromechanical system vary greatly, it is still a difficult problem to formulate a threshold method for data preprocessing. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method, system and storage medium for processing energy consumption data of building electromechanical equipment in view of the defects of the prior art.

[0005] The technical solution adopted by the present invention to solve the technical problem is: construct a method for processing the operating energy consumption data of building electromechanical equipment, comprising the following steps:

[0006] Obtain the operating energy consumption data of all electromechanical equipment at preset time intervals throughout the year, process the daily energy consumption data as a unit, and obtain a daily energy consumption curve set of all electromechanical equipment throughout the year;

[0007] Preprocessing the daily energy consumption curve set to obtain a preprocessed daily energy consumption curve set;

[0008] Calculating based on the preprocessed daily energy consumption curve set to obtain the daily total energy consumption of each daily energy consumption curve;

[0009] Calculate the CV value of the total daily energy consumption of each electromechanical equipment throughout the year based on the total daily energy consumption, and determine the flexible operation equipment and rigid operation equipment based on the CV values ​​of all electromechanical equipment;

[0010] Performing feature analysis on the preprocessed daily energy consumption curve set of the flexible operation equipment and the preprocessed daily energy consumption curve set of the rigid operation equipment to obtain the daily operation characteristics of the flexible operation equipment and the daily operation characteristics of the rigid operation equipment;

[0011] According to the daily operation characteristics of the flexible operation equipment, the box plot method is used to process abnormal points to obtain the daily energy consumption curve of the flexible operation equipment, and according to the daily operation characteristics of the rigid operation equipment, the box plot method is used to process abnormal points to obtain the daily energy consumption curve of the rigid operation equipment;

[0012] The random forest method is used to isolate and remove the one-time processing daily energy consumption curve of the flexible operation equipment and the one-time processing daily energy consumption curve of the rigid operation equipment, respectively, to obtain the de-isolated daily energy consumption curve of the flexible operation equipment and the de-isolated daily energy consumption curve of the rigid operation equipment.

[0013] In the method for processing the operating energy consumption data of mechanical and electrical equipment of a building according to the present invention, the preprocessing of the daily energy consumption curve set to obtain the preprocessed daily energy consumption curve set comprises:

[0014] Performing a process of removing missing values ​​on the daily energy consumption curve set to obtain a daily energy consumption curve after removing the missing values;

[0015] The daily energy consumption curves containing vacant values ​​are subjected to deduplication processing to obtain daily energy consumption curves with identical deduplication removed; all daily energy consumption curves with identical deduplication removed are the preprocessed daily energy consumption curve set.

[0016] In the method for processing the operating energy consumption data of building electromechanical equipment of the present invention, the CV value of the total daily energy consumption of each electromechanical equipment throughout the year is calculated according to the total daily energy consumption, and the flexible operating equipment and the rigid operating equipment are determined according to the CV values ​​of all electromechanical equipment, including:

[0017] Calculate the CV value of the total daily energy consumption of each electromechanical equipment throughout the year based on the total daily energy consumption;

[0018] comparing the CV value with a CV target value;

[0019] Acquire a CV value greater than the CV target value and a CV value less than the CV target value;

[0020] determining the flexible operation device based on the CV value greater than the CV target value;

[0021] The rigid operating device is determined based on the CV value that is smaller than the CV target value.

[0022] In the method for processing the operating energy consumption data of mechanical and electrical equipment of a building according to the present invention, the feature analysis of the preprocessed daily energy consumption curve set of the flexible operating equipment and the preprocessed daily energy consumption curve set of the rigid operating equipment to obtain the daily operating characteristics of the flexible operating equipment and the daily operating characteristics of the rigid operating equipment includes:

[0023] Calculate the opening time, maximum value, 75% quantile, median, 25% quantile, minimum value, mean value, and variance of each pre-processed daily energy consumption curve in the pre-processed daily energy consumption curve set of the flexible operation equipment to obtain the daily operation characteristics of the flexible operation equipment;

[0024] The pre-processing daily energy consumption curve set of the rigid operation equipment is calculated, and the opening time, maximum value, 75% quantile, median, 25% quantile, minimum value, mean and variance of each pre-processing daily energy consumption curve of the opening time period are calculated to obtain the daily operation characteristics of the flexible operation equipment.

[0025] In the method for processing the operating energy consumption data of building electromechanical equipment of the present invention, the abnormal point processing using the box plot method according to the daily operating characteristics of the flexible operating equipment to obtain the one-time processing daily energy consumption curve of the flexible operating equipment, and the abnormal point processing using the box plot method according to the daily operating characteristics of the rigid operating equipment to obtain the one-time processing daily energy consumption curve of the rigid operating equipment include:

[0026] The box plot method was used to analyze the opening time of each flexible operation equipment, the maximum value, 75% quantile, median, 25% quantile, minimum value, mean and variance of the opening time period, and the abnormal points were eliminated to obtain the one-time treatment daily energy consumption curve of all flexible operation equipment;

[0027] The box plot method was used to analyze the opening time and the maximum value of the opening time period of each rigid operation equipment, and the abnormal points were eliminated to obtain the one-time processing daily energy consumption curve of all rigid operation equipment.

[0028] In the method for processing the operating energy consumption data of mechanical and electrical equipment of a building according to the present invention, the random forest method is used to perform isolation and removal processing on the once-processed daily energy consumption curve of the flexible operating equipment and the once-processed daily energy consumption curve of the rigid operating equipment, respectively, to obtain the isolated daily energy consumption curve of the flexible operating equipment and the isolated daily energy consumption curve of the rigid operating equipment, which includes:

[0029] A two-dimensional vector data set is formed based on the opening time and the maximum value of the opening time period of each rigid operation equipment;

[0030] According to the two-dimensional vector data set and the random forest model, an isolated detection is performed on the one-time processing daily energy consumption curve of each rigid operation equipment, and the isolated daily energy consumption curve is removed to obtain the de-isolated daily energy consumption curves of all rigid operation equipment.

[0031] In the method for processing the operating energy consumption data of mechanical and electrical equipment of a building according to the present invention, the random forest method is used to perform isolation and removal processing on the once-processed daily energy consumption curve of the flexible operating equipment and the once-processed daily energy consumption curve of the rigid operating equipment, respectively, to obtain the isolated daily energy consumption curve of the flexible operating equipment and the isolated daily energy consumption curve of the rigid operating equipment, which includes:

[0032] An eight-dimensional vector data set is formed based on the opening time, maximum opening time, 75% quantile, median, 25% quantile, minimum value, mean and variance of each flexible operation device;

[0033] According to the eight-dimensional vector data set and the random forest model, an isolated detection is performed on the one-time processing daily energy consumption curve of each flexible operation equipment, and the isolated daily energy consumption curve is removed to obtain the de-isolated daily energy consumption curves of all flexible operation equipment.

[0034] The present invention also provides a building electromechanical equipment operation energy consumption data processing system, comprising:

[0035] A data acquisition and processing module is used to acquire the operating energy consumption data of all electromechanical equipment at preset time intervals throughout the year, process the daily energy consumption data as a unit, and obtain a daily energy consumption curve set of all electromechanical equipment throughout the year;

[0036] A curve preprocessing module, used for preprocessing the daily energy consumption curve set to obtain a preprocessed daily energy consumption curve set;

[0037] A calculation module, used for performing calculation based on the preprocessed daily energy consumption curve set to obtain the daily total energy consumption of each daily energy consumption curve;

[0038] An equipment differentiation module, used to calculate the CV value of the daily total energy consumption of each electromechanical equipment throughout the year according to the daily total energy consumption, and determine the flexible operation equipment and the rigid operation equipment according to the CV values ​​of all electromechanical equipment;

[0039] A feature analysis module, used to perform feature analysis on the preprocessed daily energy consumption curve set of the flexible operation equipment and the preprocessed daily energy consumption curve set of the rigid operation equipment to obtain the daily operation characteristics of the flexible operation equipment and the daily operation characteristics of the rigid operation equipment;

[0040] An abnormality processing module, used to process abnormal points by using a box plot method according to the daily operation characteristics of the flexible operation equipment to obtain a daily energy consumption curve of the flexible operation equipment, and to process abnormal points by using a box plot method according to the daily operation characteristics of the rigid operation equipment to obtain a daily energy consumption curve of the rigid operation equipment;

[0041] The isolation processing module is used to use the random forest method to perform isolation and removal processing on the one-time processing daily energy consumption curve of the flexible operation equipment and the one-time processing daily energy consumption curve of the rigid operation equipment, respectively, to obtain the de-isolated daily energy consumption curve of the flexible operation equipment and the de-isolated daily energy consumption curve of the rigid operation equipment.

[0042] The present invention also provides an electronic device, the electronic device comprising: a processor and a memory;

[0043] The memory is used to store computer executable instructions;

[0044] The processor is used to implement the above-mentioned method for processing the operating energy consumption data of building electromechanical equipment when executing the computer executable instructions.

[0045] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the processor processes the steps of the above-mentioned method for processing energy consumption data of building mechanical and electrical equipment.

[0046] The method, system and storage medium for processing the operating energy consumption data of mechanical and electrical equipment of the present invention have the following beneficial effects: including: obtaining the operating energy consumption data of all mechanical and electrical equipment at preset time intervals throughout the year and processing to obtain a daily energy consumption curve set; preprocessing the daily energy consumption curve set to obtain a preprocessed daily energy consumption curve set; obtaining the daily total energy consumption of each daily energy consumption curve; determining the flexible operating equipment and the rigid operating equipment; performing feature analysis on the daily energy consumption curve to obtain the daily operating characteristics of the flexible operating equipment and the rigid operating equipment; using the box plot method to process the abnormal points of the daily operating characteristics of the flexible operating equipment and the daily operating characteristics of the rigid operating equipment respectively, and obtaining the once-processed daily energy consumption curve of the flexible operating equipment and the rigid operating equipment; using the random forest method to process to obtain the isolated daily energy consumption curve. The present invention identifies and eliminates abnormal and isolated daily energy consumption curves, intelligently realizes the abnormal identification of the operating energy consumption of mechanical and electrical equipment, solves the drawbacks of the traditional single-point fixed threshold monitoring of abnormal points, realizes in-depth data preprocessing, has low cost and strong versatility, is suitable for data preprocessing of the building system big data platform, provides reliable data, improves the level of intelligence, and reduces the investment of manpower and material resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0048] Figure 1 It is a flow chart of a method for processing energy consumption data of mechanical and electrical equipment in buildings provided by an embodiment of the present invention;

[0049] Figure 2 It is a flow chart of a preferred embodiment of a method for processing building electromechanical equipment operation energy consumption data provided by an embodiment of the present invention;

[0050] Figure 3 It is a schematic diagram of the data preprocessing process provided by an embodiment of the present invention;

[0051] Figure 4 is a schematic diagram of a process for distinguishing rigid operation equipment from flexible operation equipment based on pre-processed daily energy consumption curve analysis provided by an embodiment of the present invention;

[0052] Figure 5 It is a schematic diagram of the process of daily energy consumption curve characteristic analysis provided by an embodiment of the present invention;

[0053] Figure 6 It is a schematic diagram of a daily energy consumption curve process for eliminating abnormalities of rigid operation equipment provided by an embodiment of the present invention;

[0054] Figure 7 It is a schematic diagram of a daily energy consumption curve process for eliminating abnormalities of flexible operation equipment provided by an embodiment of the present invention;

[0055] Figure 8 It is a schematic diagram of a process flow for eliminating isolated daily energy consumption curves of rigid operation equipment provided by an embodiment of the present invention;

[0056] Fig. 9 It is a schematic diagram of a process for eliminating isolated daily energy consumption curves of flexible operation equipment provided by an embodiment of the present invention;

[0057] Fig.10 It is a principle block diagram of a building electromechanical equipment operation energy consumption data processing system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, specific embodiments of the present invention are now described in detail with reference to the accompanying drawings.

[0059] refer to Figure 1 , is a flow chart of an optional embodiment of a method for processing energy consumption data of building electromechanical equipment provided by the present invention. The method for processing energy consumption data of building electromechanical equipment can be applied to all electromechanical equipment in a building system, including but not limited to a central air conditioning system.

[0060] Specifically, Figure 1As shown, the method for processing the energy consumption data of the building electromechanical equipment operation includes the following steps:

[0061] Step S101: Acquire the operating energy consumption data of all electromechanical equipment at preset time intervals throughout the year, process the data in daily energy consumption units, and obtain a daily energy consumption curve set of all electromechanical equipment throughout the year.

[0062] Optionally, in an embodiment of the present invention, the preset time interval may be every hour, that is, the operating energy consumption data of all electromechanical equipment in the building system is obtained every hour throughout the year. The building system may be a building, such as an office building, a factory building, etc.

[0063] Step S102: preprocess the daily energy consumption curve set to obtain a preprocessed daily energy consumption curve set.

[0064] In some embodiments, the daily energy consumption curve set is preprocessed to obtain the preprocessed daily energy consumption curve set, including: removing missing values ​​from the daily energy consumption curve set to obtain daily energy consumption curves after removing missing values; removing duplicates from the daily energy consumption curves after removing duplicate identical daily energy consumption curves; all daily energy consumption curves remaining after removing duplicate identical daily energy consumption curves are the preprocessed daily energy consumption curve set.

[0065] Step S103: Calculate based on the preprocessed daily energy consumption curve set to obtain the daily total energy consumption of each daily energy consumption curve.

[0066] Specifically, a set of preprocessed daily energy consumption curves is obtained, and the total daily energy consumption of each daily energy consumption curve is calculated.

[0067] Step S104: Calculate the CV value of the total daily energy consumption of each electromechanical device throughout the year according to the total daily energy consumption, and determine the flexible operation equipment and the rigid operation equipment according to the CV values ​​of all electromechanical devices.

[0068] In some embodiments, the CV value of the daily total energy consumption of each electromechanical device throughout the year is calculated based on the daily total energy consumption, and the flexible operation device and the rigid operation device are determined based on the CV values ​​of all electromechanical devices, including: calculating the CV value of the daily total energy consumption of each electromechanical device throughout the year based on the daily total energy consumption; comparing the CV value with the CV target value; obtaining a CV value greater than the CV target value and a CV value less than the CV target value; determining the flexible operation device based on the CV value greater than the CV target value; and determining the rigid operation device based on the CV value less than the CV target value. That is, the electromechanical device with a CV value greater than the CV target value is a flexible operation device, and the electromechanical device with a CV value less than the CV target value is a rigid operation device.

[0069] Optionally, in an embodiment of the present invention, the CV target value can be obtained in a pre-set manner, or, by sorting the CV values ​​of all electromechanical equipment from small to large, finding the critical point where the CV value changes from a rapid change to a gentle change, and the critical point can be determined as the CV target value.

[0070] In the embodiment of the present invention, the CV value is the variation coefficient, also known as the dispersion coefficient, which is a normalized measure of the degree of dispersion of the probability distribution analysis data sample set, and is defined as the ratio of the standard deviation to the mean value. That is:

[0071]

[0072] (1) In the formula, σ is the standard deviation statistic calculated from the data sample set; μ is the mean statistic calculated from the data sample set; CV is the CV statistic calculated from the data sample set.

[0073] Step S105 : performing feature analysis on the preprocessed daily energy consumption curve set of the flexible operation equipment and the preprocessed daily energy consumption curve set of the rigid operation equipment to obtain the daily operation features of the flexible operation equipment and the daily operation features of the rigid operation equipment.

[0074] In some embodiments, feature analysis is performed on a set of preprocessed daily energy consumption curves of flexible operation equipment and a set of preprocessed daily energy consumption curves of rigid operation equipment to obtain daily operation features of the flexible operation equipment and daily operation features of the rigid operation equipment, including: calculating the opening time, maximum value, 75% quantile, median, 25% quantile, minimum value, mean, and variance of each preprocessed daily energy consumption curve in the set of preprocessed daily energy consumption curves of flexible operation equipment to obtain the daily operation features of the flexible operation equipment; calculating the opening time, maximum value, 75% quantile, median, 25% quantile, minimum value, mean, and variance of each preprocessed daily energy consumption curve in the set of preprocessed daily energy consumption curves of rigid operation equipment to obtain the daily operation features of the flexible operation equipment.

[0075] It can be understood that in the embodiment of the present invention, the daily operation characteristics of the rigid operation equipment and the flexible operation equipment both refer to the daily operation characteristics of the daily energy consumption curve of the equipment.

[0076] Step S106, using the box plot method to process abnormal points according to the daily operation characteristics of the flexible operation equipment to obtain a daily energy consumption curve of the flexible operation equipment, and using the box plot method to process abnormal points according to the daily operation characteristics of the rigid operation equipment to obtain a daily energy consumption curve of the rigid operation equipment.

[0077] In some embodiments, a box plot method is used to process abnormal points according to the daily operation characteristics of the flexible operation equipment to obtain a one-time processing daily energy consumption curve of the flexible operation equipment, and a box plot method is used to process abnormal points according to the daily operation characteristics of the rigid operation equipment to obtain a one-time processing daily energy consumption curve of the rigid operation equipment, including: using the box plot method to analyze the opening time, the maximum value, 75% quantile, median, 25% quantile, minimum value, mean and variance of each flexible operation equipment, eliminating abnormal points, and obtaining a one-time processing daily energy consumption curve of all flexible operation equipment; using the box plot method to analyze the opening time and the maximum value of the opening time period of each rigid operation equipment, eliminating abnormal points, and obtaining a one-time processing daily energy consumption curve of all rigid operation equipment.

[0078] Among them, the box plot method is used to detect the data sample set to remove outliers, which specifically includes: arranging all the data in the data sample set from small to large according to the numerical size and dividing them into four equal parts, and identifying outliers in the data sample set by setting the upper limit and lower limit of the numerical interval. Among them, the values ​​between the upper limit and the lower limit of the numerical interval are normal values; Q1-1.5*IQR is defined as the lower limit of the numerical interval, and if the lower limit value is less than 0, the value is 0; Q3+1.5*IQR is defined as the upper limit of the numerical interval; Q1 is the first quartile value, Q3 is the third quartile value, and IQR (IQR=Q3-Q1) is the interquartile range.

[0079] Step S107, using the random forest method to isolate and remove the primary processing daily energy consumption curve of the flexible operation equipment and the primary processing daily energy consumption curve of the rigid operation equipment, respectively, to obtain the isolated daily energy consumption curve of the flexible operation equipment and the isolated daily energy consumption curve of the rigid operation equipment.

[0080] In some embodiments, a random forest method is used to isolate and remove the one-time processing daily energy consumption curve of the flexible operation equipment and the one-time processing daily energy consumption curve of the rigid operation equipment, respectively, to obtain the de-isolated daily energy consumption curve of the flexible operation equipment and the de-isolated daily energy consumption curve of the rigid operation equipment, including: forming a two-dimensional vector data set based on the opening time and the maximum value of the opening time period of each rigid operation equipment; isolating the one-time processing daily energy consumption curve of each rigid operation equipment according to the two-dimensional vector data set and the random forest model, and removing the isolated daily energy consumption curves to obtain the de-isolated daily energy consumption curves of all rigid operation equipment.

[0081] The random forest method is used to isolate and remove the one-time processing daily energy consumption curve of the flexible operation equipment and the one-time processing daily energy consumption curve of the rigid operation equipment, respectively, to obtain the de-isolated daily energy consumption curve of the flexible operation equipment and the de-isolated daily energy consumption curve of the rigid operation equipment, including: forming an eight-dimensional vector data set based on the opening time, maximum opening time, 75% quantile, median, 25% quantile, minimum value, mean and variance of each flexible operation equipment; according to the eight-dimensional vector data set and the random forest model, the one-time processing daily energy consumption curve of each flexible operation equipment is isolated and detected, and the isolated daily energy consumption curves are removed to obtain the de-isolated daily energy consumption curves of all flexible operation equipment.

[0082] Among them, the random forest method is used to detect the daily energy consumption curve and eliminate isolated daily energy consumption curves, which specifically includes: using the random forest model to detect abnormal samples, specifically, given n sample data X = [X1, X2, ..., X n ] T , the anomaly score of each sample is calculated according to the following formula:

[0083]

[0084] According to the relationship between the abnormal score of the sample and the expected value of the isolated tree, determine whether the sample is an abnormal sample;

[0085] (2)In the formula, n represents the array dimension; h(x) is the path length of the sample point x; H(i), i = (1, 2, ..., n-1) is the harmonic number; c(n) is the average path length when the number of samples n is given; E(h(x)) is the expected path length of sample x in a batch of isolated trees; s(x, n) is the anomaly score of sample x.

[0086] The method for processing the operating energy consumption data of mechanical and electrical equipment in a building provided by an embodiment of the present invention firstly takes the daily energy consumption data of the mechanical and electrical equipment as a unit to obtain a daily energy consumption curve set, and obtains a preprocessed daily energy consumption curve by removing the daily energy consumption curves with vacant values ​​and repeated values; secondly, the CV value of the total daily energy consumption of all the electromechanical equipment throughout the year (that is, the CV value of the total daily energy consumption of all the electromechanical equipment throughout the year) is calculated, and then the CV value is used to distinguish between the flexible operation equipment and the rigid operation equipment; thirdly, the opening time length, the maximum value of the opening time period, and the 75 % quantile (i.e. 75% quantile of daily energy consumption), median (i.e. median of daily energy consumption), 25% quantile (i.e. 25% quantile of daily energy consumption), minimum (i.e. minimum value of daily energy consumption), mean (i.e. mean of daily energy consumption), variance (i.e. variance of daily energy consumption), and eight features of daily energy consumption curves of all electromechanical equipment were obtained; then, the box plot method was used to use the obtained features to remove the daily energy consumption curves containing abnormal points. Among them, the two features of opening time and maximum value of opening section were used for detection of rigid operation equipment to obtain rigid The daily energy consumption curve of the operating equipment with abnormal oscillation removed (i.e., the daily energy consumption curve of the rigid operating equipment processed once) is obtained. For the flexible operating equipment, eight features are used for detection, including the opening time, the maximum value of the opening time period, the 75% quantile of the daily energy consumption, the median of the daily energy consumption, the 25% quantile of the daily energy consumption, the minimum value of the daily energy consumption, the mean value of the daily energy consumption, and the variance of the daily energy consumption, so as to obtain the daily energy consumption curve of the flexible operating equipment with abnormal oscillation removed (i.e., the daily energy consumption curve of the flexible operating equipment processed once); finally, the random forest method is adopted and the obtained daily operating features are used to eliminate the isolated daily energy consumption curves of the operating energy consumption. Among them, for the rigid operating equipment, the opening time and the maximum value of the opening section are used for detection, so as to obtain the daily energy consumption curve of the rigid operating equipment with isolated oscillation removed. For the flexible operating equipment, eight features are used for detection, including the opening time, the maximum value of the opening time period, the 75% quantile of the daily energy consumption, the median of the daily energy consumption, the 25% quantile of the daily energy consumption, the minimum value of the daily energy consumption, the mean value of the daily energy consumption, and the variance of the daily energy consumption, so as to obtain the daily energy consumption curve of the flexible operating equipment with isolated oscillation removed. The present invention starts from the daily operating energy consumption characteristics of electromechanical equipment, distinguishes between flexible operating equipment and rigid operating equipment according to the operating energy consumption of electromechanical equipment, and defines eight statistical features based on the characteristics of electromechanical equipment startup, and removes daily energy consumption curves containing abnormal points and daily energy consumption curves with isolated operating energy consumption in turn, thereby intelligently realizing the identification of equipment operating energy consumption anomalies, solving the drawbacks of traditional single-point fixed threshold monitoring of abnormal points, realizing in-depth data preprocessing, with low cost and strong versatility, and being suitable for data preprocessing of building system big data platform, providing reliable data, improving the level of intelligence, and reducing the investment in manpower and material resources.

[0087] refer to Figure 2 , which is a flow chart of a preferred embodiment of a method for processing operating energy consumption data of building electromechanical equipment provided by the present invention.

[0088] like Figure 2 As shown, in this embodiment, the method for processing the energy consumption data of the building electromechanical equipment operation may include the following steps:

[0089] Step S201: Obtain the operating energy consumption data of all electromechanical equipment at every preset time period throughout the year.

[0090] Step S202: Process all the acquired operating energy consumption data in units of days to obtain a sample set of daily energy consumption curves of all electromechanical equipment.

[0091] Step S203: preprocess all daily energy consumption curves in the daily energy consumption curve sample set to remove missing values ​​and duplicates, and obtain a preprocessed daily energy consumption curve set of all electromechanical equipment throughout the year.

[0092] Step S204: Calculate the total daily energy consumption of each electromechanical device based on the preprocessed daily energy consumption curve set.

[0093] Step S205: Calculate the daily total energy consumption CV value of all electromechanical equipment throughout the year according to the daily total energy consumption of each electromechanical equipment.

[0094] Step S206: Determine the rigid operation device and the flexible operation device according to the CV value.

[0095] Step S207, characterize and analyze the preprocessed daily energy consumption curves of the rigid operation equipment and the flexible operation equipment to obtain the opening time, maximum opening time period, 75% quantile, median, 25% quantile, minimum value, mean and variance of the daily energy consumption curves of the rigid operation equipment and the flexible operation equipment.

[0096] Step S208, using the box plot method to detect and remove the daily energy consumption curve containing abnormal points in the rigid operation equipment using the opening time and the maximum value of the opening time period, and using the box plot method to remove the daily energy consumption curve containing abnormal points in the flexible operation equipment using the opening time, the maximum value of the opening time period, the 75% quantile, the median, the 25% quantile, the minimum value, the mean and the variance.

[0097] Step S209, using the random forest method to detect and remove the isolated daily energy consumption curves in the rigid equipment using the turn-on time and the maximum value of the turn-on time period, and using the random forest method to remove the isolated daily energy consumption curves in the flexible operation equipment using the turn-on time, the maximum value of the turn-on time period, the 75% quantile, the median, the 25% quantile, the minimum value, the mean and the variance.

[0098] refer to Figure 3 , which is a schematic diagram of the data preprocessing process provided by the present invention.

[0099] like Figure 3As shown, the data preprocessing includes the following steps:

[0100] Step S301: Process the acquired operating energy consumption data of all electromechanical equipment throughout the year in units of days to obtain a sample set of daily energy consumption curves of all electromechanical equipment throughout the year.

[0101] Step S302: Delete the daily energy consumption curve with missing values.

[0102] Step S303: Delete the duplicate daily energy consumption curves.

[0103] Step S304: Obtain a preprocessed daily energy consumption curve set after preprocessing.

[0104] refer to Figure 4 , which is a schematic diagram of a process for distinguishing rigid operation equipment from flexible operation equipment based on the pre-processed daily energy consumption curve analysis provided by the present invention.

[0105] like Figure 4 As shown, the specific distinguishing method includes the following steps:

[0106] Step S401: Obtain a preprocessing daily energy consumption curve set.

[0107] Step S402: Calculate according to the daily energy consumption curve in the pre-processed daily energy consumption curve set to obtain the daily total energy consumption value of the daily energy consumption curve of each electromechanical device.

[0108] Step S403: Calculate the CV value of the daily total energy consumption data of each electromechanical device.

[0109] Step S404: sort the CV values ​​of all electromechanical devices from small to large.

[0110] Step S405: determining the critical point where the CV value changes from a rapid change to a gentle change based on the sorting result.

[0111] Step S406: Differentiate between rigid operation equipment and flexible operation equipment according to the critical point.

[0112] refer to Figure 5 , which is a schematic diagram of the process of daily energy consumption curve characteristic analysis provided in an embodiment of the present invention.

[0113] like Figure 5 As shown, the specific feature analysis includes the following steps:

[0114] Step S501: Obtain a set of preprocessed daily energy consumption curves of rigid operation equipment and flexible operation equipment.

[0115] Step S502: Determine the hourly on / off state based on the comparison of the hourly energy consumption of the daily energy consumption curve and 5% rated power. If the hourly energy consumption of the daily energy consumption curve is greater than 5% rated power, it is in the on state; if the hourly energy consumption of the daily energy consumption curve is less than 5% rated power, it is in the off state.

[0116] Step S503: Calculate the opening duration of the daily energy consumption curve according to the opening / closing status hour by hour, wherein the opening duration of the daily energy consumption curve is the accumulation of the opening time points.

[0117] Step S504: determine the maximum value of the daily energy consumption curve in the on time period.

[0118] Step S505: Calculate the 75% quantile of the daily energy consumption curve.

[0119] Step S506: Calculate the median (50% quantile) of the daily energy consumption curve.

[0120] Step S507: Calculate the 25% quantile of the daily energy consumption curve.

[0121] Step S508: Calculate the minimum value of the daily energy consumption curve.

[0122] Step S509: Calculate the average of the daily energy consumption curve.

[0123] Step S510: Calculate the variance of the daily energy consumption curve.

[0124] Step S511: Obtain daily energy consumption curves represented by eight characteristics of all electromechanical equipment.

[0125] refer to Figure 6 , which is a schematic diagram of a daily energy consumption curve process for eliminating abnormalities in rigid operation equipment provided in an embodiment of the present invention.

[0126] like Figure 6 As shown in the figure, the elimination of abnormal points of rigid running equipment specifically includes the following steps:

[0127] Step S601: Obtain a pre-processed daily energy consumption curve set of rigid operation equipment.

[0128] Step S602: Using the box plot method and the opening time, the pre-processing daily energy consumption curve of the rigid operation equipment is detected.

[0129] Step S603: Remove the values ​​that exceed the upper limit of the set value interval or are lower than the lower limit of the interval, that is, the daily energy consumption curve corresponding to the abnormal opening time characteristic statistical value.

[0130] Step S604: Use the maximum value of the opening time period to detect the pre-processed daily energy consumption curve of the rigid operation equipment, and eliminate the daily energy consumption curve containing the maximum value of the abnormal opening time period.

[0131] refer to Figure 7 , which is a schematic diagram of a daily energy consumption curve process for eliminating abnormalities in flexible operation equipment provided in an embodiment of the present invention.

[0132] like Figure 7 As shown, the specific steps include:

[0133] Step S701: Obtain a preprocessed daily energy consumption curve set of the flexible operation equipment.

[0134] Step S702: Use the box plot method to detect the pre-processed daily energy consumption curve of the flexible operation equipment using the opening time, maximum opening time period, 75% quantile, median, 25% quantile, minimum value, mean, and variance.

[0135] Step S703: Eliminate abnormal daily energy consumption curves.

[0136] refer to Figure 8 , which is a schematic diagram of a process for eliminating isolated daily energy consumption curves for rigidly operating equipment provided in an embodiment of the present invention.

[0137] like Figure 8 As shown, the following steps may be specifically included:

[0138] Step S801: Obtain the daily energy consumption curve of the rigid operation equipment after removing abnormal points.

[0139] Step S802: using the random forest method to analyze the two-dimensional vector data consisting of the maximum value of the opening time and the opening time period.

[0140] Step S803: setting the abnormal proportion of the random forest model and default algorithm parameters.

[0141] Step S804: Perform detection based on the random forest model to obtain an isolated or normal daily energy consumption curve.

[0142] Step S805: Eliminate isolated daily energy consumption curves.

[0143] refer to Fig. 9 , which is a schematic diagram of a process for eliminating isolated daily energy consumption curves of flexible operation equipment provided in an embodiment of the present invention.

[0144] Step S901: Obtain the daily energy consumption curve of the flexible operation equipment after removing abnormal points.

[0145] Step S902, using the random forest method to analyze the eight-dimensional vector data consisting of the opening time, the maximum value of the opening time period, the 75% quantile, the median, the 25% quantile, the minimum value, the mean, and the variance.

[0146] Step S903: setting the abnormal proportion and default algorithm parameters of the random forest model.

[0147] Step S904: Perform detection based on the random forest model to obtain an isolated or normal daily energy consumption curve.

[0148] Step S905: Eliminate isolated daily energy consumption curves.

[0149] refer to Fig.10 , is a principle block diagram of a system for processing building electromechanical equipment operation energy consumption data provided by an embodiment of the present invention. The system for processing building electromechanical equipment operation energy consumption data can use the method for processing building electromechanical equipment operation energy consumption data provided by an embodiment of the present invention to process data.

[0150] like Fig.10 As shown, the building electromechanical equipment operation energy consumption data processing system includes:

[0151] The data acquisition processing module 110 is used to acquire the operating energy consumption data of all electromechanical equipment at preset time intervals throughout the year, process the daily energy consumption data as a unit, and obtain the daily energy consumption curve set of all electromechanical equipment throughout the year.

[0152] The curve preprocessing module 111 is used to preprocess the daily energy consumption curve set to obtain a preprocessed daily energy consumption curve set.

[0153] The calculation module 112 is used to perform calculations based on the preprocessed daily energy consumption curve set to obtain the daily total energy consumption of each daily energy consumption curve.

[0154] The equipment differentiation module 113 is used to calculate the CV value of the daily total energy consumption of each electromechanical equipment throughout the year according to the daily total energy consumption, and to determine the flexible operation equipment and the rigid operation equipment according to the CV values ​​of all electromechanical equipment.

[0155] The feature analysis module 114 is used to perform feature analysis on the preprocessed daily energy consumption curve set of the flexible operation equipment and the preprocessed daily energy consumption curve set of the rigid operation equipment to obtain the daily operation features of the flexible operation equipment and the daily operation features of the rigid operation equipment.

[0156] The exception processing module 115 is used to use the box plot method to process abnormal points according to the daily operation characteristics of the flexible operation equipment to obtain the daily energy consumption curve of the flexible operation equipment, and to use the box plot method to process abnormal points according to the daily operation characteristics of the rigid operation equipment to obtain the daily energy consumption curve of the rigid operation equipment.

[0157] The isolation processing module 116 is used to use the random forest method to perform isolation and removal processing on the primary processing daily energy consumption curve of the flexible operation equipment and the primary processing daily energy consumption curve of the rigid operation equipment, respectively, to obtain the de-isolated daily energy consumption curve of the flexible operation equipment and the de-isolated daily energy consumption curve of the rigid operation equipment.

[0158] The present invention also provides an electronic device, characterized in that the electronic device comprises: a processor and a memory.

[0159] The memory is used to store computer executable instructions.

[0160] The processor is used to implement the method for processing the operating energy consumption data of the building electromechanical equipment disclosed in the embodiment of the present invention when executing the computer executable instructions.

[0161] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the processor processes the steps of the method for processing the operating energy consumption data of building electromechanical equipment disclosed in an embodiment of the present invention.

[0162] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0163] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0164] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0165] The above embodiments are only for illustrating the technical concept and features of the present invention, and their purpose is to enable people familiar with the technology to understand the content of the present invention and implement it accordingly, and they cannot limit the scope of protection of the present invention. All equivalent changes and modifications made to the scope of the claims of the present invention should fall within the scope of the claims of the present invention.

Claims

1. A method for processing energy consumption data of building electromechanical equipment, characterized in that: The following steps are involved: Obtain the operating energy consumption data of all electromechanical equipment at preset time intervals throughout the year, process the daily energy consumption data as a unit, and obtain a daily energy consumption curve set of all electromechanical equipment throughout the year; Preprocessing the daily energy consumption curve set to obtain a preprocessed daily energy consumption curve set; Calculating based on the preprocessed daily energy consumption curve set to obtain the daily total energy consumption of each daily energy consumption curve; Calculate the CV value of the total daily energy consumption of each electromechanical equipment throughout the year according to the total daily energy consumption, and determine the flexible operation equipment and the rigid operation equipment according to the CV values ​​of all electromechanical equipment; the CV value is the ratio of the standard deviation statistical value calculated by the data sample set to the mean statistical value calculated by the data sample set; Performing feature analysis on the preprocessed daily energy consumption curve set of the flexible operation equipment and the preprocessed daily energy consumption curve set of the rigid operation equipment to obtain the daily operation characteristics of the flexible operation equipment and the daily operation characteristics of the rigid operation equipment; According to the daily operation characteristics of the flexible operation equipment, the box plot method is used to process abnormal points to obtain the daily energy consumption curve of the flexible operation equipment, and according to the daily operation characteristics of the rigid operation equipment, the box plot method is used to process abnormal points to obtain the daily energy consumption curve of the rigid operation equipment; The random forest method is used to isolate and remove the one-time processing daily energy consumption curve of the flexible operation equipment and the one-time processing daily energy consumption curve of the rigid operation equipment, respectively, to obtain the de-isolated daily energy consumption curve of the flexible operation equipment and the de-isolated daily energy consumption curve of the rigid operation equipment.

2. The method for processing energy consumption data of building mechanical and electrical equipment according to claim 1, characterized in that: The preprocessing of the daily energy consumption curve set to obtain the preprocessed daily energy consumption curve set includes: Performing a process of removing missing values ​​on the daily energy consumption curve set to obtain a daily energy consumption curve after removing the missing values; The daily energy consumption curves containing vacant values ​​are subjected to deduplication processing to obtain daily energy consumption curves with identical deduplication removed; all daily energy consumption curves with identical deduplication removed are the preprocessed daily energy consumption curve set.

3. The method for processing energy consumption data of building mechanical and electrical equipment according to claim 1, characterized in that: The method of calculating the CV value of the total daily energy consumption of each electromechanical device throughout the year according to the total daily energy consumption, and determining the flexible operation equipment and the rigid operation equipment according to the CV values ​​of all electromechanical devices includes: Calculate the CV value of the total daily energy consumption of each electromechanical equipment throughout the year based on the total daily energy consumption; comparing the CV value with a CV target value; Acquire a CV value greater than the CV target value and a CV value less than the CV target value; determining the flexible operation device based on the CV value greater than the CV target value; The rigid operating device is determined based on the CV value that is smaller than the CV target value.

4. The method for processing energy consumption data of building mechanical and electrical equipment according to claim 1, characterized in that: The performing feature analysis on the preprocessed daily energy consumption curve set of the flexible operation equipment and the preprocessed daily energy consumption curve set of the rigid operation equipment to obtain the daily operation features of the flexible operation equipment and the daily operation features of the rigid operation equipment comprises: Calculate the opening time, maximum value, 75% quantile, median, 25% quantile, minimum value, mean value, and variance of each pre-processed daily energy consumption curve in the pre-processed daily energy consumption curve set of the flexible operation equipment to obtain the daily operation characteristics of the flexible operation equipment; The pre-processing daily energy consumption curve set of the rigid operation equipment is calculated, and the opening time, maximum value, 75% quantile, median, 25% quantile, minimum value, mean and variance of each pre-processing daily energy consumption curve of the opening time period are calculated to obtain the daily operation characteristics of the flexible operation equipment.

5. The method for processing energy consumption data of building mechanical and electrical equipment according to claim 1, characterized in that: The process of processing abnormal points by using a box plot method according to the daily operation characteristics of the flexible operation equipment to obtain a daily energy consumption curve of the flexible operation equipment, and processing abnormal points by using a box plot method according to the daily operation characteristics of the rigid operation equipment to obtain a daily energy consumption curve of the rigid operation equipment includes: The box plot method was used to analyze the opening time of each flexible operation equipment, the maximum value, 75% quantile, median, 25% quantile, minimum value, mean and variance of the opening time period, and the abnormal points were eliminated to obtain the one-time treatment daily energy consumption curve of all flexible operation equipment; The box plot method was used to analyze the opening time and the maximum value of the opening time period of each rigid operation equipment, and the abnormal points were eliminated to obtain the one-time processing daily energy consumption curve of all rigid operation equipment.

6. The method for processing energy consumption data of building mechanical and electrical equipment according to claim 1, characterized in that: The use of the random forest method to perform isolation removal processing on the one-time processing daily energy consumption curve of the flexible operation equipment and the one-time processing daily energy consumption curve of the rigid operation equipment respectively to obtain the isolated daily energy consumption curve of the flexible operation equipment and the isolated daily energy consumption curve of the rigid operation equipment includes: A two-dimensional vector data set is formed based on the opening time and the maximum value of the opening time period of each rigid operation equipment; According to the two-dimensional vector data set and the random forest model, an isolated detection is performed on the one-time processing daily energy consumption curve of each rigid operation equipment, and the isolated daily energy consumption curve is removed to obtain the de-isolated daily energy consumption curves of all rigid operation equipment.

7. The method for processing energy consumption data of building mechanical and electrical equipment according to claim 1, characterized in that: The use of the random forest method to perform isolation removal processing on the one-time processing daily energy consumption curve of the flexible operation equipment and the one-time processing daily energy consumption curve of the rigid operation equipment respectively to obtain the isolated daily energy consumption curve of the flexible operation equipment and the isolated daily energy consumption curve of the rigid operation equipment includes: An eight-dimensional vector data set is formed based on the opening time, maximum opening time, 75% quantile, median, 25% quantile, minimum value, mean and variance of each flexible operation device; According to the eight-dimensional vector data set and the random forest model, an isolated detection is performed on the one-time processing daily energy consumption curve of each flexible operation equipment, and the isolated daily energy consumption curve is removed to obtain the de-isolated daily energy consumption curves of all flexible operation equipment.

8. A building electromechanical equipment operation energy consumption data processing system, characterized in that: include: A data acquisition and processing module is used to acquire the operating energy consumption data of all electromechanical equipment at preset time intervals throughout the year, process the daily energy consumption data as a unit, and obtain a daily energy consumption curve set of all electromechanical equipment throughout the year; A curve preprocessing module, used for preprocessing the daily energy consumption curve set to obtain a preprocessed daily energy consumption curve set; A calculation module, used for performing calculation based on the preprocessed daily energy consumption curve set to obtain the daily total energy consumption of each daily energy consumption curve; An equipment differentiation module is used to calculate the CV value of the daily total energy consumption of each electromechanical equipment throughout the year according to the daily total energy consumption, and determine the flexible operation equipment and the rigid operation equipment according to the CV values ​​of all electromechanical equipment; the CV value is the ratio of the standard deviation statistical value calculated by the data sample set to the mean statistical value calculated by the data sample set; A feature analysis module, used to perform feature analysis on the preprocessed daily energy consumption curve set of the flexible operation equipment and the preprocessed daily energy consumption curve set of the rigid operation equipment to obtain the daily operation characteristics of the flexible operation equipment and the daily operation characteristics of the rigid operation equipment; An abnormality processing module, used to process abnormal points by using a box plot method according to the daily operation characteristics of the flexible operation equipment to obtain a daily energy consumption curve of the flexible operation equipment, and to process abnormal points by using a box plot method according to the daily operation characteristics of the rigid operation equipment to obtain a daily energy consumption curve of the rigid operation equipment; The isolation processing module is used to use the random forest method to perform isolation and removal processing on the one-time processing daily energy consumption curve of the flexible operation equipment and the one-time processing daily energy consumption curve of the rigid operation equipment, respectively, to obtain the de-isolated daily energy consumption curve of the flexible operation equipment and the de-isolated daily energy consumption curve of the rigid operation equipment.

9. An electronic device, characterized in that: The electronic device comprises: a processor and a memory; The memory is used to store computer executable instructions; The processor is used to implement the method for processing the operating energy consumption data of building electromechanical equipment as described in any one of claims 1 to 7 when executing the computer executable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor processes the steps of the method for processing the operating energy consumption data of mechanical and electrical equipment of a building according to any one of claims 1 to 6.

Images