BIM-based building digital operation and maintenance collaborative management system

Abstract

The application discloses a kind of based on BIM's building digitization operation and maintenance collaborative management system, it is related to big data analysis technical field, the present application is by reading building equipment management partial structured data, analysis constructs associated data set and selects target sensor, in combination with time series integration historical operation data constructs fault feature analysis set, further associated fault before operation data and historical maintenance data, carry out feature analysis to data and predict fault time by neural network model, its output end links sensor acquisition frequency setting module calculates two kinds of acquisition frequency coefficients and weighted fusion dynamic adjustment acquisition frequency, finally by the output end of sensor acquisition frequency setting module connects multi-sensor operation and maintenance monitoring module through sliding window, threshold calculation and abnormal early warning guarantee multi-sensor stable operation, realize the collaborative management of building digitization operation and maintenance, improve data correlation accuracy, fault prediction reliability and operation and maintenance stability.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data analysis, and particularly relates to a building digital operation and maintenance collaborative management system based on BIM. BACKGROUND

[0002] The operation and maintenance phase is the longest and resource input highest link in the whole life cycle of a building, and the traditional operation and maintenance has problems such as information fragmentation of multiple systems, poor collaboration, lagging fault response, high cost and the like, while the BIM building digital operation and maintenance collaborative management can integrate multi-dimensional operation and maintenance information, break through the information barrier, realize collaborative work of all parties and early warning of equipment failure, significantly improve operation and maintenance efficiency, prolong equipment life, reduce operation and maintenance cost, and guarantee safe and stable operation of the building, and is the core support for transformation and upgrading of building operation and maintenance under the background of smart building, and is crucial for improving the operation and maintenance value of the whole life cycle of the building.

[0003] In the building operation and maintenance phase, the operation monitoring of the building mechanical and electrical system relies on multiple types of sensors to collect the operation data of the equipment in service, and the monitoring data quality of different equipment is significantly heterogeneous due to differences in service environment, operation load and maintenance cycle; the existing fixed frequency static data collection mode is difficult to adapt to the actual monitoring needs of the equipment, and is easy to generate redundant data to occupy BIM resources, interfere with data analysis, and even miss the high load equipment failure precursor data, thereby affecting the accuracy of operation and maintenance decision; therefore, a building digital operation and maintenance collaborative management system based on BIM is urgently needed. SUMMARY

[0004] The present application aims to provide a building digital operation and maintenance collaborative management system based on BIM to solve the problems in the prior art.

[0005] To achieve the above-mentioned purpose, the present application provides the following technical scheme: a building digital operation and maintenance collaborative management system based on BIM, the building digital operation and maintenance collaborative management system comprising a target sensor determination module, a fault analysis set construction module, a fault feature analysis set construction module, a fault time prediction module, a sensor collection frequency setting module and a multi-sensor operation and maintenance monitoring module.

[0006] The target sensor determination module is used for obtaining the structured data of the building equipment management part in the BIM model, and analyzing and extracting an associated data set composed of various sensor types, monitored equipment and data collection parameters corresponding to the building equipment monitoring requirements;

[0007] The building equipment management part is a professional management module in the BIM model, which is specially constructed for various types of equipment in service state in the building, such as air conditioning, water supply and drainage, electrical system equipment, and integrated equipment inherent parameters, sensor deployment information, real-time operation data, historical maintenance records and other structured data, which provide data support and function carrier for equipment operation state monitoring, fault warning analysis and whole life cycle operation and maintenance;

[0008] The target sensor determination module comprises a structured data reading unit, an associated data set construction unit and a target sensor selection unit;

[0009] The structured data reading unit is used to read the inherent attribute data of the building equipment and the sensor deployment configuration data contained in the building equipment management part through the structured data storage path and the standard data interface of the building equipment management part in the BIM model, and obtain the structured data;

[0010] The associated data set construction unit is used to perform field analysis on the read structured data, extract the type identification of each sensor and the unique code of the monitored equipment, select the unique code of the monitored equipment as the key, and select the type identification of the sensor as the value to construct the associated data set;

[0011] The target sensor selection unit is used to classify the system categories of the monitored equipment in the associated data set according to the type identification of the sensor, and select any one sensor from the classified associated data set as the target sensor;

[0012] Relying on the BIM model to read structured data, constructing an associated data set with the unique code of the monitored equipment as the key and the type identification of the sensor as the value, classifying and selecting the target sensor, realizes efficient association of sensor type, monitored equipment and data collection parameters, realizes clear data specification, clear association and strong selection pertinence, and accurately matches the monitoring requirements.

[0013] The fault analysis set construction module is used to obtain historical collection data, and analyze the monitored equipment served by the target sensor and the monitored equipment operation data, and arrange them in order according to time sequence to construct the monitored equipment fault analysis set;

[0014] The fault analysis set construction module comprises a historical collection data calling unit, a data time association arrangement unit and a fault analysis set construction unit;

[0015] The historical collection data calling unit is used to read the data collection period parameters of the target sensor in the BIM model, call the historical collection data generated by the target sensor during the service period from the data storage module based on the data collection period parameters, and separate the identification information of the monitored equipment and the operation data of the monitored equipment from the called historical collection data.

[0016] The data time correlation arrangement unit is configured to mark the separated operation data of the monitored device as monitored device operation data, extract the collection time stamp corresponding to the monitored device operation data, select the collection time stamp as a reference, correlate the identification information of the monitored device with the corresponding monitored device operation data, and arrange them in chronological order;

[0017] The fault analysis set construction unit is configured to select the identification information of the monitored device as a subset in the correlation data set, select the collection time stamp of the monitored device operation data as the key, and select the monitored device operation data as the value to construct the monitored device fault analysis set;

[0018] Based on the collection period parameter of the target sensor, historical data is retrieved and separated into device identification and operation data, and after correlation and sorting according to the collection time stamp, a fault analysis set is constructed with the device identification as a subset, the time stamp as a key, and the operation data as a value, realizing the time-sequenced structured integration of historical operation data, accurate data retrieval, correlated and ordered data, and a standardized set, providing a reliable data foundation for fault analysis;

[0019] The fault feature analysis set construction module is configured to analyze the structured data to obtain historical maintenance data of the monitored device, and then extract the corresponding monitored device operation data based on the historical maintenance data analysis to construct a monitored device fault feature analysis set;

[0020] The fault feature analysis set construction module includes a historical maintenance data reading unit, a fault data duration threshold reading unit, and a fault feature analysis set integration unit;

[0021] The historical maintenance data reading unit is configured to call a BIM model interface to read structured data stored in the building equipment management part of the BIM model, and to filter out the historical maintenance data of the monitored device from the structured data. The historical maintenance data includes a fault occurrence time stamp and a corresponding monitored device identification. The historical maintenance data represents the data record of the monitored device after a fault occurs and is repaired during the historical service process;

[0022] The fault data duration threshold reading unit is configured to read the pre-set fault data collection duration threshold of the monitored device from the system configuration file. The fault data collection duration threshold is defined as a fixed collection duration parameter of continuous historical operation data with the fault occurrence time as the end point when the monitored device fails. The fault data collection duration threshold and the data collection period of the target sensor have the same time unit;

[0023] The fault feature analysis set integration unit is configured to, for each fault occurrence timestamp and corresponding monitored device identifier in the historical maintenance data, select, according to the fault data collection duration threshold and the monitored device identifier, the fault occurrence timestamp as a reference, and forwardly intercept monitored device operation data equal to the fault data collection duration threshold from the monitored device fault analysis set, and integrate all the intercepted monitored device operation data in chronological order to form a monitored device fault feature analysis set;

[0024] The BIM model interface is called to read the historical maintenance data containing the fault occurrence timestamp and the device identifier, and the preset fault data duration threshold is read, according to which the operation data of the corresponding device within the threshold duration before the fault occurrence is intercepted from the fault analysis set and integrated in chronological order to construct the fault feature analysis set, thereby realizing accurate association of the pre-fault operation data and the historical maintenance data, strong data interception pertinence, ordered integration, and accurate data support for fault feature extraction;

[0025] The fault time prediction module is configured to extract fluctuation features from the monitored device operation data, and construct a fault prediction model to analyze the mapping relationship between the fluctuation features and the timestamps, and predict the fault occurrence time of the monitored device according to the fault prediction model, which is recorded as a predicted fault time.

[0026] The fault time prediction module includes an operation data preprocessing unit, a fluctuation feature extraction unit, a fault prediction model construction unit, and a predicted fault time output unit.

[0027] The operation data preprocessing unit is configured to perform preprocessing on the monitored device operation data in the monitored device fault feature analysis set, fill in the corresponding missing operation data for the collection timestamps with missing data by using a linear interpolation method, so that each collection timestamp matches unique monitored device operation data, rearrange the preprocessed operation data in ascending order of collection timestamps to form an ordered preprocessed data set.

[0028] The fluctuation feature extraction unit is configured to extract fluctuation features from the ordered preprocessed data set: define N as a preset number of short-term fluctuation calculation periods; calculate the difference between the monitored device operation data corresponding to two adjacent collection timestamps, which is recorded as an instantaneous fluctuation value; calculate the difference between the maximum and minimum values of the monitored device operation data within the timestamp range corresponding to N consecutive data collection periods, which is recorded as a short-term fluctuation amplitude; calculate the change amount of the monitored device operation data within two adjacent collection periods divided by the duration of the data collection period, which is recorded as a fluctuation rate; and integrate the instantaneous fluctuation value, the short-term fluctuation amplitude, and the fluctuation rate to form a fluctuation feature set.

[0029] The fault prediction model construction unit is configured to map the instantaneous fluctuation value, the short-term fluctuation amplitude, and the fluctuation rate in the fluctuation feature set to corresponding fault occurrence timestamps in the monitored device fault feature analysis set, divide a fault training set and a fault test set from the fluctuation feature set according to a preset ratio, and obtain a fault prediction model by processing the fault training set and the fault test set through a neural network model.

[0030] The predicted fault time output unit is configured to obtain the latest running data of the monitored device transmitted by the target sensor in real time, input real-time fluctuation features into the fault prediction model after performing preprocessing, and output a predicted fault time of the monitored device, denoted as predicted fault time.

[0031] The calculation formula of the instantaneous fluctuation value is as follows:

[0032] △x i =x i+1 -x i ;

[0033] In the formula, △x i represents the instantaneous fluctuation value x i+1 of the i th instantaneous fluctuation; x i represents the monitored device running data corresponding to the time stamp of the i+1 th instantaneous fluctuation; and x j represents the monitored device running data corresponding to the time stamp of the i th instantaneous fluctuation.

[0034] The calculation formula of the short-term fluctuation amplitude is as follows:

[0035] A j =max(x j+1 ,x j+N-1 )-min(x j ,x j+1 ,...,x j+N-1 );

[0036] In the formula, A j represents the fluctuation amplitude of the monitored device running data in the j th data collection period, specifically the difference between the maximum value and the minimum value of the monitored device running data in the continuous preset N data collection periods; and N represents the number of data collection periods for preset short-term fluctuation amplitude calculation.

[0037] The calculation formula of the fluctuation rate is as follows:

[0038] V i =△x i ÷t;

[0039] In the formula, V i represents the fluctuation rate of the i th instantaneous fluctuation; and t represents the duration of the data collection period.

[0040] The sensor acquisition frequency setting module is configured to calculate a first acquisition frequency coefficient and a second acquisition frequency coefficient of the current monitored device and to perform non-dimensionalization, to obtain a comprehensive dynamic adjustment coefficient by weighted fusion based on a preset weight, and to set an acquisition frequency;

[0041] The sensor acquisition frequency setting module comprises a first acquisition frequency coefficient calculation unit, a second acquisition frequency coefficient calculation unit, a comprehensive dynamic adjustment coefficient calculation unit, an acquisition frequency range reading unit, an extreme value adjustment coefficient calculation unit, and an acquisition frequency calculation unit.

[0042] The first acquisition frequency coefficient calculation unit is configured to extract real-time fluctuation characteristics corresponding to current operation data of the monitored device, wherein the real-time fluctuation characteristics include instantaneous fluctuation values, short-term fluctuation amplitudes, and fluctuation rates; extract fluctuation characteristics corresponding to each fault sample from a fault feature analysis set of the monitored device to form a fault fluctuation feature library; calculate a matching degree of the real-time fluctuation characteristics and each feature vector in the fault fluctuation feature library using a feature vector matching algorithm, and select a maximum matching degree value of the feature vector as the first acquisition frequency coefficient of the monitored device.

[0043] The specific calculation process of the maximum matching degree of the feature vector is as follows:

[0044] Cosine similarity algorithm is selected as the core to perform feature vector matching, and the real-time fluctuation characteristics corresponding to the current operation data of the monitored device are constructed into a real-time fluctuation feature vector, including instantaneous fluctuation values, short-term fluctuation amplitudes, and fluctuation rates. Then, the fault sample fluctuation feature vectors corresponding to each historical fault sample are extracted from the fault fluctuation feature library, and the data dimensions are consistent with the real-time vector. The cosine similarity is obtained by calculating the ratio of the dot product and the modulus product of the two types of vectors. The similarity is mapped to the [0, 1] interval after normalization processing to form the normalized matching degree of each sample. Finally, the maximum normalized matching degree is selected as the first acquisition frequency coefficient. The larger the coefficient value, the higher the similarity between the current device fluctuation characteristics and the historical fault characteristics, and the higher the fault risk.

[0045] The second acquisition frequency coefficient calculation unit is configured to obtain a current system time of the monitored device, calculate a time difference value between the current system time and a predicted fault time, input the time difference value into a preset inverse exponential growth function, and output a value of the function as the second acquisition frequency coefficient of the monitored device.

[0046] The calculation formula of the second acquisition frequency coefficient is as follows:

[0047] ;

[0048] In the formula, C2 represents a second acquisition frequency coefficient; △t represents a time interval from a current time to a predicted failure time; T represents a longest time interval of a historical failure; and e is 2.718;

[0049] When △t≤T, it is determined that the target sensor is in a failure attention period, and the second acquisition frequency coefficient C2 exponentially increases with the decrease of △t, and reaches a maximum value e when △t=0;

[0050] When △t>T, it is determined that the target sensor is not in the failure attention period, and C2 is fixed as 1, and the acquisition frequency of the target sensor does not change;

[0051] The comprehensive dynamic adjustment coefficient calculation unit is configured to perform dimensionless processing on the first acquisition frequency coefficient and the second acquisition frequency coefficient respectively, call preset weight parameters in a system configuration file, wherein the weight parameters include a weight of the first acquisition frequency coefficient and a weight of the second acquisition frequency coefficient, and the weight of the first acquisition frequency coefficient and the weight of the second acquisition frequency coefficient are 1; multiply the dimensionless first acquisition frequency coefficient by the corresponding weight to obtain a first product, multiply the dimensionless second acquisition frequency coefficient by the corresponding weight to obtain a second product, and add the first product and the second product to obtain the comprehensive dynamic adjustment coefficient of the monitored equipment;

[0052] The acquisition frequency range reading unit is configured to call the system configuration file, read preset minimum acquisition frequency and maximum acquisition frequency of the target sensor, wherein the minimum acquisition frequency represents a preset lowest data acquisition frequency of the target sensor in a normal operation state of the monitored equipment, and the maximum acquisition frequency represents a preset highest data acquisition frequency of the target sensor in a high failure risk state of the monitored equipment;

[0053] The extreme value adjustment coefficient calculation unit is configured to set the matching degree as 1 and the time difference value as 0, and bring them into the weighted fusion to obtain a maximum dynamic adjustment coefficient; set the matching degree as 0 and the time difference value as the predicted failure time, and bring them into the weighted fusion to obtain a minimum dynamic adjustment coefficient;

[0054] The acquisition frequency calculation unit is configured to calculate a difference value between the preset maximum acquisition frequency and the preset minimum acquisition frequency of the target sensor, denoted as an acquisition frequency difference value; calculate a difference value between the maximum dynamic adjustment coefficient and the minimum dynamic adjustment coefficient of the target sensor, denoted as an adjustment coefficient difference value; divide the acquisition frequency difference value by the adjustment coefficient difference value to obtain a proportional mapping value of the acquisition frequency and the dynamic adjustment coefficient of the target sensor; and multiply the comprehensive dynamic adjustment coefficient of the target sensor by the proportional mapping value to obtain the acquisition frequency of the target sensor.

[0055] The running data in the fault feature analysis set is preprocessed, and fluctuation features such as instantaneous fluctuation value, short-term fluctuation amplitude and fluctuation rate are extracted, the relationship between the fluctuation features and the fault timestamp is mapped through a neural network model, the occurrence time of the monitored equipment fault is accurately predicted, the data preprocessing is complete, the feature extraction is comprehensive, and the model prediction is reliable; the sensor acquisition frequency setting module calculates the maximum matching degree of the real-time fluctuation features and the fault feature library to obtain a first acquisition frequency coefficient, combines a time difference value and an inverse exponential growth function to obtain a second acquisition frequency coefficient, and forms a comprehensive dynamic adjustment coefficient through dimensionless and weighted fusion, and then calculates a target acquisition frequency based on the maximum and minimum acquisition frequencies, so that the dynamic adaptation of the acquisition frequency is realized.

[0056] The multi-sensor operation and maintenance monitoring module is used for processing each sensor corresponding to the building equipment monitoring demand, and monitoring the data amount collected by each sensor;

[0057] The multi-sensor operation and maintenance monitoring module includes an operation and maintenance sliding window initialization unit, a data total amount monitoring threshold calculation unit and a data increment abnormality early warning unit.

[0058] The operation and maintenance sliding window initialization unit is used for setting a data operation and maintenance sliding window and calling a system configuration file, reading preset window time length and sliding step parameters of the data operation and maintenance sliding window, the window time length represents the time span of the data operation and maintenance sliding window for intercepting data information of the monitored equipment fault analysis set at a time, and the sliding step represents the time interval of the data operation and maintenance sliding window moving along the time axis each time, the initial start time of the data operation and maintenance sliding window is set as the time point of the current system time minus the window time length, and the initial end time is set as the current system time, and the initialization configuration of the data operation and maintenance sliding window is completed.

[0059] The data total amount monitoring threshold calculation unit is used for obtaining historical sliding process data of the data operation and maintenance sliding window, extracting the total number of newly added monitoring data records of all sensors of the building equipment management part in each historical sliding step corresponding time interval, recording as historical data increment of each step, calculating the arithmetic mean value of the historical data increment of each step based on the historical data increment of each step, recording as the historical data increment average value, and calculating the standard deviation of the historical data increment of each step, recording as the historical data increment standard deviation, adding the historical data increment average value and the historical data increment standard deviation to obtain the data total amount monitoring threshold.

[0060] The data increment anomaly early warning unit is used for, after the data operation sliding window is completed once along the time axis sliding by the preset sliding step, counting the total number of newly added monitoring data records of all sensors of the building equipment management part in the time interval corresponding to the current sliding step, recorded as the current step data increment, and performing numerical comparison between the current step data increment and the data total quantity monitoring threshold value: if the current step data increment exceeds the data total quantity monitoring threshold value, an data increment fluctuation anomaly early warning signal is sent out; if the current step data increment does not exceed the data total quantity monitoring threshold value, the data information intercepted in the data operation sliding window is continuously monitored and operated;

[0061] By setting the window length and the sliding step and completing window initialization through the operation sliding window initialization unit, the data total quantity monitoring threshold value calculation unit calculates the arithmetic mean value and the standard deviation based on the historical step data increments and adds them to obtain the data total quantity monitoring threshold value, the data increment anomaly early warning unit counts the current step data increment after the window is slid by the step and compares it with the threshold value, and an anomaly early warning is sent out when it is exceeded, and the monitoring is continued when it is not exceeded, so as to realize dynamic monitoring of the data quantity collected by each sensor related to building equipment monitoring, can scientifically set the threshold value, timely identify data increment anomaly, and guarantee the stability of multi-sensor operation.

[0062] The output end of the target sensor determination module is electrically connected to the input end of the fault analysis set construction module; the output end of the fault analysis set construction module is electrically connected to the input end of the fault feature analysis set construction module; the output end of the fault feature analysis set construction module is electrically connected to the input end of the fault time prediction module; the output end of the fault time prediction module is electrically connected to the input end of the sensor acquisition frequency setting module; and the output end of the sensor acquisition frequency setting module is electrically connected to the input end of the multi-sensor operation monitoring module.

[0063] Compared with the prior art, the beneficial effects of the present application are:

[0064] 1、The target sensor determination module reads the structured data of the building equipment management part relying on the BIM model, constructs an associated data set taking the unique code of the monitored equipment as the key and the sensor type identifier as the value, selects the target sensor, and when matched with the fault analysis set construction module, time-series integrates the historical operation data, the fault feature analysis set construction module associates the pre-fault operation data with the maintenance data, realizes data specification association and accurate integration, provides reliable data support for subsequent fault prediction, and effectively matches the building equipment monitoring demand.

[0065] 2. This invention preprocesses the data in the fault feature analysis set through the fault time prediction module, extracts fluctuation features such as instantaneous fluctuation values, and constructs a neural network model to accurately predict the fault time of the monitored equipment; the sensor acquisition frequency setting module calculates the real-time fluctuation feature matching degree to obtain the first coefficient, and combines the time difference with the inverse exponential growth function to obtain the second coefficient. The acquisition frequency is dynamically adjusted through weighted fusion to balance monitoring accuracy and resource consumption.

[0066] 3. This invention initializes the sliding window through a multi-sensor operation and maintenance monitoring module, calculates monitoring thresholds based on historical data, and provides timely warnings of anomalies by comparing current data increments, thus ensuring the stability of multi-sensor operation and maintenance. Furthermore, modules such as target sensor determination and fault analysis are electrically connected in sequence to form a complete process from sensor determination to operation and maintenance monitoring, connecting all aspects of digital building operation and maintenance, and improving collaborative management efficiency and system reliability. Attached Figure Description

[0067] Figure 1 This is a schematic diagram of the structure of a BIM-based digital building operation and maintenance collaborative management system according to the present invention. Detailed Implementation

[0068] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0069] Example 1: As Figure 1 As shown, the present invention provides a technical solution, a BIM-based building digital operation and maintenance collaborative management system, which includes: a target sensor determination module, a fault analysis set construction module, a fault feature analysis set construction module, a fault time prediction module, a sensor acquisition frequency setting module, and a multi-sensor operation and maintenance monitoring module.

[0070] The target sensor determination module is used to acquire structured data of the building equipment management section in the BIM model, and analyze and extract the associated data set consisting of various sensor types, monitored equipment and data acquisition parameters corresponding to the building equipment monitoring requirements.

[0071] The target sensor determination module includes a structured data reading unit, an associated data set construction unit, and a target sensor selection unit;

[0072] The structured data reading unit is configured to read inherent attribute data and sensor deployment configuration data of the building equipment included in the building equipment management part through a structured data storage path and a standard data interface of the building equipment management part in the BIM model, and obtain structured data;

[0073] The associated data set construction unit is configured to perform field analysis on the read structured data, extract type identifiers of various sensors and unique codes of the monitored equipment, select the unique code of the monitored equipment as a key, and select the type identifier of the sensor as a value to construct an associated data set;

[0074] The target sensor selection unit is configured to classify system categories of the monitored equipment in the associated data set according to the type identifiers of the sensors, and select any one sensor from the classified associated data set as a target sensor;

[0075] The fault analysis set construction module is configured to obtain historical collection data, analyze the monitored equipment served by the target sensor and the monitored equipment operation data, and sequentially arrange the monitored equipment operation data according to time sequences to construct a monitored equipment fault analysis set;

[0076] The fault analysis set construction module includes a historical collection data calling unit, a data time correlation arrangement unit, and a fault analysis set construction unit.

[0077] The historical collection data calling unit is configured to read preset data collection period parameters of the target sensor in the BIM model, call historical collection data generated by the target sensor during service from a data storage module based on the data collection period parameters, separate identification information of the monitored equipment and operation data of the monitored equipment from the called historical collection data;

[0078] The data time correlation arrangement unit is configured to mark the separated operation data of the monitored equipment as monitored equipment operation data, extract collection time stamps corresponding to the monitored equipment operation data, select the collection time stamps as a reference, correlate the identification information of the monitored equipment with the corresponding monitored equipment operation data, and arrange them in chronological order;

[0079] The fault analysis set construction unit is configured to select the identification information of the monitored equipment as a subset in the associated data set, select the collection time stamps of the monitored equipment operation data as keys in the subset, and select the monitored equipment operation data as values to construct a monitored equipment fault analysis set.

[0080] The fault feature analysis set construction module is configured to analyze the structured data to obtain historical maintenance data of the monitored equipment, extract corresponding monitored equipment operation data according to the historical maintenance data analysis, and construct a monitored equipment fault feature analysis set.

[0081] The fault feature analysis set construction module comprises a historical maintenance data reading unit, a fault data duration threshold reading unit and a fault feature analysis set integration unit.

[0082] The historical maintenance data reading unit is configured to call a BIM model interface, read structured data stored in a building equipment management part of a BIM model, and filter historical maintenance data of a monitored equipment from the structured data. The historical maintenance data comprises a fault occurrence timestamp and a corresponding monitored equipment identifier. The historical maintenance data represents a data record of the monitored equipment after a fault occurs and is repaired in a historical service process.

[0083] The fault data duration threshold reading unit is configured to read a preset fault data collection duration threshold of the monitored equipment from a system configuration file. The fault data collection duration threshold is defined as a fixed collection duration parameter of continuous historical operation data with the fault occurrence time as the end point when the monitored equipment fails. The fault data collection duration threshold is the same as the time unit of the data collection period of the target sensor.

[0084] The fault feature analysis set integration unit is configured to, for each fault occurrence timestamp and corresponding monitored equipment identifier in the historical maintenance data, select, according to the fault data collection duration threshold and the monitored equipment identifier, monitored equipment operation data equal to the fault data collection duration threshold from the monitored equipment fault analysis set with the fault occurrence timestamp as the reference, integrate all the monitored equipment operation data in time sequence, and form a monitored equipment fault feature analysis set.

[0085] The fault time prediction module is configured to extract a fluctuation feature from the monitored equipment operation data, construct a fault prediction model to analyze a mapping relationship between the fluctuation feature and the timestamp, and predict a fault occurrence time of the monitored equipment according to the fault prediction model, which is recorded as a predicted fault time.

[0086] The fault time prediction module comprises an operation data preprocessing unit, a fluctuation feature extraction unit, a fault prediction model construction unit and a predicted fault time output unit.

[0087] The operation data preprocessing unit is configured to perform preprocessing on the monitored equipment operation data in the monitored equipment fault feature analysis set. For a collection timestamp with missing data, a linear interpolation method is used to fill in the corresponding missing operation data, so that each collection timestamp matches unique monitored equipment operation data. The preprocessed operation data is rearranged in ascending order of the collection timestamp to form an ordered preprocessed data set.

[0088] The fluctuation feature extraction unit is configured to extract fluctuation features from the ordered preprocessed data set: define N as a preset number of short-term fluctuation calculation periods; calculate a difference value of the monitored device operation data corresponding to adjacent two collection time stamps, denoted as an instantaneous fluctuation value; calculate a difference value of the maximum value and the minimum value of the monitored device operation data in the time stamp range corresponding to consecutive N data collection periods, denoted as a short-term fluctuation amplitude; calculate a change amount of the monitored device operation data in adjacent two collection periods divided by the length of the data collection period, denoted as a fluctuation rate; integrate the instantaneous fluctuation value, the short-term fluctuation amplitude, and the fluctuation rate to form a fluctuation feature set;

[0089] The fault prediction model construction unit is configured to establish a mapping relationship between the instantaneous fluctuation value, the short-term fluctuation amplitude, and the fluctuation rate in the fluctuation feature set and the corresponding fault occurrence time stamp in the monitored device fault feature analysis set, divide a fault training set and a fault test set from the fluctuation feature set according to a preset proportion, and obtain a fault prediction model by processing the fault training set and the fault test set through a neural network model;

[0090] The predicted fault time output unit is configured to obtain the latest monitored device operation data transmitted by the target sensor in real time, input real-time fluctuation features into the fault prediction model after pre-processing, and output a predicted fault time of the monitored device, denoted as a predicted fault time.

[0091] The sensor collection frequency setting module is configured to calculate and non-dimensionalize a first collection frequency coefficient and a second collection frequency coefficient of the current monitored device, obtain a comprehensive dynamic adjustment coefficient by weighted fusion based on a preset weight, and set the collection frequency;

[0092] The sensor collection frequency setting module includes a first collection frequency coefficient calculation unit, a second collection frequency coefficient calculation unit, a comprehensive dynamic adjustment coefficient calculation unit, a collection frequency range reading unit, an extreme value adjustment coefficient calculation unit, and a collection frequency calculation unit.

[0093] The first collection frequency coefficient calculation unit is configured to extract real-time fluctuation features corresponding to the current monitored device operation data, wherein the real-time fluctuation features include an instantaneous fluctuation value, a short-term fluctuation amplitude, and a fluctuation rate; extract fluctuation features corresponding to each fault sample from the monitored device fault feature analysis set to form a fault fluctuation feature library; calculate a matching degree of the real-time fluctuation features and each feature vector in the fault fluctuation feature library by using a feature vector matching algorithm, and select a maximum matching degree value of the feature vector as the first collection frequency coefficient of the monitored device.

[0094] The second acquisition frequency coefficient calculation unit is configured to obtain a current system time of the monitored device, calculate a time difference value between the current system time and the predicted failure time, and input the time difference value into a preset inverse exponential growth function, and take an output value of the function as the second acquisition frequency coefficient of the monitored device;

[0095] The comprehensive dynamic adjustment coefficient calculation unit is configured to perform dimensionless processing on the first acquisition frequency coefficient and the second acquisition frequency coefficient respectively, call a preset weight parameter in a system configuration file, take a sum of a weight of the first acquisition frequency coefficient and a weight of the second acquisition frequency coefficient as 1, multiply the dimensionless first acquisition frequency coefficient by the corresponding weight to obtain a first product, multiply the dimensionless second acquisition frequency coefficient by the corresponding weight to obtain a second product, and add the first product and the second product to obtain the comprehensive dynamic adjustment coefficient of the monitored device.

[0096] The acquisition frequency range reading unit is configured to call the system configuration file, read a preset minimum acquisition frequency and a preset maximum acquisition frequency of the target sensor, the minimum acquisition frequency representing a preset minimum data acquisition frequency of the target sensor in a normal operation state of the monitored device, and the maximum acquisition frequency representing a preset maximum data acquisition frequency of the target sensor in a high failure risk state of the monitored device.

[0097] The extreme value adjustment coefficient calculation unit is configured to take the matching degree as 1 and the time difference value as 0, and input them into the weighted fusion to obtain the maximum dynamic adjustment coefficient, and take the matching degree as 0 and the time difference value as the predicted failure time, and input them into the weighted fusion to obtain the minimum dynamic adjustment coefficient.

[0098] The acquisition frequency calculation unit is configured to calculate a difference between the maximum acquisition frequency and the minimum acquisition frequency of the target sensor, and take the difference as an acquisition frequency difference value, calculate a difference between the maximum dynamic adjustment coefficient and the minimum dynamic adjustment coefficient of the target sensor, and take the difference as an adjustment coefficient difference value, divide the acquisition frequency difference value by the adjustment coefficient difference value to obtain a proportional mapping value of the acquisition frequency and the dynamic adjustment coefficient of the target sensor, multiply the comprehensive dynamic adjustment coefficient of the target sensor by the proportional mapping value, and add the minimum acquisition frequency to obtain the acquisition frequency of the target sensor.

[0099] The multi-sensor operation and maintenance monitoring module is configured to process each sensor corresponding to a building device monitoring requirement, and monitor a data amount collected by each sensor.

[0100] The multi-sensor operation and maintenance monitoring module includes an operation and maintenance sliding window initialization unit, a data total amount monitoring threshold calculation unit, and a data increment anomaly early warning unit.

[0101] The operation and maintenance sliding window initialization unit is configured to set a data operation and maintenance sliding window, call a system configuration file, read preset window duration and sliding step parameters of the data operation and maintenance sliding window, the window duration represents a time span of the data operation and maintenance sliding window for intercepting data information in a monitored equipment fault analysis set once, and the sliding step represents a time interval of the data operation and maintenance sliding window for moving along a time axis each time, the initial start time of the data operation and maintenance sliding window is set as a time point of the current system time minus the window duration, and the initial end time is set as the current system time, so as to complete the initialization configuration of the data operation and maintenance sliding window.

[0102] The data total amount monitoring threshold value calculation unit is configured to obtain historical sliding process data of the data operation and maintenance sliding window, extract a total number of newly added monitoring data records of all sensors in the building equipment management part in each historical sliding step corresponding time interval, and record the total number of newly added monitoring data records of all sensors in the building equipment management part in each historical sliding step corresponding time interval as a historical step data increment, calculate an arithmetic mean value of the historical step data increment, and record the arithmetic mean value of the historical step data increment as a historical data increment average value; and calculate a standard deviation of the historical step data increment, and record the standard deviation of the historical step data increment as a historical data increment standard deviation. The historical data increment average value and the historical data increment standard deviation are added to obtain a data total amount monitoring threshold value.

[0103] The data increment abnormality early warning unit is configured to, after the data operation and maintenance sliding window completes a sliding along a time axis according to a preset sliding step, count a total number of newly added monitoring data records of all sensors in the building equipment management part in a current sliding step corresponding time interval, record the total number of newly added monitoring data records of all sensors in the building equipment management part in the current sliding step corresponding time interval as a current step data increment, and perform a numerical comparison between the current step data increment and the data total amount monitoring threshold value. If the current step data increment exceeds the data total amount monitoring threshold value, an abnormal fluctuation early warning signal of the data increment is sent. If the current step data increment does not exceed the data total amount monitoring threshold value, the monitoring and operation of the intercepted data information in the data operation and maintenance sliding window are continued.

[0104] For example, the instantaneous fluctuation value is 0.6°C, the short-term fluctuation amplitude is 1.5°C, and the fluctuation rate is 0.12°C / min. The 2024-03-15 fault sample vector V 故障1 =【0.5℃,1.4℃,0.11℃ / min】 is extracted from the fault fluctuation feature library.

[0105] The cosine similarity is calculated as follows:

[0106] The dot product = 0.6*0.5+1.5*1.4+0.12*0.11=0.3+2.1+0.0132=2.4132.

[0107] V 实时模长 = = = ≈1.62.

[0108] V故障1模长 = = = ≈1.491;

[0109] Similarity = 2.4132 ÷ (1.62 x 1.491) ≈ 2.4132 ÷ 2.415 ≈ 0.999;

[0110] Normalization: (0.999 + 1) ÷ 2 ≈ 0.999;

[0111] Get the maximum matching degree C1 = 0.999;

[0112] The current system time is 2024-04-01 10:00:00, the predicted failure time is 2024-04-01 11:20:00, and △t = 80 min; the longest historical failure interval T = 60 min (2024-07-20 failure warning interval);

[0113] Since △t > T, according to: when △t ≤ T, it is judged to be in the failure attention period, and the second collection frequency coefficient C2 increases exponentially as △t decreases, reaching a maximum value e when △t = 0;

[0114] When △t > T, it is judged to be not in the failure attention period, and C2 is fixed at 1, and the collection frequency of the target sensor does not change;

[0115] Get C2 = 1;

[0116] After dimensionless, C1 = 0.999; C2 = 1; the weight of the first collection frequency coefficient is 0.8, and the weight of the second collection frequency coefficient is 0.2;

[0117] According to the weighted fusion calculation, the comprehensive dynamic adjustment coefficient is:

[0118] C 综合 = 0.999 x 0.8 + 1 x 0.2 = 0.7992 + 0.2 = 0.9992;

[0119] According to the reading of the target sensor, the minimum collection frequency is 0.2 times / min, and the maximum collection frequency is 1 time / min;

[0120] Extreme value adjustment coefficient calculation:

[0121] 1 x 0.8 + e x 0.2 ≈ 0.8 + 0.5436 = 1.3436; (when matching degree 1, △t = 0, C2 takes the natural constant e ≈ 2.718, and the maximum dynamic adjustment coefficient is calculated)

[0122] 0 x 0.8 + 1 x 0.2 = 0.2; (when matching degree 0, △t > T, C2 = 1, and the minimum dynamic adjustment coefficient is calculated)

[0123] The acquisition frequency difference value: 1-0.2=0.8 times / min;

[0124] The adjustment coefficient difference value: 1.3436-0.2=1.1436;

[0125] The proportional mapping value of the target sensor acquisition frequency and the dynamic adjustment coefficient is obtained by dividing the acquisition frequency difference value by the adjustment coefficient difference value, and the proportional mapping value is obtained as follows:

[0126] 0.8÷1.1436≈0.6995 times / min;

[0127] The acquisition frequency of the target sensor is obtained by multiplying the product of the comprehensive dynamic adjustment coefficient of the target sensor and the proportional mapping value and adding the minimum acquisition frequency, and the acquisition frequency of the target sensor is obtained as follows:

[0128] 0.6995×0.9992+0.2≈0.6989+0.2=0.8989;

[0129] The acquisition frequency of the target sensor is obtained by rounding to 0.9 times / min.

[0130] The output end of the target sensor determination module is electrically connected to the input end of the fault analysis set construction module; the output end of the fault analysis set construction module is electrically connected to the input end of the fault feature analysis set construction module; the output end of the fault feature analysis set construction module is electrically connected to the input end of the fault time prediction module; the output end of the fault time prediction module is electrically connected to the input end of the sensor acquisition frequency setting module; and the output end of the sensor acquisition frequency setting module is electrically connected to the input end of the multi-sensor operation and maintenance monitoring module.

[0131] It is apparent for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application. Therefore, the embodiments should be considered as exemplary and non-limiting, and the scope of the present application is defined by the appended claims rather than the above description, and all changes falling within the meaning and range of the equivalent elements of the claims are intended to be included in the present application. Any reference signs in the claims should not be considered as limiting the claims involved.

Claims

1. A BIM-based building digital operation and maintenance collaborative management system, characterized in that: The building digital operation and maintenance collaborative management system comprises a target sensor determination module, a fault analysis set construction module, a fault feature analysis set construction module, a fault time prediction module, a sensor collection frequency setting module and a multi-sensor operation and maintenance monitoring module; The target sensor determination module is used for obtaining the structured data of the building equipment management part in the BIM model, and analyzing and extracting the associated data set composed of various sensor types, monitored equipment and data collection parameters corresponding to the building equipment monitoring requirements; The fault analysis set construction module is used for obtaining the historical collection data, and analyzing and obtaining the monitored equipment served by the target sensor and the monitored equipment operation data, which are sequentially arranged according to the time sequence to construct the monitored equipment fault analysis set; The fault feature analysis set construction module is used for analyzing the historical maintenance data of the monitored equipment according to the structured data, and extracting the corresponding monitored equipment operation data according to the historical maintenance data analysis to construct the monitored equipment fault feature analysis set; The fault time prediction module is used for extracting the fluctuation feature of the monitored equipment operation data, and constructing a fault prediction model to analyze the mapping relationship between the fluctuation feature and the time stamp, and predicting the fault occurrence time of the monitored equipment according to the fault prediction model, which is recorded as the predicted fault time; The sensor collection frequency setting module is used for calculating the first collection frequency coefficient and the second collection frequency coefficient of the current monitored equipment and performing dimensionless processing, weighting and fusing the comprehensive dynamic adjustment coefficient based on the preset weight to set the collection frequency; The sensor collection frequency setting module comprises a first collection frequency coefficient calculation unit, a second collection frequency coefficient calculation unit and a comprehensive dynamic adjustment coefficient calculation unit; The first collection frequency coefficient calculation unit is used for extracting the real-time fluctuation feature corresponding to the current operation data of the monitored equipment, wherein the real-time fluctuation feature comprises instantaneous fluctuation value, short-term fluctuation amplitude and fluctuation rate; the fluctuation features corresponding to each fault sample are extracted from the monitored equipment fault feature analysis set to form a fault fluctuation feature library; The feature vector matching algorithm is adopted to calculate the matching degree of the real-time fluctuation feature and each feature vector in the fault fluctuation feature library, and the maximum matching degree value of the feature vector is selected as the first collection frequency coefficient of the monitored equipment; The second collection frequency coefficient calculation unit is used for obtaining the current system time of the monitored equipment, calculating the time difference value between the current system time and the predicted fault time; and inputting the time difference value into a preset inverse exponential growth function, and the function output value is used as the second collection frequency coefficient of the monitored equipment; The comprehensive dynamic adjustment coefficient calculation unit is used for performing dimensionless processing on the first collection frequency coefficient and the second collection frequency coefficient, respectively. Call the preset weight parameter in the system configuration file, the weight parameter includes the weight of the first acquisition frequency coefficient and the weight of the second acquisition frequency coefficient, and the weight of the first acquisition frequency coefficient and the weight of the second acquisition frequency coefficient are 1; the dimensionless first acquisition frequency coefficient is multiplied by the corresponding weight to obtain the first product, the dimensionless second acquisition frequency coefficient is multiplied by the corresponding weight to obtain the second product, and the first product and the second product are added to obtain the comprehensive dynamic adjustment coefficient of the monitored equipment; The sensor acquisition frequency setting module further includes an acquisition frequency range reading unit, an extreme value adjustment coefficient calculation unit and an acquisition frequency calculation unit; The acquisition frequency range reading unit is used to call the system configuration file, read the preset minimum acquisition frequency and maximum acquisition frequency of the target sensor, the minimum acquisition frequency represents the lowest data acquisition frequency preset by the target sensor under the normal operation state of the monitored equipment, and the maximum acquisition frequency represents the highest data acquisition frequency preset by the target sensor under the high fault risk state of the monitored equipment; The extreme value adjustment coefficient calculation unit is used to set the matching degree to 1 and the time difference value to 0, and then input them into the weighted fusion to obtain the maximum dynamic adjustment coefficient; Set the matching degree to 0 and the time difference value to the predicted fault time, and then input them into the weighted fusion to obtain the minimum dynamic adjustment coefficient; The acquisition frequency calculation unit is used to calculate the difference between the maximum acquisition frequency and the minimum acquisition frequency preset by the target sensor, which is recorded as the acquisition frequency difference; Calculate the difference between the maximum dynamic adjustment coefficient and the minimum dynamic adjustment coefficient of the target sensor, which is recorded as the adjustment coefficient difference; Divide the acquisition frequency difference by the adjustment coefficient difference to obtain the proportional mapping value of the acquisition frequency and the dynamic adjustment coefficient of the target sensor, multiply the proportional mapping value by the comprehensive dynamic adjustment coefficient of the target sensor, and then add the minimum acquisition frequency to obtain the acquisition frequency of the target sensor; The multi-sensor operation and maintenance monitoring module is used to process each sensor corresponding to the building equipment monitoring demand and monitor the data amount collected by each sensor.

2. The BIM-based building digital operation and maintenance collaborative management system according to claim 1, characterized in that: The target sensor determination module includes a structured data reading unit, an associated data set construction unit and a target sensor selection unit; The structured data reading unit is used to read the building equipment inherent attribute data and sensor deployment configuration data contained in the building equipment management part through the structured data storage path and standard data interface of the building equipment management part in the BIM model to obtain structured data; The associated data set construction unit is used to perform field analysis on the read structured data, extract the type identifier of each sensor and the unique code of the monitored equipment, select the unique code of the monitored equipment as the key, select the type identifier of the sensor as the value, and construct the associated data set; The target sensor selection unit is used to classify the system categories of the monitored equipment in the associated data set according to the type identifier of the sensor, and select any one sensor from the classified associated data set as the target sensor.

3. The BIM-based building digital operation and maintenance collaborative management system according to claim 2, characterized in that: The fault analysis set construction module comprises a historical acquisition data calling unit, a data time correlation arrangement unit and a fault analysis set construction unit; The historical acquisition data calling unit is configured to read the data acquisition period parameter of the target sensor in the BIM model, call the historical acquisition data generated by the target sensor during service from the data storage module based on the data acquisition period parameter, and separate the identification information of the monitored equipment and the operation data of the monitored equipment from the called historical acquisition data; The data time correlation arrangement unit is configured to mark the separated operation data of the monitored equipment as monitored equipment operation data, extract the acquisition time stamp corresponding to the monitored equipment operation data, select the acquisition time stamp as a reference, correlate the identification information of the monitored equipment with the corresponding monitored equipment operation data, and arrange them in chronological order; The fault analysis set construction unit is configured to select the identification information of the monitored equipment as a subset in the correlation data set, select the acquisition time stamp of the monitored equipment operation data as a key, and select the monitored equipment operation data as a value to construct the monitored equipment fault analysis set.

4. The BIM-based building digital operation and maintenance collaborative management system according to claim 3, characterized in that: The fault feature analysis set construction module comprises a historical maintenance data reading unit and a fault data duration threshold reading unit; The historical maintenance data reading unit is configured to call the BIM model interface, read the structured data stored in the building equipment management part of the BIM model, and filter the historical maintenance data of the monitored equipment from the structured data, wherein the historical maintenance data comprises a fault occurrence time stamp and a corresponding monitored equipment identification, and the historical maintenance data represents the data record of the monitored equipment after the fault occurs and is repaired in the historical service process; The fault data duration threshold reading unit is configured to read the pre-set fault data acquisition duration threshold of the monitored equipment from the system configuration file, wherein the fault data acquisition duration threshold is defined as a fixed acquisition duration parameter of continuous historical operation data selected from the moment when the fault occurs as an endpoint, and the fault data acquisition duration threshold and the time unit of the data acquisition period of the target sensor are the same.

5. The BIM-based building digital operation and maintenance collaborative management system according to claim 4, characterized in that: The fault feature analysis set construction module further comprises a fault feature analysis set integration unit; The fault feature analysis set integration unit is configured to, for each fault occurrence time stamp and corresponding monitored equipment identification in the historical maintenance data, select the fault occurrence time stamp as a reference from the monitored equipment fault analysis set according to the fault data acquisition duration threshold and the monitored equipment identification, forwardly intercept the monitored equipment operation data equal to the fault data acquisition duration threshold, integrate all the intercepted monitored equipment operation data in chronological order, and form the monitored equipment fault feature analysis set.

6. The BIM-based building digital operation and maintenance collaborative management system according to claim 5, characterized in that: The fault time prediction module comprises an operation data preprocessing unit and a fluctuation feature extraction unit; The operation data preprocessing unit is configured to perform preprocessing on the monitored equipment operation data in the monitored equipment fault feature analysis set, fill in the corresponding missing operation data by using linear interpolation for the collection time stamps with missing data, match each collection time stamp with unique monitored equipment operation data, rearrange the preprocessed operation data in ascending order of collection time stamps, and form an ordered preprocessed data set; The fluctuation feature extraction unit is configured to extract fluctuation features from the ordered preprocessed data set: define N as a preset number of short-term fluctuation calculation periods; calculate the difference between the monitored equipment operation data corresponding to adjacent two collection time stamps, denoted as an instantaneous fluctuation value; calculate the difference between the maximum and minimum values of the monitored equipment operation data within the time stamp range corresponding to consecutive N data collection periods, denoted as a short-term fluctuation amplitude; calculate the change amount of the monitored equipment operation data in adjacent two collection periods divided by the duration of the data collection period, denoted as a fluctuation rate; and integrate the instantaneous fluctuation value, the short-term fluctuation amplitude, and the fluctuation rate to form a fluctuation feature set.

7. The BIM-based building digital operation and maintenance collaborative management system according to claim 6, characterized in that: The fault time prediction module further includes a fault prediction model construction unit and a predicted fault time output unit. The fault prediction model construction unit is configured to establish a mapping relationship between the instantaneous fluctuation value, the short-term fluctuation amplitude, and the fluctuation rate in the fluctuation feature set and the corresponding fault occurrence time stamp in the monitored equipment fault feature analysis set, divide a fault training set and a fault test set from the fluctuation feature set according to a preset proportion, and obtain a fault prediction model by processing the fault training set and the fault test set through a neural network model. The predicted fault time output unit is configured to obtain the latest monitored equipment operation data transmitted by a target sensor in real time, input real-time fluctuation features into the fault prediction model after preprocessing, and output a predicted fault time of the monitored equipment, denoted as a predicted fault time.

8. The BIM-based building digital operation and maintenance collaborative management system according to claim 7, characterized in that: The multi-sensor operation and maintenance monitoring module includes an operation and maintenance sliding window initialization unit, a data total amount monitoring threshold calculation unit, and a data increment anomaly early warning unit. The operation and maintenance sliding window initialization unit is configured to set a data operation and maintenance sliding window and call a system configuration file, read preset window duration and sliding step parameters of the data operation and maintenance sliding window, the window duration represents the time span of the data operation and maintenance sliding window for intercepting data information in the monitored equipment fault analysis set at a time, the sliding step represents the time interval of the data operation and maintenance sliding window moving along the time axis each time, set the initial start time of the data operation and maintenance sliding window as the time point of the current system time minus the window duration, and set the initial end time as the current system time, to complete the initialization configuration of the data operation and maintenance sliding window. The data total amount monitoring threshold value calculation unit is used for obtaining historical sliding process data completed by the data operation and maintenance sliding window, extracting total number of newly added monitoring data records of all sensors of the building equipment management part in each historical sliding step corresponding time interval, recording as historical data increment of each step, calculating arithmetic mean value based on the historical data increment of each step, recording as historical data increment average value, calculating standard deviation of the historical data increment of each step, recording as historical data increment standard deviation, adding the historical data increment average value and the historical data increment standard deviation to obtain the data total amount monitoring threshold value; The data increment abnormal early warning unit is used for, after the data operation and maintenance sliding window completes sliding along the time axis once according to the preset sliding step, counting total number of newly added monitoring data records of all sensors of the building equipment management part in the time interval corresponding to the current sliding step, recording as current step data increment, performing numerical comparison between the current step data increment and the data total amount monitoring threshold value: if the current step data increment exceeds the data total amount monitoring threshold value, an abnormal fluctuation early warning signal of the data increment is sent; if the current step data increment does not exceed the data total amount monitoring threshold value, the data information intercepted in the data operation and maintenance sliding window is continuously monitored and maintained.

Images