CN117494484B - Building fault diagnosis prediction and health management method based on large model training - Google Patents

Building fault diagnosis prediction and health management method based on large model training Download PDF

Info

Publication number
CN117494484B
CN117494484B CN202410003453.3A CN202410003453A CN117494484B CN 117494484 B CN117494484 B CN 117494484B CN 202410003453 A CN202410003453 A CN 202410003453A CN 117494484 B CN117494484 B CN 117494484B
Authority
CN
China
Prior art keywords
lighting device
lighting
energy
saving
target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202410003453.3A
Other languages
Chinese (zh)
Other versions
CN117494484A (en
Inventor
寇明
周小平
史进
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Tellhow Intelligent Engineering Co ltd
Original Assignee
Beijing Tellhow Intelligent Engineering Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Tellhow Intelligent Engineering Co ltd filed Critical Beijing Tellhow Intelligent Engineering Co ltd
Priority to CN202410003453.3A priority Critical patent/CN117494484B/en
Publication of CN117494484A publication Critical patent/CN117494484A/en
Application granted granted Critical
Publication of CN117494484B publication Critical patent/CN117494484B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/08—Construction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/06—Power analysis or power optimisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Data Mining & Analysis (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Mathematical Physics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Mathematical Analysis (AREA)
  • Quality & Reliability (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Computational Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Artificial Intelligence (AREA)
  • Geometry (AREA)
  • Educational Administration (AREA)
  • Algebra (AREA)
  • Development Economics (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Public Health (AREA)

Abstract

The invention belongs to the technical field of building equipment operation and maintenance management, and relates to a building fault diagnosis prediction and health management method based on large model training.

Description

Building fault diagnosis prediction and health management method based on large model training
Technical Field
The invention belongs to the technical field of operation and maintenance management of building equipment, and particularly relates to a building fault diagnosis prediction and health management method based on large model training.
Background
In the modern urban process, public building areas play important social functions and cultural communication centers, the areas comprise markets, libraries, office buildings and the like, and lighting equipment is not only a tool for providing illumination in public buildings, but also an important component for maintaining building safety and improving user experience, so that efficient management of the lighting equipment in the public building areas is important, but the traditional maintenance method is possibly inexperienced, and a building fault diagnosis prediction and health management method based on large model training provides a brand-new solution to the challenge.
The existing operation and maintenance management method for the lighting equipment in the public building area can realize real-time monitoring and analysis of the lighting equipment by adopting the Internet of things and a sensor technology, and has the following concrete advantages that the method meets certain requirements, but has limitations: on one hand, the existing method lacks sufficient depth and precision for fault risk assessment of the lighting equipment in the public building area, focuses on external lighting performance of the lighting equipment, such as lighting brightness or lighting operation temperature, and the like, ignores consideration of internal lighting performance of the lighting equipment, such as light efficiency rationality, power consumption rationality and the like, so that the fault risk assessment result of the lighting equipment in the public building area is not accurate and reliable, and further cannot effectively reflect the overall performance and potential risk of the lighting equipment, and the lighting effect and operation efficiency of the public building area are affected.
On the other hand, the existing method aims at the defect of energy-saving optimization strength of the lighting equipment in the public building area, focuses on taking the whole consumption power of a unit building or the accumulated consumption power of multiple lighting equipment as an energy-saving optimization reference object, omits detailed evaluation on the energy-saving performance of an individual lighting equipment, and cannot accurately optimize energy saving of each lighting equipment.
Disclosure of Invention
In order to overcome the defects in the background technology, the embodiment of the invention provides a building fault diagnosis prediction and health management method based on large model training, which can effectively solve the problems related to the background technology.
The aim of the invention can be achieved by the following technical scheme: a building fault diagnosis prediction and health management method based on large model training comprises the following steps: s1, acquiring information of lighting equipment: and marking each lighting device in the target public building area as each target lighting device, and acquiring basic information and lighting information of each target lighting device.
S2, potential fault risk assessment of the lighting equipment: based on the basic information and the illumination information of each target illumination apparatus, potential failure risk coefficients of each target illumination apparatus are analyzed, each target illumination apparatus is classified into each normal illumination apparatus and each abnormal illumination apparatus, and S3 and S5 are executed respectively.
S3, energy-saving qualification evaluation of the lighting equipment: and analyzing the energy-saving qualification coefficients of the normal lighting devices, screening the energy-saving lighting devices from the normal lighting devices, and further analyzing the supply current value down-regulation value of the energy-saving lighting devices.
S4, energy-saving feedback of current supplied by the lighting equipment: and carrying out supply current energy-saving feedback on each energy-saving lighting device in the target public building area, and providing a corresponding supply current value down-regulation value.
S5, fault alert feedback of the lighting equipment: and carrying out fault warning feedback on each abnormal lighting device in the target public building area.
Preferably, the basic information includes a type, a model number, a service life, a rated supply voltage value, and a rated supply current value.
The lighting information comprises lighting operation parameters and lighting environment parameters, wherein the lighting operation parameters comprise output voltage values, output current values, operation temperature values and luminous fluxes at each monitoring time point in a monitoring time period.
The lighting environment parameters include initial illuminance defining each azimuth of the lighting area and illuminance at each monitoring time point in the monitoring period.
Preferably, the specific analysis process of the potential failure risk coefficient of each target lighting device includes: according to rated supply voltage value in basic information of each target lighting equipmentAnd rated supply current value/>Wherein/>Numbering for each target lighting device,/>Combining output voltage values/>, at each monitoring time point in the monitoring time period, in the lighting operation parameters of each target lighting deviceAnd output current value/>Wherein/>For the number of each monitoring time point in the monitoring time period,/>Respectively calculating the consumed power and the output power of each monitoring time point in each target lighting equipment monitoring time period, and recording as/>，/>,/>。
According to the type, model and service life of each target lighting equipment in the basic informationExtracting standard consumed power/>, which is specified by a lighting equipment manufacturer, of corresponding type and corresponding model of each target lighting equipment from WEB cloudAnd standard light efficiency/>Analyzing the energy consumption anomaly coefficient/>, within each target lighting device monitoring periodThe calculation formula is as follows: wherein/> Is a natural constant,/>To monitor the number of time points within a monitoring period,/>A reasonable deviation threshold value of power consumption for the preset lighting equipment.
Analyzing abnormal coefficients of light efficiency in monitoring time periods of each target lighting deviceThe calculation formula is as follows: wherein/> Is a preset reasonable deviation threshold value of the lighting effect of the lighting equipment.
And then is represented by the formulaObtaining the intrinsic performance coefficient of illumination in each target illumination device monitoring time period,/>The weight ratio is respectively corresponding to a preset energy consumption abnormal coefficient and a light efficiency abnormal coefficient.
Preferably, the specific analysis process of the potential failure risk coefficient of each target lighting device further includes: according to the initial illuminance of each direction of the defined illumination area in the illumination environment parameters of each target illumination device, and the illuminance of each monitoring time point in the monitoring time period，/>To define the number of each azimuth of the illuminated area,/>Calculating average lifting illuminance/>, for each azimuth within each target lighting device defined lighting areaCombining luminous flux/>, at each monitoring time point in each monitoring time period, in each target lighting device lighting operation parameterBy the formula/>And obtaining the illumination basic capability coefficient of each target illumination device in the monitoring time period.
From the formulaObtaining a lighting basic quality coefficient in each target lighting device monitoring time period, wherein/>For a preset reasonable fluctuation variance threshold of luminous flux of the lighting equipment,/>For reasonably deviating illuminance threshold values among preset illumination area orientations,/>To define the number of illumination area orientations,/>For/>The individual target lighting devices define a lighting area/>First/>, within a personal bearing monitoring periodThe illuminance at the time point is monitored.
According to the operation temperature value of each monitoring time point in each monitoring time period in the illumination operation parameters of each target illumination deviceCalculating the abnormal coefficient/>, of the illumination temperature in each target illumination device monitoring time period。
And then is represented by the formulaAnd obtaining the external performance coefficient of the illumination in the monitoring time period of each target illumination device.
Analyzing potential fault risk coefficients of each target lighting deviceThe calculation formula is as follows:。
preferably, the calculation formula of the illumination temperature anomaly coefficient in the monitoring time period of each target illumination device is as follows: ，/> And (5) reasonably operating the temperature threshold for the preset lighting equipment.
Preferably, the specific process of classifying each target lighting device into each normal lighting device and each abnormal lighting device includes: comparing the potential fault risk coefficient of each target lighting device with a preset potential fault risk coefficient warning threshold value of the public building lighting device stored in the WEB cloud, if the potential fault risk coefficient of a certain target lighting device is larger than or equal to the preset potential fault risk coefficient warning threshold value of the public building lighting device, marking the target lighting device as abnormal lighting device, otherwise marking the target lighting device as normal lighting device, and further obtaining each abnormal lighting device and each normal lighting device.
Preferably, the specific analysis process of the energy conservation qualification rate coefficient of each normal lighting device comprises the following steps: obtaining the output voltage value and the output current value of each normal lighting device at the current time point, and calculating the power consumption of each normal lighting device at the current time point，/>Numbering for each normal lighting device,/>。
Obtaining output voltage value and output current value of each normal lighting equipment history at the same time point as the current time point, and calculating power consumption of each normal lighting equipment history at the same time point as the current time pointWhereinFor the number of each day of history,/>。
From the formulaObtaining a first-order energy-saving qualification evaluation coefficient of each normal lighting device, wherein/>For historical days,/>Is the normal number of lighting devices.
Collecting traffic flow of passers-by defining illumination area in each normal illumination device monitoring time period according to infrared sensor built in illumination deviceAnd extracting the intrinsic performance coefficient of illumination in each normal illumination device monitoring periodAnd the external performance coefficient of illumination/>By the formula/>And obtaining a second-order energy-saving qualification evaluation coefficient of each normal lighting device.
And further calculate the energy-saving qualification coefficients of the normal lighting devices，/>。
Preferably, the specific screening process of each energy-saving lighting device comprises: comparing the energy-saving qualification rate coefficient of each normal lighting device with a preset public building lighting device energy-saving qualification rate coefficient standard-reaching threshold stored in the WEB cloud, and if the energy-saving qualification rate coefficient of a certain normal lighting device is larger than or equal to the preset public building lighting device energy-saving qualification rate coefficient standard-reaching threshold, marking the normal lighting device as an energy-saving lighting device, and further screening each energy-saving lighting device from each normal lighting device.
Preferably, the specific analysis process of the supply current value down-regulation value of each energy-saving lighting device comprises: acquiring a day and night phase of the current time point, and extracting energy-saving adjustment weight of lighting equipment corresponding to the day and night phase of the current time point from the WEB cloud。
Extracting power consumption of each energy-saving lighting device at the same time point of each day as the current time pointAnd power consumption at the current point in time/>，/>Numbering for each energy-saving lighting device,/>From the formulaAnd obtaining the effective energy-saving power of each energy-saving lighting device.
According to technical specification content provided by a WEB cloud storage lighting equipment manufacturer for various types of lighting equipment, the technical specification content comprises basic supply current values and test consumption power corresponding to the supply current values under the same supply voltage values, and the basic supply current values of the energy-saving lighting equipment are obtained by combining the types and the models of the energy-saving lighting equipmentAnd testing the consumed power corresponding to each supplied current value under the same supplied voltage value, further constructing a consumed power-supplied current test graph of each energy-saving lighting device taking the consumed power as a horizontal axis and taking the supplied current value as a vertical axis, importing the consumed power-supplied current test graph into Matlab software, acquiring a consumed power-supplied current test relation function of each energy-saving lighting device by using a fitting tool of the Matlab software, substituting a value 1 into the consumed power-supplied current test relation function of each energy-saving lighting device, and acquiring a supplied current change value/>, corresponding to each energy-saving lighting device unit consumed power, of each energy-saving lighting deviceAnd then by the formulaObtaining a supply current value down-regulation value of each energy-saving lighting device, wherein/>For/>Rated supply current value of each energy-saving lighting device.
Compared with the prior art, the embodiment of the invention has at least the following advantages or beneficial effects: (1) According to the invention, the energy consumption anomaly coefficient and the light efficiency anomaly coefficient in the monitoring time period of each target lighting device are analyzed, the illumination internal performance coefficient in the monitoring time period of each target lighting device is comprehensively considered from three angles of power consumption rationality, fluctuation and light efficiency rationality, the defect of the existing method on the illumination internal performance coefficient of the lighting device is overcome, and the depth and the accuracy of fault risk assessment of the lighting device in the public building area are effectively improved.
According to the invention, the illumination basic capability coefficient, the illumination basic quality coefficient and the illumination temperature anomaly coefficient in each target illumination equipment monitoring time period are effectively combined, the illumination external performance coefficient in each target illumination equipment monitoring time period is reasonably analyzed, the actual running state of the illumination equipment is more comprehensively and accurately reflected from the self luminous flux performance, the environment illuminance performance and the running temperature performance, and the scientificity, the accuracy and the reliability of the illumination equipment external performance analysis result are improved.
According to the invention, the intrinsic performance coefficient of illumination and the extrinsic performance coefficient of illumination in the monitoring time period of each target illumination device are combined, the potential fault risk coefficient of each target illumination device is comprehensively analyzed, the performance and performance of the illumination device are comprehensively understood, and further decision and operation are better performed, so that potential faults can be found in time, corresponding measures are taken for prevention and maintenance, the fault rate of the illumination device is reduced, and the reliability and stability of the device are improved.
According to the invention, through the first-order energy-saving qualification evaluation coefficient and the second-order energy-saving qualification evaluation coefficient of each normal lighting device, the energy-saving qualification evaluation coefficient of each normal lighting device is comprehensively analyzed and considered, so that the detailed evaluation of the energy-saving performance of each normal lighting device is performed, clear personalized energy-saving qualification suggestion is provided, the reasonable energy-saving plan and scheme can be formulated, and the energy saving and the high-efficiency utilization can be realized.
According to the invention, the energy-saving space of each energy-saving lighting device is reasonably analyzed by combining the deviation condition of the energy-saving lighting device and the historical average power consumption, the deviation condition of the energy-saving lighting device and the current average power consumption of other lighting devices and the day and night stage of the current time point, and the energy-saving optimization of each energy-saving lighting device is realized under the condition that the normal lighting is not influenced by a unified mode of down-regulating the supply current, so that the energy-saving optimization maximization of the lighting energy source of the target public building area is realized.
Drawings
The invention will be further described with reference to the accompanying drawings, in which embodiments do not constitute any limitation of the invention, and other drawings can be obtained by one of ordinary skill in the art without inventive effort from the following drawings.
FIG. 1 is a flow chart of the steps of the method of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides a building fault diagnosis prediction and health management method based on large model training, comprising: s1, acquiring information of lighting equipment: and marking each lighting device in the target public building area as each target lighting device, and acquiring basic information and lighting information of each target lighting device.
Specifically, the basic information includes a type, a model number, a service life, a rated supply voltage value, and a rated supply current value.
The basic information of the lighting device is extracted from the data storage unit of the lighting device management center of the target public building area, the corresponding type, model, use date, rated supply voltage value and rated supply current value of the lighting device are extracted and input before the lighting device is used, and the service life is obtained by the absolute value difference between the current date and the use date.
The lighting information comprises lighting operation parameters and lighting environment parameters, wherein the lighting operation parameters comprise output voltage values, output current values, operation temperature values and luminous fluxes at each monitoring time point in a monitoring time period.
It should be noted that, the above-mentioned lighting operation parameters are obtained by installing a voltage sensor and a current sensor at the output end of the lighting equipment line, and installing a micro temperature sensor and a light flux monitoring sensor around the lamp core of the lighting equipment.
The lighting environment parameters include initial illuminance defining each azimuth of the lighting area and illuminance at each monitoring time point in the monitoring period.
The above-mentioned lighting device defines lighting area according to the type and model of lighting device, and the lighting device manufacturer makes the rule, and the initial illuminance of lighting device in every direction of lighting device defined lighting area and illuminance of every monitoring time point in monitoring time period are obtained by means of illumination monitoring sensor mounted in correspondent direction, and used as auxiliary monitoring analysis of lighting device management of target public building.
S2, potential fault risk assessment of the lighting equipment: based on the basic information and the illumination information of each target illumination apparatus, potential failure risk coefficients of each target illumination apparatus are analyzed, each target illumination apparatus is classified into each normal illumination apparatus and each abnormal illumination apparatus, and S3 and S5 are executed respectively.
Specifically, the specific analysis process of the potential failure risk coefficient of each target lighting device comprises the following steps: according to rated supply voltage value in basic information of each target lighting equipmentAnd rated supply current value/>Wherein/>Numbering for each target lighting device,/>Combining output voltage values/>, at each monitoring time point in the monitoring time period, in the lighting operation parameters of each target lighting deviceAnd output current value/>Wherein/>For the number of each monitoring time point in the monitoring time period,/>Respectively calculating the consumed power and the output power of each monitoring time point in each target lighting equipment monitoring time period, and recording as/>，/>,/>。
According to the type, model and service life of each target lighting equipment in the basic informationExtracting standard consumed power/>, which is specified by a lighting equipment manufacturer, of corresponding type and corresponding model of each target lighting equipment from WEB cloudAnd standard light efficiency/>Analyzing the energy consumption anomaly coefficient/>, within each target lighting device monitoring periodThe calculation formula is as follows: wherein/> Is a natural constant,/>To monitor the number of time points within a monitoring period,/>A reasonable deviation threshold value of power consumption for the preset lighting equipment.
Analyzing abnormal coefficients of light efficiency in monitoring time periods of each target lighting deviceThe calculation formula is as follows: wherein/> Is a preset reasonable deviation threshold value of the lighting effect of the lighting equipment.
It should be noted that the preset reasonable deviation threshold of the power consumption of the lighting device and the reasonable deviation threshold of the light efficiency of the lighting device are obtained according to relevant national standards and industry specifications. For example, national standards (GB 50617-2010) for construction and acceptance specifications for building electrical lighting devices specify requirements for power and light efficiency deviations for lighting devices.
For example, for a lamp rated power, the deviation should not be greater than 0.5W when it is not greater than 5W, and the deviation should not be greater than 10% of the rated value when it is greater than 5W.
And then is represented by the formulaObtaining the intrinsic performance coefficient of illumination in each target illumination device monitoring time period,/>The weight ratio is respectively corresponding to a preset energy consumption abnormal coefficient and a light efficiency abnormal coefficient.
According to the embodiment of the invention, the energy consumption abnormal coefficient and the light efficiency abnormal coefficient in the monitoring time period of each target lighting device are analyzed, the illumination internal performance coefficient in the monitoring time period of each target lighting device is comprehensively considered from three angles of power consumption rationality, fluctuation and light efficiency rationality, the defect of the existing method on the illumination internal performance consideration of the lighting device is overcome, and the depth and the accuracy of fault risk assessment of the lighting device in the public building area are effectively improved.
Specifically, the specific analysis process of the potential failure risk coefficient of each target lighting device further includes: according to the initial illuminance of each direction of the defined illumination area in the illumination environment parameters of each target illumination device, and the illuminance of each monitoring time point in the monitoring time period，/>To define the number of each azimuth of the illuminated area,/>Calculating average lifting illuminance/>, for each azimuth within each target lighting device defined lighting areaCombining luminous flux/>, at each monitoring time point in each monitoring time period, in each target lighting device lighting operation parameterBy the formula/>And obtaining the illumination basic capability coefficient of each target illumination device in the monitoring time period.
The calculation formula of the average lifting illuminance of each direction in the illumination area defined by each target illumination device is as follows:，/> for/> The individual target lighting devices define a lighting area/>Initial illuminance for each bearing.
From the formulaObtaining a lighting basic quality coefficient in each target lighting device monitoring time period, wherein/>For a preset reasonable fluctuation variance threshold of luminous flux of the lighting equipment,/>For reasonably deviating illuminance threshold values among preset illumination area orientations,/>To define the number of illumination area orientations,/>For/>The individual target lighting devices define a lighting area/>First/>, within a personal bearing monitoring periodThe illuminance at the time point is monitored.
It should be noted that, the reasonable fluctuation variance threshold of the luminous flux of the preset lighting device and the reasonable deviation illuminance threshold between the orientations of the lighting areas are obtained by a public building designer according to the basic requirements and practical experience of lighting design and by combining national standard (GB 50617-2010) of construction and acceptance standardization of building electric lighting devices.
According to the operation temperature value of each monitoring time point in each monitoring time period in the illumination operation parameters of each target illumination deviceCalculating the abnormal coefficient/>, of the illumination temperature in each target illumination device monitoring time period。
And then is represented by the formulaAnd obtaining the external performance coefficient of the illumination in the monitoring time period of each target illumination device.
According to the embodiment of the invention, the illumination basic capability coefficient, the illumination basic quality coefficient and the illumination temperature anomaly coefficient in each target illumination equipment monitoring time period are effectively combined, the illumination external performance coefficient in each target illumination equipment monitoring time period is reasonably analyzed, the actual running state of the illumination equipment is more comprehensively and accurately reflected from the self luminous flux performance, the environment illuminance performance and the running temperature performance, and the scientificity, the accuracy and the reliability of the analysis result of the illumination external performance are improved.
Analyzing potential fault risk coefficients of each target lighting deviceThe calculation formula is as follows:。
According to the embodiment of the invention, the intrinsic performance coefficient of illumination and the extrinsic performance coefficient of illumination in the monitoring time period of each target illumination device are combined, the potential failure risk coefficient of each target illumination device is comprehensively analyzed, the performance and performance of the illumination device are comprehensively understood, and further decision and operation are better carried out, so that potential failures can be found in time, corresponding measures are taken for prevention and maintenance, the failure rate of the illumination device is reduced, and the reliability and stability of the device are improved.
Specifically, the calculation formula of the abnormal coefficient of the illumination temperature in the monitoring time period of each target illumination device is as follows:，/> And (5) reasonably operating the temperature threshold for the preset lighting equipment.
Specifically, the specific process of classifying each target lighting device into each normal lighting device and each abnormal lighting device comprises the following steps: comparing the potential fault risk coefficient of each target lighting device with a preset potential fault risk coefficient warning threshold value of the public building lighting device stored in the WEB cloud, if the potential fault risk coefficient of a certain target lighting device is larger than or equal to the preset potential fault risk coefficient warning threshold value of the public building lighting device, marking the target lighting device as abnormal lighting device, otherwise marking the target lighting device as normal lighting device, and further obtaining each abnormal lighting device and each normal lighting device.
S3, energy-saving qualification evaluation of the lighting equipment: and analyzing the energy-saving qualification coefficients of the normal lighting devices, screening the energy-saving lighting devices from the normal lighting devices, and further analyzing the supply current value down-regulation value of the energy-saving lighting devices.
Specifically, the specific analysis process of the energy conservation qualification rate coefficient of each normal lighting device comprises the following steps: obtaining the output voltage value and the output current value of each normal lighting device at the current time point, and calculating the power consumption of each normal lighting device at the current time point，/>Numbering for each normal lighting device,/>。
Obtaining output voltage value and output current value of each normal lighting equipment history at the same time point as the current time point, and calculating power consumption of each normal lighting equipment history at the same time point as the current time pointWhereinFor the number of each day of history,/>。
The output voltage value and the output current value of each normal lighting device at the same time point as the current time point in each day are extracted from the lighting device management center data storage unit of the target public building area.
From the formulaObtaining a first-order energy-saving qualification evaluation coefficient of each normal lighting device, wherein/>For historical days,/>Is the normal number of lighting devices.
Collecting traffic flow of passers-by defining illumination area in each normal illumination device monitoring time period according to infrared sensor built in illumination deviceAnd extracting the intrinsic performance coefficient of illumination in each normal illumination device monitoring periodAnd the external performance coefficient of illumination/>By the formula/>And obtaining a second-order energy-saving qualification evaluation coefficient of each normal lighting device.
And further calculate the energy-saving qualification coefficients of the normal lighting devices，/>。
According to the embodiment of the invention, the energy-saving qualification evaluation coefficients of the normal lighting equipment are comprehensively analyzed and considered through the first-order energy-saving qualification evaluation coefficients and the second-order energy-saving qualification evaluation coefficients of the normal lighting equipment, so that the energy-saving performance of the normal lighting equipment is evaluated in detail, clear personalized energy-saving qualification suggestions are provided, a reasonable energy-saving plan and scheme can be formulated, and energy conservation and efficient utilization can be realized.
Specifically, the specific screening process of each energy-saving lighting device comprises the following steps: comparing the energy-saving qualification rate coefficient of each normal lighting device with a preset public building lighting device energy-saving qualification rate coefficient standard-reaching threshold stored in the WEB cloud, and if the energy-saving qualification rate coefficient of a certain normal lighting device is larger than or equal to the preset public building lighting device energy-saving qualification rate coefficient standard-reaching threshold, marking the normal lighting device as an energy-saving lighting device, and further screening each energy-saving lighting device from each normal lighting device.
Specifically, the specific analysis process of the supply current value down-regulation value of each energy-saving lighting device comprises the following steps: acquiring a day and night phase of the current time point, and extracting energy-saving adjustment weight of lighting equipment corresponding to the day and night phase of the current time point from the WEB cloud。
The above-mentioned day and night phases are mainly divided into a daytime phase and a nighttime phase, and because the natural illuminance at night is low relative to the daytime, and the artificial lighting requirement is greater, the energy-saving adjustment weight of the daytime phase at the current time point is greater relative to the nighttime phase, and the provision of summer and winter is comprehensively considered for the division of the day and night phasesThe rest of the time is classified into a daytime stage and a nighttime stage.
Extracting power consumption of each energy-saving lighting device at the same time point of each day as the current time pointAnd power consumption at the current point in time/>，/>Numbering for each energy-saving lighting device,/>From the formulaAnd obtaining the effective energy-saving power of each energy-saving lighting device.
According to technical specification content provided by a WEB cloud storage lighting equipment manufacturer for various types of lighting equipment, the technical specification content comprises basic supply current values and test consumption power corresponding to the supply current values under the same supply voltage values, and the basic supply current values of the energy-saving lighting equipment are obtained by combining the types and the models of the energy-saving lighting equipmentAnd testing the consumed power corresponding to each supplied current value under the same supplied voltage value, further constructing a consumed power-supplied current test graph of each energy-saving lighting device taking the consumed power as a horizontal axis and taking the supplied current value as a vertical axis, importing the consumed power-supplied current test graph into Matlab software, acquiring a consumed power-supplied current test relation function of each energy-saving lighting device by using a fitting tool of the Matlab software, substituting a value 1 into the consumed power-supplied current test relation function of each energy-saving lighting device, and acquiring a supplied current change value/>, corresponding to each energy-saving lighting device unit consumed power, of each energy-saving lighting deviceAnd then by the formulaObtaining a supply current value down-regulation value of each energy-saving lighting device, wherein/>For/>Rated supply current value of each energy-saving lighting device.
It should be noted that the above basic supply current refers to the lowest current required for the lighting device to operate normally.
According to the embodiment of the invention, the energy-saving space of each energy-saving lighting device is reasonably analyzed by combining the deviation condition of the energy-saving lighting device and the historical average power consumption, the deviation condition of the energy-saving lighting device and the current average power consumption of other lighting devices and the day and night stage of the current time point, and the energy-saving optimization of each energy-saving lighting device is realized under the condition that normal lighting is not affected by a unified mode of supply current downregulation, so that the maximization of energy-saving optimization of lighting energy sources of a target public building area is realized.
S4, energy-saving feedback of current supplied by the lighting equipment: and carrying out supply current energy-saving feedback on each energy-saving lighting device in the target public building area, and providing a corresponding supply current value down-regulation value.
S5, fault alert feedback of the lighting equipment: and carrying out fault warning feedback on each abnormal lighting device in the target public building area.
The foregoing is merely illustrative of the structures of this invention and various modifications, additions and substitutions for those skilled in the art of describing particular embodiments without departing from the structures of the invention or exceeding the scope of the invention as defined by the claims.

Claims (6)

1. The building fault diagnosis prediction and health management method based on large model training is characterized by comprising the following steps of:
S1, acquiring information of lighting equipment: marking each lighting device in the target public building area as each target lighting device, and acquiring basic information and lighting information of each target lighting device;
S2, potential fault risk assessment of the lighting equipment: analyzing potential failure risk coefficients of the target lighting devices based on the basic information and the lighting information of the target lighting devices, screening the target lighting devices into normal lighting devices and abnormal lighting devices, and executing S3 and S5 respectively;
S3, energy-saving qualification evaluation of the lighting equipment: analyzing the energy-saving qualification evaluation coefficients of the normal lighting devices, screening the energy-saving lighting devices from the normal lighting devices, and further analyzing the supply current value down-regulation value of the energy-saving lighting devices;
s4, energy-saving feedback of current supplied by the lighting equipment: carrying out supply current energy-saving feedback on each energy-saving lighting device in the target public building area, and providing a corresponding supply current value down-regulation value;
s5, fault alert feedback of the lighting equipment: performing fault warning feedback on each abnormal lighting device in the target public building area;
The specific analysis process of the energy-saving qualification rate coefficient of each normal lighting device comprises the following steps: obtaining the output voltage value and the output current value of each normal lighting device at the current time point, and calculating the power consumption of each normal lighting device at the current time point ，/>Numbering for each normal lighting device,/>；
Obtaining output voltage value and output current value of each normal lighting equipment history at the same time point as the current time point, and calculating power consumption of each normal lighting equipment history at the same time point as the current time pointWherein/>For the number of each day of history,/>；
From the formulaObtaining a first-order energy-saving qualification evaluation coefficient of each normal lighting device, wherein/>For historical days,/>Is the normal lighting equipment number;
collecting traffic flow of passers-by defining illumination area in each normal illumination device monitoring time period according to infrared sensor built in illumination device And extracting the intrinsic performance coefficient/>, of the illumination during each normal illumination device monitoring periodAnd the external performance coefficient of illumination/>By the formula/>Obtaining second-order energy-saving qualification evaluation coefficients of each normal lighting device;
And further calculate the energy-saving qualification coefficients of the normal lighting devices ，/>；
The specific screening process of each energy-saving lighting device comprises the following steps: comparing the energy-saving qualification rate coefficient of each normal lighting device with a preset public building lighting device energy-saving qualification rate coefficient standard-reaching threshold stored in the WEB cloud, if the energy-saving qualification rate coefficient of a certain normal lighting device is larger than or equal to the preset public building lighting device energy-saving qualification rate coefficient standard-reaching threshold, marking the normal lighting device as an energy-saving lighting device, and further screening each energy-saving lighting device from each normal lighting device;
the specific analysis process of the supply current value down-regulation value of each energy-saving lighting device comprises the following steps: acquiring a day and night phase of the current time point, and extracting energy-saving adjustment weight of lighting equipment corresponding to the day and night phase of the current time point from the WEB cloud ；
Extracting power consumption of each energy-saving lighting device at the same time point of each day as the current time pointAnd power consumption at the current point in time/>，/>Numbering for each energy-saving lighting device,/>From the formulaObtaining effective energy-saving power of each energy-saving lighting device;
According to technical specification content provided by a WEB cloud storage lighting equipment manufacturer for various types of lighting equipment, the technical specification content comprises basic supply current values and test consumption power corresponding to the supply current values under the same supply voltage values, and the basic supply current values of the energy-saving lighting equipment are obtained by combining the types and the models of the energy-saving lighting equipment And testing the consumed power corresponding to each supplied current value under the same supplied voltage value, further constructing a consumed power-supplied current test graph of each energy-saving lighting device taking the consumed power as a horizontal axis and taking the supplied current value as a vertical axis, importing the consumed power-supplied current test graph into Matlab software, acquiring a consumed power-supplied current test relation function of each energy-saving lighting device by using a fitting tool of the Matlab software, substituting a value 1 into the consumed power-supplied current test relation function of each energy-saving lighting device, and acquiring a supplied current change value/>, corresponding to each energy-saving lighting device unit consumed power, of each energy-saving lighting deviceAnd then by the formulaObtaining a supply current value down-regulation value of each energy-saving lighting device, wherein/>For/>Rated supply current value of each energy-saving lighting device.
2. The building fault diagnosis prediction and health management method based on large model training according to claim 1, wherein: the basic information comprises types, models, service life, rated supply voltage values and rated supply current values;
the lighting information comprises lighting operation parameters and lighting environment parameters, wherein the lighting operation parameters comprise output voltage values, output current values, operation temperature values and luminous fluxes at each monitoring time point in a monitoring time period;
The lighting environment parameters include initial illuminance defining each azimuth of the lighting area and illuminance at each monitoring time point in the monitoring period.
3. The building fault diagnosis prediction and health management method based on large model training according to claim 2, wherein: the specific analysis process of the potential failure risk coefficient of each target lighting device comprises the following steps: according to rated supply voltage value in basic information of each target lighting equipmentAnd rated supply current value/>Wherein/>Numbering for each target lighting device,/>Combining output voltage values/>, at each monitoring time point in the monitoring time period, in the lighting operation parameters of each target lighting deviceAnd output current value/>Wherein/>To monitor the number of each monitoring time point in the time period,Respectively calculating the consumed power and the output power of each monitoring time point in each target lighting equipment monitoring time period, and recording as/>，/>,/>；
According to the type, model and service life of each target lighting equipment in the basic informationExtracting standard consumed power/>, which is specified by a lighting equipment manufacturer, of corresponding type and corresponding model of each target lighting equipment from WEB cloudAnd standard light efficiency/>Analyzing the energy consumption anomaly coefficient/>, within each target lighting device monitoring periodThe calculation formula is as follows: wherein/> Is a natural constant,/>To monitor the number of time points within a monitoring period,/>A reasonable deviation threshold value of power consumption for a preset lighting device;
analyzing abnormal coefficients of light efficiency in monitoring time periods of each target lighting device The calculation formula is as follows: wherein/> A preset reasonable deviation threshold value of the lighting effect of the lighting equipment;
And then is represented by the formula Obtaining the intrinsic performance coefficient of illumination in each target illumination device monitoring time period,/>The weight ratio is respectively corresponding to a preset energy consumption abnormal coefficient and a light efficiency abnormal coefficient.
4. A building fault diagnosis and health management method based on large model training according to claim 3, characterized in that: the specific analysis process of the potential failure risk coefficient of each target lighting device further comprises the following steps: according to the initial illuminance of each direction of the defined illumination area in the illumination environment parameters of each target illumination device, and the illuminance of each monitoring time point in the monitoring time period，/>To define the number of each azimuth of the illuminated area,/>Calculating average lifting illuminance/>, for each azimuth within each target lighting device defined lighting areaCombining luminous flux/>, at each monitoring time point in each monitoring time period, in each target lighting device lighting operation parameterBy the formula/>Obtaining the illumination basic capability coefficient of each target illumination device in the monitoring time period;
From the formula Obtaining a lighting basic quality coefficient in each target lighting device monitoring time period, wherein/>For a preset reasonable fluctuation variance threshold of luminous flux of the lighting equipment,/>For reasonably deviating illuminance threshold values among preset illumination area orientations,/>To define the number of illumination area orientations,/>Is the firstThe individual target lighting devices define a lighting area/>First/>, within a personal bearing monitoring periodIlluminance at each monitoring time point;
According to the operation temperature value of each monitoring time point in each monitoring time period in the illumination operation parameters of each target illumination device Calculating the abnormal coefficient/>, of the illumination temperature in each target illumination device monitoring time period；
And then is represented by the formulaObtaining the external performance coefficient of illumination in the monitoring time period of each target illumination device;
analyzing potential fault risk coefficients of each target lighting device The calculation formula is as follows:。
5. The building fault diagnosis prediction and health management method based on large model training according to claim 4, wherein: the calculation formula of the abnormal coefficient of the illumination temperature in the monitoring time period of each target illumination device is as follows: ，/> And (5) reasonably operating the temperature threshold for the preset lighting equipment.
6. The building fault diagnosis prediction and health management method based on large model training according to claim 4, wherein: the specific process of screening each target lighting device into each normal lighting device and each abnormal lighting device comprises the following steps: comparing the potential fault risk coefficient of each target lighting device with a preset potential fault risk coefficient warning threshold value of the public building lighting device stored in the WEB cloud, if the potential fault risk coefficient of a certain target lighting device is larger than or equal to the preset potential fault risk coefficient warning threshold value of the public building lighting device, marking the target lighting device as abnormal lighting device, otherwise marking the target lighting device as normal lighting device, and further obtaining each abnormal lighting device and each normal lighting device.
CN202410003453.3A 2024-01-02 2024-01-02 Building fault diagnosis prediction and health management method based on large model training Active CN117494484B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410003453.3A CN117494484B (en) 2024-01-02 2024-01-02 Building fault diagnosis prediction and health management method based on large model training

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410003453.3A CN117494484B (en) 2024-01-02 2024-01-02 Building fault diagnosis prediction and health management method based on large model training

Publications (2)

Publication Number Publication Date
CN117494484A CN117494484A (en) 2024-02-02
CN117494484B true CN117494484B (en) 2024-05-10

Family

ID=89673074

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410003453.3A Active CN117494484B (en) 2024-01-02 2024-01-02 Building fault diagnosis prediction and health management method based on large model training

Country Status (1)

Country Link
CN (1) CN117494484B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012140152A1 (en) * 2011-04-12 2012-10-18 Aleksander Gerbec Network comprising nodes associated with outdoor lighting devices
EP2703916A2 (en) * 2012-08-30 2014-03-05 energicos Systems LLP Method for permanent daily analysis of the energy used by building technology systems
KR20200048302A (en) * 2018-10-29 2020-05-08 상명대학교산학협력단 Lighting control system for energy savings
KR20200113796A (en) * 2019-03-26 2020-10-07 (주)에코메이텍 Energy Management System of Building Smart Lighting
KR102468888B1 (en) * 2021-11-30 2022-11-21 주식회사 건강 A system for monitoring the condition of a building based on IoT
WO2023208995A1 (en) * 2022-04-26 2023-11-02 Tridonic Gmbh & Co Kg Artificial intelligence-based lifetime analytic calculations for intelligent devices of building infrastructure systems

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2946219B2 (en) * 2013-01-16 2022-01-19 Signify Holding B.V. Method, apparatus and computer-program product for determining faults in a lighting system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012140152A1 (en) * 2011-04-12 2012-10-18 Aleksander Gerbec Network comprising nodes associated with outdoor lighting devices
EP2703916A2 (en) * 2012-08-30 2014-03-05 energicos Systems LLP Method for permanent daily analysis of the energy used by building technology systems
KR20200048302A (en) * 2018-10-29 2020-05-08 상명대학교산학협력단 Lighting control system for energy savings
KR20200113796A (en) * 2019-03-26 2020-10-07 (주)에코메이텍 Energy Management System of Building Smart Lighting
KR102468888B1 (en) * 2021-11-30 2022-11-21 주식회사 건강 A system for monitoring the condition of a building based on IoT
WO2023208995A1 (en) * 2022-04-26 2023-11-02 Tridonic Gmbh & Co Kg Artificial intelligence-based lifetime analytic calculations for intelligent devices of building infrastructure systems

Also Published As

Publication number Publication date
CN117494484A (en) 2024-02-02

Similar Documents

Publication Publication Date Title
CN104915562B (en) Build efficiency diagnostic method and system
CN111539559B (en) Environment control and operation guarantee platform for public building
BR112013026307B1 (en) DYNAMIC EVALUATION SYSTEM FOR MONITORING HIGH VOLTAGE ELECTRICAL COMPONENTS AND METHOD FOR EVALUATION OF AT LEAST ONE HIGH VOLTAGE ELECTRICAL COMPONENT
CN103903408A (en) Device fault detecting and early warning method and system
CN105956752A (en) Energy efficiency evaluation and diagnosis analysis method used for green public building operation phase
CN111638692B (en) Intelligent park management system
CN107036238A (en) Intelligent energy-saving control method for dynamically predicting external air and load
CN117078017A (en) Intelligent decision analysis system for monitoring power grid equipment
CN117494484B (en) Building fault diagnosis prediction and health management method based on large model training
CN110750760A (en) Abnormal theoretical line loss detection method based on situation awareness and control chart
CN117394535A (en) Digital twin system of AC/DC hybrid power distribution network
CN112165755A (en) Building brightening intelligent control management system based on big data
CN116468302A (en) Building park energy structure evaluation method, system, electronic equipment and storage medium
CN115183389A (en) Intelligent diagnosis method based on full life cycle of air conditioner room
CN112798318B (en) Cold junction performance monitoring and intelligent diagnosis system of wet cooling unit
CN115238957A (en) Early warning method and system for power transmission line corridor
CN113962100A (en) Automatic optimization intelligent energy control system and method based on big data analysis
CN111178768A (en) Smart energy management system based on cloud platform
Tang et al. An Intelligent Fault Diagnosis Method for Street Lamps
CN111245097A (en) Intelligent power grid management and control system and method
CN111142491B (en) Smart energy management platform system based on Internet of things and cloud computing technology
CN117391678B (en) Comprehensive management platform for recycling and reutilizing high-efficiency energy sources
CN115996503B (en) Self-optimizing building illumination sensor energy-saving control system
CN117094475B (en) Fault analysis system for electric power distribution network
CN117172625B (en) Comprehensive analysis method for energy-saving reconstruction of existing building

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant