CN117057784B - Street lamp running state monitoring method and system - Google Patents
Street lamp running state monitoring method and system Download PDFInfo
- Publication number
- CN117057784B CN117057784B CN202311307099.5A CN202311307099A CN117057784B CN 117057784 B CN117057784 B CN 117057784B CN 202311307099 A CN202311307099 A CN 202311307099A CN 117057784 B CN117057784 B CN 117057784B
- Authority
- CN
- China
- Prior art keywords
- street lamp
- data
- state
- real
- image data
- 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
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012423 maintenance Methods 0.000 claims abstract description 114
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 63
- 230000006698 induction Effects 0.000 claims abstract description 60
- 238000005286 illumination Methods 0.000 claims abstract description 50
- 238000004891 communication Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 15
- 230000004913 activation Effects 0.000 claims description 24
- 239000011159 matrix material Substances 0.000 claims description 16
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000003672 processing method Methods 0.000 claims description 5
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 238000011176 pooling Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000007537 lampworking Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000009435 building construction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- 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
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J1/00—Photometry, e.g. photographic exposure meter
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M11/00—Testing of optical apparatus; Testing structures by optical methods not otherwise provided for
- G01M11/02—Testing optical properties
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2291—User-Defined Types; Storage management thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Human Resources & Organizations (AREA)
- Computational Linguistics (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Multimedia (AREA)
- Economics (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Circuit Arrangement For Electric Light Sources In General (AREA)
Abstract
The invention relates to the field of illumination, in particular to a method and a system for monitoring the running state of a street lamp. The lighting fault street lamp in the road can be accurately judged, and the electric power resource is effectively utilized. The real-time lighting image data and the light induction intensity data of the street lamp are obtained through the sensor device, and the data are transmitted to the server through the ZigBee wireless communication module. Inputting real-time lighting image data to be trained into a target ResNet convolutional neural network model for training to obtain real-time state data of the street lamp, establishing a street lamp maintenance measure database, judging the state of the street lamp according to the real-time state data of the street lamp and the light induction intensity data of the street lamp, generating street lamp maintenance measures according to the street lamp maintenance measure database when the street lamp is the street lamp in a state to be maintained, sending the street lamp maintenance measures to a server for early warning, and monitoring the street lamp in the state to be maintained through a sensor device when the street lamp is the street lamp in the state to be maintained.
Description
Technical Field
The invention relates to the field of illumination, in particular to a method and a system for monitoring the running state of a street lamp.
Background
Today in the industry of building construction, the progress of rural road modernization is accelerated, wherein lighting systems in rural roads, provinces and national roads are increasingly valued. The traditional lighting system is generally started one by one according to the longitude and latitude of the street lamp and the timing switch time control system of different weather, the brightness of the lamp source is kept constant when the street lamp is lighted, the maintenance needs to be carried out manually to constantly visit and maintain the lighting condition of each street lamp on site at regular time to check whether the street lamp breaks down or is damaged, a great deal of lighting resources, manpower resources, financial resources and material resources are wasted, and along with the acceleration of urban progress of villages, more street lamps need to be checked and maintained, so the maintenance of the street lamp by traditional manual work becomes a little constraint. How to quickly identify the state of the street lamp and improve the maintenance and detection efficiency of the street lamp is a technical problem to be solved in the current stage.
Disclosure of Invention
The invention aims to solve the problems and designs a method and a system for monitoring the running state of a street lamp.
The technical scheme for achieving the purpose is that in the street lamp running state monitoring method, the street lamp running state monitoring method comprises the following steps of:
acquiring real-time lighting image data of a street lamp through a sensor device, and performing data preprocessing on the real-time lighting image data to obtain real-time lighting image data to be trained;
the street lamp light induction intensity data of the street lamp are obtained by using the sensor device, and the street lamp light induction intensity data and the real-time lighting image data to be trained are transmitted to a server through the ZigBee wireless communication module;
establishing an initial ResNet convolutional neural network model based on a neural network, and replacing a ReLU activation function in the initial ResNet convolutional neural network model by using a P-ReLU activation function to obtain a target ResNet convolutional neural network model;
inputting the real-time lighting image data to be trained into the target ResNet convolutional neural network model for training to obtain real-time state data of the street lamp;
a street lamp maintenance measure database is established, the state of the street lamp is judged according to the real-time state data and the light induction intensity data of the street lamp, if the street lamp is the street lamp in the state to be maintained, street lamp maintenance measures are generated according to the street lamp maintenance measure database in the state to be maintained, and the street lamp maintenance measures are sent to a server for early warning;
if the street lamp is a street lamp in a state to be overhauled, the street lamp in the state to be overhauled is monitored through the sensor device.
Further, in the above method for monitoring an operation state of a street lamp, the acquiring real-time lighting image data of the street lamp by the sensor device, performing data preprocessing on the real-time lighting image data to obtain real-time lighting image data to be trained, includes:
acquiring real-time lighting image data of the street lamp through a sensor device, wherein the sensor device at least comprises an image acquisition sensor, a light induction intensity sensor and a temperature sensor;
acquiring real-time lighting image data, and adjusting the real-time lighting image data into image data with the same size to obtain a lighting image data set;
performing image processing on the bright light image dataset by using an image contrast enhancement, histogram equalization and fuzzy processing method to obtain a target image dataset;
classifying the target image data set based on an SVM image classifier, and clustering the target image data set by using a hierarchical clustering algorithm;
calculating a similarity matrix of the target image data set to obtain a similarity matrix image data set; acquiring all image samples according to the similarity matrix image data set, and determining cluster image data according to all the image samples;
combining the two cluster image data with the highest similarity to obtain cluster image data; and when the number of the cluster image data is 1, merging and stopping to obtain the real-time lighting image data to be trained.
Further, in the above method for monitoring a running state of a street lamp, the acquiring, by using a sensor device, street lamp light induction intensity data of the street lamp, and transmitting, by using a ZigBee wireless communication module, the street lamp light induction intensity data and the real-time lighting image data to be trained to a server includes:
the method comprises the steps of obtaining street lamp light induction intensity data of a street lamp by using a sensor device, wherein the street lamp light induction intensity data at least comprises illumination brightness data and illumination time data;
transmitting the street lamp photoinduction intensity data and the real-time lighting image data to be trained to a server through a ZigBee wireless communication module;
the sensor device and the ZigBee wireless communication module are arranged at the middle and lower positions of the street lamp pole part and are used for collecting street lamp light induction intensity data and real-time lighting image data.
Further, in the above street lamp operation state monitoring method, the establishing an initial ResNet convolutional neural network model based on the neural network, replacing a ReLU activation function in the initial ResNet convolutional neural network model with a P-ReLU activation function to obtain a target ResNet convolutional neural network model, includes:
establishing an initial ResNet convolutional neural network model based on a convolutional neural network, wherein the initial ResNet convolutional neural network model at least comprises an input layer, a convolutional calculation layer, a ReLU activation layer, a pooling layer and a full connection layer;
replacing a ReLU activation function in the initial ResNet convolutional neural network model with a P-ReLU activation function;
adding batch normalization after each convolution layer in the initial ResNet convolution neural network model;
and replacing an SGD random gradient descent algorithm in the initial ResNet convolutional neural network model by using an Adam optimization algorithm to obtain a target ResNet convolutional neural network model.
Further, in the above method for monitoring a street lamp running state, the step of inputting the real-time lighting image data to be trained into the target res net convolutional neural network model for training to obtain the street lamp real-time state data includes:
inputting the real-time lighting image data to be trained into the target ResNet convolutional neural network model for training to obtain real-time state data of the street lamp;
the street lamp real-time state data at least comprises a full brightness street lamp, a moderate brightness street lamp, a flash brightness street lamp and a full non-brightness street lamp.
Further, in the above method for monitoring the operation state of a street lamp, the step of establishing a street lamp maintenance measure database, judging the state of the street lamp according to the real-time state data and the light induction intensity data of the street lamp, and if the street lamp is a street lamp in a state to be maintained, generating a street lamp maintenance measure according to the street lamp maintenance measure database in the state to be maintained, and sending the street lamp maintenance measure to a server for early warning, wherein the method comprises the steps of:
the method comprises the steps of collecting street lamp historical maintenance data of street lamps in a server and street lamp reference maintenance data in an Internet database through a data acquisition module;
clustering the historical maintenance data of the street lamp and the reference maintenance data of the street lamp by using an FCM fuzzy clustering algorithm to obtain a street lamp maintenance measure database;
if the real-time state of the street lamp is completely not on, and the illumination brightness data and the illumination time data in the street lamp light induction intensity data of the corresponding street lamp are both 0, the street lamp is judged to be the street lamp in the state to be maintained;
if the real-time state of the street lamp is a flashing street lamp, and the illumination brightness data and the illumination time data in the street lamp light induction intensity data of the corresponding street lamp are less than 50%, the street lamp is judged to be a street lamp in a state to be maintained;
generating street lamp maintenance measures for the street lamp in the state to be maintained according to the street lamp maintenance measure database, and sending the street lamp maintenance measures to a server for early warning.
Further, in the above method for monitoring a street lamp operating state, if the street lamp is a street lamp in a state to be overhauled, monitoring the street lamp in the state to be overhauled through a sensor device includes:
if the real-time state of the street lamp is a full brightness street lamp, and the illumination brightness data and the illumination time data in the street lamp light induction intensity data of the corresponding street lamp are both 100%, judging the street lamp as a healthy street lamp;
if the real-time state of the street lamp is a moderate brightness street lamp and the illumination brightness data and the illumination time data in the street lamp light induction intensity data of the corresponding street lamp are 80%, the street lamp is judged to be a street lamp in a state to be overhauled;
monitoring the street lamp in the state to be overhauled through the sensor device, and if the illumination brightness data and the illumination time data in the street lamp photoinduction intensity data are reduced, carrying out early warning on the server;
if the real-time state of the street lamp in the state to be overhauled is changed into the state that the street lamp is not lightened completely, generating street lamp maintenance measures according to a street lamp maintenance measure database, and sending the street lamp maintenance measures to a server for early warning.
Further, in the above-mentioned street lamp running state monitoring system, the street lamp running state monitoring system includes:
the data acquisition module is used for acquiring real-time lighting image data of the street lamp through the sensor device, and carrying out data preprocessing on the real-time lighting image data to obtain real-time lighting image data to be trained;
the data transmission module is used for acquiring street lamp light induction intensity data of the street lamp by utilizing the sensor device, and transmitting the street lamp light induction intensity data and the real-time lighting image data to be trained to a server through the ZigBee wireless communication module;
the model building module is used for building an initial ResNet convolutional neural network model based on the neural network, and processing the initial ResNet convolutional neural network model based on the RAdam algorithm optimizer to obtain a target ResNet convolutional neural network model;
the model training module is used for inputting the real-time lighting image data to be trained into the target ResNet convolutional neural network model for training to obtain real-time state data of the street lamp;
the maintenance early warning module is used for establishing a street lamp maintenance measure database, judging the state of the street lamp according to the real-time state data and the light induction intensity data of the street lamp, generating street lamp maintenance measures according to the street lamp maintenance measure database when the street lamp is the street lamp in the state to be maintained, and sending the street lamp maintenance measures to a server for early warning;
and the street lamp monitoring module is used for monitoring the street lamp in the state to be overhauled through the sensor device if the street lamp is in the state to be overhauled.
Further, in the above street lamp operation state monitoring system, the data acquisition module includes the following submodules:
the acquisition sub-module is used for acquiring real-time lighting image data of the street lamp through the sensor device, and the sensor device at least comprises an image acquisition sensor, a light induction intensity sensor and a temperature sensor;
the adjustment sub-module is used for acquiring real-time lighting image data, and adjusting the real-time lighting image data into image data with the same size to obtain a lighting image data set;
the processing sub-module is used for carrying out image processing on the bright-light image data set by utilizing an image contrast enhancement, histogram equalization and fuzzy processing method to obtain a target image data set;
the clustering sub-module is used for classifying the target image data set based on the SVM image classifier and clustering the target image data set by using a hierarchical clustering algorithm;
the computing sub-module is used for computing a similar matrix of the target image dataset to obtain a similar matrix image dataset; acquiring all image samples according to the similarity matrix image data set, and determining cluster image data according to all the image samples;
the obtaining sub-module is used for merging the two cluster image data with the highest similarity to obtain cluster image data; and when the number of the cluster image data is 1, merging and stopping to obtain the real-time lighting image data to be trained.
Further, in the above-mentioned street lamp running state monitoring system, the maintenance early warning module includes the following submodules:
the collecting sub-module is used for collecting the street lamp historical maintenance data of the street lamp in the server and the street lamp reference maintenance data in the Internet database through the data collecting module;
the clustering sub-module is used for clustering the street lamp historical maintenance data and the street lamp reference maintenance data by using an FCM fuzzy clustering algorithm to obtain a street lamp maintenance measure database;
the first judging submodule is used for judging the street lamp as the street lamp in a state to be maintained if the street lamp is not lightened completely in a real-time state and the illumination brightness data and the illumination time data in the street lamp light induction intensity data of the corresponding street lamp are both 0;
the second judging sub-module is used for judging the street lamp as the street lamp in the state to be maintained if the real-time state of the street lamp is a flashing street lamp and the illumination brightness data and the illumination time data in the street lamp light induction intensity data of the corresponding street lamp are less than 50 percent;
and the early warning sub-module is used for generating street lamp maintenance measures for the street lamp in the state to be maintained according to the street lamp maintenance measure database, and sending the street lamp maintenance measures to a server for early warning.
The street lamp working state detection device has the advantages that the working state of the street lamp can be detected through the real-time lighting image and the real-time brightness data of the street lamp, whether the street lamp is in a state requiring maintenance and health or not is accurately judged, and labor cost is saved; the streetlamp to be maintained is provided with a maintenance scheme and is uploaded to a server for early warning, so that maintenance efficiency of streetlamp maintenance is improved; the street lamp with the brightness data changed is monitored, so that the maintenance times of the street lamp can be reduced. The street lamp with the lighting fault in the road can be accurately distinguished, the electric power resource is effectively utilized, the waste of energy is avoided as much as possible, the management level of urban infrastructure is improved, and manpower, material resources and financial resources are effectively saved.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention.
Fig. 1 is a schematic diagram of a first embodiment of a method for monitoring an operation state of a street lamp according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a second embodiment of a method for monitoring an operation state of a street lamp according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a third embodiment of a method for monitoring an operation state of a street lamp according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a first embodiment of a streetlight operation state monitoring system according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The invention is specifically described below with reference to the accompanying drawings, as shown in fig. 1, and the method for monitoring the running state of the street lamp comprises the following steps:
step 101, acquiring real-time lighting image data of a street lamp through a sensor device, and performing data preprocessing on the real-time lighting image data to obtain real-time lighting image data to be trained;
specifically, in this embodiment, real-time lighting image data of the street lamp is obtained through a sensor device, where the sensor device at least includes an image acquisition sensor, a light induction intensity sensor, and a temperature sensor; acquiring real-time lighting image data, and adjusting the real-time lighting image data into image data with the same size to obtain a lighting image data set; performing image processing on the bright light image dataset by using an image contrast enhancement, histogram equalization and fuzzy processing method to obtain a target image dataset; classifying the target image data set based on the SVM image classifier, and clustering the target image data set by using a hierarchical clustering algorithm; calculating a similarity matrix of the target image data set to obtain a similarity matrix image data set; acquiring all image samples according to the similarity matrix image data set, and determining cluster image data according to all the image samples; circularly combining the two cluster image data with highest similarity, and updating the similarity matrix image data set; and when the number of the cluster image data is 1, merging and stopping to obtain the real-time lighting image data to be trained.
102, acquiring street lamp light induction intensity data of a street lamp by using a sensor device, and transmitting the street lamp light induction intensity data and real-time lighting image data to be trained to a server through a ZigBee wireless communication module;
in particular, in the embodiment, the sensor device is utilized to obtain the light induction intensity data of the street lamp, and the light induction intensity data of the street lamp at least comprises illumination brightness data and illumination time data; transmitting the street lamp light induction intensity data and the real-time lighting image data to be trained to a server through the ZigBee wireless communication module; the sensor device and the ZigBee wireless communication module are arranged at the middle and lower positions of the street lamp pole part and are used for collecting street lamp light induction intensity data and real-time lighting image data.
Step 103, establishing an initial ResNet convolutional neural network model based on the neural network, and replacing a ReLU activation function in the initial ResNet convolutional neural network model by using a P-ReLU activation function to obtain a target ResNet convolutional neural network model;
specifically, in this embodiment, an initial res net convolutional neural network model is established based on a convolutional neural network, where the initial res net convolutional neural network model at least includes an input layer, a convolutional calculation layer, a ReLU activation layer, a pooling layer, and a full connection layer; replacing a ReLU activation function in the initial ResNet convolutional neural network model with a P-ReLU activation function; adding batch normalization after each convolution layer in the initial ResNet convolution neural network model; and replacing an SGD random gradient descent algorithm in the initial ResNet convolutional neural network model by using an Adam optimization algorithm to obtain the target ResNet convolutional neural network model.
104, inputting the real-time lighting image data to be trained into a target ResNet convolutional neural network model for training to obtain real-time state data of the street lamp;
specifically, in this embodiment, real-time lighting image data to be trained is input into a target ResNet convolutional neural network model for training, so as to obtain real-time state data of the street lamp; the street lamp real-time status data at least comprises a full brightness street lamp, a moderate brightness street lamp, a flash brightness street lamp and a full non-brightness street lamp.
105, establishing a street lamp maintenance measure database, judging the state of the street lamp according to the real-time state data and the light induction intensity data of the street lamp, generating street lamp maintenance measures according to the street lamp maintenance measure database when the street lamp is in the state to be maintained, and sending the street lamp maintenance measures to a server for early warning;
specifically, in this embodiment, through a data acquisition module, street lamp historical maintenance data of the street lamps in the server and street lamp reference maintenance data in the internet database are collected; clustering the historical maintenance data of the street lamp and the reference maintenance data of the street lamp by using an FCM fuzzy clustering algorithm to obtain a street lamp maintenance measure database; if the real-time state of the street lamp is completely not on, and the illumination brightness data and the illumination time data in the street lamp light induction intensity data of the corresponding street lamp are both 0, the street lamp is judged to be the street lamp in the state to be maintained; if the real-time state of the street lamp is a flashing lighting street lamp and the illumination brightness data and the illumination time data in the street lamp light induction intensity data of the corresponding street lamp are less than 50%, the street lamp is judged to be a street lamp in a state to be maintained; generating street lamp maintenance measures according to the street lamp maintenance measures database and sending the street lamp maintenance measures to the server for early warning.
And 106, if the street lamp is a street lamp in a state to be overhauled, monitoring the street lamp in the state to be overhauled through a sensor device.
Specifically, in the embodiment, if the real-time state of the street lamp is a full brightness street lamp, and the illumination brightness data and the illumination time data in the street lamp light induction intensity data corresponding to the street lamp are both 100%, the street lamp is judged to be a healthy street lamp; if the real-time state of the street lamp is a moderate brightness street lamp and the illumination brightness data and the illumination time data in the street lamp light induction intensity data of the corresponding street lamp are 80%, the street lamp is judged to be a street lamp in a state to be overhauled; monitoring the street lamp in the state to be overhauled through the sensor device, and if the illumination brightness data and the illumination time data in the street lamp photoinduction intensity data are reduced, carrying out early warning on the server; if the real-time state of the street lamp in the state to be overhauled is changed into the state that the street lamp is not lightened completely, generating street lamp maintenance measures according to a street lamp maintenance measure database, and sending the street lamp maintenance measures to a server for early warning.
The street lamp working state detection device has the advantages that the working state of the street lamp can be detected through the real-time lighting image and the real-time brightness data of the street lamp, whether the street lamp is in a state requiring maintenance and health or not is accurately judged, and labor cost is saved; the streetlamp to be maintained is provided with a maintenance scheme and is uploaded to a server for early warning, so that maintenance efficiency of streetlamp maintenance is improved; the street lamp with the brightness data changed is monitored, so that the maintenance times of the street lamp can be reduced. The street lamp with the lighting fault in the road can be accurately distinguished, the electric power resource is effectively utilized, the waste of energy is avoided as much as possible, the management level of urban infrastructure is improved, and manpower, material resources and financial resources are effectively saved.
In this embodiment, referring to fig. 2, in a second embodiment of a method for monitoring a street lamp running state according to the present invention, an initial res net convolutional neural network model is built based on a neural network, and a P-re lu activation function is used to replace a re lu activation function in the initial res net convolutional neural network model, so as to obtain a target res net convolutional neural network model, which includes the following steps:
step 201, establishing an initial ResNet convolutional neural network model based on a convolutional neural network, wherein the initial ResNet convolutional neural network model at least comprises an input layer, a convolutional calculation layer, a ReLU activation layer, a pooling layer and a full connection layer;
step 202, replacing a ReLU activation function in an initial ResNet convolutional neural network model by using a P-ReLU activation function;
step 203, adding batch normalization to each convolution layer in the initial ResNet convolution neural network model;
and 204, replacing an SGD random gradient descent algorithm in the initial ResNet convolutional neural network model by using an Adam optimization algorithm to obtain a target ResNet convolutional neural network model.
In this embodiment, referring to fig. 3, in a third embodiment of a method for monitoring a running state of a street lamp according to the present invention, the state of the street lamp is determined according to real-time state data of the street lamp and light induction intensity data of the street lamp, if the street lamp is a street lamp in a state to be maintained, street lamp maintenance measures are generated according to a street lamp maintenance measure database for the street lamp in the state to be maintained, and the street lamp maintenance measures are sent to a server and early warning is performed, including the following steps:
step 301, collecting street lamp historical maintenance data of street lamps in a server and street lamp reference maintenance data in an internet database through a data acquisition module;
step 302, clustering historical maintenance data of the street lamp and reference maintenance data of the street lamp by using an FCM fuzzy clustering algorithm to obtain a street lamp maintenance measure database;
step 303, if the real-time state of the street lamp is completely not on, and the illumination brightness data and the illumination time data in the street lamp light induction intensity data of the corresponding street lamp are both 0, the street lamp is judged to be the street lamp in the state to be maintained;
step 304, if the real-time state of the street lamp is a flashing street lamp, and the illumination brightness data and the illumination time data in the street lamp light induction intensity data of the corresponding street lamp are both less than 50%, the street lamp is judged to be a street lamp in a state to be maintained;
and 305, generating street lamp maintenance measures according to the street lamp maintenance measures database and sending the street lamp maintenance measures to the server for early warning.
The method for monitoring the running state of the street lamp provided by the embodiment of the invention is described above, and the system for monitoring the running state of the street lamp according to the embodiment of the invention is described below, referring to fig. 4, and one embodiment of the system for monitoring the running state of the street lamp according to the embodiment of the invention includes:
the data acquisition module is used for acquiring real-time lighting image data of the street lamp through the sensor device, and carrying out data preprocessing on the real-time lighting image data to obtain real-time lighting image data to be trained;
the data transmission module is used for acquiring street lamp light induction intensity data of the street lamp by utilizing the sensor device, and transmitting the street lamp light induction intensity data and the real-time lighting image data to be trained to the server through the ZigBee wireless communication module;
the model building module is used for building an initial ResNet convolutional neural network model based on the neural network, and processing the initial ResNet convolutional neural network model based on the RAdam algorithm optimizer to obtain a target ResNet convolutional neural network model;
the model training module is used for inputting the real-time lighting image data to be trained into the target ResNet convolutional neural network model for training to obtain real-time state data of the street lamp;
the maintenance early warning module is used for establishing a street lamp maintenance measure database, judging the state of the street lamp according to the real-time state data and the light induction intensity data of the street lamp, generating street lamp maintenance measures according to the street lamp maintenance measure database when the street lamp is the street lamp in the state to be maintained, and sending the street lamp maintenance measures to the server for early warning;
and the street lamp monitoring module is used for monitoring the street lamp in the state to be overhauled through the sensor device if the street lamp is in the state to be overhauled.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the above-described embodiments, and that the above-described embodiments and descriptions are only preferred embodiments of the present invention, and are not intended to limit the invention, and that various changes and modifications may be made therein without departing from the spirit and scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. The method for monitoring the running state of the street lamp is characterized by comprising the following steps of:
acquiring real-time lighting image data of the street lamp through a sensor device, wherein the sensor device at least comprises an image acquisition sensor, a light induction intensity sensor and a temperature sensor; acquiring real-time lighting image data, and adjusting the real-time lighting image data into image data with the same size to obtain a lighting image data set; performing image processing on the bright light image dataset by using an image contrast enhancement, histogram equalization and fuzzy processing method to obtain a target image dataset; classifying the target image data set based on an SVM image classifier, and clustering the target image data set by using a hierarchical clustering algorithm; calculating a similarity matrix of the target image data set to obtain a similarity matrix image data set; acquiring all image samples according to the similarity matrix image data set, and determining cluster image data according to all the image samples; combining the two cluster image data with the highest similarity to obtain cluster image data; merging and terminating when the number of the cluster image data is 1, so as to obtain real-time lighting image data to be trained;
the street lamp light induction intensity data of the street lamp are obtained by using the sensor device, and the street lamp light induction intensity data and the real-time lighting image data to be trained are transmitted to a server through the ZigBee wireless communication module;
establishing an initial ResNet convolutional neural network model based on a neural network, and replacing a ReLU activation function in the initial ResNet convolutional neural network model by using a P-ReLU activation function to obtain a target ResNet convolutional neural network model;
inputting the real-time lighting image data to be trained into the target ResNet convolutional neural network model for training to obtain real-time state data of the street lamp;
a street lamp maintenance measure database is established, the state of the street lamp is judged according to the real-time state data and the light induction intensity data of the street lamp, if the street lamp is the street lamp in the state to be maintained, street lamp maintenance measures are generated according to the street lamp maintenance measure database in the state to be maintained, and the street lamp maintenance measures are sent to a server for early warning;
if the street lamp is a street lamp in a state to be overhauled, the street lamp in the state to be overhauled is monitored through the sensor device.
2. The method for monitoring the running state of the street lamp according to claim 1, wherein the step of obtaining street lamp light induction intensity data of the street lamp by using the sensor device, and transmitting the street lamp light induction intensity data and the real-time lighting image data to be trained to the server through the ZigBee wireless communication module comprises the steps of:
the method comprises the steps of obtaining street lamp light induction intensity data of a street lamp by using a sensor device, wherein the street lamp light induction intensity data at least comprises illumination brightness data and illumination time data;
transmitting the street lamp photoinduction intensity data and the real-time lighting image data to be trained to a server through a ZigBee wireless communication module;
the sensor device and the ZigBee wireless communication module are arranged at the middle and lower positions of the street lamp pole part and are used for collecting street lamp light induction intensity data and real-time lighting image data.
3. The street lamp running state monitoring method as claimed in claim 1, wherein the establishing an initial res net convolutional neural network model based on the neural network, replacing a re lu activation function in the initial res net convolutional neural network model with a P-re lu activation function, and obtaining a target res net convolutional neural network model comprises:
establishing an initial ResNet convolutional neural network model based on a convolutional neural network, wherein the initial ResNet convolutional neural network model at least comprises an input layer, a convolutional calculation layer, a ReLU activation layer, a pooling layer and a full connection layer;
replacing a ReLU activation function in the initial ResNet convolutional neural network model with a P-ReLU activation function;
adding batch normalization after each convolution layer in the initial ResNet convolution neural network model;
and replacing an SGD random gradient descent algorithm in the initial ResNet convolutional neural network model by using an Adam optimization algorithm to obtain a target ResNet convolutional neural network model.
4. The method for monitoring the running state of the street lamp according to claim 1, wherein the step of inputting the real-time lighting image data to be trained into the target ResNet convolutional neural network model for training to obtain the real-time state data of the street lamp comprises the following steps:
inputting the real-time lighting image data to be trained into the target ResNet convolutional neural network model for training to obtain real-time state data of the street lamp;
the street lamp real-time state data at least comprises a full brightness street lamp, a moderate brightness street lamp, a flash brightness street lamp and a full non-brightness street lamp.
5. The method for monitoring the operation state of a street lamp according to claim 1, wherein the step of creating a street lamp maintenance measure database, judging the state of the street lamp according to the real-time state data of the street lamp and the light induction intensity data of the street lamp, and if the street lamp is the street lamp in the state to be maintained, generating a street lamp maintenance measure according to the street lamp maintenance measure database, and sending the street lamp maintenance measure to a server for early warning, comprises:
the method comprises the steps of collecting street lamp historical maintenance data of street lamps in a server and street lamp reference maintenance data in an Internet database through a data acquisition module;
clustering the historical maintenance data of the street lamp and the reference maintenance data of the street lamp by using an FCM fuzzy clustering algorithm to obtain a street lamp maintenance measure database;
if the real-time state of the street lamp is completely not on, and the illumination brightness data and the illumination time data in the street lamp light induction intensity data of the corresponding street lamp are both 0, the street lamp is judged to be the street lamp in the state to be maintained;
if the real-time state of the street lamp is a flashing street lamp, and the illumination brightness data and the illumination time data in the street lamp light induction intensity data of the corresponding street lamp are less than 50%, the street lamp is judged to be a street lamp in a state to be maintained;
generating street lamp maintenance measures for the street lamp in the state to be maintained according to the street lamp maintenance measure database, and sending the street lamp maintenance measures to a server for early warning.
6. The method for monitoring the operation state of a street lamp according to claim 1, wherein if the street lamp is a street lamp in a state to be overhauled, monitoring the street lamp in the state to be overhauled through a sensor device comprises:
if the real-time state of the street lamp is a full brightness street lamp, and the illumination brightness data and the illumination time data in the street lamp light induction intensity data of the corresponding street lamp are both 100%, judging the street lamp as a healthy street lamp;
if the real-time state of the street lamp is a moderate brightness street lamp and the illumination brightness data and the illumination time data in the street lamp light induction intensity data of the corresponding street lamp are 80%, the street lamp is judged to be a street lamp in a state to be overhauled;
monitoring the street lamp in the state to be overhauled through the sensor device, and if the illumination brightness data and the illumination time data in the street lamp photoinduction intensity data are reduced, carrying out early warning on the server;
if the real-time state of the street lamp in the state to be overhauled is changed into the state that the street lamp is not lightened completely, generating street lamp maintenance measures according to a street lamp maintenance measure database, and sending the street lamp maintenance measures to a server for early warning.
7. The street lamp running state monitoring system is characterized by comprising the following modules:
the data acquisition module is used for acquiring real-time lighting image data of the street lamp through the sensor device, and the sensor device at least comprises an image acquisition sensor, a light induction intensity sensor and a temperature sensor; acquiring real-time lighting image data, and adjusting the real-time lighting image data into image data with the same size to obtain a lighting image data set; performing image processing on the bright light image dataset by using an image contrast enhancement, histogram equalization and fuzzy processing method to obtain a target image dataset; classifying the target image data set based on an SVM image classifier, and clustering the target image data set by using a hierarchical clustering algorithm; calculating a similarity matrix of the target image data set to obtain a similarity matrix image data set; acquiring all image samples according to the similarity matrix image data set, and determining cluster image data according to all the image samples; combining the two cluster image data with the highest similarity to obtain cluster image data; merging and terminating when the number of the cluster image data is 1, so as to obtain real-time lighting image data to be trained;
the data transmission module is used for acquiring street lamp light induction intensity data of the street lamp by utilizing the sensor device, and transmitting the street lamp light induction intensity data and the real-time lighting image data to be trained to a server through the ZigBee wireless communication module;
the model building module is used for building an initial ResNet convolutional neural network model based on the neural network, and processing the initial ResNet convolutional neural network model based on the RAdam algorithm optimizer to obtain a target ResNet convolutional neural network model;
the model training module is used for inputting the real-time lighting image data to be trained into the target ResNet convolutional neural network model for training to obtain real-time state data of the street lamp;
the maintenance early warning module is used for establishing a street lamp maintenance measure database, judging the state of the street lamp according to the real-time state data and the light induction intensity data of the street lamp, generating street lamp maintenance measures according to the street lamp maintenance measure database when the street lamp is the street lamp in the state to be maintained, and sending the street lamp maintenance measures to a server for early warning;
and the street lamp monitoring module is used for monitoring the street lamp in the state to be overhauled through the sensor device if the street lamp is in the state to be overhauled.
8. The streetlamp operational state monitoring system of claim 7, wherein the maintenance pre-warning module comprises the following sub-modules:
the collecting sub-module is used for collecting the street lamp historical maintenance data of the street lamp in the server and the street lamp reference maintenance data in the Internet database through the data collecting module;
the clustering sub-module is used for clustering the street lamp historical maintenance data and the street lamp reference maintenance data by using an FCM fuzzy clustering algorithm to obtain a street lamp maintenance measure database;
the first judging submodule is used for judging the street lamp as the street lamp in a state to be maintained if the street lamp is not lightened completely in a real-time state and the illumination brightness data and the illumination time data in the street lamp light induction intensity data of the corresponding street lamp are both 0;
the second judging sub-module is used for judging the street lamp as the street lamp in the state to be maintained if the real-time state of the street lamp is a flashing street lamp and the illumination brightness data and the illumination time data in the street lamp light induction intensity data of the corresponding street lamp are less than 50 percent;
and the early warning sub-module is used for generating street lamp maintenance measures for the street lamp in the state to be maintained according to the street lamp maintenance measure database, and sending the street lamp maintenance measures to a server for early warning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311307099.5A CN117057784B (en) | 2023-10-10 | 2023-10-10 | Street lamp running state monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311307099.5A CN117057784B (en) | 2023-10-10 | 2023-10-10 | Street lamp running state monitoring method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117057784A CN117057784A (en) | 2023-11-14 |
| CN117057784B true CN117057784B (en) | 2024-01-30 |
Family
ID=88664761
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311307099.5A Active CN117057784B (en) | 2023-10-10 | 2023-10-10 | Street lamp running state monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117057784B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107484312A (en) * | 2017-08-22 | 2017-12-15 | 姚静洁 | A kind of intelligent street lamp control system |
| CN114118129A (en) * | 2021-10-26 | 2022-03-01 | 上海市区电力照明工程有限公司 | Method for detecting urban lighting facilities |
| CN116406056A (en) * | 2023-02-21 | 2023-07-07 | 暨南大学 | Street lamp control method and device based on IA-YOLO target detection |
| CN116503817A (en) * | 2023-03-20 | 2023-07-28 | 上海三思电子工程有限公司 | Street lamp illumination monitoring method, system, terminal, medium and illumination system based on image recognition |
| CN116600446A (en) * | 2023-07-17 | 2023-08-15 | 智隆(广州)网络科技有限公司 | Intelligent street lamp system based on Internet of things technology |
| CN116721095A (en) * | 2023-08-04 | 2023-09-08 | 杭州瑞琦信息技术有限公司 | Aerial photographing road illumination fault detection method and device |
| CN116736734A (en) * | 2023-08-08 | 2023-09-12 | 深圳小米房产网络科技有限公司 | Intelligent household equipment control method and system based on sensing network |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200051038A1 (en) * | 2017-03-28 | 2020-02-13 | Signify Holding B.V. | Calibration of cloud-based information for lifetime prediction of luminaires |
-
2023
- 2023-10-10 CN CN202311307099.5A patent/CN117057784B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107484312A (en) * | 2017-08-22 | 2017-12-15 | 姚静洁 | A kind of intelligent street lamp control system |
| CN114118129A (en) * | 2021-10-26 | 2022-03-01 | 上海市区电力照明工程有限公司 | Method for detecting urban lighting facilities |
| CN116406056A (en) * | 2023-02-21 | 2023-07-07 | 暨南大学 | Street lamp control method and device based on IA-YOLO target detection |
| CN116503817A (en) * | 2023-03-20 | 2023-07-28 | 上海三思电子工程有限公司 | Street lamp illumination monitoring method, system, terminal, medium and illumination system based on image recognition |
| CN116600446A (en) * | 2023-07-17 | 2023-08-15 | 智隆(广州)网络科技有限公司 | Intelligent street lamp system based on Internet of things technology |
| CN116721095A (en) * | 2023-08-04 | 2023-09-08 | 杭州瑞琦信息技术有限公司 | Aerial photographing road illumination fault detection method and device |
| CN116736734A (en) * | 2023-08-08 | 2023-09-12 | 深圳小米房产网络科技有限公司 | Intelligent household equipment control method and system based on sensing network |
Non-Patent Citations (1)
| Title |
|---|
| 基于ZigBee的自适应智慧路灯系统的设计与实现;陶奉春;陶皖;欧坤;;佳木斯大学学报(自然科学版)(03);正文第140-143, 170页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117057784A (en) | 2023-11-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112557598B (en) | Urban air quality monitoring and management method based on Internet of things | |
| KR102127080B1 (en) | Smart street lamp control system using lora communication | |
| CN113012428B (en) | Big data analysis processing method and system based on terminal | |
| CN107450439B (en) | A kind of street lamp intelligent failure diagnosis method | |
| CN116168356B (en) | Vehicle damage judging method based on computer vision | |
| CN112738959A (en) | Urban road street lamp energy saving and emission reduction control system based on smart city | |
| CN117057784B (en) | Street lamp running state monitoring method and system | |
| CN116884266A (en) | Smart city parking management method and management system based on big data | |
| CN116311028B (en) | Guardrail control method and system based on Internet of things | |
| CN117082701A (en) | LED lighting control system based on wireless technology | |
| CN113505346B (en) | Urban street lamp data processing and combined regulation and control system based on artificial intelligence | |
| CN109635345B (en) | Lighting device early warning method based on cloud computing | |
| CN115857385A (en) | Sewage early warning and treatment analysis system based on Internet of things and deep learning | |
| CN115471132A (en) | Street lamp inspection method for municipal engineering of smart city | |
| CN115493642A (en) | Road environment detection system of intelligent networked automobile | |
| CN111914493B (en) | System and method for simulating service life of LED street lamp | |
| CN103984960B (en) | A kind of remote sensing images sample intelligent acquisition method | |
| Gao et al. | Detection method of potholes on highway pavement based on yolov5 | |
| Ashokkumar et al. | A Literature Survey on Artificial Intelligence-Based Smart City Automation Using LoRa and IOT for Street Lights and Air Quality Check | |
| Tang et al. | An Intelligent Fault Diagnosis Method for Street Lamps | |
| CN116193666B (en) | LED lamp control method and system | |
| CN115327675B (en) | Method, system, equipment and storage medium for monitoring running state of meteorological equipment | |
| Srinivasan et al. | Safety evaluation of converting traffic signals from incandescent to led bulbs | |
| CN116321608A (en) | Intelligent illumination control method based on road detection | |
| CN114364080A (en) | Expressway tunnel illumination carbon emission prediction model |
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 |