CN115588265B - Intelligent monitoring system of wind power plant - Google Patents
Intelligent monitoring system of wind power plant Download PDFInfo
- Publication number
- CN115588265B CN115588265B CN202211588773.7A CN202211588773A CN115588265B CN 115588265 B CN115588265 B CN 115588265B CN 202211588773 A CN202211588773 A CN 202211588773A CN 115588265 B CN115588265 B CN 115588265B
- Authority
- CN
- China
- Prior art keywords
- fan
- image
- power plant
- neural network
- wind power
- 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
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The embodiment of the present specification provides an intelligent monitoring system for a wind power plant, which belongs to the field of wind power generation and comprises: the sensing layer is characterized in that a first data acquisition unit of the sensing layer is used for acquiring image data of a wind power plant, a second data acquisition unit is used for acquiring image data inside a fan, and a third data acquisition unit is used for acquiring image data of a booster station; the platform layer is used for judging whether the wind power plant is invaded or not through the first convolutional neural network model, judging whether the state of electrical equipment inside the fan is abnormal or not through the second convolutional neural network model and judging whether the operation of operators inside the fan is safe or not; judging whether the state of the electrical equipment of the booster station is abnormal or not and judging whether the operation of the operator of the booster station is safe or not through a third convolutional neural network model; and the application layer is used for visualizing the judgment result and sending out warning information according to the judgment result, and has the advantage of ensuring the real-time property and the accuracy of detection.
Description
Technical Field
The specification relates to the field of wind power generation, in particular to an intelligent monitoring system of a wind power plant.
Background
The main technical scheme of equipment monitoring of the current wind power plant is that a common video monitoring system and various sensors are installed in each area or equipment of the wind power plant, and whether the equipment has defects or not is analyzed and judged by checking real-time videos and monitoring data changes of the various sensors by operating personnel. However, because the wind power plant needs more video monitoring devices, the video picture of each device occupies a small part on the display screen, and the operator cannot clearly monitor the video picture of each device in real time, so that the labor intensity of the operator is high; furthermore, many factors for uncontrollable human behaviors indicate that it is difficult for a human to keep high attention to a still picture for a long time, and generally, after staring at the monitoring picture for 20 minutes, a monitor cannot see more than 95% of activity information in the monitoring picture. Therefore, equipment failure and abnormality are easy to occur, and people cannot find the equipment failure and abnormality in time.
Therefore, an intelligent monitoring system for a wind power plant is needed, which is used for automatically realizing intelligent detection on station safety, personnel safety and equipment operation through a convolutional neural network model, and ensuring the real-time performance and accuracy of the detection.
Disclosure of Invention
In order to solve the technical problems that in the prior art, by manually checking real-time videos and monitoring data changes of various sensors, whether equipment has defects is analyzed and judged, the efficiency is low, and misjudgment are easy to occur, one of the embodiments of the present specification provides an intelligent monitoring system for a wind power plant, which includes: the sensing layer comprises a first data acquisition unit, a second data acquisition unit and a third data acquisition unit, wherein the first data acquisition unit is used for acquiring image data of a wind power plant, the second data acquisition unit is used for acquiring image data inside a fan, and the third data acquisition unit is used for acquiring image data of a booster station; the platform layer is used for judging whether the wind power plant is invaded or not based on the image data of the wind power plant through a first convolutional neural network model, and is also used for judging whether the state of the electrical equipment inside the fan is abnormal or not and judging whether the operation of the operating personnel inside the fan is safe or not based on the image data inside the fan through a second convolutional neural network model; the system is also used for judging whether the state of the electrical equipment of the booster station is abnormal or not and judging whether the operation of the operator of the booster station is safe or not based on the image data of the booster station through a third convolutional neural network model; and the application layer is used for visualizing the judgment results of the first convolutional neural network model, the second convolutional neural network model and the third convolutional neural network model and sending out warning information according to the judgment results of the first convolutional neural network model, the second convolutional neural network model and the third convolutional neural network model.
It can be understood that, the intelligent monitoring system of the wind farm judges whether the wind farm is invaded or not based on the image data of the wind farm through the first convolutional neural network model, judges whether the state of the electrical equipment inside the fan is abnormal or not and judges whether the operation of the operator inside the fan is safe or not based on the image data inside the fan through the second convolutional neural network model, judges whether the state of the electrical equipment of the booster station is abnormal or not and judges whether the operation of the operator of the booster station is safe or not based on the image data of the booster station through the third convolutional neural network model, does not need to manually continue the judgment of whether the wind farm is invaded or not, whether the state of the electrical equipment inside the fan is abnormal or not, whether the operation of the operator of the booster station is safe or not, is higher in real-time performance and higher in accuracy.
In some embodiments, the first data collecting unit comprises a plurality of living body sensing devices, at least one total image collecting device and a plurality of partial image collecting devices, wherein the plurality of living body sensing devices and the plurality of partial image collecting devices are respectively arranged at different positions of the wind power plant, the partial image collecting devices are used for acquiring local images of a target area of the wind power plant, and the at least one total image collecting device is used for acquiring an overall image of the target area of the wind power plant; the first data acquisition unit collects image data of a wind power plant, and comprises: judging whether living bodies exist in the wind power plant or not according to output signals of the living body sensing devices; if the living body does not exist in the wind power plant, the at least one total image acquisition device acquires an overall image of a target area of the wind power plant according to a first image acquisition frequency; and if the living body exists in the wind power plant, the at least one general image acquisition device acquires the whole image of the target area of the wind power plant according to a second image acquisition frequency, wherein the second image acquisition frequency is greater than the first image acquisition frequency.
In some embodiments, the first convolutional neural network model determining whether the wind power plant is intruded based on the image data of the wind power plant comprises: the first convolution neural network model judges whether a human body exists in a target area of the wind power plant based on an overall image of the target area of the wind power plant; when the first convolution neural network model judges that a human body exists in the target area of the wind power plant, determining the position of the human body based on the whole image of the target area of the wind power plant; the first data acquisition unit collects image data of a wind power plant, and comprises: when the first convolution neural network model judges that a human body exists in the target area of the wind power plant based on the whole image of the target area of the wind power plant, determining a target partial image acquisition device from the plurality of partial image acquisition devices based on the position of the human body and/or the output signals of the plurality of living body induction devices; the target sub-image acquisition device acquires a local image of the target area; first convolution neural network model is based on the image data judgement of wind power plant whether the invasion takes place for the wind power plant still includes: and carrying out face recognition on the human body according to the local image of the target area, and judging whether the wind power plant is invaded or not based on a face recognition result.
In some embodiments, the first convolutional neural network model determines whether the wind power plant is invaded based on the image data of the wind power plant, further comprising: and the first convolution neural network model judges whether the wind power plant is not invaded based on the face recognition result, and identifies the wearing of the human body based on the local image of the target area to judge whether the wearing of the human body meets the preset requirement.
In some embodiments, the second data acquisition unit includes a thermal infrared imager, an operation parameter acquisition device, and an image acquisition device inside the fan, where the thermal infrared imager is configured to acquire a thermal infrared image of electrical equipment inside the fan, the operation parameter acquisition device is configured to acquire an operation parameter of the electrical equipment inside the fan, and the image acquisition device inside the fan is configured to acquire an environment image inside the fan; the second data acquisition unit acquires image data inside the fan, wherein the image data includes historical operation data of electrical equipment inside the fan, and the historical operation data includes thermal infrared images, operation parameters and environment images inside the fan of the electrical equipment inside the fan at a plurality of historical time points; training based on the historical operating data to obtain a fault prediction model; the fault prediction model determines an operation risk value of the interior of the fan at the current time point based on a thermal infrared image of the electrical equipment in the fan acquired by the infrared thermal imager at the current time point, the operation parameters of the electrical equipment in the fan acquired by the operation parameter acquisition device at the current time point and an environment image of the interior of the fan acquired by the image acquisition device in the fan at the current time point; and adjusting the data acquisition frequency of the thermal infrared imager, the operation parameter acquisition device and the fan internal image acquisition device according to the operation risk value of the fan internal at the current time point.
In some embodiments, the second convolutional neural network model determining whether the state of the electrical device inside the wind turbine is abnormal based on the image data inside the wind turbine includes: the second convolutional neural network model judges whether the state of the electrical equipment inside the fan is abnormal or not based on the thermal infrared image of the electrical equipment inside the fan, which is acquired by the infrared thermal imager at the current time point, the operating parameters of the electrical equipment inside the fan, which are acquired by the operating parameter acquisition device at the current time point, and the environment image of the electrical equipment inside the fan, which is acquired by the image acquisition device inside the fan at the current time point.
In some embodiments, the second data acquisition device further comprises an operation and maintenance image acquisition device arranged on a safety helmet and used for acquiring operation images of operators inside the fan; the second convolutional neural network model judges whether the operation of the operating personnel in the fan is safe or not based on the image data in the fan, and the method comprises the following steps: the second convolutional neural network model determines a risk area inside the fan based on a thermal infrared image of the electrical equipment inside the fan, which is acquired by the infrared thermal imager at the current time point, the operating parameters of the electrical equipment inside the fan, which are acquired by the operating parameter acquisition device at the current time point, and an environment image inside the fan, which is acquired by the fan inside image acquisition device at the current time point; the second convolutional neural network model judges whether the operating personnel in the fan is located in a risk area or not based on the environment image in the fan, which is acquired by the fan internal image acquisition device at the current time point, the operating image of the operating personnel in the fan, which is acquired by the operation and maintenance image acquisition device, and the risk area in the fan; the second convolution neural network model judges whether the wearing of the operating personnel in the fan meets preset requirements or not based on the environment image in the fan acquired by the image acquisition device in the fan at the current time point and the operation image of the operating personnel in the fan acquired by the operation and maintenance image acquisition device.
In some embodiments, the second data acquisition unit further comprises a blade image acquisition device for acquiring an image of a blade of the wind turbine; the second data acquisition unit is further used for predicting the icing thickness of the blades of the fan in a future time period; the second data acquisition unit is further used for starting the blade image acquisition device to acquire the image of the blade of the fan when the predicted icing thickness of the blade of the fan in the future time period is greater than the icing thickness threshold.
In some embodiments, the second data acquisition unit predicts an icing thickness of a blade of the wind turbine over a future time period, comprising: determining meteorological element forecast data of the wind power plant based on a numerical forecast product and micro-terrain data; correcting meteorological element forecast data of the wind power plant based on the height of the blade, and determining the corrected meteorological element forecast data; and predicting the icing thickness of the blades of the fan in a future time period based on the corrected meteorological element forecast data.
In some embodiments, the third convolutional neural network model determining whether a state of an electrical device of the booster station is abnormal and determining whether an operation of an operator of the booster station is safe based on the image data of the booster station includes: and the third convolutional neural network model is based on an SSD algorithm, and is used for judging whether the state of the electrical equipment of the booster station is abnormal or not and judging whether the operation of the operator of the booster station is safe or not according to the image data of the booster station.
The invention has the beneficial effects that:
1. whether the wind power plant invades or not is judged on the basis of image data of the wind power plant through the first convolutional neural network model, whether the state of electrical equipment inside the fan is abnormal or not and whether the operation of an operator inside the fan is safe or not is judged on the basis of the image data inside the fan through the second convolutional neural network model, whether the state of the electrical equipment of the booster station is abnormal or not and whether the operation of the operator of the booster station is safe or not are judged on the basis of the image data of the booster station through the third convolutional neural network model, and whether the wind power plant invades or not, whether the state of the electrical equipment inside the fan is abnormal or not, whether the operation of the operator inside the fan is safe or not, whether the state of the electrical equipment of the booster station is abnormal or not and whether the operation of the operator of the booster station is safe or not are judged without manual continuation, so that the real-time performance is higher, and the accuracy is higher;
2. the image and video data are fully utilized, the integrated intelligent monitoring of the wind power plant is realized, and the working efficiency of operators on duty is improved;
3. an SSD algorithm based on a convolutional neural network is utilized to carry out an intelligent detection method for field station safety, personnel safety and equipment operation, so that the real-time performance and the accuracy rate of detection are ensured;
4. training the model by using a plurality of data enhancement methods, and improving the generalization performance and detection precision of the SSD algorithm;
5. and the detected historical result is fed back to the SSD algorithm by combining an online learning method, so that the accuracy and the robustness of the SSD algorithm are improved by continuously learning.
Drawings
The present description will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and in these embodiments like numerals are used to indicate like structures, wherein:
FIG. 1 is a block schematic diagram of an intelligent monitoring system for a wind farm according to some embodiments herein;
FIG. 2 is a schematic flow diagram of a first data acquisition unit acquiring image data of a wind power plant in accordance with some embodiments described herein;
FIG. 3 is a schematic flow chart illustrating a second data acquisition unit acquiring image data of an interior of a wind turbine according to some embodiments of the present disclosure.
Detailed Description
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only examples or embodiments of the present description, and that for a person skilled in the art, the present description can also be applied to other similar scenarios on the basis of these drawings without inventive effort. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.
It should be understood that "system," "device," "unit," and/or "module" as used herein is a method for distinguishing between different components, elements, parts, portions, or assemblies of different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.
As used in this specification and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.
Flow charts are used in this description to illustrate operations performed by a system according to embodiments of the present description. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.
FIG. 1 is a block schematic diagram of an intelligent monitoring system for a wind farm, as shown in FIG. 1, which may include a perception layer, a platform layer, and an application layer, according to some embodiments herein. The following describes the sensing layer, the platform layer, and the application layer in this order.
As shown in fig. 1, the sensing layer may include a first data acquisition unit, a second data acquisition unit, and a third data acquisition unit, where the first data acquisition unit is configured to acquire image data of a wind power plant, the second data acquisition unit is configured to acquire image data inside a wind turbine, and the third data acquisition unit is configured to acquire image data of a booster station.
In some embodiments, the first data collecting unit may include a plurality of living body sensing devices, at least one total image collecting device, and a plurality of partial image collecting devices, wherein the plurality of living body sensing devices and the plurality of partial image collecting devices are respectively disposed at different positions of the wind power plant, the partial image collecting devices are configured to obtain a partial image of a target area of the wind power plant, and the at least one total image collecting device is configured to obtain an overall image of the target area of the wind power plant.
Wherein the target area may be an area of the wind power plant where access by persons other than staff of the wind power plant is forbidden.
In some embodiments, the living body sensing device may include an infrared pyroelectric sensor.
Fig. 2 is a schematic flow chart illustrating a first data acquisition unit acquiring image data of a wind power plant according to some embodiments of the present disclosure, and as shown in fig. 2, in some embodiments, the first data acquisition unit acquiring image data of the wind power plant may include:
judging whether living bodies exist in the wind power plant or not according to output signals of the living body sensing devices;
if the living body does not exist in the wind power plant, at least one total image acquisition device acquires an overall image of a target area of the wind power plant according to a first image acquisition frequency;
and if the living body exists in the wind power plant, at least one total image acquisition device acquires the whole image of the target area of the wind power plant according to the second image acquisition frequency.
Wherein the second image acquisition frequency is greater than the first image acquisition frequency.
It is understood that when a living body is sensed by the at least one living body sensing device, the first data collection unit may determine whether a living body is present in the wind power plant.
In some embodiments, when the living body sensing device senses that a living body exists in the wind power plant, the collection frequency of the total image collection device is increased, more overall images of a target area can be obtained in a short time, and the real-time performance of judging whether the wind power plant invades is improved.
The platform layer may be configured to determine whether the wind power plant is intruded based on image data of the wind power plant through the first convolutional neural network model.
The first convolutional neural network model may comprise a ResNext-50 network.
In some embodiments, the first convolutional neural network model determines whether the wind power plant is invaded based on the image data of the wind power plant, including:
the first convolution neural network model judges whether a human body exists in a target area of the wind power plant or not based on an overall image of the target area of the wind power plant;
when the first convolution neural network model judges that a human body exists in a target area of the wind power plant, the position of the human body is determined based on an overall image of the target area of the wind power plant.
In some embodiments, a first data acquisition unit acquires image data of a wind power plant, comprising:
when the first convolution neural network model judges that a human body exists in a target area of the wind power plant based on an overall image of the target area of the wind power plant, determining target partial image acquisition devices from a plurality of partial image acquisition devices based on positions of the human body and/or output signals of a plurality of living body induction devices;
the target sub-image acquisition device acquires a local image of a target area;
in some embodiments, the first data collecting unit may use a partial image collecting device near a living body sensing device sensing a living body as the target partial image collecting device, or a partial image collecting device near a position of a human body determined by the first convolution neural network model based on an overall image of a target area of the wind power plant as the target partial image collecting device.
In some embodiments, the first convolutional neural network model determines whether the wind power plant is invaded based on the image data of the wind power plant, further comprising:
and carrying out face recognition on a human body according to the local image of the target area, and judging whether the wind power plant is invaded or not based on a face recognition result.
In some embodiments, the first convolutional neural network model may extract a face image from a local image of the target region, perform face recognition on the face image, and determine that the wind power plant is not invaded when the face is recognized as an image of a worker of the wind power plant; and when the face is not the image of the staff of the wind power plant, judging that the wind power plant is invaded.
According to the method, the target sub-image acquisition devices which are closer to the human body are determined from the plurality of sub-image acquisition devices based on the position of the human body and/or the output signals of the plurality of living body induction devices, the human face images of the human body are acquired more clearly through the target sub-image acquisition devices, and the accuracy of judging whether the wind power plant invades or not is improved.
In some embodiments, the first convolutional neural network model determines whether the wind power plant is invaded based on the image data of the wind power plant, further comprising:
when the first convolution neural network model judges that the wind power plant is not invaded based on the face recognition result, the wearing of the human body is recognized based on the local image of the target area, and whether the wearing of the human body meets the preset requirement is judged.
In some embodiments, the first convolutional neural network model may identify wearing of the human body based on the local image of the target region, determine whether the human body wears the work clothes and the safety helmet, and when the human body does not wear the work clothes and/or the safety helmet, the wearing of the human body does not meet the preset requirement.
In some embodiments, the second data collecting unit includes a thermal infrared imager, an operation parameter collecting device, and an internal fan image collecting device, where the thermal infrared imager is configured to obtain a thermal infrared image of the electrical device inside the fan, the operation parameter collecting device is configured to obtain an operation parameter (e.g., current, voltage, etc.) of the electrical device inside the fan, and the internal fan image collecting device is configured to obtain an environmental image inside the fan.
Fig. 3 is a schematic flow chart illustrating the second data acquisition unit acquiring image data of the interior of the wind turbine according to some embodiments of the present description, and as shown in fig. 3, in some embodiments, the second data acquisition unit acquires image data of the interior of the wind turbine, including,
acquiring historical operation data of electrical equipment inside the fan, wherein the historical operation data comprises thermal infrared images, operation parameters and environment images inside the fan of the electrical equipment inside the fan at a plurality of historical time points;
training based on historical operating data to obtain a fault prediction model;
the fault prediction model determines an operation risk value of the interior of the fan at the current time point based on a thermal infrared image of electrical equipment in the fan, which is acquired by an infrared thermal imager at the current time point, operation parameters of the electrical equipment in the fan, which are acquired by an operation parameter acquisition device at the current time point, and an environment image of the interior of the fan, which is acquired by the fan interior image acquisition device at the current time point;
and adjusting the data acquisition frequency of the thermal infrared imager, the operation parameter acquisition device and the fan internal image acquisition device according to the operation risk value of the fan internal at the current time point.
The failure prediction model may be one of a Convolutional Neural Network (CNN), a Deep Neural Network (DNN), a Recurrent Neural Network (RNN), a multi-layer neural network (MLP), a antagonistic neural network (GAN), or any combination thereof.
In some embodiments, the second data collecting unit may generate a plurality of training samples according to the historical operating data, the training samples may include thermal infrared images, operating parameters, and environmental images of the interior of the wind turbine at a historical time point of the electrical device of the interior of the wind turbine, and the label of the training sample may be an operating risk value of the electrical device of the interior of the wind turbine at the historical time point.
In some embodiments, the data acquisition frequency of the thermal infrared imager, the operation parameter acquisition device and the fan interior image acquisition device increases with an increase in the operation risk value of the fan interior at the current time point.
It can be understood that the data acquisition frequency of the thermal infrared imager, the operation parameter acquisition device and the fan internal image acquisition device is set to increase along with the increase of the operation risk value of the fan internal at the current time point, so that when the electric equipment in the fan breaks down with a high probability, the thermal infrared image of the electric equipment in the fan internal, the operation parameters of the electric equipment in the fan internal and the environment image in the fan internal can be acquired more frequently, and the second convolutional neural network model can judge the state of the electric equipment in the fan internal in real time.
The platform layer can also be used for judging whether the state of the electrical equipment in the fan is abnormal or not and judging whether the operation of the operating personnel in the fan is safe or not on the basis of the image data in the fan through the second convolutional neural network model.
In some embodiments, the second convolutional neural network model determining whether the state of the electrical device inside the wind turbine is abnormal based on the image data inside the wind turbine includes:
the second convolution neural network model judges whether the state of the electrical equipment inside the fan is abnormal or not based on the thermal infrared image of the electrical equipment inside the fan, which is acquired by the infrared thermal imager at the current time point, the operation parameters of the electrical equipment inside the fan, which are acquired by the operation parameter acquisition device at the current time point, and the environment image of the electrical equipment inside the fan, which is acquired by the fan inside image acquisition device at the current time point.
In some embodiments, the second convolutional neural network model may determine the temperature of the electrical device inside the wind turbine based on a thermal infrared image of the electrical device inside the wind turbine, and may determine whether smoke or flame exists inside the wind turbine based on an environment image inside the wind turbine, determine whether the voltage and current parameters of the electrical device inside the wind turbine are within an allowable range according to the operating parameters of the electrical device inside the wind turbine, and determine that the state of the electrical device inside the wind turbine is abnormal when the temperature of the electrical device inside the wind turbine is greater than a temperature threshold, smoke or flame exists inside the wind turbine, and the voltage and current parameters of the electrical device inside the wind turbine are not within the allowable range.
In some embodiments, the second data acquisition device further comprises an operation and maintenance image acquisition device arranged on the safety helmet and used for acquiring operation images of operators inside the fan. When the safety helmet is worn, the operation and maintenance image acquisition device on the safety helmet is opened to acquire the operation images of the operating personnel in the fan.
In some embodiments, the second convolutional neural network model determines whether the operation of the worker inside the wind turbine is safe based on the image data inside the wind turbine, including:
the second convolution neural network model determines a risk area inside the fan based on a thermal infrared image of the electrical equipment inside the fan, which is acquired by the infrared thermal imager at the current time point, the operation parameters of the electrical equipment inside the fan, which are acquired by the operation parameter acquisition device at the current time point, and an environment image inside the fan, which is acquired by the fan inside image acquisition device at the current time point;
the second convolutional neural network model judges whether the operating personnel in the fan is located in the risk area or not based on the environment image in the fan, which is acquired by the fan internal image acquisition device at the current time point, the operating image of the operating personnel in the fan, which is acquired by the operation and maintenance image acquisition device, and the risk area in the fan;
the second convolution neural network model judges whether the wearing of the operating personnel in the fan meets the preset requirement or not based on the environment image in the fan acquired by the image acquisition device in the fan at the current time point and the operation image of the operating personnel in the fan acquired by the operation and maintenance image acquisition device.
The risk area may be the area of a malfunctioning electrical device, the area of smoke or flames.
In some embodiments, the second convolutional neural network model determines whether the action of the operator inside the fan is a risk action based on an environment image inside the fan acquired by the fan inside image acquisition device at the current time point and an operation image of the operator inside the fan acquired by the operation and maintenance image acquisition device.
In some embodiments, when the worker inside the fan is located the risk area, the worker inside the fan is not in line with the preset requirement when wearing the fan or the worker inside the fan moves to be a risk movement, the worker inside the fan is judged to be unsafe in operation.
In some embodiments, the second data acquisition unit further comprises a blade image acquisition device for acquiring images of the blades of the wind turbine.
In some embodiments, the second data acquisition unit is further configured to predict an icing thickness of the blade of the wind turbine in a future time period, and further configured to turn on the blade image acquisition device to acquire the image of the blade of the wind turbine when the predicted icing thickness of the blade of the wind turbine in the future time period is greater than an icing thickness threshold.
In some embodiments, the second data acquisition unit predicts an icing thickness of a blade of the wind turbine over a future time period, comprising:
determining meteorological element forecast data of the wind power plant based on the numerical forecast product and the micro-terrain data;
correcting meteorological element forecast data of a wind power plant based on the height of the blade, and determining the corrected meteorological element forecast data;
and predicting the icing thickness of the blade of the fan in a future time period based on the corrected meteorological element forecast data.
The numerical forecast product may include air temperature, humidity, wind speed, precipitation, etc. of the target area over the target time period.
In some embodiments, the second data acquisition unit may modify the numerical forecasting product based on the micro-terrain data to determine meteorological element forecasting data for the wind power plant. In some embodiments, meteorological element forecast data for a wind power plant is determined by modifying a numerical forecast product based on micro-terrain data using a multivariate non-linear regression model. The dependent variable of the multivariate nonlinear regression model comprises meteorological element forecast data of a wind power plant, and the independent variable of the multivariate nonlinear regression model comprises a geographic factor in the micro-terrain data. The multivariate nonlinear regression model can be expressed as the following formula:
wherein Z is a meteorological element,
、
、
、
、
、
and
as a function of the number of the coefficients,
elevation, A is the slope direction, and B is the slope.
In some embodiments, the second data collecting unit may establish a corresponding relationship between the height of the blade and the corrected meteorological element forecast data according to the historical data, correct the meteorological element forecast data of the wind power plant according to the height of the blade, and determine the corrected meteorological element forecast data.
In some embodiments, the second data acquisition unit may predict an icing thickness of the blade of the wind turbine over a future time period based on the modified meteorological element forecast data via a prediction model. The prediction model may be one of a Convolutional Neural Network (CNN), a Deep Neural Network (DNN), a Recurrent Neural Network (RNN), a multi-layer neural network (MLP), a antagonistic neural network (GAN), or any combination thereof.
It can be understood that once icing occurs on the fan blade, the performance of the wind turbine blade is changed, output of the wind turbine can be reduced, safety accidents caused by the fact that the icing falls off can also occur when the blade rotates, and the blade can be locked and shut down even when the icing is seriously coated, so that when the predicted icing thickness of the fan blade in the future time period is larger than the icing thickness threshold value, the blade image acquisition device is started to acquire images of the fan blade, and the icing condition of the fan blade is monitored in real time.
The platform layer can also be used for judging whether the state of the electrical equipment of the booster station is abnormal or not and judging whether the operation of the operator of the booster station is safe or not based on the image data of the booster station through the third convolutional neural network model.
In some embodiments, the third convolutional neural network model determining whether a state of an electrical device of the booster station is abnormal and determining whether an operation of an operator of the booster station is safe based on the image data of the booster station includes: and the third convolutional neural network model is based on an SSD algorithm, and is used for judging whether the state of the electrical equipment of the booster station is abnormal or not and judging whether the operation of the operator of the booster station is safe or not according to the image data of the booster station.
In some embodiments, the manner of determining whether the state of the electrical equipment of the booster station is abnormal and determining whether the operation of the operator of the booster station is safe based on the image data of the booster station by the third convolutional neural network model is similar to the manner of determining whether the state of the electrical equipment of the blower station is abnormal and determining whether the operation of the operator of the blower station is safe based on the image data of the blower station by the second convolutional neural network model, and more description about the manner of determining whether the state of the electrical equipment of the booster station is abnormal and determining whether the operation of the operator of the booster station is safe based on the image data of the blower station by the third convolutional neural network model may be referred to as related description of determining whether the state of the electrical equipment of the blower station is abnormal and determining whether the operation of the operator of the blower station is safe based on the image data of the blower station by the second convolutional neural network model.
The application layer can be used for visualizing the judgment results of the first convolutional neural network model, the second convolutional neural network model and the third convolutional neural network model and sending out warning information according to the judgment results of the first convolutional neural network model, the second convolutional neural network model and the third convolutional neural network model.
In some embodiments, when the wind power plant is invaded, the second convolutional neural network model judges the state of the electrical equipment inside the fan to be abnormal and/or judges the operation of the operator inside the fan to be unsafe based on the image data inside the fan, and the third convolutional neural network model judges the state of the electrical equipment of the booster station to be abnormal and/or judges the operation of the operator of the booster station to be unsafe based on the image data inside the booster station, the application layer may display warning information or send the warning information to a terminal used by the operator of the wind power plant to prompt the operator of the wind power plant to process in time.
In some embodiments, an SSD algorithm for station intrusion detection and smoke detection may be constructed for wind farm video monitoring data; and constructing an SSD algorithm for high-temperature detection of equipment, safety detection of equipment operation, safety helmet detection of operators and safety behavior detection of operators for the video data of the booster station and the video data of the fan.
In some embodiments, the SSD algorithm is constructed, and a structure suitable for intelligent monitoring of a wind farm is selected based on the learning rate and the data volume of a main network of ResNext-50 in consideration of the real-time requirement.
In some embodiments, in order to solve the problem of insufficient data volume of deep learning training, data enhancement methods such as image rotation, image inversion, contrast enhancement, brightness enhancement and the like are adopted during model training, so that the accuracy is improved.
In some embodiments, the online learning method is combined, and the detected historical result is fed back to the SSD algorithm, so that the accuracy and robustness of the SSD algorithm are improved through continuous learning.
In some embodiments, each video image may be transmitted to the SSD algorithm, to obtain detection results of the station intrusion detection, the smoke detection, the high-temperature detection of the booster station and the fan device, the device operation safety detection, the worker safety helmet detection, and the safety behavior detection, and the detection results are stored in the database.
In some embodiments, the intelligent monitoring system of the wind farm can have at least the following beneficial effects:
1. whether the wind power plant invades or not is judged on the basis of image data of the wind power plant through the first convolutional neural network model, whether the state of electrical equipment inside the fan is abnormal or not and whether the operation of an operator inside the fan is safe or not is judged on the basis of the image data inside the fan through the second convolutional neural network model, whether the state of the electrical equipment of the booster station is abnormal or not and whether the operation of the operator of the booster station is safe or not are judged on the basis of the image data of the booster station through the third convolutional neural network model, and whether the wind power plant invades or not, whether the state of the electrical equipment inside the fan is abnormal or not, whether the operation of the operator inside the fan is safe or not, whether the state of the electrical equipment of the booster station is abnormal or not and whether the operation of the operator of the booster station is safe or not are judged without manual continuation, so that the real-time performance is higher, and the accuracy is higher;
2. the image and video data are fully utilized, the integrated intelligent monitoring of the wind power plant is realized, and the working efficiency of operators on duty is improved;
3. an SSD algorithm based on a convolutional neural network is utilized to carry out an intelligent detection method for field station safety, personnel safety and equipment operation, so that the real-time performance and the accuracy rate of detection are ensured;
4. training the model by using a plurality of data enhancement methods, and improving the generalization performance and detection precision of the SSD algorithm;
5. and the detected historical result is fed back to the SSD algorithm by combining an online learning method, so that the accuracy and the robustness of the SSD algorithm are improved by continuously learning.
Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting the present specification. Various modifications, improvements and adaptations to the present description may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present specification and thus fall within the spirit and scope of the exemplary embodiments of the present specification.
Also, the description uses specific words to describe embodiments of the description. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the specification is included. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the specification may be combined as appropriate.
Additionally, the order in which the elements and sequences of the process are recited in the specification, the use of alphanumeric characters, or other designations, is not intended to limit the order in which the processes and methods of the specification occur, unless otherwise specified in the claims. While certain presently contemplated useful embodiments of the invention have been discussed in the foregoing disclosure by way of various examples, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein described. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.
Similarly, it should be noted that in the preceding description of embodiments of the present specification, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to imply that more features than are expressly recited in a claim. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.
Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the number allows a variation of ± 20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range in some embodiments of the specification are approximations, in specific embodiments, such numerical values are set forth as precisely as possible within the practical range.
Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present disclosure. Other variations are also possible within the scope of the present description. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the present specification can be seen as consistent with the teachings of the present specification. Accordingly, the embodiments of the present description are not limited to only those embodiments explicitly described and depicted herein.
Claims (9)
1. An intelligent monitoring system for a wind farm, comprising:
the sensing layer comprises a first data acquisition unit, a second data acquisition unit and a third data acquisition unit, wherein the first data acquisition unit is used for acquiring image data of a wind power plant, the second data acquisition unit is used for acquiring image data inside a fan, and the third data acquisition unit is used for acquiring image data of a booster station;
the platform layer is used for judging whether the wind power plant is invaded or not based on the image data of the wind power plant through a first convolutional neural network model, and is also used for judging whether the state of the electrical equipment inside the fan is abnormal or not and judging whether the operation of the operating personnel inside the fan is safe or not based on the image data inside the fan through a second convolutional neural network model; the system is also used for judging whether the state of the electrical equipment of the booster station is abnormal or not and judging whether the operation of the operator of the booster station is safe or not based on the image data of the booster station through a third convolutional neural network model;
the application layer is used for visualizing the judgment results of the first convolutional neural network model, the second convolutional neural network model and the third convolutional neural network model and sending out warning information according to the judgment results of the first convolutional neural network model, the second convolutional neural network model and the third convolutional neural network model;
the second data acquisition unit comprises a thermal infrared imager, an operation parameter acquisition device and an image acquisition device in the fan, wherein the thermal infrared imager is used for acquiring a thermal infrared image of electrical equipment in the fan, the operation parameter acquisition device is used for acquiring operation parameters of the electrical equipment in the fan, and the image acquisition device in the fan is used for acquiring an environment image in the fan;
the second data acquisition unit acquires image data inside the fan, and comprises:
acquiring historical operation data of the electrical equipment inside the fan, wherein the historical operation data comprises thermal infrared images, operation parameters and environment images of the electrical equipment inside the fan at a plurality of historical time points;
training based on the historical operating data to obtain a fault prediction model;
the fault prediction model determines an operation risk value of the interior of the fan at the current time point based on a thermal infrared ray image of the electrical equipment in the fan acquired by the thermal infrared imager at the current time point, the operation parameters of the electrical equipment in the fan acquired by the operation parameter acquisition device at the current time point and an environment image of the interior of the fan acquired by the image acquisition device in the fan at the current time point;
and adjusting the data acquisition frequency of the thermal infrared imager, the operation parameter acquisition device and the fan internal image acquisition device according to the operation risk value of the fan internal at the current time point.
2. The intelligent monitoring system for a wind farm according to claim 1, wherein the first data acquisition unit comprises a plurality of living body sensing devices, at least one total image acquisition device and a plurality of partial image acquisition devices, wherein the plurality of living body sensing devices and the plurality of partial image acquisition devices are respectively arranged at different positions of the wind farm, the partial image acquisition devices are used for acquiring local images of a target area of the wind farm, and the at least one total image acquisition device is used for acquiring a whole image of the target area of the wind farm;
the first data acquisition unit collects image data of a wind power plant, and comprises:
judging whether living bodies exist in the wind power plant or not according to output signals of the living body sensing devices;
if the living body does not exist in the wind power plant, the at least one total image acquisition device acquires an overall image of a target area of the wind power plant according to a first image acquisition frequency;
and if the living body exists in the wind power plant, the at least one general image acquisition device acquires the whole image of the target area of the wind power plant according to a second image acquisition frequency, wherein the second image acquisition frequency is greater than the first image acquisition frequency.
3. The intelligent monitoring system for wind farms of claim 2, wherein the first convolutional neural network model determines whether the wind farm is intruding based on the image data of the wind farm, comprising:
the first convolution neural network model judges whether a human body exists in a target area of the wind power plant based on an overall image of the target area of the wind power plant;
when the first convolution neural network model judges that a human body exists in a target area of the wind power plant, determining the position of the human body based on an overall image of the target area of the wind power plant;
the first data acquisition unit collects image data of a wind power plant, and comprises:
when the first convolutional neural network model judges that a human body exists in the target area of the wind power plant based on the overall image of the target area of the wind power plant, determining a target partial image acquisition device from the plurality of partial image acquisition devices based on the position of the human body and/or the output signals of the plurality of living body induction devices;
the target sub-image acquisition device acquires a local image of the target area;
first convolution neural network model is based on the image data judgement of wind power plant whether the invasion takes place for the wind power plant still includes:
and carrying out face recognition on the human body according to the local image of the target area, and judging whether the wind power plant is invaded or not based on a face recognition result.
4. The intelligent monitoring system for wind farms of claim 3, wherein the first convolutional neural network model determines whether the wind farm is intruding based on the image data of the wind farm, further comprising:
and the first convolution neural network model judges whether the wind power plant is not invaded based on the face recognition result, and identifies the wearing of the human body based on the local image of the target area to judge whether the wearing of the human body meets the preset requirement.
5. The intelligent monitoring system for a wind farm according to claim 1, wherein the second convolutional neural network model judges whether the state of the electrical device inside the wind turbine is abnormal based on the image data inside the wind turbine, and comprises:
the second convolutional neural network model judges whether the state of the electrical equipment inside the fan is abnormal or not based on the thermal infrared image of the electrical equipment inside the fan, which is acquired by the thermal infrared imager at the current time point, the operating parameters of the electrical equipment inside the fan, which are acquired by the operating parameter acquisition device at the current time point, and the environment image of the electrical equipment inside the fan, which is acquired by the image acquisition device inside the fan at the current time point.
6. The intelligent monitoring system for the wind farm according to claim 1, wherein the second data acquisition unit further comprises an operation and maintenance image acquisition device arranged on a safety helmet and used for acquiring operation images of operators inside the wind turbine;
the second convolutional neural network model judges whether the operation of the operating personnel in the fan is safe or not based on the image data in the fan, and the method comprises the following steps:
the second convolutional neural network model determines a risk area inside the fan based on a thermal infrared image of the electrical equipment inside the fan, which is acquired by the thermal infrared imager at the current time point, the operating parameters of the electrical equipment inside the fan, which are acquired by the operating parameter acquisition device at the current time point, and an environment image inside the fan, which is acquired by the fan internal image acquisition device at the current time point;
the second convolutional neural network model judges whether the operating personnel in the fan is located in a risk area or not based on the environment image in the fan, which is acquired by the fan internal image acquisition device at the current time point, the operating image of the operating personnel in the fan, which is acquired by the operation and maintenance image acquisition device, and the risk area in the fan;
the second convolutional neural network model judges whether the wearing of the operating personnel in the fan meets preset requirements or not based on the environment image in the fan acquired by the image acquisition device in the fan at the current time point and the operation image of the operating personnel in the fan acquired by the operation and maintenance image acquisition device.
7. The intelligent monitoring system for a wind farm according to claim 1, wherein the second data acquisition unit further comprises a blade image acquisition device for acquiring images of blades of the wind turbine;
the second data acquisition unit is further used for predicting the icing thickness of the blades of the fan in a future time period;
the second data acquisition unit is further used for starting the blade image acquisition device to acquire an image of the blade of the fan when the predicted icing thickness of the blade of the fan in the future time period is greater than the icing thickness threshold.
8. The intelligent monitoring system for a wind farm according to claim 7, wherein the second data acquisition unit predicts an icing thickness of blades of the wind turbine over a future time period comprising:
determining meteorological element forecast data of the wind power plant based on a numerical forecast product and micro-terrain data;
correcting meteorological element forecast data of the wind power plant based on the height of the blade, and determining the corrected meteorological element forecast data;
and predicting the icing thickness of the blades of the fan in a future time period based on the corrected meteorological element forecast data.
9. The intelligent monitoring system for a wind farm according to any one of claims 1 to 4, wherein the third convolutional neural network model judges whether or not the state of the electrical device of the booster station is abnormal and whether or not the work of the worker of the booster station is safe based on the image data of the booster station, and comprises:
and the third convolutional neural network model is based on an SSD algorithm, and is used for judging whether the state of the electrical equipment of the booster station is abnormal or not and judging whether the operation of the operator of the booster station is safe or not according to the image data of the booster station.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211588773.7A CN115588265B (en) | 2022-12-12 | 2022-12-12 | Intelligent monitoring system of wind power plant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211588773.7A CN115588265B (en) | 2022-12-12 | 2022-12-12 | Intelligent monitoring system of wind power plant |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115588265A CN115588265A (en) | 2023-01-10 |
| CN115588265B true CN115588265B (en) | 2023-04-07 |
Family
ID=84783194
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211588773.7A Active CN115588265B (en) | 2022-12-12 | 2022-12-12 | Intelligent monitoring system of wind power plant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115588265B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105403811A (en) * | 2015-12-14 | 2016-03-16 | 北京天诚同创电气有限公司 | Wind power plant power grid fault diagnosis method and device |
| JP2020087036A (en) * | 2018-11-27 | 2020-06-04 | 日本電気通信システム株式会社 | Monitoring apparatus, monitoring system, monitoring method, and program |
| CN113361326A (en) * | 2021-04-30 | 2021-09-07 | 国能浙江宁海发电有限公司 | Wisdom power plant management and control system based on computer vision target detection |
| CN113657221A (en) * | 2021-08-04 | 2021-11-16 | 浙江浙能台州第二发电有限责任公司 | Power plant equipment state monitoring method based on intelligent sensing technology |
| CN114363558A (en) * | 2021-11-19 | 2022-04-15 | 南京瀚元科技有限公司 | Intelligent monitoring data acquisition method |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101640789B (en) * | 2008-07-31 | 2011-07-13 | 比亚迪股份有限公司 | Monitor terminal, monitor method and remote monitor system used for remote monitoring |
| JP6867153B2 (en) * | 2016-12-21 | 2021-04-28 | ホーチキ株式会社 | Abnormality monitoring system |
| CN108174165A (en) * | 2018-01-17 | 2018-06-15 | 重庆览辉信息技术有限公司 | Electric power safety operation and O＆M intelligent monitoring system and method |
| CN109145789A (en) * | 2018-08-09 | 2019-01-04 | 炜呈智能电力科技（杭州）有限公司 | Power supply system safety work support method and system |
| CN109460719A (en) * | 2018-10-24 | 2019-03-12 | 四川阿泰因机器人智能装备有限公司 | A kind of electric operating safety recognizing method |
| CN109711275A (en) * | 2018-12-05 | 2019-05-03 | 湖北凯瑞知行智能装备有限公司 | A kind of power plant's operation process security risk acquisition identification system and method |
| CN111784026B (en) * | 2020-05-28 | 2022-08-23 | 国网信通亿力科技有限责任公司 | Cloud-side cooperative sensing-based all-dimensional physical examination system for electrical equipment of transformer substation |
| CN113726724B (en) * | 2020-09-15 | 2023-08-25 | 天翼数字生活科技有限公司 | Method and gateway for evaluating and detecting security risk of home network environment |
| CN113159334B (en) * | 2021-02-24 | 2022-10-11 | 广西大学 | Electrical equipment infrared image real-time detection and diagnosis method based on light-weight deep learning |
| CN113551775B (en) * | 2021-06-23 | 2022-10-04 | 国网福建省电力有限公司 | Equipment fault on-line monitoring alarm method and system based on infrared thermal imaging |
| CN114373245B (en) * | 2021-12-16 | 2023-10-27 | 南京南自信息技术有限公司 | Intelligent inspection system based on digital power plant |
| CN114863621A (en) * | 2022-04-27 | 2022-08-05 | 安徽工业大学科技园有限公司 | Visual perception-based crossing behavior monitoring method and system, memory and processor |
| CN115047544B (en) * | 2022-08-16 | 2022-12-30 | 成都信息工程大学 | Icing early warning method and system |
-
2022
- 2022-12-12 CN CN202211588773.7A patent/CN115588265B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105403811A (en) * | 2015-12-14 | 2016-03-16 | 北京天诚同创电气有限公司 | Wind power plant power grid fault diagnosis method and device |
| JP2020087036A (en) * | 2018-11-27 | 2020-06-04 | 日本電気通信システム株式会社 | Monitoring apparatus, monitoring system, monitoring method, and program |
| CN113361326A (en) * | 2021-04-30 | 2021-09-07 | 国能浙江宁海发电有限公司 | Wisdom power plant management and control system based on computer vision target detection |
| CN113657221A (en) * | 2021-08-04 | 2021-11-16 | 浙江浙能台州第二发电有限责任公司 | Power plant equipment state monitoring method based on intelligent sensing technology |
| CN114363558A (en) * | 2021-11-19 | 2022-04-15 | 南京瀚元科技有限公司 | Intelligent monitoring data acquisition method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115588265A (en) | 2023-01-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112737121A (en) | Intelligent video monitoring, analyzing, controlling and managing system for power grid | |
| CN113551775A (en) | Equipment fault on-line monitoring and alarming method and system based on infrared thermal imaging | |
| US9158302B2 (en) | System and method for detecting electric power plant equipment overheating with real-time plural parallel detection and analysis parameters | |
| CN113763667B (en) | Fire disaster early warning and state monitoring device and method based on 5G edge calculation | |
| CN107588799A (en) | A kind of architectural electricity equipment on-line monitoring system | |
| CN110941228B (en) | Intelligent railway traction substation management and control system | |
| CN115484263A (en) | Cross-regional intelligent factory real-time safety monitoring system based on edge calculation | |
| CN116826958A (en) | Intelligent safety inspection method for digital transmission channel | |
| CN115663999A (en) | Transformer substation online intelligent inspection system and method based on big data and deep learning | |
| CN115588265B (en) | Intelligent monitoring system of wind power plant | |
| CN117708552A (en) | Power station operation data real-time monitoring method based on edge calculation | |
| CN116910491B (en) | Lightning monitoring and early warning system and method, electronic equipment and storage medium | |
| CN117607590A (en) | High-voltage switch cabinet fault early warning detection method | |
| CN115328986A (en) | Power plant safety early warning data analysis processing method and system | |
| CN113225525B (en) | Indoor monitoring method and system | |
| CN115841730A (en) | Video monitoring system and abnormal event detection method | |
| CN105424224B (en) | A kind of disconnecting switch state monitoring method and device | |
| CN113435371A (en) | Equipment surrounding environment control method, device and equipment based on power internet of things and artificial intelligence | |
| KR102606526B1 (en) | System for multi functional monitoring of unmanned stations based on Artificial Intelligence | |
| KR102668287B1 (en) | Monitorable electric vehicle charging station fire prevention distribution panel and the operating method | |
| CN117932278B (en) | Smart city environment-friendly monitoring system and method | |
| CN117450942B (en) | Line icing imaging monitoring system and method | |
| KR102618658B1 (en) | Switchboard system and method using energy harvesting | |
| CN118198885B (en) | Ring main unit condensation preventing method | |
| CN117912153A (en) | Automatic access control management system and method applying intelligent community |
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 |