CN117590873B - Intelligent monitoring system based on artificial intelligence and photovoltaic energy supply - Google Patents
Intelligent monitoring system based on artificial intelligence and photovoltaic energy supply Download PDFInfo
- Publication number
- CN117590873B CN117590873B CN202410069907.7A CN202410069907A CN117590873B CN 117590873 B CN117590873 B CN 117590873B CN 202410069907 A CN202410069907 A CN 202410069907A CN 117590873 B CN117590873 B CN 117590873B
- Authority
- CN
- China
- Prior art keywords
- data
- monitoring
- photovoltaic
- photovoltaic module
- power generation
- 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 82
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 13
- 238000010248 power generation Methods 0.000 claims abstract description 55
- 238000004146 energy storage Methods 0.000 claims abstract description 32
- 238000003062 neural network model Methods 0.000 claims abstract description 31
- 238000012806 monitoring device Methods 0.000 claims abstract description 30
- 230000007613 environmental effect Effects 0.000 claims abstract description 28
- 230000003044 adaptive effect Effects 0.000 claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 48
- 230000005855 radiation Effects 0.000 claims description 41
- 238000000034 method Methods 0.000 claims description 26
- 238000012549 training Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 8
- 238000005286 illumination Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 5
- 238000002310 reflectometry Methods 0.000 claims description 4
- 230000002457 bidirectional effect Effects 0.000 claims description 3
- 230000005611 electricity Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 15
- 238000009434 installation Methods 0.000 description 10
- 230000005540 biological transmission Effects 0.000 description 6
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000006467 substitution reaction Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000005684 electric field Effects 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 230000002441 reversible effect Effects 0.000 description 3
- PXHVJJICTQNCMI-UHFFFAOYSA-N Nickel Chemical compound [Ni] PXHVJJICTQNCMI-UHFFFAOYSA-N 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007257 malfunction Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 241000252233 Cyprinus carpio Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000010894 electron beam technology Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 229910052759 nickel Inorganic materials 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D3/00—Control of position or direction
- G05D3/12—Control of position or direction using feedback
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention discloses an intelligent monitoring system based on artificial intelligence and photovoltaic energy supply, which comprises a photovoltaic power generation terminal and a monitoring center; the photovoltaic power generation terminal comprises a photovoltaic module and an energy storage box; the photovoltaic module is used for adaptively adjusting the inclination angle, and the energy storage box can provide additional power support; the monitoring center comprises monitoring equipment and an upper computer; the monitoring equipment is used for executing the starting instruction and configuring the operation parameters of the equipment according to the first configuration instruction; encrypting the monitoring data; the upper computer is used for decrypting the encrypted data and evaluating the picture definition of the video data; if the definition is lower than a second preset value, inputting the environmental data and the picture definition into the adaptive neural network model to generate a second configuration instruction; the monitoring device is used for updating the operation parameters of the device according to the second configuration instruction and continuously monitoring. The invention can adaptively adjust the distribution control angle of the photovoltaic module and the operation parameters of the monitoring equipment, thereby realizing long-time and high-quality intelligent monitoring.
Description
Technical Field
The invention relates to the technical field of photovoltaic energy supply, in particular to an intelligent monitoring system based on artificial intelligence and photovoltaic energy supply.
Background
The photovoltaic energy supply is a power generation system which directly converts solar radiation energy into electric energy by adopting a photovoltaic module, and for outdoor monitoring, the applicable scene comprises outdoor environment monitoring, unmanned agricultural cultivation management and control, field combat and the like. For example, the handheld, dialogue machine, command, observation and reconnaissance equipment required in the field combat process consumes power when in use, the equipment needs to charge the battery when the electric quantity is low, and the power source for charging the equipment depends on a photovoltaic energy supply system for supplying power.
However, because of many factors that influence photovoltaic power generation, including weather, temperature etc., therefore current outdoor monitored control system based on photovoltaic energy is difficult to accomplish long-time continuous control, and simultaneously because intelligent degree is lower, the data quality that its control obtained is not ideal, for example because the light is darker and leads to the video of gathering to blur, can't monitor effective information etc.. Therefore, it is necessary to provide an intelligent monitoring system based on photovoltaic energy supply, which has long endurance time and good monitoring quality.
Disclosure of Invention
In order to solve at least one technical problem, the invention provides an intelligent monitoring system based on artificial intelligence and photovoltaic energy supply.
The invention provides an intelligent monitoring system based on artificial intelligence and photovoltaic energy supply, which comprises:
photovoltaic power generation terminal and monitoring center;
the photovoltaic power generation terminal is used for supplying power to the monitoring center through photovoltaic power generation; the photovoltaic power generation terminal comprises a photovoltaic module and an energy storage box; the photovoltaic module is foldable and is used for adaptively adjusting the inclination along with the change rule of solar radiation, and the energy storage box is used for providing power support when the generating capacity of the photovoltaic module is lower than a first preset value;
The monitoring center comprises monitoring equipment and an upper computer;
the upper computer is used for sending a starting instruction and a configuration instruction to the monitoring equipment;
The monitoring equipment is used for executing the starting instruction and configuring the operation parameters of the equipment according to the first configuration instruction; the system is also used for encrypting the monitoring data and transmitting the encrypted data to the upper computer; the monitoring data comprises video data, position data and environment data;
The upper computer is used for decrypting the encrypted data and evaluating the picture definition of the decrypted video data; when the picture definition is determined to be lower than a second preset value, inputting the environment data and the target picture definition into a trained self-adaptive neural network model to generate a second configuration instruction;
the monitoring equipment is used for receiving the second configuration instruction and updating the operation parameters of the equipment according to the second configuration instruction so as to continuously monitor the surrounding environment.
In a preferred embodiment, the upper computer is further configured to calculate an optimal inclination angle of the photovoltaic module to control a folding angle of the photovoltaic module, and includes:
Calculating the tilt angle Solar radiation quantity/>:
;
;
In the method, in the process of the invention,Representing the amount of solar direct radiation on the horizontal plane; /(I)Representing the amount of solar scattered radiation in the horizontal plane; Representing the radiation factor; /(I) Representing the ground reflectivity; /(I)Representing a solar stability number factor; /(I)Representing 12 months of a year; /(I)Represents the number of days longer than 5 hours in the maximum month of sunshine duration in one year,/>Representing the number of days with the sunlight time longer than 5 hours in the month with the least sunlight time in one year;
Solving for Maximum corresponding tilt angle/>And sending the folding inclination angle/>, the photovoltaic module and the photovoltaic power generation terminal to the photovoltaic power generation terminal, wherein the photovoltaic power generation terminal is used for controlling the folding inclination angle/>And generating power.
In a preferred embodiment, the upper computer is further configured to:
calculating the generated energy of the photovoltaic module, and judging whether the generated energy is smaller than a first preset value or not;
when the generated energy is determined to be smaller than a first preset value, controlling the starting of the energy storage box to supply energy, and calculating the current solar radiation amount;
judging whether the current solar radiation amount is larger than a third preset value or not;
And when the solar radiation amount is determined to be larger than a third preset value, generating a detection instruction and carrying out EL test on the photovoltaic module so as to judge whether the photovoltaic module fails.
In a preferred embodiment, the monitoring device is configured to encrypt the monitoring data, and includes:
Performing primary encryption on video data and/or position data, wherein the primary encryption comprises performing bidirectional identity authentication on monitoring equipment and an upper computer by utilizing an RSA algorithm;
When the authentication is passed, processing the video data and/or the position data by using an AES algorithm to generate a first secret key;
Encrypting the time stamp generated by the video data and/or the time stamp generated by the position data by utilizing a hash function, and iterating by utilizing an iteration function to generate a second secret key;
a combined key is generated using the first key and the second key.
In a preferred embodiment, the monitoring device is configured to encrypt the monitoring data, and further includes:
The environmental data is secondarily encrypted, including digitally signing the environmental data using a private key.
In a preferred embodiment, the upper computer is further configured to perform risk early warning according to video data, including:
Performing image recognition on the decrypted video data, and extracting personnel information and vehicle information in the video;
Judging whether to lock a person or a vehicle as a suspicious target according to the time length and the frequency of the person or the vehicle in the video;
And when the person or the vehicle is determined to be a suspicious target, carrying out positioning tracking on the current suspicious target by utilizing YOLOv target detection algorithm, and triggering an alarm prompt.
In a preferred embodiment, the upper computer is further configured to perform risk early warning according to environmental data, including:
Judging whether the environmental data is in a safety threshold, and triggering an alarm prompt when any one or more environmental data is detected to be out of the safety threshold; the environment data comprise temperature and humidity, illumination intensity, air pressure and sound.
In a preferred embodiment, the host computer is further configured to obtain a trained adaptive neural network model, where training the adaptive neural network model includes:
acquiring environmental data acquired by history monitoring, operation parameters of monitoring equipment and picture definition of video data as a training set;
performing feature dimension reduction on the image definition by using a t-SNE algorithm, fitting the dimension reduced features by using a self-adaptive integration algorithm, and screening out the feature quantity with the largest correlation from the fitting result;
Fusing the environment data and the characteristic quantity, taking the environment data and the characteristic quantity as input of a self-adaptive neural network model, and taking the operation parameters of the corresponding monitoring equipment as output of the self-adaptive neural network model so as to perform model training; wherein the adaptive neural network model adopts an RNN network.
In a preferred embodiment, the upper computer is further configured to construct a loss function based on a weighted average of the mean square error and cross entropy when training the adaptive neural network model.
Compared with the prior art, the invention has the beneficial effects that:
1) The photovoltaic power generation terminal comprises the photovoltaic module and the energy storage box, and can provide additional power support when the generated energy of the photovoltaic module is lower than a first preset value due to the action of the energy storage box, so that long-time cruising is ensured. And secondly, the photovoltaic module adopted in the invention is foldable equipment, and can sense the change of solar radiation to automatically adjust the distribution angle so as to improve the generating capacity and the conversion rate of the photovoltaic module from the angle of a light source, thereby further ensuring the long-time power supply capacity.
2) According to the invention, after data are collected, the picture definition is evaluated, when the picture definition is determined to be lower than a second preset value, the environment data and the picture definition are input into the trained self-adaptive neural network model to generate a second configuration instruction, and the monitoring equipment can automatically update the current operation parameters based on the second configuration instruction, so that the quality of a monitoring picture is ensured, and the effectiveness of monitoring work is improved; in addition, the security of the monitoring data is improved by encrypting the monitoring data.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
In order to more clearly describe the embodiments of the present invention or the technical solutions in the background art, the following description will describe the drawings that are required to be used in the embodiments of the present invention or the background art.
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the technical aspects of the disclosure.
FIG. 1 is a schematic diagram of an intelligent monitoring system based on artificial intelligence and photovoltaic energy supply according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a foldable photovoltaic module according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of training an adaptive neural network model according to an embodiment of the present invention;
Fig. 4 is a schematic flow chart of risk early warning according to video data according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms first, second and the like in the description and in the claims and in the above-described figures are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
The term "and/or" is herein merely an association relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, may mean including any one or more elements selected from the group consisting of A, B and C.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better illustration of the invention. It will be understood by those skilled in the art that the present invention may be practiced without some of these specific details. In some instances, well known methods, procedures, components, and circuits have not been described in detail so as not to obscure the present invention.
At present, an outdoor monitoring system based on photovoltaic energy supply is difficult to realize continuous monitoring for a long time, and meanwhile, due to low intelligent degree, the quality of data obtained by monitoring is not ideal, for example, collected video is fuzzy due to dark light, and effective information and the like cannot be monitored. Therefore, the invention provides an intelligent monitoring system based on artificial intelligence and photovoltaic energy supply, and the distribution angle can be adjusted in a self-adaptive manner through the foldable photovoltaic module, so that the photovoltaic conversion rate is improved, and the long-endurance function is realized by combining the action of an energy storage box; by evaluating the monitoring data, when the definition does not accord with a preset value, the current environment data and the definition of the target picture are combined through the trained self-adaptive neural network model, so that the operation parameters required by the equipment under the current environment can be output, the quality of the monitoring picture is ensured, and the effectiveness of the monitoring work is improved.
An intelligent monitoring system based on artificial intelligence and photovoltaic energy supply, the system comprising:
a photovoltaic power generation terminal 10 and a monitoring center 20;
The photovoltaic power generation terminal 10 is used for supplying power to the monitoring center 20 through photovoltaic power generation;
In this embodiment, the photovoltaic power generation terminal 10, that is, the photovoltaic power generation system, is different from a large-sized photovoltaic array or a distributed photovoltaic power generation system, and since the monitoring system is used outdoors, a smaller-sized photovoltaic power generation system can be adopted. Wherein, the unit of solar photovoltaic power generation energy storage system includes following part:
The solar photovoltaic power generation panel is a core part of the solar photovoltaic power generation energy storage system. The photovoltaic effect of solar energy is utilized to convert light energy into electric energy. The quality and efficiency of solar photovoltaic panels directly affect the performance of the overall system.
The energy storage battery is a key component of a solar photovoltaic power generation energy storage system, and stores electric energy generated by a solar photovoltaic power generation panel and releases the electric energy when needed. Common energy storage batteries include lead acid batteries, nickel batteries, carp ion batteries, and the like.
The controller is a control center of the solar photovoltaic power generation energy storage system. The solar photovoltaic power generation system controls the running states of the solar photovoltaic power generation panel and the energy storage battery, so that the stable running of the whole system is realized. The controller typically includes microprocessor power electronics, sensors, and the like.
The load is an electric equipment network of the solar photovoltaic power generation energy storage system. It may be any device requiring electrical energy, such as a residence, commercial building, electric car, etc.
In particular, in determining a small photovoltaic power generation system, consideration should be given to:
Installation site: first, the sunshine time and the sunshine intensity of an installation site and the shielding condition of the surrounding environment are considered. Generally, the sunshine in the southern area has longer sunshine time and larger sunshine intensity, and is suitable for building a photovoltaic power generation system; and northern areas may be less suitable because of the short sunshine duration in winter.
Electricity consumption requirement: the amount of electricity required per day needs to be calculated, and then based on this data, it is determined how many photovoltaic modules 101 and inverters are required. Generally, the number of photovoltaic modules 101 should be twice the inverter output power to ensure that the system can operate at the maximum power point.
Mounting angle: the installation angle of the photovoltaic module 101 should be determined according to the local latitude, and generally, the installation angle should be the same as or slightly deviated from the local latitude. If the installation angle is too high or too low, the power generation efficiency of the photovoltaic module 101 may be affected.
The installation mode is as follows: the small photovoltaic power generation system can adopt two modes of ground installation or roof installation. The ground installation occupies a certain space, but can be more convenient to maintain and manage; roof installation requires consideration of the load-bearing capacity and waterproof performance of the roof.
Further, the photovoltaic power generation terminal 10 includes a photovoltaic module 101 and an energy storage tank 102;
the photovoltaic module 101 is foldable and is used for adaptively adjusting the inclination angle along with the change rule of solar radiation.
The photovoltaic panel of the conventional photovoltaic module 101 is not foldable, and is usually irradiated by sunlight according to a fixed control manner to realize photovoltaic power generation. However, in practical applications, the amount of solar radiation also changes position because the sun is in motion. In order to achieve higher conversion efficiency, the embodiment preferably adopts a foldable photovoltaic module 101, and in the module, a photovoltaic panel can adaptively adjust a distribution angle along with the change of a solar radiation angle, so that the photovoltaic power generation amount is improved as much as possible.
Referring to fig. 2, fig. 2 provides a schematic structural diagram of a foldable photovoltaic module 101, and as can be seen from fig. 2, the photovoltaic module 101 is a foldable photovoltaic panel, wherein the control angle should be determined according to the solar radiation amount.
In a preferred embodiment, calculating the optimal inclination angle of the photovoltaic module 101 to control the folding angle of the photovoltaic module 101 is mainly implemented by the host computer 201, and the specific calculation process includes:
Calculating the tilt angle Solar radiation quantity/>:
;
;
In the method, in the process of the invention,Representing the amount of solar direct radiation on the horizontal plane; /(I)Representing the amount of solar scattered radiation in the horizontal plane; Representing the radiation factor; /(I) Representing the ground reflectivity; /(I)Representing a solar stability number factor; /(I)Representing 12 months of a year; /(I)Represents the number of days longer than 5 hours in the maximum month of sunshine duration in one year,/>Representing the number of days with the sunlight time longer than 5 hours in the month with the least sunlight time in one year;
Solving for Maximum corresponding tilt angle/>And transmitted to the photovoltaic power generation terminal 10, and the photovoltaic power generation terminal 10 is used for controlling the folding inclination angle/>, of the photovoltaic module 101And generating power.
Specifically, the photovoltaic module 101 shown in fig. 2 may further be provided with an angle sensor for monitoring the folding angle of the photovoltaic module 101 in real time, when calculating the inclination angle of the photovoltaic module 101 to be controlledWhen the angle sensor detects the angle of the photovoltaic module 101, the upper computer 201 sends the data to the controller, the controller controls the folding angle of the photovoltaic module 101, and the angle sensor detects whether the angle control result is equal to the inclination angle/>, and the controller determines whether the angle control result is equal to the inclination angle/>, and if the angle control result is equal to the inclination angle/>, the controller determines that the photovoltaic module is foldedAnd consistent.
In this embodiment, the relationship between the solar radiation amount and the inclination angle is calculated according to the indexes such as the solar direct radiation amount on the horizontal plane, the solar scattered radiation amount on the horizontal plane, the radiation factor, the ground reflectivity, the solar stability factor, and the like, and when the relationship between the solar radiation amount and the inclination angle is calculatedThereafter, only one of the/>, is selectedMaximum corresponding tilt angle/>So that the photovoltaic module 101 is at this tilt angle/>And carrying out folding control so as to maximize the radiation quantity and improve the photovoltaic power generation quantity.
Further, the photovoltaic power generation terminal 10 further includes an energy storage tank 102, and the energy storage tank 102 is a device for storing electric energy, which can release electric energy during peak demand periods or when electric power supply is excessive, so as to balance the supply and demand relationship of the electric power system. The energy storage tank 102 is typically comprised of a battery pack, a battery management system, a charge controller, electrical connectors, a cooling system, and the like. The energy storage tank 102 works on the principle that the battery pack is used for storing electric energy, and when the electric power demand is in peak period or the electric power supply is excessive, the energy storage tank 102 can release the stored electric energy so as to balance the supply and demand relationship of the electric power system.
In this embodiment, the energy storage tank 102 is used to provide power support when the power generation amount of the photovoltaic module 101 is lower than a first preset value. For example, in night or overcast and rainy days, the photovoltaic power generation amount cannot reach a certain preset value to ensure stable power supply to the monitoring device 202, and then the energy storage box 102 can be used for continuously supplying power to the monitoring device 202, so that continuous and effective monitoring can be performed in the weather with insufficient solar radiation.
In summary, the photovoltaic power generation terminal 10 adopted in the embodiment includes the photovoltaic module 101 and the energy storage box 102, and due to the effect of the energy storage box 102, additional power support can be provided when the power generation amount of the photovoltaic module 101 is lower than the first preset value, so as to ensure long-time cruising. Secondly, the photovoltaic module 101 adopted in the invention is foldable equipment, and can sense the change of solar radiation to automatically adjust the distribution angle so as to improve the generating capacity and the conversion rate of the photovoltaic module 101 from the light source angle, thereby further ensuring the long-time power supply capacity.
Further, the monitoring center 20 includes a monitoring device 202 and an upper computer 201;
the upper computer 201 is configured to send a start instruction and a configuration instruction to the monitoring device 202; the monitoring device 202 typically includes a camera and a sensor, as shown in fig. 1. Wherein the camera is used for collecting video data and the sensor is used for monitoring environmental data, position data and the like.
The monitoring device 202 is first configured to execute a start-up instruction and to configure an operating parameter of the device according to a first configuration instruction.
In this embodiment, the upper computer 201 first generates a start instruction, which is used to control the monitoring device 202 to start itself. In some scenarios, since the environment needs to be monitored for 24 hours, the start instruction is usually only executed when the monitoring device 202 is started at first, but in other application scenarios, when only the key time period or the key position needs to be monitored, the generation frequency of the start instruction may be set preferentially, so that the monitoring device 202 is started according to a certain rule or at a certain time interval, so that the energy consumption can be reduced. The start-up instruction is thus generated to be set in connection with the specific application scenario.
The configuration instructions are mainly set for the initial operation parameters of the monitoring device 202, for example, when the monitoring device 202 is a camera, the operation parameters include resolution, minimum illumination, aperture, frame rate, focal length, compression format, lens type, photosensitive element, and the like. Before the monitoring device 202 is started, the upper computer 201 preferably configures initial operation parameters to control the monitoring device 202 to operate according to the parameters, such as the resolution of a camera, the frequency of data acquisition by a sensor, the format of data acquisition, and the like.
The monitoring device 202 begins operation, i.e., begins collecting data, after configuring the operating parameters of the device according to the first configuration instructions. Specifically, the monitoring data includes video data, location data, and environment data.
The video data includes video and photo collected by the camera. These data may be used to identify information such as faces, license plates, vehicle types, etc. The environmental data comprises environmental data collected by a temperature and humidity sensor, an illumination sensor, an air pressure sensor and the like, and can be used for identifying information such as weather, illumination intensity, air quality and the like. The position data comprise position data acquired by positioning equipment such as GPS and the like, and can be used for identifying information such as the position of the equipment, the running route of the vehicle and the like. In other embodiments, sound data may be collected according to monitoring requirements, including sound data collected by a microphone, which may be used to identify information such as voice commands and environmental noise, or motion data, including motion data collected by sensors such as an accelerometer and a gyroscope, which may be used to identify information such as human motion and vehicle travel track.
It will be appreciated that data for monitoring an outdoor environment often relates to some important information, such as geographical location information, a person's portrait or license plate number, etc. privacy information. Therefore, in one embodiment, in order to ensure the security of information transmission, after the monitoring device 202 collects the data, it is further required to encrypt the monitoring data and send the encrypted data to the upper computer 201.
In a preferred embodiment, the monitoring device 202 is configured to encrypt the monitoring data, including:
The video data and/or the position data is primary encrypted,
The primary encryption comprises the steps of performing bidirectional identity authentication on the monitoring equipment 202 and the upper computer 201 by utilizing an RSA algorithm;
When the authentication is passed, processing the video data and/or the position data by using an AES algorithm to generate a first secret key;
Encrypting the time stamp generated by the video data and/or the time stamp generated by the position data by utilizing a hash function, and iterating by utilizing an iteration function to generate a second secret key;
a combined key is generated using the first key and the second key.
The RSA algorithm is one of the most commonly used asymmetric encryption algorithms, belongs to the most typical and perfect public key block cipher system at present, can resist most cipher attacks at present, and has better confidentiality. The algorithm first generates a pair of RSA keys by the receiver, wherein the public key can be issued in the network and the secret key is only owned by the user; the sender encrypts the file by using the public key and then sends the encrypted file to the receiver, and the receiver can decrypt and recover the plaintext by using the private key.
The AES algorithm is a symmetric encryption algorithm, typically divided into 4 steps: byte substitution, row displacement, column mixing, round key addition. Each step is reversible, so that the decryption algorithm is the corresponding inverse operation. Wherein the byte substitution is a nonlinear byte-by-byte substitution operation that follows a substitution table. The line shift is a linear transformation, each line of the state matrix is circularly shifted right in units of bytes, and the linear shift amount is a multiple of 4. In the column mixing stage, four elements of each column of the state matrix are used as coefficients to form a column polynomial, and the column polynomial is subjected to modular multiplication with a specific polynomial. And in the round key adding stage, performing exclusive OR operation on columns of the round key matrix and columns of the state matrix byte by byte. Compared with an asymmetric encryption algorithm, the encryption and decryption speed of the AES algorithm is hundreds of times faster.
SHA algorithm is the most widely used hash encryption algorithm following MD5 algorithm, which has encryption irreversibility and is commonly used as a digital signature to verify the legitimacy of a data signature.
In this embodiment, first, the RSA algorithm is mainly used to perform identity authentication on both the monitoring device 202 (transmitting end) and the host computer 201 (receiving end) at the same time. In practical application, the receiving end verifies the identity of the data sending end, but once the identity of the sending end is problematic, the file received by the receiving end is likely to be abnormal, and even information leakage of the monitoring center 20 is caused when the file is serious. Therefore, in order to enhance the security of the transmission process, authentication of both sides is required in this step. It can be understood that, when the identities of the two parties pass, the monitoring device 202 (transmitting end) and the upper computer 201 (receiving end) can establish a communication link, otherwise, data transmission cannot be performed.
Preferably, the identity authentication includes validity authentication, and uniqueness authentication.
Further, when the authentication is passed, the upper computer 201 first acquires the electronic file to be transmitted from the system, and then processes the video data and/or the position data by using the AES algorithm. Because the encryption and decryption speed of the AES algorithm is hundreds of times faster than that of the RSA algorithm, after the RSA algorithm is adopted to pass the identity authentication of the two parties, the AES algorithm is adopted to encrypt and decrypt the data sent by the two parties. The key of the security of the AES algorithm is to ensure the security of the secret key, and the security of the secret key is ensured by the AES algorithm in the encryption chain. The AES algorithm can be divided into three versions, AES-128, AES-192, and AES-256, respectively, depending on the key length. In order to speed up its decryption, in a preferred embodiment, the first key is generated by processing the video data and/or the position data using AES-128 version.
In order to enhance the security of encrypted transmission, in this embodiment, a hash algorithm MD5 is used to encrypt a timestamp generated by video data and/or a timestamp generated by position data to generate a timestamp ciphertext. And then, iterating the time stamp ciphertext by adopting an iteration function to generate a second key.
Preferably, the time stamp ciphertext is iterated using the divergent non-reversible function Fun, generating a key of the 128-bit AES encryption algorithm as the second key. Finally, a combined key is obtained using the first key and the second key.
In this embodiment, the hash algorithm MD5 and the advanced AES encryption algorithm are combined to encrypt the time stamp of the video data and/or the position data, and the non-hackability of the encryption algorithm is enhanced by diverging the non-reversible function, so that the security of data transmission is greatly improved.
Further, the monitoring device 202 is configured to encrypt the monitoring data, and further includes:
Secondary encrypting the environmental data, the secondary encrypting comprising digitally signing the environmental data using a private key
Digital signatures are a technique for verifying the integrity and authenticity of information or documents, primarily to prevent the information from being tampered with and counterfeited, and also to verify the identity of the sender of the information. The main working principle of digital signature is to adopt an asymmetric cryptosystem (public key cryptosystem), namely, a sender encrypts data by using a private key, and a receiver decrypts the data by using a corresponding public key.
In this embodiment, since the video data or the position data has more private information and has greater potential safety hazard after leakage, the video data or the position data is encrypted as primary encryption, and the environment data is encrypted as secondary encryption, where the primary encryption is higher in level than the secondary encryption. By adopting the digital signature mode, the safety of the environmental data transmission can be effectively ensured.
When the monitoring device 202 encrypts the monitoring data, the encrypted monitoring data is sent to the upper computer 201 for data analysis.
In one embodiment, after receiving the encrypted data, the upper computer 201 decrypts the encrypted data, and then evaluates the picture definition of the decrypted video data.
Specifically, an objective evaluation method may be used in the evaluation, and the image quality in the video is evaluated according to some objective criteria, such as VMAF algorithm. VMAF video multi-method Assessment Fusion, which evaluates the quality of a video by means of human visual models and machine learning. VMAF the evaluation index mainly contains VIF, DLM and TI. VIF and DLM are spatial domains, representing features within a frame of picture; TI is time-domain and represents a correlation characteristic between multiple frames. At the time of evaluation, a final score for the picture sharpness may be generated based on the weighted average of the three indices.
When the picture definition is determined to be lower than a second preset value, inputting the environment data and the target picture definition into a trained self-adaptive neural network model to generate a second configuration instruction;
the monitoring device 202 is configured to receive the second configuration instruction, and update an operation parameter of the device according to the second configuration instruction to continuously monitor the surrounding environment.
In this embodiment, a second preset value may be set preferentially, for example, the definition of the picture is more than 70 minutes, so that the monitoring information is ensured to be effective, that is, accurate information such as a license plate number, a figure outline of a person, etc. cannot be obtained due to blurring of the picture. Then after the second preset value is set to 70, the scoring result of the picture definition calculated in the previous step is compared with the value, if the scoring result is greater than the value, the picture definition shot by the current monitoring device 202 is indicated to be capable of meeting the requirement, that is, no continuous adjustment on the device operation parameters is needed, otherwise, if the scoring result is less than 70, the picture definition is indicated to be insufficient, and at the moment, the operation parameters of the monitoring device 202 should be recalculated and adjusted.
Specifically, the currently acquired environmental data and the target image definition are input to the trained adaptive neural network model, so that a second configuration instruction can be directly generated, the second configuration instruction includes the recalculated operation parameters of the device, and the operation parameters can enable the image definition of the video data shot by the monitoring device 202 to reach a second preset value. Finally, the upper computer 201 sends the second configuration instruction to the monitoring device 202, the monitoring device 202 receives the second configuration instruction, and updates the operation parameters of the device according to the second configuration instruction, so as to continuously monitor the surrounding environment, and the quality of the video data collected at the moment is ensured.
In the embodiment, after data are collected, the definition of the picture is evaluated, when the definition of the picture is lower than a second preset value, the environment data and the definition of the picture are input into a trained self-adaptive neural network model to generate a second configuration instruction, and the monitoring equipment 202 can automatically update the current operation parameters based on the second configuration instruction, so that the quality of a monitoring picture is ensured, and the effectiveness of monitoring work is improved; in addition, the security of the monitoring data is improved due to the fact that the monitoring data is encrypted.
In a preferred embodiment, the upper computer 201 is further configured to obtain a trained adaptive neural network model, where a flow of training the adaptive neural network model is shown in fig. 3, and specifically includes the following steps:
s10, acquiring the environmental data collected by history monitoring, the operation parameters of the monitoring equipment 202 and the picture definition of the video data as a training set;
S20, performing feature dimension reduction on the image definition by using a t-SNE algorithm, fitting the dimension reduced features by using a self-adaptive integration algorithm, and screening out the feature quantity with the largest correlation from the fitting result;
S30, fusing the environment data and the characteristic quantity, taking the environment data and the characteristic quantity as input of a self-adaptive neural network model, and taking the operation parameters of the corresponding monitoring equipment 202 as output of the self-adaptive neural network model so as to perform model training; wherein the adaptive neural network model adopts an RNN network.
The basic idea of the t-SNE algorithm is that if two data are similar in high-dimensional space, they should be closely spaced when reducing the dimensions to two-dimensional space. Specifically, the t-SNE converts the similarity between data points into conditional probabilities that similar data in the original space should be close together in the reduced-dimension space and dissimilar data should be far apart in the reduced-dimension space. Therefore, the feature dimension reduction can be carried out on the features in the picture definition through the t-SNE algorithm.
The self-adaptive integrated algorithm is an algorithm for dynamically adjusting the combination mode of the integrated learning model according to the characteristics of data in the integrated learning so as to improve the overall prediction performance. The method has the core concept that the weight of each model in the integrated model is dynamically adjusted according to the distribution condition of data and the performance of the model, so that the prediction performance of the whole integrated model is optimal. In this embodiment, the feature after dimension reduction is fitted by the adaptive integration algorithm, and the combination mode of the integration model can be dynamically adjusted according to different data characteristics, so that the feature quantity with the largest correlation is screened out.
And finally, fusing the environment data and the screened characteristic quantity to be used as the input of the self-adaptive neural network model to train the self-adaptive neural network model, wherein the self-adaptive neural network model adopts an RNN network. In the training process, the model can identify the number of the operation parameters correspondingly adopted along with the data of different environmental data and video definition, and when the model is applied, the configuration scheme of the operation parameters of the monitoring equipment 202 can be obtained only by collecting the current environmental data and inputting the ideal target picture definition into the model together. Because the self-adaptive neural network model is adopted, the network parameters can be automatically optimized in the training process, so that the training efficiency is improved.
In a preferred embodiment, the upper computer 201 is further configured to construct a loss function based on a weighted average of the mean square error and cross entropy when training the adaptive neural network model.
Mean square error refers to the square of the average difference between the predicted value and the true value. The performance of regression problems, such as linear regression, polynomial regression, etc., is typically measured by MSE. A smaller MSE indicates a better fit of the model to the true value. Cross entropy is used as an indicator of the performance of classification problems, such as binary classification, multi-class classification, etc. The larger the cross entropy, the weaker the model's predictive power for classification problems. Cross entropy is typically used on probability distribution predictions such as logistic regression, softmax regression, etc. The present embodiment can improve the generalization ability of the model by constructing the loss function by using the two indexes.
In a preferred embodiment, the upper computer 201 is further configured to:
Calculating the generated energy of the photovoltaic module 101, and judging whether the generated energy is smaller than a first preset value or not;
When the generated energy is determined to be smaller than a first preset value, controlling the energy storage box 102 to be started for energy supply, and calculating the current solar radiation amount;
judging whether the current solar radiation amount is larger than a third preset value or not;
When the solar radiation amount is determined to be larger than a third preset value, a detection instruction is generated and EL test is performed on the photovoltaic module 101 to judge whether the photovoltaic module 101 fails.
In this embodiment, the power generation amount of the photovoltaic module 101 is calculated first, the power of the photovoltaic module 101 can be obtained by measuring the voltage and the current of the photovoltaic module 101, and then the total power generation amount is calculated by multiplying the effective sunlight hours. After calculating the power generation amount, judging whether the value is smaller than a first preset value, if so, performing functions by using the energy storage box 102, and calculating the current solar radiation amount; if the solar radiation amount is less than or equal to the third preset value, it indicates that the current power generation amount is smaller due to insufficient solar illumination intensity, but if the solar radiation amount is greater than the third preset value, it indicates that the photovoltaic module 101 may malfunction, and at this time, a detection instruction may be generated to perform EL test on the photovoltaic module 101 to determine whether the photovoltaic module 101 malfunctions.
Specifically, the EL test judges the quality of the photovoltaic module 101 by applying a low-voltage electric field to the photovoltaic module 101 and observing whether or not a fluorescence phenomenon occurs. The principle of the EL test is to excite the PN junction in the photovoltaic module 101 to emit light by using an electron beam, thereby observing the brightness and color of the PN junction to judge the quality of the photovoltaic module 101. In the EL test, the photovoltaic module 101 is first placed in a dark room, and then a low-voltage electric field, typically about several hundred volts, is applied to the surface thereof. When an electric field is applied, if the photovoltaic module 101 is defective or damaged, the PN junction is caused to emit fluorescence, and the fluorescence presents a bright light spot under an EL microscope.
Therefore, in the embodiment, under the condition of smaller photovoltaic power generation amount, the solar radiation amount is tested, and whether the photovoltaic module 101 fails or not is judged through the EL test, and the photovoltaic module 101 can be intervened in time when failing, and the energy storage box 102 is used for supplying energy, so that stable and continuous power supply to the monitoring system is ensured.
In a preferred embodiment, the upper computer 201 is further configured to perform risk early warning according to video data, where a flow of risk early warning according to the video data is shown in fig. 4, and specifically includes the following steps:
s01, performing image recognition on the decrypted video data, and extracting personnel information and vehicle information in the video;
S02, judging whether a person or a vehicle is locked as a suspicious target according to the time length and the frequency of the person or the vehicle in the video;
and S03, when the person or the vehicle is determined to be a suspicious target, carrying out positioning tracking on the current suspicious target by utilizing YOLOv target detection algorithm, and triggering an alarm prompt.
Preferably, the upper computer 201 is further configured to perform risk early warning according to environmental data, including:
Judging whether the environmental data is in a safety threshold, and triggering an alarm prompt when any one or more environmental data is detected to be out of the safety threshold; the environment data comprise temperature and humidity, illumination intensity, air pressure and sound.
Note that each convolution portion of the backbone network Darknet53 of YOLOv uses a specific DarknetConv D structure, and regularizes each time of convolution, and performs normalization and ReLU activation functions after convolution is completed.
In this embodiment, for video data, the upper computer determines whether the behavior data hey of the upper computer locks the target as a suspicious target by extracting personnel information and vehicle information in the video, and once the target is locked, the upper computer uses a YOLOv3 target detection algorithm to locate and track the target and trigger an alarm prompt, thereby realizing risk management and control of a monitored object. For the environmental data, whether the environmental data is within the safety threshold is determined, for example, the temperature of a certain area is monitored to exceed the threshold, which indicates that the area may fire, or loud noise occurs in the sound, and also indicates that certain accidents or disasters may occur. Thus, when any one or more environmental data is detected to be outside the safety threshold, an alarm prompt is triggered immediately. The staff can arrive at the site in time for processing according to the alarm prompt and the position data, thereby reducing the loss caused by accidents or dangers.
Therefore, the embodiment can effectively monitor the safety of the environment by analyzing the video data and the environment data, and timely alarm prompt and manual intervention can be carried out on the accident place, thereby enhancing the energy efficiency of monitoring the outdoor environment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein. It will be further apparent to those skilled in the art that the descriptions of the various embodiments of the present invention are provided with emphasis, and that the same or similar parts may not be described in detail in different embodiments for convenience and brevity of description, and thus, parts not described in one embodiment or in detail may be referred to in description of other embodiments.
In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present invention, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted across a computer-readable storage medium. The computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital subscriber line (digital subscriber line, DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a digital versatile disk (DIGITAL VERSATILE DISC, DVD)), or a semiconductor medium (e.g., a Solid State Disk (SSD)), or the like.
Those of ordinary skill in the art will appreciate that implementing all or part of the above-described method embodiments may be accomplished by a computer program to instruct related hardware, the program may be stored in a computer readable storage medium, and the program may include the above-described method embodiments when executed. And the aforementioned storage medium includes: a read-only memory (ROM) or a random-access memory (random access memory, RAM), a magnetic disk or an optical disk, or the like.
Claims (4)
1. An intelligent monitoring system based on artificial intelligence and photovoltaic energy supply, characterized in that the system comprises:
photovoltaic power generation terminal and monitoring center;
the photovoltaic power generation terminal is used for supplying power to the monitoring center through photovoltaic power generation; the photovoltaic power generation terminal comprises a photovoltaic module and an energy storage box; the photovoltaic module is foldable and is used for adaptively adjusting the inclination along with the change rule of solar radiation, and the energy storage box is used for providing power support when the generating capacity of the photovoltaic module is lower than a first preset value;
The monitoring center comprises monitoring equipment and an upper computer;
the upper computer is used for sending a starting instruction and a configuration instruction to the monitoring equipment;
The monitoring equipment is used for executing the starting instruction and configuring the operation parameters of the equipment according to the first configuration instruction; the system is also used for encrypting the monitoring data and transmitting the encrypted data to the upper computer; the monitoring data comprises video data, position data and environment data;
The monitoring device is used for encrypting the monitoring data, and comprises:
Performing primary encryption on video data and/or position data, wherein the primary encryption comprises performing bidirectional identity authentication on monitoring equipment and an upper computer by utilizing an RSA algorithm;
When the authentication is passed, processing the video data and/or the position data by using an AES algorithm to generate a first secret key;
Encrypting the time stamp generated by the video data and/or the time stamp generated by the position data by utilizing a hash function, and iterating by utilizing an iteration function to generate a second secret key;
generating a combined key using the first key and the second key;
performing secondary encryption on the environment data, wherein the secondary encryption comprises digital signature on the environment data by using a private key;
The upper computer is used for decrypting the encrypted data and evaluating the picture definition of the decrypted video data; when the picture definition is determined to be lower than a second preset value, inputting the environment data and the target picture definition into a trained self-adaptive neural network model to generate a second configuration instruction;
the monitoring equipment is used for receiving the second configuration instruction and updating the operation parameters of the equipment according to the second configuration instruction so as to continuously monitor the surrounding environment;
The upper computer is also used for carrying out risk early warning according to the environmental data, and comprises:
Judging whether the environmental data is in a safety threshold, and triggering an alarm prompt when any one or more environmental data is detected to be out of the safety threshold; the environment data comprise temperature and humidity, illumination intensity, air pressure and sound;
The upper computer is also used for calculating the optimal inclination angle of the photovoltaic module so as to control the folding angle of the photovoltaic module, and comprises the following components:
Calculating the tilt angle Solar radiation quantity/>：
；
；
In the method, in the process of the invention,Representing the amount of solar direct radiation on the horizontal plane; /(I)Representing the amount of solar scattered radiation in the horizontal plane; /(I)Representing the radiation factor; /(I)Representing the ground reflectivity; /(I)Representing a solar stability number factor; /(I)Representing 12 months of a year; represents the number of days with the sunshine duration longer than 5 hours in the maximum month in one year, Representing the number of days with the sunlight time longer than 5 hours in the month with the least sunlight time in one year;
Solving for Maximum corresponding tilt angle/>And sending the folding inclination angle/>, the photovoltaic module and the photovoltaic power generation terminal to the photovoltaic power generation terminal, wherein the photovoltaic power generation terminal is used for controlling the folding inclination angle/>Generating electricity;
The upper computer is also used for calculating the generated energy of the photovoltaic module and judging whether the generated energy is smaller than a first preset value or not;
when the generated energy is determined to be smaller than a first preset value, controlling the starting of the energy storage box to supply energy, and calculating the current solar radiation amount;
judging whether the current solar radiation amount is larger than a third preset value or not;
And when the solar radiation amount is determined to be larger than a third preset value, generating a detection instruction and carrying out EL test on the photovoltaic module so as to judge whether the photovoltaic module fails.
2. The intelligent monitoring system based on artificial intelligence and photovoltaic energy supply according to claim 1, wherein the upper computer is further used for risk early warning according to video data, and comprises:
Performing image recognition on the decrypted video data, and extracting personnel information and vehicle information in the video;
Judging whether to lock a person or a vehicle as a suspicious target according to the time length and the frequency of the person or the vehicle in the video;
And when the person or the vehicle is determined to be a suspicious target, carrying out positioning tracking on the current suspicious target by utilizing YOLOv target detection algorithm, and triggering an alarm prompt.
3. The intelligent monitoring system based on artificial intelligence and photovoltaic energy of claim 1, wherein the host computer is further configured to obtain a trained adaptive neural network model, wherein training the adaptive neural network model comprises:
acquiring environmental data acquired by history monitoring, operation parameters of monitoring equipment and picture definition of video data as a training set;
performing feature dimension reduction on the image definition by using a t-SNE algorithm, fitting the dimension reduced features by using a self-adaptive integration algorithm, and screening out the feature quantity with the largest correlation from the fitting result;
Fusing the environment data and the characteristic quantity, taking the environment data and the characteristic quantity as input of a self-adaptive neural network model, and taking the operation parameters of the corresponding monitoring equipment as output of the self-adaptive neural network model so as to perform model training; wherein the adaptive neural network model adopts an RNN network.
4. The intelligent monitoring system based on artificial intelligence and photovoltaic energy according to claim 3, wherein the host computer is further configured to construct a loss function based on a weighted average of mean square error and cross entropy when training the adaptive neural network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410069907.7A CN117590873B (en) | 2024-01-18 | 2024-01-18 | Intelligent monitoring system based on artificial intelligence and photovoltaic energy supply |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410069907.7A CN117590873B (en) | 2024-01-18 | 2024-01-18 | Intelligent monitoring system based on artificial intelligence and photovoltaic energy supply |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117590873A CN117590873A (en) | 2024-02-23 |
| CN117590873B true CN117590873B (en) | 2024-04-19 |
Family
ID=89922280
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410069907.7A Active CN117590873B (en) | 2024-01-18 | 2024-01-18 | Intelligent monitoring system based on artificial intelligence and photovoltaic energy supply |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117590873B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118013450B (en) * | 2024-04-10 | 2024-06-18 | 甘肃自然能源研究所(联合国工业发展组织国际太阳能技术促进转让中心) | Photovoltaic optimization system based on total solar radiation calculation |
| CN118154609B (en) * | 2024-05-11 | 2024-07-26 | 徐州太一世纪能源科技有限公司 | Photovoltaic module fault detection method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107508550A (en) * | 2017-09-08 | 2017-12-22 | 深圳市智物联网络有限公司 | A kind of photovoltaic apparatus monitoring method and system based on Internet of Things |
| CN108089509A (en) * | 2017-12-22 | 2018-05-29 | 苏州正易鑫新能源科技有限公司 | A kind of photo-voltaic power generation station long-distance management device and system |
| CN108565947A (en) * | 2018-03-13 | 2018-09-21 | 北京恒泰能联科技发展有限公司 | Photovoltaic monitoring system power supply method for optimizing configuration based on photovoltaic off-grid |
| CN115173550A (en) * | 2022-06-07 | 2022-10-11 | 华能南京金陵发电有限公司 | Distributed photovoltaic power generation real-time monitoring method and system |
| CN115589187A (en) * | 2022-10-28 | 2023-01-10 | 浙江中新电力工程建设有限公司 | Photovoltaic power generation system and method for improving power generation efficiency of solar cell |
| CN115865320A (en) * | 2022-11-14 | 2023-03-28 | 广东工业大学 | Block chain-based security service management method and system |
| CN116937569A (en) * | 2023-07-26 | 2023-10-24 | 广东永光新能源设计咨询有限公司 | Intelligent energy storage method and device for photovoltaic power generation and electronic equipment |
| CN117277958A (en) * | 2023-11-21 | 2023-12-22 | 江苏达海智能系统股份有限公司 | Intelligent operation and maintenance management method and system for photovoltaic power station based on big data |
-
2024
- 2024-01-18 CN CN202410069907.7A patent/CN117590873B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107508550A (en) * | 2017-09-08 | 2017-12-22 | 深圳市智物联网络有限公司 | A kind of photovoltaic apparatus monitoring method and system based on Internet of Things |
| CN108089509A (en) * | 2017-12-22 | 2018-05-29 | 苏州正易鑫新能源科技有限公司 | A kind of photo-voltaic power generation station long-distance management device and system |
| CN108565947A (en) * | 2018-03-13 | 2018-09-21 | 北京恒泰能联科技发展有限公司 | Photovoltaic monitoring system power supply method for optimizing configuration based on photovoltaic off-grid |
| CN115173550A (en) * | 2022-06-07 | 2022-10-11 | 华能南京金陵发电有限公司 | Distributed photovoltaic power generation real-time monitoring method and system |
| CN115589187A (en) * | 2022-10-28 | 2023-01-10 | 浙江中新电力工程建设有限公司 | Photovoltaic power generation system and method for improving power generation efficiency of solar cell |
| CN115865320A (en) * | 2022-11-14 | 2023-03-28 | 广东工业大学 | Block chain-based security service management method and system |
| CN116937569A (en) * | 2023-07-26 | 2023-10-24 | 广东永光新能源设计咨询有限公司 | Intelligent energy storage method and device for photovoltaic power generation and electronic equipment |
| CN117277958A (en) * | 2023-11-21 | 2023-12-22 | 江苏达海智能系统股份有限公司 | Intelligent operation and maintenance management method and system for photovoltaic power station based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117590873A (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117590873B (en) | Intelligent monitoring system based on artificial intelligence and photovoltaic energy supply | |
| CN108430060A (en) | Secured session between mobile device and base station communicates | |
| CN110784493B (en) | Comprehensive meteorological data acquisition system based on NB-IoT communication | |
| Pahi et al. | Analysis and assessment of situational awareness models for national cyber security centers | |
| KR102433926B1 (en) | The combined smartpole with CPTED BOX and the Way to contract with muli-provider system of Smartpole CPTED BOX with a anti- crime CCTV, PA/AV broadcasting system, and the Way to broadcast municipal public relations and Health Management CCTV monitor for worker's disaster prevention and the Industrial Safety and Health Management CCTV minitor system with A.l. for worker's disaster prevention | |
| CN105893988A (en) | Iris acquisition method and terminal thereof | |
| CN113312635A (en) | Multi-agent fault-tolerant consistency method and system based on state privacy protection | |
| Argyropoulos et al. | Addressing cybersecurity in the next generation mobility ecosystem with CARAMEL | |
| Sabev et al. | Analysis of practical cyberattack scenarios for wind farm SCADA systems | |
| Abdi et al. | The Role of Deep Learning in Advancing Proactive Cybersecurity Measures for Smart Grid Networks: A Survey | |
| Kumar et al. | Cybersecurity Threats, Detection Methods, and Prevention Strategies in Smart Grid | |
| CN117278109B (en) | Satellite in-orbit security anomaly identification method, system and computer readable storage medium | |
| Aljohani et al. | A comprehensive survey of cyberattacks on EVs: Research domains, attacks, defensive mechanisms, and verification methods | |
| Behdadnia et al. | Leveraging deep learning to increase the success rate of DOS attacks in PMU-based automatic generation control systems | |
| CN117640207A (en) | Smart power grid information safety protection method | |
| CN112233282A (en) | Block chain type artificial intelligent safety intelligent door lock system | |
| CN110097017B (en) | Power transmission network special-type ammeter monitoring system and method | |
| CN116938513A (en) | Key management method and system applied to security management platform | |
| Harnett et al. | Government Fleet and Public Sector Electric Vehicle Supply Equipment (EVSE) Cybersecurity Best Practices and Procurement Language Report | |
| De Peralta et al. | Framework for Identifying Cybersecurity Vulnerability and Determining Risk for Marine Renewable Energy Systems | |
| CN112615740A (en) | Transmission network communication safety system | |
| Narwal et al. | Simulating manual signature using Elman back propagation model to create pseudo digital signature | |
| CN117992941B (en) | Method for monitoring login state of self-service terminal and actively protecting security | |
| US20240154784A1 (en) | Optical encryption camera | |
| Sanapannavar et al. | A deep learning-based surveillance system for enhancing public safety through internet of things and digital technology using Raspberry Pi. |
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 |