CN115712873A - Photovoltaic grid-connected operation abnormity detection system and method based on data analysis and infrared image information fusion - Google Patents
Photovoltaic grid-connected operation abnormity detection system and method based on data analysis and infrared image information fusion Download PDFInfo
- Publication number
- CN115712873A CN115712873A CN202211444265.1A CN202211444265A CN115712873A CN 115712873 A CN115712873 A CN 115712873A CN 202211444265 A CN202211444265 A CN 202211444265A CN 115712873 A CN115712873 A CN 115712873A
- Authority
- CN
- China
- Prior art keywords
- infrared image
- data analysis
- image information
- output
- photovoltaic
- 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.)
- Pending
Links
Images
Landscapes
- Photovoltaic Devices (AREA)
Abstract
The invention discloses a photovoltaic grid-connected operation abnormity detection system and method based on data analysis and infrared image information fusion, wherein the data analysis comprises the following steps: s1: setting BP neural network parameters; s2: initializing a PSO; s3: ELM training learning, and calculating the fitness of each particle; s4: solving the historical optimal positions of the particle individuals and the historical optimal positions in the group; s5, updating the speed and the position of the particles; s6, sorting the population particles according to the adaptive values, and determining the optimal fitness and the like; according to the invention, the infrared image and the big data analysis technology are fused, and the thermal infrared information of the infrared image and the data analysis of current, voltage, power and the like are fused in the same scene, so that the target outline can be highlighted, the noise can be effectively inhibited, the target expression effect of a single infrared image is improved, the accurate monitoring of the all-weather state of the photovoltaic grid-connected system is facilitated, and the on-site dynamics can be conveniently mastered in time.
Description
Technical Field
The invention relates to a photovoltaic grid-connected operation abnormity detection system and method based on data analysis and infrared image information fusion, and belongs to the technical field of power system data analysis and infrared image fault identification.
Background
In the face of the current energy crisis and the environmental problems brought by using a large amount of fossil energy, people must develop green energy to gradually replace the limited non-renewable energy for realizing sustainable development. The new energy sources comprise wind energy, tidal energy, nuclear energy, solar energy and the like, and the factors influenced in the development process of the new energy sources, such as development difficulty, cost, energy supply stability and the like, are comprehensively considered. Needless to say, solar energy is the choice of green energy development, so that the working efficiency and reliability of a photovoltaic grid-connected power generation system are improved, the photovoltaic industry is vigorously developed, and the solar energy photovoltaic grid-connected power generation system has important theoretical research and practical significance.
The domestic photovoltaic power generation technology is still in the development period, the monitoring scheme of the photovoltaic power generation system is mainly composed of a single chip microcomputer, RS485 and configuration software, the data transmission efficiency of the mode is low, the number of accommodated nodes is small, and the maintenance cost of follow-up workers is high. In order to monitor the photovoltaic power generation system in real time and improve the stability and reliability of the system, the photovoltaic power generation system is monitored by adopting the fusion of big data and image information, and the method is a future development trend. The impact on the power grid can be effectively relieved by predicting the output power of the photovoltaic grid-connected power generation system, and meanwhile, power station managers can conveniently decide the power dispatching system. In addition, factors influencing the prediction of the output power of the photovoltaic power generation are more, such as illumination intensity, temperature and humidity, sunshine duration and the like, so that the complexity of the modeling process is higher. The photovoltaic grid-connected operation abnormity detection method and the photovoltaic grid-connected operation abnormity detection device aim at data such as photovoltaic output current, voltage, power and infrared images, and realize monitoring of a photovoltaic power generation system and abnormal detection of photovoltaic grid-connected operation.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a photovoltaic grid-connected operation abnormity detection system and method based on data analysis and infrared image information fusion, on one hand, the insufficient target detection capability of using data analysis or infrared image analysis only is overcome, because some data receive external interference or some targets with low temperature exist in equipment, the infrared image background is relatively fuzzy, the contrast is low, the characteristic or image detail expression capability is limited by low pixel resolution, the data or image quality is seriously interfered by environment and outside, the data analysis is inaccurate or the infrared target edge is fuzzy, and the target position is not easy to be accurately positioned; the infrared image and the big data analysis technology are fused, thermal infrared information of the infrared image and data analysis such as current, voltage and power are fused in the same scene, the target contour can be highlighted, noise can be effectively inhibited, the target expression effect of a single infrared image is improved, accurate monitoring on all-weather states of a photovoltaic grid-connected system is facilitated, and on-site dynamics can be mastered in time conveniently.
In order to achieve the purpose, the invention adopts the technical scheme that:
in a first aspect, the application provides a method for detecting abnormal operation of a photovoltaic grid-connected system based on data analysis and infrared image information fusion, wherein the data analysis comprises the following steps:
s1: setting BP neural network parameters;
s2: initializing a PSO;
s3: ELM training learning is carried out, and the fitness of each particle is calculated;
s4: solving historical optimal positions of the particle individuals and historical optimal positions in the group;
s5, updating the speed and the position of the particles;
s6, sorting the population particles according to the adaptive values, and determining the optimal fitness;
s7, if the termination condition is met: the community convergence is taken as the standard, or the community reaches the equilibrium stable state; executing the next step; if the termination condition is not met, generating a next generation population, performing new iterative optimization, and returning to execute S2;
s8, predicting the fault by using the obtained optimal parameters;
the infrared image information analysis comprises the following steps:
step 1: inputting a photovoltaic power station field infrared image;
step 2: segmenting an input image;
and step 3: judging by using a fuzzy temperature difference judging method;
and 4, step 4: performing fault diagnosis and early warning analysis according to the judgment result;
and summarizing and transmitting the data analysis result and the infrared image information analysis result to a server for fault diagnosis and early warning analysis.
In an embodiment, in the step S1, taking a neuron of the neural network system as an example, it is assumed that input units of the neuron are x respectively i Corresponding to a weighting coefficient of w i I =0,1,2.., n-1f is the excitation function in the neural network to achieve the output of the neurons; the final output of the neuron is shown as follows:
after the neural network structure is designed, input and output parameters in the network need to be trained; the BP network not only comprises input nodes and output nodes, but also comprises one or more hidden (layer) nodes;
firstly, transmitting a transmission signal to a hidden node, and then transmitting output information of the hidden node to an output node after action; finally, an output result is given, and the excitation part of the node is generally an S-shaped function; this algorithm is called back-propagation because it propagates the weight modifications caused by the total error back to the first hidden layer, starting from the output node;
for a multilayer network formed by interconnection of a series of determined units, a back propagation algorithm can be utilized to learn the weight of the multilayer network; the method adopts a gradient descent method to reduce the square error between a network output value and a target value as much as possible; since it is necessary to consider a network of output units, rather than just one unit as it was, the error E needs to be recalculated, thereby summing the errors of all network outputs, resulting in the error shown in equation 2,
where outputs are a collection of network output units, t kd And o kd Is the correlation output value with the training sample d and the kth output unit.
In one embodiment, in step S2, on the basis of continuous learning and training of the BP neural network on the sample data, the whole training process is further optimized by using a Particle Swarm Optimization (PSO), and the main implementation principle is to continuously learn and train the particles in the training data set to obtain the optimal relative speed and relative position, and finally find the optimal solution; in this process, the corresponding speed and position relationship is as follows:
v ik (t+1)＝wv ik (t)+c 1 r 1 (pbest ik (t)-x ik (t))+c 2 r 2 (gbest(t)-x ik (t)) (3)
x ik (t+1)＝x ik (t)+v ik (t+1) (4)
wherein v is ik (t)、x ik (t) is respectively the particle velocity, position, pbest ik (t) is the individual extremum of the example, gbest (t) is the global variable, w is the inertial weight, c 1 、c 2 Is the coefficient of acceleration, r 1 、r 2 Is [0,1]Uniformly distributed random numbers of intervals.
In one embodiment, the input layer weight and the hidden element bias are optimized by adopting a particle swarm optimization algorithm, and the optimized input layer weight and hidden element bias are applied to the prediction of the output voltage, current and maximum power of the photovoltaic grid-connected power generation system, and the specific steps are as follows:
1) Randomly generating a population; the number of population particle samples in the training sample data set is m, the individual dimension is D, and the initial values of learning factors are c 1ini And c 2ini Maximum number of iterations k max ；
2) Selecting an inertia weight value; setting the maximum and minimum inertia weight as w max And w min N is the number of iterations of the current prediction model, according to the expression w = w max -(w max -w min )×n/k max The inertia weight value can be obtained by the calculation;
3) Determining a fitness function; fitness function of
Y i And
actual values and predicted values of output voltage, current and power are respectively, N is a training sample set, and a fitness function value obtained through calculation is the fitness of the model;
4) The velocity and position of the particles change during the training process; the speed variation follows the following expression:
5) Globally solving the optimal fitness; the function value f (x) of the current fitness is calculated i ) Function value f (P) of optimal fitness with history best ) Comparing to obtain a determined value, wherein the constraint condition of evaluation is the maximum iteration number or is less than the expected precision by 0.001;
6) Determining an optimal convergence criterion; the method comprises the following steps that (1) consideration is required when a termination condition is determined, the termination condition cannot enable a particle swarm algorithm to be converged prematurely, and the particle swarm algorithm falls into a local optimal solution; the convergence criterion is based on community convergence or the community reaches a stable equilibrium state;
7) And inputting the test data into the optimized PSO-ELM model for training and solving.
In one embodiment, in the infrared image information analysis, in order to accurately judge whether the photovoltaic array fails, a relative temperature difference judgment method is generally adopted for diagnosis; the relative temperature difference is the percentage of the temperature difference between two corresponding measuring points and the temperature rise ratio of a hot point therein, and can be expressed as:
because the overheating phenomenon of the photovoltaic array has the regional characteristic on the image, the extraction and the positioning of the overheating area of the photovoltaic array are realized by establishing a topological matrix and modifying and eliminating a method of isolated pulse noise points;
firstly, realizing preliminary identification of a photovoltaic array infrared thermal image overheating area by adopting a threshold value method; let x (I, j) represent the gray value of the image pixel (I, j), using I m×n And the matrix of m multiplied by n orders formed by the gray values of all pixel points of the image is represented. Setting the maximum value of the gray value of the pixel point to be Max m×n Setting a threshold value as T h Let T h ＝Max m×n When x (i, j) is not less than T h Marking the original image with 1, when x (i, j)<T h Marking the original image with 0 to obtain an mxn order topological matrix p m×n Then go through p m×n All pixel points are searched for a 4x4 order identity matrix, if the identity matrix exists, the positions of the pixel points are assigned to an mxn order matrix with all zero element values
Corresponding position is 1, matrix
Assigning the other elements to 0, if there is no such 4 th order identity matrix, let T h ＝Max m×n N, n =1,2,3. The search for the assignment is repeated, and the loop is ended until the identity matrix of 4x4 order is found;
after the overheating area is identified, the infrared image database can be established, the photovoltaic array picture to be diagnosed is stored, the infrared image to be detected is matched with the picture of the same type in the infrared image database, the relative temperature rise is calculated according to a relative temperature difference judging method by calculating various temperature information of the detected picture, and whether the equipment is in a fault state or not is judged according to a temperature threshold value determined by existing knowledge. According to the influence, the hazard degree and the damage trend which may develop of the thermal fault of the electrical equipment, the thermal fault can be divided into three levels of dangerous thermal fault early warning (primary early warning), serious thermal fault early warning (secondary early warning) and general thermal fault early warning (tertiary early warning), and measures are required to be taken corresponding to the three fault levels.
In a second aspect, the present application provides a photovoltaic grid-connected operation anomaly detection system based on data analysis and infrared image information analysis and fusion, including: the system comprises a photovoltaic power station field device layer, a local remote monitoring layer and a server;
the photovoltaic power station field device layer sends the collected data information to a local remote monitoring layer for data fusion, analysis and processing;
and sending fault diagnosis and early warning to a server through the fused, analyzed and processed data.
In a third aspect, the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and when the processor executes the computer program, the method for detecting the abnormal operation of the photovoltaic grid-connected system based on data analysis and infrared image information fusion is implemented.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of a method for detecting abnormal operation of a photovoltaic grid-connected system based on data analysis and infrared image information fusion.
As can be seen from the above description, on one hand, the present invention overcomes the insufficient target detection capability of using only data analysis or using only infrared image analysis, because some data receive external interference or some targets with insufficient temperature exist in the device, the infrared image background is relatively blurred and has low contrast, the lower pixel resolution limits the feature or image detail expression capability thereof, the data or image quality is seriously interfered by the environment and the outside, which causes inaccurate data analysis or blurred infrared target edge and is not favorable for accurately positioning the target position; the infrared image and the big data analysis technology are fused, thermal infrared information of the infrared image and data analysis such as current, voltage and power are fused in the same scene, the target contour can be highlighted, noise can be effectively inhibited, the target expression effect of a single infrared image is improved, accurate monitoring on all-weather states of a photovoltaic grid-connected system is facilitated, and on-site dynamics can be mastered in time conveniently.
Drawings
FIG. 1 is a flow chart of a photovoltaic grid-connected operation anomaly detection method based on data analysis and infrared image information fusion according to the invention;
FIG. 2 is a structural diagram of a photovoltaic grid-connected operation anomaly detection system based on data analysis and infrared image information fusion according to the invention;
FIG. 3 is a diagram of a neural network model of the present invention;
FIG. 4 is a photovoltaic array thermal fault warning grading diagram of the present invention;
fig. 5 is a schematic structural diagram of an electronic device in an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clear, the present invention is further described in detail below with reference to the accompanying drawings and embodiments; it should be understood, however, that the description herein of specific embodiments is only intended to illustrate the invention and not to limit the scope of the invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, and the terms used herein in the specification of the present invention are for the purpose of describing particular embodiments only and are not intended to limit the present invention.
The embodiment of the invention provides a specific implementation mode of a photovoltaic grid-connected operation abnormity detection method based on data analysis and infrared image information fusion, and the method specifically comprises the following steps of: a photovoltaic grid-connected operation abnormity detection method based on data analysis and infrared image information fusion is disclosed, wherein the data analysis comprises the following steps:
s1: setting BP neural network parameters;
s2: initializing a PSO;
s3: ELM training learning, and calculating the fitness of each particle;
s4: solving the historical optimal positions of the particle individuals and the historical optimal positions in the group;
s5, updating the speed and the position of the particles;
s6, sorting the population particles according to the adaptive values, and determining the optimal fitness;
s7, if the termination condition is met: the community convergence is taken as the standard, or the community reaches a balanced and stable state; executing the next step; if the termination condition is not met, generating a next generation population, performing new iterative optimization, and returning to execute S2;
s8, predicting the fault by using the obtained optimal parameters;
the infrared image information analysis comprises the following steps:
step 1: inputting a photovoltaic power station field infrared image;
step 2: segmenting an input image;
and step 3: judging by using a fuzzy temperature difference judging method;
and 4, step 4: performing fault diagnosis and early warning analysis according to the judgment result;
and summarizing and transmitting the data analysis result and the infrared image information analysis result to a server for fault diagnosis and early warning analysis.
In an embodiment, referring to fig. 1 in step S1, taking a neuron of a neural network system as an example, it is assumed that input units in the neuron are x respectively i Corresponding to a weighting coefficient of w i I =0,1,2, n-1f is a firing function in the neural network for implementing the output of the neuron; the final output of the neuron is shown as follows:
after the neural network structure is designed, input and output parameters in the network need to be trained; the BP network not only comprises input nodes and output nodes, but also comprises one or more hidden (layer) nodes;
firstly, transmitting a transmission signal to a hidden node, and then transmitting output information of the hidden node to an output node after action; finally, an output result is given, and the excitation part of the node is generally an S-shaped function; this algorithm is called back-propagation because it propagates the weight modifications caused by the total error back to the first hidden layer, starting from the output node;
for a multilayer network formed by interconnection of a series of determined units, a back propagation algorithm can be utilized to learn the weight of the multilayer network; the method adopts a gradient descent method to reduce the square error between a network output value and a target value as much as possible; because it is necessary to consider a network of output cells, rather than just one cell as it was, error E needs to be recalculated, adding the errors of all network outputs, resulting in the error shown in equation 2,
where outputs are a collection of network output units, t kd And o kd Is the output value associated with training sample d and the kth output unit.
In one embodiment, in step S2, on the basis of continuous learning training of the BP neural network on the sample data, the whole training process is further optimized by using a Particle Swarm Optimization (PSO), and the main implementation principle is to continuously learn and train the particles in the training data set to obtain the optimal relative speed and relative position, and finally find the optimal solution; in this process, the corresponding speed and position relationship is as follows:
v ik (t+1)＝wv ik (t)+c 1 r 1 (pbest ik (t)-x ik (t))+c 2 r 2 (gbest(t)-x ik (t)) (3)
x ik (t+1)＝x ik (t)+v ik (t+1) (4)
wherein v is ik (t)、x ik (t) is respectively the particle velocity, position, pbest ik (t) is the individual extremum of the example, gbest (t) is the global variable, w is the inertial weight, c 1 、c 2 Is the coefficient of acceleration, r 1 、r 2 Is [0,1]The random numbers are uniformly distributed in the interval.
In one embodiment, the input layer weight and the hidden element bias are optimized by adopting a particle swarm optimization algorithm, and the optimized input layer weight and hidden element bias are applied to the prediction of the output voltage, current and maximum power of the photovoltaic grid-connected power generation system, and the specific steps are as follows:
1) Randomly generating a population; the number of population particle samples in the training sample data set is m, the individual dimension is D, and the initial values of learning factors are c 1ini And c 2ini Maximum number of iterations k max ；
2) Selecting an inertia weight value; setting the maximum and minimum inertia weight as w max And w min N is the number of iterations of the current prediction model, according to the expression w = w max -(w max -w min )×n/k max The inertia weight value can be obtained by the calculation;
3) Determining fitnessA response function; fitness function is
Y i And
respectively outputting actual values and predicted values of voltage, current and power, wherein N is a training sample set, and a fitness function value obtained through calculation is the fitness of the model;
4) The velocity and position of the particles change during the training process; the speed variation follows the following expression:
5) Globally solving the optimal fitness; the function value f (x) of the current fitness is calculated i ) Function value f (P) of optimal fitness with history best ) Comparing to obtain a determined value, wherein the evaluation constraint condition is that the maximum iteration number is less than or equal to the expected precision by 0.001;
6) Determining an optimal convergence criterion; the method comprises the following steps that (1) consideration is required when a termination condition is determined, the termination condition cannot enable a particle swarm algorithm to be converged prematurely, and the particle swarm algorithm falls into a local optimal solution; the convergence criterion is based on community convergence or the community reaches a stable equilibrium state;
7) And inputting the test data into the optimized PSO-ELM model for training and solving.
In one embodiment, in order to accurately determine whether a photovoltaic array fails in the infrared image information analysis described with reference to fig. 4, a relative temperature difference determination method is generally used for diagnosis; the relative temperature difference is the percentage of the temperature difference between two corresponding measuring points and the temperature rise ratio of a hot point, and can be expressed as follows:
because the overheating phenomenon of the photovoltaic array has the regional characteristic on the image, the extraction and the positioning of the overheating area of the photovoltaic array are realized by establishing a topological matrix and modifying and eliminating a method of isolated pulse noise points;
firstly, realizing preliminary identification of a photovoltaic array infrared thermal image overheating area by adopting a threshold value method; let x (I, j) represent the gray value of the image pixel (I, j), using I m×n And the matrix of m multiplied by n orders formed by the gray values of all pixel points of the image is represented. Setting the maximum value of the gray value of the pixel point as Max m×n Setting a threshold value as T h Let T h ＝Max m×n When x (i, j) is not less than T h Marking the original image with 1, when x (i, j)<T h Marking the original image with 0 to obtain an mxn order topological matrix p m×n Then go through p m×n All pixel points are searched for a 4x4 order identity matrix, if the identity matrix exists, the positions of the pixel points are assigned to an mxn order matrix with all zero element values
Corresponding position is 1, matrix
Assigning the other elements to 0, if there is no such 4 th order identity matrix, let T h ＝Max m×n N, n =1,2,3. The search for the assignment is repeated, and the loop is ended until the identity matrix of 4x4 order is found;
after the overheating area is identified, the infrared image database can be established, the photovoltaic array picture to be diagnosed is stored, the infrared image to be detected is matched with the picture of the same type in the infrared image database, the relative temperature rise is calculated according to a relative temperature difference judging method by calculating various temperature information of the detected picture, and whether the equipment is in a fault state or not is judged according to a temperature threshold value determined by existing knowledge. According to the influence, the damage degree and the possible developing damage trend of the thermal fault of the electrical equipment, the thermal fault can be divided into three levels of dangerous thermal fault early warning (primary early warning), serious thermal fault early warning (secondary early warning) and general thermal fault early warning (tertiary early warning), and measures need to be taken corresponding to the three fault levels.
As can be seen from the above description, on one hand, the present invention overcomes the insufficient target detection capability of using only data analysis or using only infrared image analysis, because some data receive external interference or some targets with insufficient temperature exist in the device, the infrared image background is relatively blurred and has low contrast, the lower pixel resolution limits the feature or image detail expression capability thereof, the data or image quality is seriously interfered by the environment and the outside, which causes inaccurate data analysis or blurred infrared target edge and is not favorable for accurately positioning the target position; the infrared image and the big data analysis technology are fused, thermal infrared information of the infrared image and data analysis such as current, voltage and power are fused in the same scene, the target contour can be highlighted, noise can be effectively inhibited, the target expression effect of a single infrared image is improved, accurate monitoring on all-weather states of a photovoltaic grid-connected system is facilitated, and on-site dynamics can be mastered in time conveniently.
The embodiment of the invention provides a specific implementation mode of a photovoltaic grid-connected operation abnormity detection system based on data analysis and infrared image information fusion, and referring to fig. 2, the photovoltaic grid-connected operation abnormity detection system based on data analysis and infrared image information fusion comprises: the system comprises a photovoltaic power station field device layer, a local remote monitoring layer and a server;
the photovoltaic power station field device layer sends the collected data information to a local remote monitoring layer for data fusion, analysis and processing;
and the fused, analyzed and processed data is sent to a server for fault diagnosis and early warning.
As can be seen from the above description, on one hand, the present invention overcomes the insufficient target detection capability of using only data analysis or using only infrared image analysis, because some data receive external interference or some targets with insufficient temperature exist in the device, the infrared image background is relatively blurred and has low contrast, the lower pixel resolution limits the feature or image detail expression capability thereof, the data or image quality is seriously interfered by the environment and the outside, which causes inaccurate data analysis or blurred infrared target edge and is not favorable for accurately positioning the target position; the infrared image and the big data analysis technology are fused, thermal infrared information of the infrared image and data analysis such as current, voltage and power are fused in the same scene, the target outline can be highlighted, noise can be effectively inhibited, the target expression effect of a single infrared image is improved, accurate monitoring of the all-weather state of a photovoltaic grid-connected system is facilitated, and on-site dynamics can be mastered in time conveniently.
An embodiment of the present application further provides a specific implementation manner of an electronic device, which is capable of implementing all steps in the method for detecting the abnormal operation of the photovoltaic grid-connected system based on data analysis and infrared image information fusion in the foregoing embodiment, and referring to fig. 5, the electronic device specifically includes the following contents:
a processor (processor), a memory (memory), a communication interface (communications interface), and a bus;
the processor, the memory and the communication interface complete mutual communication through the bus.
The processor is used for calling the computer program in the memory, and when the processor executes the computer program, all the steps of the photovoltaic grid-connected operation abnormity detection method based on data analysis and infrared image information fusion in the embodiment are realized,
as can be seen from the above description, on one hand, the present invention overcomes the insufficient target detection capability of using only data analysis or using only infrared image analysis, because some data receive external interference or some targets with insufficient temperature exist in the device, the infrared image background is relatively blurred and has low contrast, the lower pixel resolution limits the feature or image detail expression capability thereof, the data or image quality is seriously interfered by the environment and the outside, which causes inaccurate data analysis or blurred infrared target edge and is not favorable for accurately positioning the target position; the infrared image and the big data analysis technology are fused, thermal infrared information of the infrared image and data analysis such as current, voltage and power are fused in the same scene, the target contour can be highlighted, noise can be effectively inhibited, the target expression effect of a single infrared image is improved, accurate monitoring on all-weather states of a photovoltaic grid-connected system is facilitated, and on-site dynamics can be mastered in time conveniently.
The embodiment of the present application further provides a computer-readable storage medium capable of implementing all steps in the method for detecting the abnormal operation of the photovoltaic grid-connected system based on data analysis and infrared image information fusion in the above embodiments, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all steps of the method for detecting the abnormal operation of the photovoltaic grid-connected system based on data analysis and infrared image information fusion in the above embodiments are implemented.
As can be seen from the above description, on one hand, the present invention overcomes the insufficient target detection capability of using only data analysis or using only infrared image analysis, because some data receive external interference or some targets with insufficient temperature exist in the device, the infrared image background is relatively blurred and has low contrast, the lower pixel resolution limits the feature or image detail expression capability thereof, the data or image quality is seriously interfered by the environment and the outside, which causes inaccurate data analysis or blurred infrared target edge and is not favorable for accurately positioning the target position; the infrared image and the big data analysis technology are fused, thermal infrared information of the infrared image and data analysis such as current, voltage and power are fused in the same scene, the target outline can be highlighted, noise can be effectively inhibited, the target expression effect of a single infrared image is improved, accurate monitoring of the all-weather state of a photovoltaic grid-connected system is facilitated, and on-site dynamics can be mastered in time conveniently.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the hardware + program class embodiment, since it is substantially similar to the method embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Although the present application provides method steps as described in an embodiment or flowchart, additional or fewer steps may be included based on routine or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an actual apparatus or client product executes, it may execute sequentially or in parallel (e.g., in the context of parallel processors or multi-threaded processing) according to the embodiments or methods shown in the figures.
Although embodiments of the present description provide method steps as described in embodiments or flowcharts, more or fewer steps may be included based on conventional or non-inventive means. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an actual apparatus or end product executes, it may execute sequentially or in parallel (e.g., parallel processors or multi-threaded environments, or even distributed data processing environments) according to the method shown in the embodiment or the figures. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in a process, method, article, or apparatus that comprises the recited elements is not excluded.
For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, in implementing the embodiments of the present description, the functions of each module may be implemented in one or more software and/or hardware, or a module implementing the same function may be implemented by a combination of multiple sub-modules or sub-units, and the like. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may therefore be considered as a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
The embodiments of this specification may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The described embodiments may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment. In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example" or "some examples" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the embodiments herein. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
The above description is only an example of the embodiments of the present disclosure, and is not intended to limit the embodiments of the present disclosure. Various modifications and variations to the embodiments described herein will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of the embodiments of the present invention should be included in the scope of the claims of the embodiments of the present invention.
Claims (8)
1. A photovoltaic grid-connected operation abnormity detection method based on data analysis and infrared image information analysis fusion is characterized in that the data analysis comprises the following steps:
s1: setting BP neural network parameters;
s2: initializing a PSO;
s3: ELM training learning, and calculating the fitness of each particle;
s4: solving the historical optimal positions of the particle individuals and the historical optimal positions in the group;
s5, updating the speed and the position of the particles;
s6, sorting the population particles according to the adaptive values, and determining the optimal fitness;
s7, if the termination condition is met: the community convergence is taken as the standard, or the community reaches the equilibrium stable state; executing the next step; if the termination condition is not met, generating a next generation population, performing new iterative optimization, and returning to execute S2;
s8, predicting the fault by using the obtained optimal parameters;
the infrared image information analysis comprises the following steps:
step 1: inputting a photovoltaic power station field infrared image;
step 2: segmenting an input image;
and step 3: judging by using a fuzzy temperature difference judging method;
and 4, step 4: performing fault diagnosis and early warning analysis according to the judgment result;
and summarizing and transmitting the data analysis result and the infrared image information analysis result to a server for fault diagnosis and early warning analysis.
2. The method for detecting the abnormal operation of the photovoltaic grid-connected system based on the fusion of the data analysis and the infrared image information analysis as claimed in claim 1, wherein in the step S1, taking a neuron of a neural network system as an example, it is assumed that input units in the neuron are x respectively i Corresponding to a weighting coefficient of w i I =0,1,2, n-1f is a firing function in the neural network for implementing the output of the neuron; the final output of the neuron is shown as follows:
after the neural network structure is designed, input and output parameters in the network need to be trained; the BP network not only comprises input nodes and output nodes, but also comprises one or more hidden (layer) nodes;
firstly, transmitting a transmission signal to a hidden node, and then transmitting output information of the hidden node to an output node after action; finally, an output result is given, and the excitation part of the node is generally an S-shaped function; this algorithm is called back-propagation because it propagates the weight modifications caused by the total error back to the first hidden layer, starting from the output node;
for a multilayer network formed by interconnection of a series of determined units, a back propagation algorithm can be utilized to learn the weight of the multilayer network; the method adopts a gradient descent method to reduce the square error between a network output value and a target value as much as possible; since it is necessary to consider a network of output units, rather than just one unit as it was, the error E needs to be recalculated, thereby summing the errors of all network outputs, resulting in the error shown in equation 2,
where outputs are a collection of network output units, t kd And o kd Is the output value associated with training sample d and the kth output unit.
3. The method for detecting the abnormal operation of the photovoltaic grid-connected system based on the combination of the data analysis and the infrared image information analysis according to claim 1, wherein in the step S2, on the basis of continuously learning and training sample data based on a BP neural network, the whole training process is further optimized by using a Particle Swarm Optimization (PSO), and the main implementation principle is to continuously learn and train particles in a training data set to obtain the optimal relative speed and relative position, and finally to find the optimal solution; in this process, the corresponding speed and position relationship is as follows:
v ik (t+1)＝wv ik (t)+c 1 r 1 (pbest ik (t)-x ik (t))+c 2 r 2 (gbest(t)-x ik (t)) (3)
x ik (t+1)＝x ik (t)+v ik (t+1) (4)
wherein v is ik (t)、x ik (t) is respectively the particle velocity, position, pbest ik (t) is the individual extremum of the example, gbest (t) is the global variable, w is the inertial weight, c 1 、c 2 Is the coefficient of acceleration, r 1 、r 2 Is [0,1]Uniformly distributed random numbers of intervals.
4. The method for detecting the abnormal operation of the photovoltaic grid-connected system based on the data analysis and the infrared image information analysis fusion of the claim 1 is characterized in that the weight of the input layer and the hidden element bias are optimized by adopting a particle swarm optimization algorithm, and the optimized input weight and the optimized hidden element bias are applied to the prediction of the output voltage, the current and the maximum power of the photovoltaic grid-connected power generation system, and the method comprises the following specific steps:
1) Randomly generating a population; the number of population particle samples in the training sample data set is m, the individual dimension is D, and the initial values of learning factors are c 1ini And c 2ini Maximum number of iterations k max ；
2) Selecting an inertia weight value; setting the maximum and minimum inertia weight as w max And w min N is the number of iterations of the current prediction model, according to the expression w = w max -(w max -w min )×n/k max The inertia weight value can be obtained by the calculation;
3) Determining a fitness function; fitness function of
Y i And
respectively outputting actual values and predicted values of voltage, current and power, wherein N is a training sample set, and a fitness function value obtained through calculation is the fitness of the model;
4) The velocity and position of the particles change during the training process; the speed variation follows the following expression:
5) Globally solving the optimal fitness; the function value f (x) of the current fitness is calculated i ) Function value f (P) of optimal fitness with history best ) Comparing to obtain a determined value, wherein the constraint condition of evaluation is the maximum iteration number or is less than the expected precision by 0.001;
6) Determining an optimal convergence criterion; the method comprises the following steps that (1) consideration is required when a termination condition is determined, the termination condition cannot enable a particle swarm algorithm to be converged prematurely, and the particle swarm algorithm falls into a local optimal solution; the convergence criterion is based on community convergence or the community reaches a stable equilibrium state;
7) And inputting the test data into the optimized PSO-ELM model for training and solving.
5. The method for detecting the abnormal operation of the photovoltaic grid-connected system based on the fusion of the data analysis and the infrared image information analysis as claimed in claim 1, wherein in the infrared image information analysis, in order to accurately judge whether the photovoltaic array has a fault, a relative temperature difference judgment method is generally adopted for diagnosis; the relative temperature difference is the percentage of the temperature difference between two corresponding measuring points and the temperature rise ratio of a hot point therein, and can be expressed as:
because the overheating phenomenon of the photovoltaic array has the regional characteristic on the image, the extraction and the positioning of the overheating area of the photovoltaic array are realized by establishing a topological matrix and modifying and eliminating a method of isolated pulse noise points;
firstly, realizing preliminary identification of a photovoltaic array infrared thermal image overheating area by adopting a threshold value method; let x (I, j) represent the gray value of the image pixel (I, j), using I m×n Representing an m multiplied by n order matrix formed by gray values of all pixel points of the image; setting the maximum value of the gray value of the pixel point to be Max m×n Setting a threshold value as T h Let T h ＝Max m×n When x (i, j) is not less than T h Marking the original image with 1, when x (i, j)<T h Marking the original image with 0 to obtain an mxn order topological matrix p m×n Then go through p m×n All pixel points are searched for a 4x4 order identity matrix, if the identity matrix exists, the positions of the pixel points are assigned to an mxn order matrix with all zero element values
Corresponding position is 1, matrix
Assigning the other elements to 0, if there is no such 4 th order identity matrix, let T h ＝Max m×n N, n =1,2,3. The search for the assignment is repeated, and the loop is ended until the identity matrix of 4x4 order is found;
after the overheating area is identified, matching an infrared image to be detected with the same type of images in an infrared image database by establishing the infrared image database and storing the photovoltaic array images to be diagnosed, calculating various temperature information of the detected images, calculating relative temperature rise according to a relative temperature difference judgment method, and judging whether the equipment is in a fault state according to a temperature threshold determined by existing knowledge; according to the influence, the damage degree and the possible developing damage trend of the thermal fault of the electrical equipment, the thermal fault can be divided into three levels of dangerous thermal fault early warning (primary early warning), serious thermal fault early warning (secondary early warning) and general thermal fault early warning (tertiary early warning), and measures need to be taken corresponding to the three fault levels.
6. The utility model provides a grid-connected PV operation anomaly detection system based on data analysis and infrared image information analysis fuse which characterized in that includes: the system comprises a photovoltaic power station field device layer, a local remote monitoring layer and a server;
the photovoltaic power station field device layer sends the collected data information to a local remote monitoring layer for data fusion, analysis and processing;
and the fused, analyzed and processed data is sent to a server for fault diagnosis and early warning.
7. An electronic device comprising a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the method for detecting the abnormal operation of the photovoltaic grid-connected device based on data analysis and infrared image information fusion according to any one of claims 1 to 5 when executing the computer program.
8. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the method for detecting the abnormal operation of the photovoltaic grid-connected system based on the data analysis and the infrared image information fusion of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211444265.1A CN115712873A (en) | 2022-11-18 | 2022-11-18 | Photovoltaic grid-connected operation abnormity detection system and method based on data analysis and infrared image information fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211444265.1A CN115712873A (en) | 2022-11-18 | 2022-11-18 | Photovoltaic grid-connected operation abnormity detection system and method based on data analysis and infrared image information fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115712873A true CN115712873A (en) | 2023-02-24 |
Family
ID=85233849
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211444265.1A Pending CN115712873A (en) | 2022-11-18 | 2022-11-18 | Photovoltaic grid-connected operation abnormity detection system and method based on data analysis and infrared image information fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115712873A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115940809A (en) * | 2023-03-09 | 2023-04-07 | 深圳市迪晟能源技术有限公司 | Solar panel fault detection method based on power data and visual analysis |
| CN116055900A (en) * | 2023-03-30 | 2023-05-02 | 北京城建智控科技股份有限公司 | Image quality correction method based on image pickup device |
| CN117237590A (en) * | 2023-11-10 | 2023-12-15 | 华能新能源股份有限公司山西分公司 | Photovoltaic module hot spot identification method and system based on image identification |
| CN117371824A (en) * | 2023-12-04 | 2024-01-09 | 天津生联智慧科技发展有限公司 | Abnormality detection method and device based on photovoltaic data |
-
2022
- 2022-11-18 CN CN202211444265.1A patent/CN115712873A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115940809A (en) * | 2023-03-09 | 2023-04-07 | 深圳市迪晟能源技术有限公司 | Solar panel fault detection method based on power data and visual analysis |
| CN116055900A (en) * | 2023-03-30 | 2023-05-02 | 北京城建智控科技股份有限公司 | Image quality correction method based on image pickup device |
| CN116055900B (en) * | 2023-03-30 | 2023-06-09 | 北京城建智控科技股份有限公司 | Image quality correction method based on image pickup device |
| CN117237590A (en) * | 2023-11-10 | 2023-12-15 | 华能新能源股份有限公司山西分公司 | Photovoltaic module hot spot identification method and system based on image identification |
| CN117237590B (en) * | 2023-11-10 | 2024-04-02 | 华能新能源股份有限公司山西分公司 | Photovoltaic module hot spot identification method and system based on image identification |
| CN117371824A (en) * | 2023-12-04 | 2024-01-09 | 天津生联智慧科技发展有限公司 | Abnormality detection method and device based on photovoltaic data |
| CN117371824B (en) * | 2023-12-04 | 2024-03-01 | 天津生联智慧科技发展有限公司 | Abnormality detection method and device based on photovoltaic data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109614981B (en) | Power system intelligent fault detection method and system based on spearman level-dependent convolutional neural network | |
| CN108647716B (en) | Photovoltaic array fault diagnosis method based on composite information | |
| CN115712873A (en) | Photovoltaic grid-connected operation abnormity detection system and method based on data analysis and infrared image information fusion | |
| Khan et al. | Batteries state of health estimation via efficient neural networks with multiple channel charging profiles | |
| Rao et al. | Solar array fault detection using neural networks | |
| CN110415215B (en) | Intelligent detection method based on graph neural network | |
| Rao et al. | Machine learning for solar array monitoring, optimization, and control | |
| CN109672406B (en) | Photovoltaic power generation array fault diagnosis and classification method based on sparse representation and SVM | |
| Kumar et al. | Cloud-based electricity consumption analysis using neural network | |
| Lu et al. | Neural network interpretability for forecasting of aggregated renewable generation | |
| CN115438897A (en) | Industrial process product quality prediction method based on BLSTM neural network | |
| CN116894180B (en) | Product manufacturing quality prediction method based on different composition attention network | |
| CN113642255A (en) | Photovoltaic power generation power prediction method based on multi-scale convolution cyclic neural network | |
| CN113033898A (en) | Electrical load prediction method and system based on K-means clustering and BI-LSTM neural network | |
| CN117114438A (en) | Building area energy system cold and hot load data driving prediction method with flexibility and interpretability | |
| CN117033923A (en) | Method and system for predicting crime quantity based on interpretable machine learning | |
| CN117764547A (en) | Photovoltaic string fault diagnosis method and system | |
| CN114219118A (en) | Method and system for predicting service life of intelligent electric meter based on D-S evidence theory | |
| Shahzad | Artificial neural network for transient stability assessment: A review | |
| CN112184037A (en) | Multi-modal process fault detection method based on weighted SVDD | |
| Şimşek et al. | A Study on Deep Learning Methods in the Concept of Digital Industry 4.0 | |
| Manoj et al. | Deep Feature Selection for Wind Forecasting‐II | |
| Huang et al. | Electricity Theft Detection based on Iterative Interpolation and Fusion Convolutional Neural Network | |
| CN117610314B (en) | Photovoltaic module modeling method, device, equipment and storage medium | |
| Hong et al. | Improved Grey Wolf Algorithm Based on Multistrategy Dual Weighting Factors with BiLSTM for PV Fault Diagnosis |
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 |