Fishing light complementation remote monitoring system and method for mobile terminal

Abstract

The invention provides a fishing light complementation remote monitoring system and method for a mobile terminal, and belongs to the technical field of control or adjustment of photovoltaic power generation, and the system comprises a data collection module which is used for deploying a sensor array in a fishing light complementation region to collect environment data, and collecting power generation data based on a preset photovoltaic panel monitoring device; the information conversion module is used for preprocessing the collected environment data and power generation data and carrying out information code conversion; the mode determination module is used for performing feature extraction on the code conversion data based on a preset algorithm so as to determine a preliminary fault mode; the rule construction module is used for constructing a fault database based on the data corresponding to the initial fault mode and further constructing an early warning rule in combination with historical data; and the information output module determines early warning information based on the collected environment data, power generation data and early warning rules, and visualizes the early warning information, so that the energy management efficiency is optimized, and manual intervention and potential loss are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of controlling or regulating photovoltaic power generation, and particularly to a mobile-side complementary fishing and photovoltaic remote monitoring system and method. Background Art

[0002] With the development of the complementary fishing and photovoltaic technology, more and more complementary fishing and photovoltaic projects are applied in the fields of new energy and ecological protection.

[0003] Existing complementary fishing and photovoltaic monitoring systems mainly collect environmental data and power generation data through independent sensors and devices. However, these systems often lack intelligent data processing and fault prediction capabilities, resulting in difficulties in timely detection of system failures and a lack of effective early warning mechanisms. Current technical solutions mostly rely on manual analysis, suffering from slow response and low efficiency.

[0004] Therefore, the present invention provides a mobile-side complementary fishing and photovoltaic remote monitoring system and method. Summary of the Invention

[0005] The present invention provides a mobile-side complementary fishing and photovoltaic remote monitoring system and method, which realizes comprehensive monitoring of the complementary fishing and photovoltaic area by integrating data acquisition, information conversion, pattern recognition, rule construction, and information output modules. Compared with the prior art, it can collect environmental and power generation data in real time, automatically analyze the data through intelligent algorithms, identify potential fault patterns, and construct early warning rules by combining the fault database and historical data. The system can give early warnings in time before faults occur, greatly improving the operation reliability of the photovoltaic system. In addition, the system supports visual output, facilitating users to respond quickly and make decisions, optimizing the energy management efficiency, and reducing manual intervention and potential losses.

[0006] The present invention provides a mobile-side complementary fishing and photovoltaic remote monitoring system, including: Data acquisition module: Deploy a sensor array in the complementary fishing and photovoltaic area to collect environmental data. At the same time, collect power generation data based on preset photovoltaic panel monitoring devices; Information conversion module: Preprocess the collected environmental data and power generation data, and perform information coding conversion; Pattern determination module: Extract features from the coded conversion data based on a preset algorithm, and then determine the preliminary fault pattern; Rule construction module: Construct a fault database based on the data corresponding to the preliminary fault pattern, and then construct early warning rules by combining historical data; Information output module: Determine early warning information based on the collected environmental data, power generation data, and early warning rules, and visualize the early warning information.

[0007] The present invention provides a data acquisition module for a mobile fishing-light complementary remote monitoring system, including: Regional analysis unit: The fishing-light complementary area includes several preset areas. Regional analysis is performed on each area to determine the regional characteristics of each area. Environmental acquisition unit: Corresponding sensor arrays are deployed based on the regional characteristics of each area, and environmental data of each area are acquired based on the corresponding sensor arrays and a preset acquisition frequency. Power generation acquisition unit: Power generation data are acquired based on a preset photovoltaic panel monitoring device and a preset acquisition frequency.

[0008] The present invention provides an information conversion module for a mobile fishing-light complementary remote monitoring system, including: Knowledge graph construction unit: A knowledge graph in the fishing-light complementary field is constructed based on a preset knowledge graph algorithm, and the acquired environmental data and power generation data are regarded as nodes in the knowledge graph. Data analysis unit: Initial analysis is performed on the environmental data and power generation data to determine the positions and weights of each node in the knowledge graph. Data processing unit: The environmental data and power generation data are normalized based on a graph neural network. Data conversion unit: Information encoding conversion is performed on the normalized environmental data and power generation data based on a preset adversarial network algorithm to obtain encoded conversion data.

[0009] The present invention provides a mode determination module for a mobile fishing-light complementary remote monitoring system, including: Feature extraction unit: Feature extraction is performed on the encoded conversion data based on a preset algorithm. Feature analysis unit: Feature analysis is performed on the extracted features to determine several feature parameters. Mode determination unit: A preliminary fault coefficient is determined based on the feature parameters, and a corresponding preliminary fault mode is determined in combination with a preset coefficient-mode database.

[0010] The present invention provides a mobile fishing-light complementary remote monitoring system, and the extracted features include environmental features and power generation features.

[0011] The present invention provides a feature analysis unit for a mobile fishing-light complementary remote monitoring system, including: Deviation acquisition sub-unit: By analyzing the light intensity feature in the environmental features, the long-term trend line of the light intensity is fitted using the least squares method, and the deviation value between the light intensity at each time point and the trend line is determined. Parameter determination sub-unit: Statistical analysis is performed on the deviation values to determine the trend deviation parameters. Derivative determination subunit: For the current feature in the power generation feature, define a time window and determine the first-order derivative of the current within the window; Mutation determination subunit: By analyzing the change of the first-order derivative, determine the mutation point of the current, and then determine the sum of the absolute values of the derivatives at the mutation point as the mutation degree parameter; Feature combination subunit: Construct a combined feature space of the environmental feature and the power generation feature, use the mutual information algorithm to determine the mutual information value between the light intensity feature and the power generation feature in the combined feature space, and then use the mutual information value as the coupling feature parameter.

[0012] The present invention provides a mobile-side fishing-light complementary remote monitoring system, a mode determination unit, including: Coefficient determination subunit: Determine the preliminary fault coefficient based on the feature parameter:

[0013] Wherein, is the preliminary fault coefficient, is the trend deviation parameter, is the mutation degree parameter, is the coupling feature parameter, is the sign function, 、 、 are preset hyperparameters, is the preset adjustment parameter; Mode determination subunit: Determine the corresponding preliminary fault mode based on the preliminary fault coefficient and the preset coefficient-mode database.

[0014] The present invention provides a mobile-side fishing-light complementary remote monitoring system, a rule construction module, including: Store the preliminary fault mode and its corresponding environmental data and power generation data into the fault database. At the same time, obtain historical fault data and organize and classify the historical fault data; Perform in-depth mining and correlation analysis on all data in the fault database based on the preset data processing algorithm; Based on the results of the data correlation analysis, combined with the preset domain knowledge, construct an early warning rule based on data features and fault associations.

[0015] The present invention provides a mobile-side fishing-light complementary remote monitoring method, including: Step 1: Deploy a sensor array in the fishing-light complementary area to collect environmental data. At the same time, collect power generation data based on the preset photovoltaic panel monitoring device; Step 2: Preprocess the collected environmental data and power generation data, and perform information coding conversion; Step 3: Extract features from the encoded conversion data based on a preset algorithm, and then determine the preliminary fault mode; Step 4: Construct a fault database based on the data corresponding to the preliminary fault mode, and then construct an early warning rule in combination with historical data; Step 5: Determine the early warning information based on the collected environmental data, power generation data, and early warning rules, and visualize the early warning information.

[0016] Compared with the prior art, the beneficial effects of the present application are as follows: By integrating data acquisition, information conversion, pattern recognition, rule construction, and information output modules, comprehensive monitoring of the fishery-photovoltaic complementary area is achieved. Compared with the prior art, environmental and power generation data can be collected in real time, and the data can be automatically analyzed through intelligent algorithms to identify potential fault modes. By constructing an early warning rule that combines a fault database and historical data, the system can give an early warning in time before a fault occurs, greatly improving the operation reliability of the photovoltaic system. In addition, the system supports visual output, which is convenient for users to quickly respond and make decisions, optimizes the energy management efficiency, and reduces manual intervention and potential losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 is a schematic structural diagram of a fishery-photovoltaic complementary remote monitoring system for mobile terminals provided by an embodiment of the present invention.

[0019] Figure 2 is a schematic flowchart of a fishery-photovoltaic complementary remote monitoring method for mobile terminals provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention with reference to the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0021] Embodiment 1: An embodiment of the present invention provides a fishery-photovoltaic complementary remote monitoring system for mobile terminals, as Figure 1 shown, including: A mobile fish-light complementary remote monitoring system, characterized by comprising: Data acquisition module: Deploy a sensor array in the fish-light complementary area to collect environmental data. Meanwhile, collect power generation data based on a preset photovoltaic panel monitoring device; Information conversion module: Preprocess the collected environmental data and power generation data, and perform information coding conversion; Mode determination module: Extract features from the encoded conversion data based on a preset algorithm, and then determine the preliminary fault mode; Rule construction module: Construct a fault database based on the data corresponding to the preliminary fault mode, and then construct warning rules in combination with historical data; Information output module: Determine warning information based on the collected environmental data, power generation data and warning rules, and visualize the warning information.

[0022] In this embodiment, the sensor array integrates a high-precision light sensor based on MEMS technology, a water quality sensor based on nanomaterials, a photovoltaic module performance sensor integrated with an AI chip, and sensors for monitoring physical parameters of the device (such as vibration, stress, etc.); In this embodiment, the preliminary fault mode refers to the preliminary signs or trends of possible faults identified by the system through feature extraction using a preset algorithm based on the collected and processed data (such as environmental data and power generation data). This is the first step in fault detection, helping the system to preliminarily judge the possibility of potential anomalies or faults. Example: For example, in a fish-light complementary system, if the power generation data of the photovoltaic panel suddenly drops, or the temperature and humidity in the environmental data change abnormally, the system may analyze these changes through a preliminary algorithm and identify some possible fault modes, such as surface contamination of the photovoltaic panel, equipment aging, disconnection of the connecting wire, etc.

[0023] In this embodiment, the warning rules are a set of rules established based on the historical data and preliminary fault modes collected by the system. These rules are used to judge and predict potential system faults, and when the data collected by the system in real time matches the rules, a warning is triggered. The warning rules are usually completed by machine learning or manual rule formulation. Assuming that the power generation efficiency of the photovoltaic panel is lower than a preset threshold, and if the environmental temperature is high and the humidity is low, the warning rule can be set as "if the power generation efficiency drops by more than 10% and the environmental temperature exceeds 40°C, then trigger a warning for overheating risk". Such warning rules can help detect potential overheating problems of the system.

[0024] In this embodiment, the warning information refers to the warning messages sent by the system when abnormal conditions are detected after comparing the real-time data of the system with the warning rules. These messages usually include possible fault types, severity levels, occurrence times, locations, etc., to help operators quickly locate problems and take necessary measures. For example, when the system detects abnormal power generation data of the photovoltaic panels and it conforms to the warning rules, the system will generate a warning message, such as: "Photovoltaic panel fault warning: The power generation efficiency of Group 1 of the photovoltaic panels has decreased by 15%. It may be due to equipment aging or loose connections. Please check in time." Such information can be pushed to relevant maintenance personnel through the mobile terminal to remind them to check the equipment and make repairs.

[0025] Advantages of the above technical solution: By integrating data acquisition, information conversion, pattern recognition, rule construction, and information output modules, comprehensive monitoring of the fishery-solar complementary area is achieved. Compared with the prior art, it can collect environmental and power generation data in real time, automatically analyze the data through intelligent algorithms, identify potential fault patterns, and through constructing warning rules combining the fault database and historical data, the system can give early warnings in time before faults occur, greatly improving the operation reliability of the photovoltaic system. In addition, the system supports visual output, facilitating quick response and decision-making by users, optimizing the energy management efficiency, and reducing manual intervention and potential losses.

[0026] Embodiment 2: The embodiment of the present invention provides a fishery-solar complementary remote monitoring system for the mobile terminal, and the data acquisition module includes: Regional analysis unit: The fishery-solar complementary area includes several preset areas. Regional analysis is carried out on each area to determine the regional characteristics of each area; Environmental acquisition unit: Based on the regional characteristics of each area, a corresponding sensor array is deployed, and the environmental data of each area is collected based on the corresponding sensor array and the preset acquisition frequency; Power generation acquisition unit: The power generation data is collected based on the preset photovoltaic panel monitoring equipment and the preset acquisition frequency.

[0027] In this embodiment, the preset areas include: photovoltaic panel areas and aquaculture areas; In this embodiment, deploying corresponding sensor arrays based on the characteristics of each region includes: in the photovoltaic panel region, installing light sensors at positions where they can fully receive light and are not blocked, such as on the frames or brackets of photovoltaic panels, to ensure that they can accurately reflect the light conditions received by the photovoltaic panels. Installing photovoltaic module performance sensors directly on the photovoltaic panels, close to the solar cells or key circuit parts, to collect power generation data in real time. Installing vibration sensors at key nodes of the frames and support structures of photovoltaic modules, and installing stress sensors at positions prone to stress concentration, such as at the joints of brackets and key load-bearing components. In the aquaculture water area, installing water quality sensors at different depths and positions in the water body to comprehensively monitor the vertical and horizontal distribution of water quality. For example, deploying sensors at the center of the water area, near the shore, and in areas where aquaculture organisms are concentrated to ensure that the water quality conditions of the entire water area can be accurately reflected. At the same time, attention should be paid to the installation depth and fixation method of the sensors to avoid being affected by water flow impact and interference from aquaculture organisms.

[0028] In this embodiment, presetting the photovoltaic panel monitoring device and the preset acquisition frequency to collect power generation data is to install a photovoltaic module performance sensor integrated with an AI chip on the photovoltaic panel to collect power generation data such as voltage, current, power, and temperature of the photovoltaic panel in real time, and at the same time record installation parameters such as the orientation and tilt angle of the photovoltaic panel, providing basic data for subsequent analysis of the power generation efficiency and performance of the photovoltaic panel.

[0029] Beneficial effects of the above technical solution: By accurately dividing the fishery-photovoltaic complementary area and analyzing the characteristics of each area, more customized and efficient data collection can be achieved. Compared with the prior art, deploying sensor arrays and photovoltaic panel monitoring devices according to the characteristics of the area ensures the pertinence and accuracy of data collection. At the same time, based on the preset acquisition frequency, real-time monitoring of environmental data and power generation data can be achieved, providing comprehensive support for subsequent fault detection and optimization management, significantly improving the monitoring efficiency, reducing the collection of invalid data, thereby optimizing resource allocation and fault warning, and enhancing the overall operation stability and economic benefits.

[0030] Embodiment 3: The embodiment of the present invention provides a fishery-photovoltaic complementary remote monitoring system for mobile terminals, including an information conversion module: Knowledge graph construction unit: Construct a knowledge graph in the field of fishery-photovoltaic complementarity based on a preset graph algorithm, and regard the collected environmental data and power generation data as nodes in the knowledge graph; Data analysis unit: Conduct initial analysis on the environmental data and power generation data, and then determine the positions and weights of each node in the knowledge graph; Data processing unit: Perform normalization processing on the environmental data and power generation data based on a graph neural network; Data conversion unit: Based on a preset adversarial network algorithm, it encodes and converts the normalized environmental data and power generation data to obtain encoded conversion data.

[0031] In this embodiment, the preset graph algorithm refers to an algorithm predefined in the system design stage for constructing and processing knowledge graphs in the field of fishery and solar complementary. This algorithm can convert information such as environmental data and power generation data into nodes in the graph, and determine the relationships and structures between the nodes through the algorithm. The graph algorithm helps to transform the data into a more systematic and structured form for subsequent data analysis and processing. For example, assume that in a fishery and solar complementary area, sensors collect temperature, humidity, and power generation data. The preset graph algorithm can convert these data into nodes of the knowledge graph, such as "temperature node", "humidity node", and "power generation data node", and represent the relationships between them through the edges in the graph (for example, the relationship between temperature change and power generation efficiency).

[0032] In this embodiment, the initial analysis refers to the preliminary statistical analysis of the collected environmental data and power generation data to determine the position and weight of each data point (node) in the knowledge graph. This step helps the system understand the importance of each node and provides a basis for subsequent data processing and graph construction. For example, the system first analyzes the collected environmental data and finds that the temperature data has a greater impact on power generation efficiency, while the humidity data has a smaller impact. Through the initial analysis, the system may assign a higher weight to the "temperature node" and a lower weight to the "humidity node". In this way, the temperature node in the knowledge graph will play a more important role in subsequent processing.

[0033] In this embodiment, the encoded conversion data refers to the result obtained by encoding and converting the data through an adversarial network algorithm after normalization by a graph neural network. These converted data are represented in a standardized and simplified form, facilitating further analysis, prediction, or decision-making by the system. Encoding conversion usually aims to improve the processing efficiency of the data and ensure that the data can be effectively utilized by subsequent modules of the system. For example, in the system, assume that the original environmental data (such as temperature and humidity) and power generation data become more consistent in value range after normalization. Through the adversarial network algorithm, the system converts these normalized data into an encoded form, perhaps representing the state of each data point through a numerical sequence, which helps to improve the accuracy of subsequent pattern recognition and fault prediction.

[0034] Beneficial effects of the above technical solution: The information conversion module realizes the efficient processing and intelligent analysis of environmental data and power generation data. Compared with the prior art, the knowledge graph construction unit converts the data into knowledge graph nodes, and the data analysis unit accurately determines the weight and position of each node, enhancing the structured data processing ability. Combining the normalization processing of the graph neural network and the encoding conversion of the adversarial network algorithm can improve the accuracy and efficiency of data analysis, optimize the fault detection and warning functions, improve the intelligence level of the system, reduce manual intervention, and can identify potential faults faster, ensuring the stable operation of the fishery-solar complementary system.

[0035] Embodiment 4: The embodiment of the present invention provides a fishery-solar complementary remote monitoring system for a mobile terminal. The mode determination module includes: Feature extraction unit: Extract features from the encoded conversion data based on a preset algorithm; Feature analysis unit: Analyze the extracted features to determine a number of feature parameters; Mode determination unit: Determine a preliminary fault coefficient based on the feature parameters, and determine the corresponding preliminary fault mode in combination with a preset coefficient-mode database.

[0036] In this embodiment, the preset algorithm is the Attention - BiLSTM algorithm.

[0037] In this embodiment, extracting features from the encoded conversion data based on the preset algorithm includes: Environmental data and power generation data are mostly time series data, and Attention - BiLSTM can effectively process such data. For environmental data, such as light intensity, temperature, water quality parameters, etc., they are sorted into sequence data in chronological order and input into the model. The forward and backward networks of BiLSTM learn the time series from the forward and backward directions respectively, capturing the feature dependence relationships at different time steps. For example, when processing light intensity data, it can not only learn the relationship between the current light intensity and the previous moment, but also consider the influence of the subsequent moment on it. The attention mechanism further focuses on the features of key time steps, assigns different weights to the features of different time steps, and highlights the features that are more important for fault judgment, such as the sharp change in light intensity during a certain critical period. For power generation data, such as the voltage, current, power of the photovoltaic panel, etc., they are also input into Attention - BiLSTM in the form of time series. Since the power generation data is closely related to the performance of the photovoltaic panel, the model can learn features related to potential faults, such as abnormal power fluctuations and sudden changes in voltage and current. For example, when there is partial shading on the photovoltaic panel, the power will show an abnormal decrease, and Attention - BiLSTM can capture this feature and assign a higher weight.

[0038] Beneficial effects of the above technical solution: The accuracy and efficiency of fault detection are improved through the mode determination module. Compared with the prior art, key features are extracted from the encoded conversion data by the feature extraction unit, and these features are deeply analyzed by the feature analysis unit to ensure that possible fault signs can be accurately identified. Through the combination of feature parameters and the preset coefficient-mode database, the preliminary fault mode can be quickly determined, providing an accurate basis for fault warning and handling, improving the intelligent level of fault detection, reducing the false alarm rate, optimizing the maintenance and management efficiency of the fishing-light complementary system, and ensuring the long-term stable operation of the system.

[0039] Embodiment 5: The embodiment of the present invention provides a fishing-light complementary remote monitoring system for a mobile terminal. The extracted features include: environmental features and power generation features.

[0040] In this embodiment, the environmental features refer to data features related to the environment of the fishing-light complementary area, such as temperature, humidity, light intensity, wind speed, etc. These features reflect the influence of environmental factors on the performance of the photovoltaic power generation system.

[0041] In this embodiment, the power generation features refer to key data during the power generation process of the photovoltaic panel, such as power generation amount, power, power generation efficiency, etc. These features reflect the working state and output performance of the photovoltaic panel.

[0042] Beneficial effects of the above technical solution: By extracting environmental features and power generation features, the data analysis ability and fault detection accuracy of the system are significantly improved. Compared with the prior art, this system extracts environmental data (such as temperature, humidity, light intensity, etc.) and power generation data (such as power generation amount, power, efficiency, etc.) respectively to comprehensively evaluate the operation status of the fishing-light complementary system. This feature extraction method can more accurately reflect the influence of the environment on power generation performance, timely discover potential fault hazards or efficiency losses in the system. With these features, the system can perform intelligent analysis and warning, improving the stability and efficiency of the fishing-light complementary system and reducing the manual monitoring cost.

[0043] Embodiment 6: The embodiment of the present invention provides a fishing-light complementary remote monitoring system for a mobile terminal. The feature analysis unit includes: Deviation acquisition sub-unit: By analyzing the light intensity feature in the environmental features, the long-term trend line of the light intensity is fitted using the least squares method to determine the deviation value between the light intensity at each time point and the trend line; Parameter determination sub-unit: Statistically analyze the deviation values to further determine the trend deviation parameter; Derivative determination sub-unit: For the current feature in the power generation features, define a time window and determine the first-order derivative of the current within the window; Mutation determination subunit: By analyzing the change of the first-order derivative, the mutation point of the current is determined, and then the sum of the absolute values of the derivatives at the mutation point is determined as the mutation degree parameter; Feature combination subunit: Constructs a joint feature space of environmental features and power generation features, uses the mutual information algorithm to determine the mutual information value of the light intensity feature and the power generation feature in the joint feature space, and then uses the mutual information value as the coupling feature parameter.

[0044] In this embodiment, the deviation values are statistically analyzed to determine a trend deviation parameter. For example, the median of the deviation values is calculated. A larger median indicates a more severe deviation of the light intensity from the normal trend. The trend deviation parameter is expressed in lux (lx), which measures the degree to which the light intensity deviates from the normal trend.

[0045] In this embodiment, the current mutation point is determined, and the sum of the absolute values of the derivatives at the mutation point is used as the mutation severity parameter. A larger sum indicates a more severe current mutation, potentially indicating a potential fault. The mutation severity parameter is expressed in amperes per second (A / s), reflecting the severity of the current change.

[0046] In this embodiment, the coupling characteristic parameter, the mutual information value, reflects the degree of information sharing between the two. An abnormally low mutual information value may indicate a system failure, affecting the normal correlation between light intensity and power generation. The coupling characteristic parameter is a dimensionless value, and its magnitude reflects the closeness of the correlation between light intensity and power generation.

[0047] The beneficial effects of this technical solution include: The feature analysis unit optimizes the accuracy of fault diagnosis and performance evaluation. Compared to existing technologies, this system utilizes a multi-level analysis approach, statistically analyzing deviations to determine trend deviation parameters, further revealing the stability of system operation. Combined with current first-order derivative and catastrophe point analysis, it can identify unexpected problems in the power generation system. Finally, a mutual information algorithm is used to construct a joint feature space of environmental and power generation characteristics, comprehensively evaluating the system's coupling effect. This helps to more accurately predict system performance changes and fault risks, enhancing the intelligent monitoring capabilities of the fish-solar hybrid system.

[0048] Example 7: An embodiment of the present invention provides a remote monitoring system for fishery-photovoltaic hybridization for a mobile terminal, wherein the mode determination unit includes: Coefficient determination subunit: Determines preliminary fault coefficient based on characteristic parameters:

[0049] in, is the preliminary failure coefficient, is the trend deviation parameter, is the mutation degree parameter, is a coupling characteristic parameter, is a sign function, , , are preset hyperparameters, is a preset adjustment parameter; Mode determination subunit: Determine the corresponding preliminary fault mode based on the preliminary fault coefficient and the preset coefficient-mode database.

[0050] In this embodiment, by performing power operation and square root operation on the trend deviation parameter and the mutation degree parameter, the influence degree of the parameter on the fault coefficient is enhanced. The sign function is used to judge the relative magnitude relationship among the three parameters, further affecting the positive and negative and magnitude of the fault coefficient. The coupling characteristic parameter is cube-rooted and placed in the denominator to highlight its inhibitory effect on the fault coefficient. When the coupling characteristic parameter is extremely small, the fault coefficient will increase. The following fraction comprehensively considers the product and sum relationship between the trend deviation parameter and the mutation degree parameter, and further refines the calculation of the fault coefficient. Through these complex operations, when the light intensity trend deviates severely, the power generation data mutates violently, and their coupling characteristics are abnormal, the preliminary fault coefficient will increase significantly, indicating an increased possibility of system failure.

[0051] In this embodiment, the three hyperparameters are respectively used to balance the influence degree of different parameters on the fault coefficient; In this embodiment, the preset adjustment parameter is an extremely small positive number, which is used to avoid the situation of denominator being zero.

[0052] Advantages of the above technical solution: The accuracy and response speed of fault recognition are improved through the mode determination unit. Through the coefficient determination subunit, multiple characteristic parameters (such as trend deviation parameter, mutation degree parameter, and coupling characteristic parameter) are converted into preliminary fault coefficients, and combined with the preset adjustment parameter and hyperparameters, the fault recognition sensitivity of the system is flexibly adjusted. Based on these preliminary fault coefficients, the mode determination subunit can accurately search and match the preset coefficient-mode database, quickly determine the corresponding fault mode, not only enhancing the accuracy of fault warning, but also realizing real-time and intelligent fault detection, and improving the stability and automatic management ability of the fishery-solar complementary system.

[0053] Embodiment 8: The embodiment of the present invention provides a fishery-solar complementary remote monitoring system for mobile terminals. The rule construction module includes: Store the preliminary fault mode and its corresponding environmental data and power generation data into the fault database. At the same time, obtain historical fault data and sort and classify the historical fault data; Deeply mine all the data in the fault database based on a preset data processing algorithm and conduct correlation analysis; Based on the results of the data correlation analysis, combined with the preset domain knowledge, construct early warning rules based on data characteristics and fault associations.

[0054] In this embodiment, sorting and classification are indexed according to dimensions such as fault type, fault cause, and fault occurrence frequency, facilitating subsequent query and analysis.

[0055] In this embodiment, correlation analysis is to analyze the correlation between different fault modes and environmental factors (such as light intensity, temperature, humidity) and equipment operation parameters (such as power generation power, current, voltage), and find out the potential laws and influencing factors of fault occurrence.

[0056] In this embodiment, early warning rules, for example, when the light intensity drops sharply within a short time and the temperature of the photovoltaic module rises abnormally, trigger the fault warning of the photovoltaic module; when the dissolved oxygen content in the water quality is lower than a certain threshold and the ammonia nitrogen content is higher than another threshold, trigger the risk warning of fishery farming. These early warning rules are stored in the early warning rule library in the form of logical expressions or mathematical models.

[0057] The beneficial effects of the above technical solutions: The accuracy of fault prediction and the intelligence of system response are improved through the rule construction module. Compared with the prior art, this system ensures the comprehensiveness and timeliness of data by storing the preliminary fault modes and the corresponding environmental data and power generation data in the fault database and combining and sorting the historical fault data. Through deep mining and correlation analysis of the data in the fault database by a preset data processing algorithm, the system can discover potential fault associations, and then generate accurate early warning rules. These early warning rules based on data characteristics and fault associations can help the system identify potential risks in advance, improve the fault prevention ability, reduce the maintenance cost, and improve the intelligent monitoring level and operation efficiency of the fishery-photovoltaic complementary system.

[0058] Embodiment 9: The embodiment of the present invention provides a fishery-photovoltaic complementary remote monitoring method for a mobile terminal, as Figure 2 shown, including: Step 1: Deploy a sensor array in the fishery-photovoltaic complementary area to collect environmental data. At the same time, collect power generation data based on a preset photovoltaic panel monitoring device; Step 2: Preprocess the collected environmental data and power generation data, and perform information coding conversion; Step 3: Extract features from the encoded conversion data based on a preset algorithm, and then determine the preliminary fault mode; Step 4: Construct a fault database based on the data corresponding to the preliminary fault mode, and then construct early warning rules in combination with historical data; Step 5: Determine the warning information based on the collected environmental data, power generation data, and warning rules, and visualize the warning information.

[0059] Beneficial effects of the above technical solution: It realizes the comprehensive monitoring of the fishery-solar complementary area. Compared with the existing technology, it can collect environmental and power generation data in real time, automatically analyze the data through intelligent algorithms, identify potential fault modes, and through the warning rules constructed by combining the fault database and historical data, the system can give early warnings in time before the occurrence of faults, greatly improving the operation reliability of the photovoltaic system. In addition, the system supports visual output, which is convenient for users to respond quickly and make decisions, optimizes the energy management efficiency, and reduces manual intervention and potential losses.

[0060] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than limiting it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A mobile-side fishery-photovoltaic complementary remote monitoring system, characterized in that, Including: Data acquisition module: Deploy a sensor array in the complementary fishing and photovoltaic area to collect environmental data. At the same time, collect power generation data based on a preset photovoltaic panel monitoring device. Information conversion module: Preprocess the collected environmental data and power generation data, and perform information coding conversion. Mode determination module: Extract features from the coded conversion data based on a preset algorithm, and then determine the preliminary fault mode. Rule construction module: Construct a fault database based on the data corresponding to the preliminary fault mode, and then construct warning rules in combination with historical data. Information output module: Determine warning information based on the collected environmental data, power generation data, and warning rules, and visualize the warning information.

2. The mobile-side fishery-photovoltaic complementary remote monitoring system according to claim 1, characterized in that, Data acquisition module, including: Regional analysis unit: The complementary fishing and photovoltaic area includes several preset regions. Perform regional analysis on each region to determine the regional characteristics of each region. Environmental acquisition unit: Deploy a corresponding sensor array based on the regional characteristics of each region, and collect environmental data of each region based on the corresponding sensor array and a preset acquisition frequency. Power generation acquisition unit: Collect power generation data based on a preset photovoltaic panel monitoring device and a preset acquisition frequency.

3. A mobile-side fish-light complementary remote monitoring system according to claim 1, characterized in that, Information conversion module, including: Knowledge graph construction unit: Construct a knowledge graph in the field of complementary fishing and photovoltaic based on a preset knowledge graph algorithm, and regard the collected environmental data and power generation data as nodes in the knowledge graph. Data analysis unit: Perform initial analysis on the environmental data and power generation data to determine the position and weight of each node in the knowledge graph. Data processing unit: Perform normalization processing on the environmental data and power generation data based on a graph neural network. Data conversion unit: Perform information coding conversion on the normalized environmental data and power generation data based on a preset adversarial network algorithm to obtain coded conversion data.

4. A mobile-side fish-light complementary remote monitoring system according to claim 1, characterized in that, Mode determination module, including: Feature extraction unit: Extract features from the coded conversion data based on a preset algorithm. Feature analysis unit: Perform feature analysis on the extracted features to determine several feature parameters. Mode determination unit: Determine the preliminary fault coefficient based on the feature parameters, and determine the corresponding preliminary fault mode in combination with a preset coefficient-mode database.

5. The mobile-side fishery-photovoltaic complementary remote monitoring system according to claim 4, characterized in that, The extracted features include: environmental features and power generation features.

6. The mobile fish-light complementary remote monitoring system according to claim 4, wherein, Feature analysis unit, including: Deviation acquisition sub-unit: By analyzing the light intensity feature in the environmental features, use the least squares method to fit the long-term trend line of the light intensity, and determine the deviation value between the light intensity at each time point and the trend line. Parameter determination sub-unit: Perform statistical analysis on the deviation values to determine the trend deviation parameter. Derivative determination sub-unit: For the current feature in the power generation features, define a time window and determine the first-order derivative of the current within the window. Mutation determination sub-unit: By analyzing the change of the first-order derivative, determine the mutation point of the current, and then determine the sum of the absolute values of the derivatives at the mutation point as the mutation degree parameter. Feature combination sub-unit: Construct a joint feature space of environmental features and power generation features, use the mutual information algorithm to determine the mutual information value between the light intensity feature and the power generation feature in the joint feature space, and then use the mutual information value as the coupling feature parameter.

7. A mobile-side fish-light complementary remote monitoring system according to claim 4, characterized in that, A mode determination unit, comprising: A coefficient determination subunit: determining a preliminary fault coefficient based on characteristic parameters; wherein, is the preliminary fault coefficient, is the trend deviation parameter, is the mutation degree parameter, is the coupling characteristic parameter, is the sign function, and and are preset hyperparameters, is the preset adjustment parameter; A mode determination subunit: determining a corresponding preliminary fault mode based on the preliminary fault coefficient and a preset coefficient-mode database.

8. A mobile-side fishery-photovoltaic complementary remote monitoring system according to claim 1, characterized in that, A rule construction module, comprising: Storing the preliminary fault mode, its corresponding environmental data, and power generation data into a fault database. Meanwhile, obtaining historical fault data and sorting and classifying the historical fault data; Performing in-depth mining on all data in the fault database based on a preset data processing algorithm and performing correlation analysis; Based on the results of the data correlation analysis, combining with preset domain knowledge, constructing an early warning rule based on data characteristics and fault associations.

9. A mobile-terminal-based remote monitoring method for complementary fishing and photovoltaic power generation, characterized in that, Including: Step 1: Deploying a sensor array in a fishery-solar complementary area to collect environmental data. Meanwhile, collecting power generation data based on a preset photovoltaic panel monitoring device; Step 2: Preprocessing the collected environmental data and power generation data and performing information coding conversion; Step 3: Extracting features from the coded conversion data based on a preset algorithm, and then determining a preliminary fault mode; Step 4: Constructing a fault database based on the data corresponding to the preliminary fault mode, and then constructing an early warning rule in combination with historical data; Step 5: Determining early warning information based on the collected environmental data, power generation data, and early warning rule, and visualizing the early warning information.

Images