New energy station monitoring system and method based on intelligent sensor

Abstract

The invention relates to the technical field of new energy station monitoring, in particular to a new energy station monitoring system and method based on an intelligent sensor, and the system comprises an intelligent model unit which builds a multi-factor model and predicts the power generation efficiency; the continuous optimization unit is used for predicting burst data according to the power generation efficiency; when the system is used, the system adapts to seasonal changes and sudden weather conditions, the operation efficiency of the new energy station is improved, energy management can be optimized, the sustainability and economical efficiency of the system are ensured, the new energy station can operate in an efficient and stable environment by continuously optimizing the operation of the units, and the new energy station is suitable for popularization and application. The power generation efficiency of the whole new energy station is further improved, the operation and maintenance cost is further reduced, the power generation efficiency and equipment state data are monitored in real time, whether equipment needs to be maintained or adjusted or not is judged, manual intervention is reduced, the intelligent degree of the system is improved, it is ensured that the power generation efficiency is always kept in the optimal state, and resource utilization is maximized.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy station monitoring, and in particular to a new energy station monitoring system and method based on intelligent sensors. Background Art

[0002] New energy site monitoring refers to a technical system that conducts real-time monitoring and management of new energy power generation facilities such as solar photovoltaic power stations, wind power plants, and biomass power plants.

[0003] The patent application number is 202011230175.3, which states in the specification that "This application relates to a new energy station monitoring system and method, which belongs to the technical field of new energy monitoring, and includes a monitoring terminal located at each new energy station and a master control terminal connected to all monitoring systems. The monitoring terminal includes a power generation detection module, a sunshine intensity detection module and a sunshine intensity prediction module. The master control terminal includes a data storage module, a ratio calculation module, an average value calculation module, an estimation module and a processing module; the daily power generation, the daily power generation time curve, the daily sunshine intensity and the daily sunshine intensity time curve of each new energy station are detected, and the detection results are calculated according to the detection results. The above technology can calculate the average unit sunshine intensity power generation efficiency according to the detection results, estimate the power generation and screen out inefficient new energy sites. However, in actual application scenarios, light intensity is not the only factor that determines power generation efficiency. The health status of photovoltaic equipment, climate change in new energy sites and the aging degree of some photovoltaic equipment will also affect the power generation efficiency. Therefore, over-reliance on the ratio of light intensity to power generation to judge the power generation efficiency will lead to misjudgment.

[0004] In summary, the development of a new energy station monitoring system and method based on intelligent sensors is still a key issue that needs to be urgently solved in the field of new energy station monitoring technology. Summary of the invention

[0005] The purpose of the present invention is to solve the problem in the prior art that although the above-mentioned technology can calculate the average unit sunshine intensity power generation efficiency according to the detection results, so as to achieve the purpose of estimating the power generation and screening out inefficient new energy sites, in actual application scenarios, light intensity is not the only factor that determines the power generation efficiency. The health status of photovoltaic equipment, climate change of new energy sites and the aging degree of some photovoltaic equipment will also affect the power generation efficiency. Therefore, excessive reliance on the ratio of light intensity and power generation to judge the power generation efficiency will lead to misjudgment. The present invention provides a new energy site monitoring system and method based on intelligent sensors.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The present invention provides a new energy station monitoring system based on intelligent sensors, comprising: an intelligent model unit, which establishes a multi-factor model to predict power generation efficiency;

[0008] A continuous optimization unit predicts burst data according to the power generation efficiency and calibrates a multi-factor model according to the burst data;

[0009] A data feedback unit stores the burst data and regularly feeds back optimization suggestions to the off-site personnel;

[0010] The automatic adjustment unit dynamically adjusts the operating status of the new energy equipment in the station according to the power generation efficiency.

[0011] Furthermore, the intelligent model unit includes:

[0012] Intelligent collection module, used to collect various data in the station environment in real time to obtain real-time data and station power generation;

[0013] A data processing module, which correlates and analyzes the real-time data with the power generation of the station and establishes a multi-factor model to predict power generation efficiency;

[0014] The continuous optimization unit includes:

[0015] A prediction and diagnosis module, which monitors the deviation between the health status of the new energy equipment in the station and the power generation efficiency in real time, and predicts the sudden data of the new energy equipment in the station by using an anomaly detection algorithm according to the power generation efficiency;

[0016] The calibration module dynamically calibrates the multi-factor model by calculating the differences between the burst data.

[0017] Furthermore, it is characterized in that the data feedback unit comprises:

[0018] A data storage module stores the collected burst data and displays the health status, power generation efficiency and burst data of the new energy equipment in the station to the staff through a display terminal;

[0019] A feedback mechanism is used to analyze the burst data and provide optimization suggestions to the station management personnel on a regular basis based on the data analysis results and the power generation efficiency;

[0020] The automatic adjustment unit includes:

[0021] The automatic adjustment module automatically gives adjustment suggestions according to the power generation efficiency, and dynamically adjusts the operating status of the new energy equipment in the station according to the adjustment suggestions.

[0022] Furthermore, it is characterized in that the workflow of the intelligent model unit includes:

[0023] The intelligent acquisition module collects various real-time data of the new energy station through various sensors, such as light intensity, temperature and humidity, wind speed, air quality, and station power generation, and transmits the real-time data to the data processing module;

[0024] The data processing module performs real-time correlation analysis on the real-time data and the power generation of the station, establishes a multi-factor model to predict the power generation efficiency under different environmental conditions, and considers various factors at the same time to analyze the impact of various factors on the power generation efficiency. The relationship between light intensity and power generation efficiency is not completely linear, and a nonlinear regression model is needed to describe it. Similarly, the relationship between temperature and humidity and power generation efficiency is more accurately modeled using a composite exponential function. The nonlinear regression model formula is: Where Q(s) is the power generation efficiency at time s, G(s) is the light intensity at time s, S(s) is the ambient temperature at time s, E(s) is the wind speed, χ is the influence coefficient of wind speed on power generation efficiency, α and β are the nonlinear relationship coefficients between light intensity and temperature, respectively. The formula of the composite exponential function is: Where Q0 is the basic power generation efficiency, S opt , R opt is the optimal value of temperature and humidity, δ1, δ2 are the coefficients of influence of temperature and humidity on power generation efficiency, S(s), R(s) are the current temperature and humidity, and then a multivariate linear regression model is used to combine different environmental factors to predict power generation efficiency, and regularization is used to prevent overfitting. According to the autoregressive integral moving average model, the time series of power generation efficiency can be predicted to adapt to short-term fluctuations and trend changes. The formula of the multivariate linear regression model is:

[0025] Among them, ε is the regularization coefficient, which controls the complexity of the model and avoids overfitting. G(s), S(s), E(s), and TY(s) are light intensity, temperature, wind speed, and air quality, respectively. The formula of the autoregressive integrated moving average model is: Where c is a constant term, φ L is the autoregressive coefficient, which indicates the influence of the power generation efficiency at the past o time points on the current power generation efficiency, ∈(s) is the white noise term, which represents random disturbance, is the moving average coefficient, which indicates the impact of the error at the past m time points on the current prediction. L is the index variable of the autoregressive part, and its value range is from 1 to o. j is the index variable of the sliding average part, and its value range is from 1 to m.

[0026] Furthermore, the workflow of the continuous optimization unit includes:

[0027] The predictive diagnosis module continuously tracks the working status of each device in the station through the equipment health monitoring sensor, records various data, compares the working status of each device with the actual power generation efficiency in real time, monitors the health status of the station equipment and the deviation of power generation efficiency in real time through the abnormal detection algorithm and prediction method, and analyzes whether the power generation efficiency is affected by equipment failure or performance degradation. At the same time, based on historical data and real-time monitoring data, the prediction algorithm is used to predict the possible sudden state of the equipment, issue an alarm in advance, and prompt the staff to take necessary preventive measures. The power generation efficiency deviation formula is: ΔQ(s)=Q predicted (s)-Q actual (s), fault detection formula: Q forecast (s)=ARIMA(Q(s)), set the deviation threshold of power generation efficiency to γ, and if |ΔQ(s)|>γ, it is considered that the equipment may fail;

[0028] The proofreading module compares the environmental data and power generation efficiency collected in real time with the historical data. According to the comparison results of the model calibration formula, the prediction model of power generation efficiency is optimized and updated through the dynamic programming formula. The updated power generation efficiency prediction model generates a new power generation efficiency prediction value, which is input into the data feedback unit and the automatic adjustment unit to ensure that the prediction of power generation efficiency is more accurate. The model calibration formula is: Among them, H new is the corrected regression coefficient, H old is the old regression coefficient, η is the learning rate control update step, ΔQ(s) is the real-time deviation, and the dynamic programming formula is:

[0029] Where K(s) is the cost function representing the sum of squares of the power generation efficiency prediction error and the regularization term, is a constant used to scale or adjust the loss function, n is the number of data points, m′ is the total number of parameters in the model, and Q actual (s) is the actual power generation efficiency, Q predicted (s) is the predicted power generation efficiency, ν j is the parameter of the model, and μ is the regularization coefficient used to control the complexity of the model.

[0030] Furthermore, the workflow of the data feedback unit includes:

[0031] The data storage module stores the collected real-time data, historical data and power generation efficiency prediction results for subsequent analysis and use. The stored historical data is used to analyze the long-term impact of environmental factors and equipment status on power generation efficiency and to learn for the optimization algorithm. At the same time, the data query formula is used to query historical data, real-time data and power generation efficiency prediction results at any time to provide decision support for managers. The data query formula is:

[0032] Among them C stored (t) is the stored data, which summarizes all the collected data at different time points. G(s), S(s), E(s), and TY(s) are the collected data of the light intensity sensor, temperature sensor, wind speed sensor, and air quality sensor, respectively;

[0033] Feedback mechanism, based on data analysis results and power generation efficiency prediction, regularly generates optimization suggestions based on historical data, and uses threshold-based rules for feedback. The optimization feedback formula is: FK(t)=if Q predicted (t) min , where Q min It is the set minimum power generation efficiency threshold. In addition, when an abnormality in the health status of the equipment or abnormal power generation efficiency is detected, an alarm will be sent to the staff immediately.

[0034] Furthermore, the workflow of the automatic adjustment unit includes:

[0035] The system maintenance module uses the automatic maintenance suggestion formula to automatically give maintenance suggestions or adjustment instructions based on the real-time data prediction of power generation efficiency and equipment status. At the same time, when the power generation efficiency is low, the system analyzes the equipment status through the equipment optimization formula to give an optimization strategy, and sends these instructions to the staff or automated equipment for execution. At the same time, the system optimizes the equipment power output according to the power generation efficiency and equipment adjustment formula to adjust the power generation efficiency of the system. In addition, the system will also decide whether to perform equipment maintenance or adjustment based on the feedback scheduling model formula. The automatic maintenance suggestion formula is: ZN(s)=if Q(s) min Then suggest_maintenance, where ZN(s) is the output of automatic adjustment, and the equipment optimization formula is: ΔB(s) = adjust(W dq , W yc ), where B(s) is the power generated by the device, W dq is the current power generation of the device, W yc It is the optimal power predicted based on environmental data. The power generation efficiency and equipment adjustment formula are:

[0036] Where ΔW(s) is the adjustment of the equipment power, Q opt (s) is the optimized power generation efficiency, Q(s) is the current power generation efficiency, W(s) is the current equipment power output, Q target is the target power output, n is the number of devices, and the feedback scheduling model formula is: Where K(s) is the feedback scheduling suggestion, Q(s) i is the power generation efficiency of the ith device, P i ​​is the weight of the ith device, Cost(Z j ) is the cost of the jth maintenance operation, n′ is the number of devices, and m″ is the number of maintenance operations.

[0037] On the other hand, the present invention also provides a new energy station monitoring method based on intelligent sensors, which comprises the following steps:

[0038] S1. Establish a multi-factor model to predict power generation efficiency;

[0039] S2. predicting burst data according to the power generation efficiency, and calibrating a multi-factor model according to the burst data;

[0040] S3, storing the burst data and regularly feeding back optimization suggestions to the off-site staff;

[0041] S4. Dynamically adjust the operating status of the new energy equipment in the station according to the power generation efficiency.

[0042] Furthermore, in step S1, a multi-factor model is established to predict the power generation efficiency as follows:

[0043] Used to collect various data in the station environment in real time to obtain real-time data and station power generation;

[0044] By correlating and analyzing the real-time data with the power generation of the station, a multi-factor model is established to predict power generation efficiency;

[0045] In step S2, the method of predicting burst data according to the power generation efficiency and calibrating the multi-factor model according to the burst data is as follows:

[0046] By real-time monitoring of the deviation between the health status of the new energy equipment in the station and the power generation efficiency, an abnormality detection algorithm is used to predict the sudden data of the new energy equipment in the station according to the power generation efficiency;

[0047] By calculating the differences between the burst data, the multi-factor model is dynamically calibrated.

[0048] Furthermore, in step S3, the method for storing the burst data and regularly feeding back optimization suggestions to the off-site is:

[0049] The collected burst data is stored, and the health status, power generation efficiency and burst data of the new energy equipment in the station are displayed to the staff through a display terminal;

[0050] Analyze the burst data, and regularly provide optimization suggestions to the site management personnel based on the data analysis results and the power generation efficiency;

[0051] In step S4, according to the power generation efficiency, the method for dynamically adjusting the operating state of the new energy equipment in the station is:

[0052] Adjustment suggestions are automatically given according to the power generation efficiency, and the operating status of the new energy equipment in the station is dynamically adjusted according to the adjustment suggestions.

[0053] Beneficial Effects

[0054] Compared with the known public technology, the technical solution provided by the present invention has the following advantages:

[0055] Beneficial effects:

[0056] When in use, the present invention adapts to seasonal changes and sudden weather conditions, which is not only conducive to improving the operating efficiency of new energy stations, but also optimizes energy management, ensures the sustainability and economy of the system, and enables new energy stations to operate in an efficient and stable environment by continuously optimizing the operation of units, further improving the overall power generation efficiency of new energy stations and reducing operation and maintenance costs. Real-time monitoring of power generation efficiency and equipment status data can determine whether each device needs maintenance or adjustment, which is conducive to reducing manual intervention, improving the intelligence of the system, ensuring that the power generation efficiency is always maintained in the best state, and maximizing resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is a system diagram of a new energy station monitoring system based on intelligent sensors of the present invention;

[0058] Figure 2 The present invention is a flow chart of a new energy station monitoring method based on intelligent sensors. DETAILED DESCRIPTION

[0059] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0060] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0061] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0062] Embodiment 1:

[0063] like Figure 1 As shown, the present invention provides a new energy station monitoring system based on intelligent sensors, including: an intelligent model unit, which establishes a multi-factor model to predict power generation efficiency;

[0064] The smart model unit includes:

[0065] Intelligent collection module, used to collect various data in the station environment in real time to obtain real-time data and station power generation;

[0066] A data processing module, which correlates and analyzes the real-time data with the power generation of the station and establishes a multi-factor model to predict power generation efficiency;

[0067] The workflow of the intelligent model unit includes:

[0068] The intelligent acquisition module collects various real-time data of the new energy station through various sensors, such as light intensity, temperature and humidity, wind speed, air quality, and station power generation, and transmits the real-time data to the data processing module;

[0069] The data processing module performs real-time correlation analysis on the real-time data and the power generation of the station, establishes a multi-factor model to predict the power generation efficiency under different environmental conditions, and considers various factors at the same time to analyze the impact of various factors on the power generation efficiency. The relationship between light intensity and power generation efficiency is not completely linear, and a nonlinear regression model is needed to describe it. Similarly, the relationship between temperature and humidity and power generation efficiency is more accurately modeled using a composite exponential function. The nonlinear regression model formula is: Where Q(s) is the power generation efficiency at time s, G(s) is the light intensity at time s, S(s) is the ambient temperature at time s, E(s) is the wind speed, χ is the influence coefficient of wind speed on power generation efficiency, α and β are the nonlinear relationship coefficients between light intensity and temperature, respectively. The formula of the composite exponential function is: Where Q0 is the basic power generation efficiency, S opt , R opt is the optimal value of temperature and humidity, δ1, δ2 are the coefficients of influence of temperature and humidity on power generation efficiency, S(s), R(s) are the current temperature and humidity, and then a multivariate linear regression model is used to combine different environmental factors to predict power generation efficiency, and regularization is used to prevent overfitting. According to the autoregressive integral moving average model, the time series of power generation efficiency can be predicted to adapt to short-term fluctuations and trend changes. The formula of the multivariate linear regression model is:

[0070] Among them, ε is the regularization coefficient, which controls the complexity of the model and avoids overfitting. G(s), S(s), E(s), and TY(s) are light intensity, temperature, wind speed, and air quality, respectively. The formula of the autoregressive integrated moving average model is: Where c is a constant term, φ L is the autoregressive coefficient, which indicates the influence of the power generation efficiency at the past o time points on the current power generation efficiency, ∈(s) is the white noise term, which represents random disturbance, is the moving average coefficient, which indicates the impact of the error at the past m time points on the current prediction, L is the index variable of the autoregressive part, and its value range is from 1 to o; j is the index variable of the sliding average part, and its value range is from 1 to m;

[0071] Specifically, in a certain new energy station, this system deploys an intelligent collection module to collect real-time environmental data, and uses a data processing module to associate these real-time data with the historical power generation efficiency of the station. Through multi-factor modeling, the power generation efficiency is predicted, and the short-term fluctuation of the power generation efficiency time series is predicted based on the autoregressive model to adapt to seasonal changes and sudden weather conditions. This is not only conducive to improving the operating efficiency of new energy stations, but also to optimizing energy management and ensuring the sustainability and economy of the system.

[0072] A continuous optimization unit predicts burst data according to the power generation efficiency and calibrates a multi-factor model according to the burst data;

[0073] The continuous optimization unit includes:

[0074] A prediction and diagnosis module, which monitors the deviation between the health status of the new energy equipment in the station and the power generation efficiency in real time, and predicts the sudden data of the new energy equipment in the station by using an anomaly detection algorithm according to the power generation efficiency;

[0075] A calibration module dynamically calibrates the multi-factor model by calculating the difference between the burst data;

[0076] The workflow of the continuous optimization unit includes:

[0077] The predictive diagnosis module continuously tracks the working status of each device in the station through the equipment health monitoring sensor, records various data, compares the working status of each device with the actual power generation efficiency in real time, monitors the health status of the station equipment and the deviation of power generation efficiency in real time through the abnormal detection algorithm and prediction method, and analyzes whether the power generation efficiency is affected by equipment failure or performance degradation. At the same time, based on historical data and real-time monitoring data, the prediction algorithm is used to predict the possible sudden state of the equipment, issue an alarm in advance, and prompt the staff to take necessary preventive measures. The power generation efficiency deviation formula is: ΔQ(s)=Q predicted (s)-Q actual (s), fault detection formula: Q forecast (s)=ARIMA(Q(s)), set the deviation threshold of power generation efficiency to γ, and if |ΔQ(s)|>γ, it is considered that the equipment may fail;

[0078] The proofreading module compares the environmental data and power generation efficiency collected in real time with the historical data. According to the comparison results of the model calibration formula, the prediction model of power generation efficiency is optimized and updated through the dynamic programming formula. The updated power generation efficiency prediction model generates a new power generation efficiency prediction value, which is input into the data feedback unit and the automatic adjustment unit to ensure that the prediction of power generation efficiency is more accurate. The model calibration formula is: Among them, H new is the corrected regression coefficient, H old is the old regression coefficient, η is the learning rate control update step, ΔQ(s) is the real-time deviation, and the dynamic programming formula is:

[0079] Where K(s) is the cost function representing the sum of squares of the power generation efficiency prediction error and the regularization term, is a constant used to scale or adjust the loss function, n is the number of data points, m′ is the total number of parameters in the model, and Q actual (s) is the actual power generation efficiency, Q predicted (s) is the predicted power generation efficiency, ν j is the parameter of the model, μ is the regularization coefficient used to control the complexity of the model;

[0080] Specifically, in a certain new energy station, based on the data collected in real time, the predictive diagnosis module can track the working status of each device and compare these data with the predicted power generation efficiency. When it is found that the equipment performance has declined and the power generation efficiency deviation exceeds the threshold of 5%, the system will trigger an early warning to prompt the staff that the equipment has failed. At the same time, the proofreading module will compare the real-time collected data with the historical data, and then adjust the regression coefficient and optimize the prediction model of power generation efficiency, so as to more accurately predict future power generation efficiency, which is conducive to continuously optimizing the operation of the unit, so that the new energy station can operate in an efficient and stable environment, further improving the overall power generation efficiency of the new energy station and reducing operation and maintenance costs.

[0081] A data feedback unit stores the burst data and regularly feeds back optimization suggestions to the off-site personnel;

[0082] The data feedback unit includes:

[0083] A data storage module stores the collected burst data and displays the health status, power generation efficiency and burst data of the new energy equipment in the station to the staff through a display terminal;

[0084] A feedback mechanism is used to analyze the burst data and provide optimization suggestions to the station management personnel on a regular basis based on the data analysis results and the power generation efficiency;

[0085] The workflow of the data feedback unit includes:

[0086] The data storage module stores the collected real-time data, historical data and power generation efficiency prediction results for subsequent analysis and use. The stored historical data is used to analyze the long-term impact of environmental factors and equipment status on power generation efficiency and to learn for the optimization algorithm. At the same time, the data query formula is used to query historical data, real-time data and power generation efficiency prediction results at any time to provide decision support for managers. The data query formula is:

[0087] Among them C stored (t) is the stored data, which summarizes all the collected data at different time points. G(s), S(s), E(s), and TY(s) are the collected data of the light intensity sensor, temperature sensor, wind speed sensor, and air quality sensor, respectively;

[0088] Feedback mechanism, based on data analysis results and power generation efficiency prediction, regularly generates optimization suggestions based on historical data, and uses threshold-based rules for feedback. The optimization feedback formula is: FK(t)=if Q predicted (t) min , where Q min ​It is the set minimum power generation efficiency threshold. In addition, when abnormal equipment health status or power generation efficiency is detected, an alarm will be immediately sent to the staff;

[0089] Specifically, in a certain new energy site, the data storage module records in real time various environmental data and power generation data transmitted from other units of the system, and provides managers with the function of viewing power generation efficiency prediction results in real time. At the same time, historical data is continuously stored to analyze the impact of past operating conditions on power generation efficiency, providing data support for subsequent optimization, and comparing the current power generation efficiency with the minimum threshold through a feedback mechanism. When the power generation efficiency is lower than the set threshold, the system will automatically generate optimization suggestions and notify the management personnel through the display terminal or alarm system. At the same time, if the health status of the equipment is abnormal, the system will immediately trigger an alarm to prompt the staff to carry out maintenance, which is conducive to improving operation and maintenance efficiency.

[0090] An automatic adjustment unit dynamically adjusts the operating state of the new energy equipment in the station according to the power generation efficiency;

[0091] The automatic adjustment unit includes:

[0092] An automatic adjustment module automatically gives adjustment suggestions according to the power generation efficiency, and dynamically adjusts the operating status of the new energy equipment in the station according to the adjustment suggestions;

[0093] The workflow of the automatic adjustment unit includes:

[0094] The system maintenance module uses the automatic maintenance suggestion formula to automatically give maintenance suggestions or adjustment instructions based on the real-time data prediction of power generation efficiency and equipment status. At the same time, when the power generation efficiency is low, the system analyzes the equipment status through the equipment optimization formula to give an optimization strategy, and sends these instructions to the staff or automated equipment for execution. At the same time, the system optimizes the equipment power output according to the power generation efficiency and equipment adjustment formula to adjust the power generation efficiency of the system. In addition, the system will also decide whether to perform equipment maintenance or adjustment based on the feedback scheduling model formula. The automatic maintenance suggestion formula is: ZN(s)=if Q(s) min Then suggest_maintenance, where ZN(s) is the output of automatic adjustment, and the equipment optimization formula is: ΔB(s) = adjust(W dq , W yc ), where B(s) is the power generated by the device, W dq is the current power generation of the device, W yc It is the optimal power predicted based on environmental data. The power generation efficiency and equipment adjustment formula are:

[0095] Where ΔW(s) is the adjustment of the equipment power, Q​opt (s) is the optimized power generation efficiency, Q(s) is the current power generation efficiency, W(s) is the current equipment power output, Q target is the target power output, n is the number of devices, and the feedback scheduling model formula is: Where K(s) is the feedback scheduling suggestion, Q(s) i is the power generation efficiency of the ith device, P i is the weight of the ith device, Cost(Z j ) is the cost of the jth maintenance operation, n′ is the number of devices, and m″ is the number of maintenance operations;

[0096] Specifically, in a certain new energy site, the system maintenance module monitors the power generation efficiency and equipment status data in real time to determine whether each device needs maintenance or adjustment. When it detects that the power generation efficiency of the equipment has dropped below the set expected value, the system will evaluate the difference between the actual power of the equipment and the predicted optimal power, and give adjustment instructions. After executing the adjustment instructions, if the power generation efficiency of the equipment still does not meet expectations, the system will optimize the power output of the equipment to improve the overall power generation efficiency, which is conducive to reducing manual intervention, improving the intelligence of the system, ensuring that the power generation efficiency is always maintained at the best state, and maximizing resource utilization.

[0097] Embodiment 2:

[0098] like Figure 2 As shown, embodiment 2 provides a new energy station monitoring method based on intelligent sensors, which includes the following steps:

[0099] S1. Establish a multi-factor model to predict power generation efficiency;

[0100] S2. predicting burst data according to the power generation efficiency, and calibrating a multi-factor model according to the burst data;

[0101] S3, storing the burst data and regularly feeding back optimization suggestions to the off-site staff;

[0102] S4. Dynamically adjust the operating status of the new energy equipment in the station according to the power generation efficiency.

[0103] Furthermore, in step S1, a multi-factor model is established to predict the power generation efficiency as follows:

[0104] Used to collect various data in the station environment in real time to obtain real-time data and station power generation;

[0105] By correlating and analyzing the real-time data with the power generation of the station, a multi-factor model is established to predict power generation efficiency;

[0106] In step S2, the method of predicting burst data according to the power generation efficiency and calibrating the multi-factor model according to the burst data is as follows:

[0107] By real-time monitoring of the deviation between the health status of the new energy equipment in the station and the power generation efficiency, an abnormality detection algorithm is used to predict the sudden data of the new energy equipment in the station according to the power generation efficiency;

[0108] By calculating the differences between the burst data, the multi-factor model is dynamically calibrated.

[0109] Furthermore, in step S3, the method for storing the burst data and regularly feeding back optimization suggestions to the off-site is:

[0110] The collected burst data is stored, and the health status, power generation efficiency and burst data of the new energy equipment in the station are displayed to the staff through a display terminal;

[0111] Analyze the burst data, and regularly provide optimization suggestions to the site management personnel based on the data analysis results and the power generation efficiency;

[0112] In step S4, according to the power generation efficiency, the method for dynamically adjusting the operating state of the new energy equipment in the station is:

[0113] Adjustment suggestions are automatically given according to the power generation efficiency, and the operating status of the new energy equipment in the station is dynamically adjusted according to the adjustment suggestions.

[0114] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A new energy station monitoring system based on intelligent sensors, characterized in that: include: Intelligent model unit, which builds a multi-factor model to predict power generation efficiency; A continuous optimization unit predicts burst data according to the power generation efficiency and calibrates a multi-factor model according to the burst data; A data feedback unit stores the burst data and regularly feeds back optimization suggestions to the off-site personnel; The automatic adjustment unit dynamically adjusts the operating status of the new energy equipment in the station according to the power generation efficiency.

2. According to claim 1, a new energy station monitoring system based on intelligent sensors is characterized in that: The smart model unit includes: Intelligent collection module, used to collect various data in the station environment in real time to obtain real-time data and station power generation; A data processing module, which correlates and analyzes the real-time data with the power generation of the station and establishes a multi-factor model to predict power generation efficiency; The continuous optimization unit includes: A prediction and diagnosis module, which monitors the deviation between the health status of the new energy equipment in the station and the power generation efficiency in real time, and predicts the sudden data of the new energy equipment in the station by using an anomaly detection algorithm according to the power generation efficiency; The calibration module dynamically calibrates the multi-factor model by calculating the differences between the burst data.

3. According to claim 2, a new energy station monitoring system based on intelligent sensors is characterized in that: The data feedback unit includes: A data storage module stores the collected burst data and displays the health status, power generation efficiency and burst data of the new energy equipment in the station to the staff through a display terminal; A feedback mechanism is used to analyze the burst data and provide optimization suggestions to the station management personnel on a regular basis based on the data analysis results and the power generation efficiency; The automatic adjustment unit includes: The automatic adjustment module automatically gives adjustment suggestions according to the power generation efficiency, and dynamically adjusts the operating status of the new energy equipment in the station according to the adjustment suggestions.

4. According to claim 3, a new energy station monitoring system based on intelligent sensors is characterized in that: The workflow of the intelligent model unit includes: The intelligent acquisition module collects various real-time data of the new energy station through various sensors, such as light intensity, temperature and humidity, wind speed, air quality, and station power generation, and transmits the real-time data to the data processing module; The data processing module performs real-time correlation analysis on the real-time data and the power generation of the station, establishes a multi-factor model to predict the power generation efficiency under different environmental conditions, and considers various factors at the same time to analyze the impact of various factors on the power generation efficiency. The relationship between light intensity and power generation efficiency is not completely linear, and a nonlinear regression model is needed to describe it. Similarly, the relationship between temperature and humidity and power generation efficiency is more accurately modeled using a composite exponential function. The nonlinear regression model formula is: Where Q(s) is the power generation efficiency at time s, G(s) is the light intensity at time s, S(s) is the ambient temperature at time s, E(s) is the wind speed, χ is the influence coefficient of wind speed on power generation efficiency, α and β are the nonlinear relationship coefficients between light intensity and temperature, respectively. The formula of the composite exponential function is: Q(s)=Q0×exp[-δ1×(S(s)-S opt ) 2 ]×exp[-δ2×(R(s)-R opt ) 2 ], where Q0 is the basic power generation efficiency, S opt , R opt is the optimal value of temperature and humidity, δ1, δ2 are the coefficients of influence of temperature and humidity on power generation efficiency, S(s), R(s) are the current temperature and humidity, and then a multivariate linear regression model is used to combine different environmental factors to predict power generation efficiency, and regularization is used to prevent overfitting. According to the autoregressive integral moving average model, the time series of power generation efficiency can be predicted to adapt to short-term fluctuations and trend changes. The formula of the multivariate linear regression model is: Among them, ε is the regularization coefficient, which controls the complexity of the model and avoids overfitting. G(s), S(s), E(s), and TY(s) are light intensity, temperature, wind speed, and air quality, respectively. The formula of the autoregressive integrated moving average model is: Where c is a constant term, φ L is the autoregressive coefficient, which indicates the influence of the power generation efficiency at the past o time points on the current power generation efficiency, ∈(s) is the white noise term, which represents random disturbance, is the moving average coefficient, which indicates the impact of the error at the past m time points on the current prediction. L is the index variable of the autoregressive part, and its value range is from 1 to o. j is the index variable of the sliding average part, and its value range is from 1 to m.

5. A new energy station monitoring system based on intelligent sensors according to claim 4, characterized in that: The workflow of the continuous optimization unit includes: The predictive diagnosis module continuously tracks the working status of each device in the station through the equipment health monitoring sensor, records various data, compares the working status of each device with the actual power generation efficiency in real time, monitors the health status of the station equipment and the deviation of power generation efficiency in real time through the abnormal detection algorithm and prediction method, and analyzes whether the power generation efficiency is affected by equipment failure or performance degradation. At the same time, based on historical data and real-time monitoring data, the prediction algorithm is used to predict the possible sudden state of the equipment, issue an alarm in advance, and prompt the staff to take necessary preventive measures. The power generation efficiency deviation formula is: ΔQ(s)=Q predicted (s)-Q actual (s), fault detection formula: Q forecast (s)=ARIMA(Q(s)), set the deviation threshold of power generation efficiency to γ, and if |ΔQ(s)|>γ, it is considered that the equipment may fail; The proofreading module compares the environmental data and power generation efficiency collected in real time with the historical data. According to the comparison results of the model calibration formula, the prediction model of power generation efficiency is optimized and updated through the dynamic programming formula. The updated power generation efficiency prediction model generates a new power generation efficiency prediction value, which is input into the data feedback unit and the automatic adjustment unit to ensure that the prediction of power generation efficiency is more accurate. The model calibration formula is: Among them, H new is the corrected regression coefficient, H old is the old regression coefficient, η is the learning rate control update step, ΔQ(s) is the real-time deviation, and the dynamic programming formula is: Where K(s) is the cost function representing the sum of squares of the power generation efficiency prediction error and the regularization term, is a constant used to scale or adjust the loss function, n is the number of data points, m′ is the total number of parameters in the model, and Q actual (s) is the actual power generation efficiency, Q predicted (s) is the predicted power generation efficiency, ν j is the parameter of the model, and μ is the regularization coefficient used to control the complexity of the model.

6. A new energy station monitoring system based on intelligent sensors according to claim 5, characterized in that: The workflow of the data feedback unit includes: The data storage module stores the collected real-time data, historical data and power generation efficiency prediction results for subsequent analysis and use. The stored historical data is used to analyze the long-term impact of environmental factors and equipment status on power generation efficiency and to learn for the optimization algorithm. At the same time, the data query formula is used to query historical data, real-time data and power generation efficiency prediction results at any time to provide decision support for managers. The data query formula is: Among them C stored (t) is the stored data, which summarizes all the collected data at different time points. G(s), S(s), E(s), and TY(s) are the collected data of the light intensity sensor, temperature sensor, wind speed sensor, and air quality sensor, respectively; Feedback mechanism, based on data analysis results and power generation efficiency prediction, regularly generates optimization suggestions based on historical data, and uses threshold-based rules for feedback. The optimization feedback formula is: FK(t)=if Q predicted (t) min , where Q min It is the set minimum power generation efficiency threshold. In addition, when an abnormality in the health status of the equipment or abnormal power generation efficiency is detected, an alarm will be sent to the staff immediately.​ 7. A new energy station monitoring system based on intelligent sensors according to claim 6, characterized in that: The workflow of the automatic adjustment unit includes: The system maintenance module uses the automatic maintenance suggestion formula to automatically give maintenance suggestions or adjustment instructions based on the real-time data prediction of power generation efficiency and equipment status. At the same time, when the power generation efficiency is low, the system analyzes the equipment status through the equipment optimization formula to give an optimization strategy, and sends these instructions to the staff or automated equipment for execution. At the same time, the system optimizes the equipment power output according to the power generation efficiency and equipment adjustment formula to adjust the power generation efficiency of the system. In addition, the system will also decide whether to perform equipment maintenance or adjustment based on the feedback scheduling model formula. The automatic maintenance suggestion formula is: ZN(s)=if Q(s) min Then suggest_maintenance, where ZN(s) is the output of automatic adjustment, and the equipment optimization formula is: ΔB(s) = adjust(W dq , W yc ), where B(s) is the power generated by the device, W dq is the current power generation of the device, W yc It is the optimal power predicted based on environmental data. The power generation efficiency and equipment adjustment formula are:​ Where ΔW(s) is the adjustment of the equipment power, Q opt (s) is the optimized power generation efficiency, Q(s) is the current power generation efficiency, W(s) is the current equipment power output, Q target is the target power output, n is the number of devices, and the feedback scheduling model formula is: Where K(s) is the feedback scheduling suggestion, Q(s) i is the power generation efficiency of the ith device, P i is the weight of the ith device, Cost(Z j ) is the cost of the jth maintenance operation, n′ is the number of devices, and m″ is the number of maintenance operations.

8. A new energy station monitoring method based on smart sensors, based on a new energy station monitoring system based on smart sensors as claimed in any one of claims 1 to 7, characterized in that: The following steps are involved: S1. Establish a multi-factor model to predict power generation efficiency; S2. predicting burst data according to the power generation efficiency, and calibrating a multi-factor model according to the burst data; S3, storing the burst data and regularly feeding back optimization suggestions to the off-site staff; S4. Dynamically adjust the operating status of the new energy equipment in the station according to the power generation efficiency.

9. A new energy station monitoring method based on intelligent sensors according to claim 8, characterized in that: In step S1, a multi-factor model is established to predict the power generation efficiency as follows: Used to collect various data in the station environment in real time to obtain real-time data and station power generation; By correlating and analyzing the real-time data with the power generation of the station, a multi-factor model is established to predict power generation efficiency; In step S2, the method of predicting burst data according to the power generation efficiency and calibrating the multi-factor model according to the burst data is as follows: By real-time monitoring of the deviation between the health status of the new energy equipment in the station and the power generation efficiency, an abnormality detection algorithm is used to predict the sudden data of the new energy equipment in the station according to the power generation efficiency; By calculating the differences between the burst data, the multi-factor model is dynamically calibrated.

10. A new energy station monitoring method based on intelligent sensors according to claim 9, characterized in that: In step S3, the method for storing the burst data and regularly feeding back optimization suggestions to the off-site is: The collected burst data is stored, and the health status, power generation efficiency and burst data of the new energy equipment in the station are displayed to the staff through a display terminal; Analyze the burst data, and regularly provide optimization suggestions to the site management personnel based on the data analysis results and the power generation efficiency; In step S4, according to the power generation efficiency, the method for dynamically adjusting the operating state of the new energy equipment in the station is: Adjustment suggestions are automatically given according to the power generation efficiency, and the operating status of the new energy equipment in the station is dynamically adjusted according to the adjustment suggestions.

Images