New energy state monitoring method based on Internet of Things

Abstract

The invention discloses a new energy state monitoring method based on Internet of Things, and relates to the technical field of new energy, and the system comprises the following components: S100, Internet of Things data acquisition system construction, S200, dynamic adaptive monitoring strategy design, S300, intelligent early warning and fault diagnosis, and S400, monitoring strategy continuous optimization. According to the method, equipment state changes can be monitored more meticulously by collecting equipment operation parameters and environment data in real time and applying a dynamic self-adaptive monitoring strategy, compared with a traditional fixed monitoring mode, the method can discover and early warn potential faults in time, the monitoring efficiency is remarkably improved, and meanwhile, the method is suitable for popularization and application. Through the application of algorithm analysis and a machine learning technology, the method can automatically optimize a monitoring strategy, and sets a more accurate early warning threshold for each monitoring parameter, thereby improving the monitoring accuracy.

Description

Technical Field

[0001] The present invention relates to the field of new energy technology, and in particular to a new energy state monitoring method based on the Internet of Things. Background Art

[0002] With the continuous development and popularization of new energy technologies, the safe and efficient operation of new energy equipment has become an urgent problem to be solved. New energy equipment is usually deployed in complex and changing environments, and its operating status is affected by many factors, including the equipment's own operating parameters and external environmental conditions. In order to ensure the stable operation of new energy equipment, it is particularly important to monitor its status changes in a timely and accurate manner.

[0003] The traditional fixed monitoring mode, that is, collecting and analyzing data according to preset time intervals and fixed monitoring parameters, is difficult to effectively capture subtle and abnormal changes in equipment status, resulting in low monitoring efficiency and delayed fault warning. Therefore, it is particularly important to develop a new energy status monitoring method based on the Internet of Things. Summary of the invention

[0004] The purpose of the present invention is to make up for the deficiencies of the prior art and provide a new energy status monitoring method based on the Internet of Things. The method realizes dynamic adaptive monitoring of equipment status through the Internet of Things technology to improve monitoring efficiency and accuracy, and timely discover and prevent potential faults.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a new energy status monitoring method based on the Internet of Things, the specific steps of the method are:

[0006] S100, IoT data collection system construction: Deploy IoT sensor networks in key parts of new energy equipment and the surrounding environment to collect equipment operating parameters and environmental data in real time. The data is transmitted wirelessly to the cloud or local data center to provide a basis for subsequent analysis;

[0007] S200, dynamic adaptive monitoring strategy design: According to the real-time working status and environmental conditions of new energy equipment, the monitoring frequency and parameter range are dynamically adjusted to monitor the equipment status changes in more detail. The algorithm analyzes the historical monitoring data, identifies the laws and trends of equipment status changes, and automatically optimizes the monitoring strategy to achieve intelligent and personalized monitoring.

[0008] S300, intelligent early warning and fault diagnosis: The IoT data collection system can continuously and accurately collect real-time monitoring data of new energy equipment, including operating parameters and environmental data, pre-process the collected data, set early warning thresholds for each monitoring parameter based on the dynamically adjusted monitoring strategy, use analytical technology to perform anomaly detection on real-time monitoring data, identify abnormal changes in equipment status, and issue early warning signals in a timely manner when abnormal status is detected to notify operation and maintenance personnel to pay attention and prepare for troubleshooting;

[0009] Combined with the expert system and knowledge base, the system conducts in-depth analysis of warning information, including but not limited to the causes and impact scope of abnormal conditions. Based on the analysis results, it provides fault diagnosis suggestions and presents them to operation and maintenance personnel in an intuitive and easy-to-understand manner, helping them to quickly locate problems and formulate corresponding countermeasures.

[0010] The operation and maintenance personnel formulate specific maintenance plans based on the fault diagnosis suggestions, implement them, evaluate the effects of the measures after implementation, collect feedback from the operation and maintenance personnel based on the evaluation results, and continuously optimize and improve the intelligent early warning and fault diagnosis system;

[0011] S400, continuous optimization of monitoring strategies: Through the feedback mechanism, the actual operation and maintenance results are combined with historical monitoring data to further optimize the monitoring strategy, form a closed-loop optimization system, introduce a continuous learning mechanism, and continuously absorb new data and new knowledge.

[0012] Furthermore, the S100 clarifies the monitoring requirements of new energy equipment, determines the type and quantity of sensors, plans data transmission paths, installs sensors at key parts of the equipment and the surrounding environment, configures data collectors, ensures the stability and security of power supply and communication, configures data transmission protocols and encryption methods, establishes a data storage system, implements data quality control measures, conducts system function and performance tests, and continuously improves and optimizes based on user feedback.

[0013] Furthermore, the S200 real-time data collection and analysis is the basis of the dynamic adaptive monitoring strategy. The IoT data acquisition system obtains the operating parameters and environmental data of new energy equipment in real time, and performs preliminary processing to ensure data quality. Based on these data, the working status of the equipment is evaluated in real time, and the monitoring frequency and parameter range are dynamically adjusted considering the influence of environmental conditions.

[0014] Furthermore, the S200 algorithm analysis and optimization is the key to improving the intelligence of monitoring strategies. By collecting and integrating historical monitoring data, machine learning algorithms are used to identify the patterns and trends of equipment status changes. Based on these analysis results, monitoring strategies are automatically adjusted, including monitoring parameters and warning thresholds. The optimized strategies are applied to actual monitoring, and user feedback is continuously collected to perform closed-loop optimization of the strategies.

[0015] Furthermore, the S300 sets a warning threshold for each monitoring parameter based on the dynamically adjusted monitoring strategy: Among them, T n is the warning threshold of parameter n, A n is the basic threshold of parameter n, α and β are adjustment coefficients, D n is the data dispersion of parameter n in the current time period, D avg is the average value of the discreteness of all monitoring parameter data, C n is the rate of change of parameter n, C avg It is the average value of the change rate of all monitored parameters.

[0016] Furthermore, the S300 uses analytical technology to perform anomaly detection on real-time monitoring data and identify abnormal changes in device status: Among them, E represents the outlier index, n is the number of monitoring parameters, and A i is the real-time monitoring value of parameter i, M i is the dynamic mean of parameter i, w i is the weight of parameter i, γ is the adjustment coefficient, and D is the dispersion index of the data.

[0017] Furthermore, the S400 establishes a feedback mechanism to optimize the monitoring strategy, collects feedback from operation and maintenance personnel on the accuracy of early warning and fault diagnosis efficiency through real-time channels, and integrates it with historical monitoring data to form a complete feedback data set, and uses association analysis and cluster analysis data analysis techniques to mine key information and provide data support for strategy adjustment.

[0018] Furthermore, the S400 adjusts monitoring parameters, warning thresholds and data collection frequency according to the analysis results, and introduces new technologies such as deep learning and edge computing to improve the level of intelligence. The optimized strategy is deployed to the IoT data collection system, and the equipment operation status and warning status are continuously monitored. The equipment operation parameters and environmental conditions monitoring data are regularly updated. The expert system and knowledge base are updated in combination with industry standards and the latest research results to achieve iterative optimization of strategies, form a closed-loop system, and continuously improve accuracy and reliability.

[0019] Compared with the existing technology, the new energy status monitoring method based on the Internet of Things has the following beneficial effects:

[0020] 1. This method can monitor equipment status changes more carefully by collecting equipment operating parameters and environmental data in real time and using dynamic adaptive monitoring strategies. Compared with the traditional fixed monitoring mode, this method can timely detect and warn of potential faults, significantly improving monitoring efficiency. At the same time, through the application of algorithm analysis and machine learning technology, this method can automatically optimize the monitoring strategy and set more accurate warning thresholds for each monitoring parameter, thereby improving the accuracy of monitoring.

[0021] 2. By combining intelligent early warning and fault diagnosis systems, this method can automatically detect anomalies in real-time monitoring data and provide fault diagnosis suggestions. Operation and maintenance personnel can quickly locate problems and formulate corresponding countermeasures based on these suggestions, thereby realizing intelligent operation and maintenance. In addition, this method also establishes a feedback mechanism. By collecting feedback from operation and maintenance personnel and continuously optimizing monitoring strategies, a closed-loop optimization system is formed. This continuous optimization mechanism enables the method to continuously absorb new data and new knowledge, further improve its accuracy and reliability, and provide strong guarantees for the stable operation of new energy equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 Operational flow chart of new energy status monitoring method based on Internet of Things. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] Embodiment 1

[0026] It is necessary to clarify the specific monitoring requirements of new energy equipment, including the operating parameters and environmental data that need to be monitored. According to the monitoring objectives, select the appropriate type of IoT sensor and determine the number of sensors required for each monitoring point. This usually requires considering the accuracy, response time, working range and cost factors of the sensor, and design the data transmission path of the sensor network, including the connection between the sensor and the data collector, and the communication method between the data collector and the cloud or local data center;

[0027] Installing sensors in key parts of new energy equipment and in the surrounding environment may require a professional installation team to ensure that the sensors can accurately and stably collect data and do not affect the normal operation of the equipment. Configure data collectors to receive data from sensors and perform preliminary processing and storage. Data collectors usually need to be paired with sensors and set appropriate data collection frequencies and transmission parameters. Provide reliable power supply for sensors and data collectors, and ensure the stability and security of the communication network. For remote or difficult-to-power monitoring points, it may be necessary to consider using solar and wind renewable energy as power sources. Configure data transmission protocols and encryption methods to ensure that sensor data can be safely and reliably transmitted to the cloud or local data center. For wireless transmission methods, it is necessary to select appropriate communication frequency bands and modulation methods to optimize the efficiency and stability of data transmission. Establish a data storage system in the cloud or local data center to store and manage sensor data. This usually includes designing database structures, setting data backup and recovery strategies, and implementing data quality control measures during data transmission and storage to ensure data accuracy and reliability.

[0028] Conduct comprehensive functional testing on the IoT data acquisition system, including the data acquisition capability of the sensor, the reliability and stability of data transmission, the integrity and security of data storage, evaluate the system's performance indicators, and make optimization adjustments based on the test results, collect user feedback, and continuously improve and optimize the system to meet the actual needs of new energy equipment status monitoring.

[0029] Ensure that the IoT data collection system can obtain the operating parameters and environmental data of new energy equipment in real time, perform preliminary processing on real-time data, identify abnormal values ​​and missing values, and perform necessary cleaning and preprocessing to ensure data quality. Based on real-time data, conduct real-time evaluation of the working status of new energy equipment, including load level and operating efficiency, analyze the impact of environmental conditions on equipment status, determine whether the monitoring strategy needs to be adjusted, and dynamically adjust the monitoring frequency and parameter range according to the equipment status and environmental conditions. For example, under high load or extreme environmental conditions, increase the monitoring frequency and expand the monitoring parameter range;

[0030] Collect and integrate historical monitoring data, including equipment status, environmental conditions, and any relevant fault records. Use machine learning algorithms to conduct in-depth analysis of historical data, identify the patterns and trends of equipment status changes, and automatically adjust monitoring strategies based on algorithm analysis results, including monitoring parameters and early warning thresholds, to achieve more intelligent and personalized monitoring. Apply the optimized monitoring strategy to actual new energy equipment status monitoring, and regularly evaluate the implementation effect of the new strategy, including the accuracy of monitoring data, the timeliness of early warning, and the accuracy of fault detection. Based on the evaluation results, collect user feedback, continuously optimize the monitoring strategy, and form a closed-loop optimization system.

[0031] The IoT data collection system can continuously and accurately collect real-time monitoring data of new energy equipment, including operating parameters and environmental data, pre-process the collected data, and set early warning thresholds for each monitoring parameter based on the dynamically adjusted monitoring strategy. Among them, T n is the warning threshold of parameter n, A n is the basic threshold of parameter n, α and β are adjustment coefficients, D n is the data dispersion of parameter n in the current time period, D avg is the average value of the discreteness of all monitoring parameter data, C n is the rate of change of parameter n, C avg It is the average value of the change rate of all monitoring parameters. It uses analytical technology to detect anomalies in real-time monitoring data and identify abnormal changes in equipment status. Among them, E represents the outlier index, n is the number of monitoring parameters, and A i is the real-time monitoring value of parameter i, M i is the dynamic mean of parameter i, w i is the weight of parameter i, γ is the adjustment coefficient, and D is the data dispersion index. When an abnormal state is detected, an early warning signal is issued in time to notify the operation and maintenance personnel to pay attention and prepare for troubleshooting;

[0032] Combined with the expert system and knowledge base, the system conducts in-depth analysis of warning information, including but not limited to the causes and impact scope of abnormal conditions. Based on the analysis results, it provides fault diagnosis suggestions and presents them to operation and maintenance personnel in an intuitive and easy-to-understand manner, helping them to quickly locate problems and formulate corresponding countermeasures.

[0033] Based on the fault diagnosis suggestions, the operation and maintenance personnel formulate and implement specific maintenance plans, evaluate the effects of the measures after implementation, collect feedback from the operation and maintenance personnel based on the evaluation results, and continuously optimize and improve the intelligent early warning and fault diagnosis system.

[0034] Establish channels to collect regular or real-time feedback from operation and maintenance personnel on the effectiveness of monitoring strategies in actual operations, including early warning accuracy and fault diagnosis efficiency. Integrate operation and maintenance feedback with historical monitoring data to form a complete feedback data set to provide data support for strategy optimization. Use data analysis technology to mine key information and potential rules in feedback data. Based on the feedback data set, evaluate the effectiveness of the current monitoring strategy and identify existing deficiencies and potential improvement directions.

[0035] According to the evaluation results, the monitoring strategy is adjusted, including monitoring parameters, early warning thresholds, and data collection frequency, to improve the accuracy of early warnings and the efficiency of fault diagnosis. In combination with industry development trends, new monitoring technologies and methods are introduced to improve the intelligence level of the monitoring strategy. The optimized monitoring strategy is deployed to the Internet of Things data collection system to ensure that the new strategy can be effectively implemented. After the new strategy is implemented, the operating status and early warning status of the equipment are continuously monitored to ensure the effectiveness of the new strategy. New monitoring data is regularly collected, including equipment operating parameters and environmental conditions, to provide a data basis for continuous learning. In combination with industry standards and the latest research results, the expert system and knowledge base are updated to ensure that the monitoring strategy can continuously absorb new knowledge. Based on new data and knowledge, the monitoring strategy is iteratively optimized to form a closed-loop optimization system to continuously improve the accuracy and reliability of the monitoring strategy.

[0036] Embodiment 2

[0037] IoT sensor networks are carefully deployed in key parts and surrounding environments of wind turbines. These sensors can sense and collect equipment operating parameters and environmental data in real time. The real-time collected data include but are not limited to equipment speed, temperature, vibration amplitude, oil condition operating parameters, and wind speed, wind direction, temperature, humidity environmental data. These data are crucial for subsequent equipment status analysis and fault diagnosis. The collected data is transmitted wirelessly to the cloud data center. During the data transmission process, advanced data encryption and security protocols are used to ensure data integrity and security.

[0038] According to the real-time working status and environmental conditions of the wind turbine, the monitoring frequency and parameter range are dynamically adjusted. For example, when the wind speed is high and the equipment load is heavy, the monitoring frequency is increased and key parameters are focused on to more carefully monitor changes in equipment status. Machine learning algorithms are used to conduct in-depth analysis of historical monitoring data to identify the patterns and trends of equipment status changes. Based on these analysis results, monitoring strategies are automatically optimized, including adjusting monitoring parameters and early warning thresholds, to achieve intelligent and personalized monitoring.

[0039] The IoT data collection system can continuously and accurately collect real-time monitoring data of wind power generation equipment, pre-process and detect anomalies of the collected data, and identify abnormal changes in the equipment status. Where E represents the outlier index, n is the number of parameters of the monitored wind power equipment, and A i is the real-time monitoring value of parameter i, M i is the dynamic mean of parameter i, w i is the weight of parameter i, γ is the adjustment coefficient, and D is the discreteness index of the data. When an abnormal state is detected, the system can issue an early warning signal in time and notify the operation and maintenance personnel through SMS, email, and APP push. The early warning information includes the specific location of the abnormal state, possible causes, and recommended countermeasures. Combined with the expert system and knowledge base, the early warning information is deeply analyzed, and the abnormal state is diagnosed using professional knowledge and experience, and detailed fault diagnosis suggestions are provided. These suggestions are presented to the operation and maintenance personnel in an intuitive and easy-to-understand way to help them quickly locate the problem and formulate corresponding countermeasures.

[0040] Through the feedback mechanism, the actual operation and maintenance effects are combined with historical monitoring data to further optimize the monitoring strategy. Feedback from operation and maintenance personnel on the accuracy of early warning and fault diagnosis efficiency is collected as an important basis for strategy adjustment. A continuous learning mechanism is introduced to continuously absorb new data and new knowledge. The intelligence level of the monitoring system is improved by using new technologies such as deep learning and edge computing. At the same time, equipment operating parameters, environmental conditions monitoring data, expert systems and knowledge bases are regularly updated to ensure the accuracy and reliability of the monitoring strategy. The optimized strategy is deployed to the Internet of Things data collection system, and the equipment operating status and early warning status are continuously monitored. According to the monitoring results and operation and maintenance feedback, the monitoring strategy is continuously adjusted and improved to form a closed-loop optimization system.

[0041] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A new energy status monitoring method based on the Internet of Things, characterized in that: The specific steps of this method are: S100, IoT data collection system construction: Deploy IoT sensor networks in key parts of new energy equipment and the surrounding environment to collect equipment operating parameters and environmental data in real time. The data is transmitted wirelessly to the cloud or local data center to provide a basis for subsequent analysis; S200, dynamic adaptive monitoring strategy design: According to the real-time working status and environmental conditions of new energy equipment, the monitoring frequency and parameter range are dynamically adjusted to monitor the equipment status changes in more detail. The algorithm analyzes the historical monitoring data, identifies the laws and trends of equipment status changes, and automatically optimizes the monitoring strategy to achieve intelligent and personalized monitoring. S300, intelligent early warning and fault diagnosis: The IoT data collection system can continuously and accurately collect real-time monitoring data of new energy equipment, including operating parameters and environmental data, pre-process the collected data, set early warning thresholds for each monitoring parameter based on the dynamically adjusted monitoring strategy, use analytical technology to perform anomaly detection on real-time monitoring data, identify abnormal changes in equipment status, and issue early warning signals in a timely manner when abnormal status is detected to notify operation and maintenance personnel to pay attention and prepare for troubleshooting; Combined with the expert system and knowledge base, the system conducts in-depth analysis of warning information, including but not limited to the causes and impact scope of abnormal conditions. Based on the analysis results, it provides fault diagnosis suggestions and presents them to operation and maintenance personnel in an intuitive and easy-to-understand manner, helping them to quickly locate problems and formulate corresponding countermeasures. The operation and maintenance personnel formulate specific maintenance plans based on the fault diagnosis suggestions, implement them, evaluate the effects of the measures after implementation, collect feedback from the operation and maintenance personnel based on the evaluation results, and continuously optimize and improve the intelligent early warning and fault diagnosis system; S400, continuous optimization of monitoring strategies: Through the feedback mechanism, the actual operation and maintenance results are combined with historical monitoring data to further optimize the monitoring strategy, form a closed-loop optimization system, introduce a continuous learning mechanism, and continuously absorb new data and new knowledge.

2. The new energy status monitoring method based on the Internet of Things according to claim 1 is characterized in that: The S100 clarifies the monitoring requirements of new energy equipment, determines the type and quantity of sensors, plans data transmission paths, installs sensors at key parts of the equipment and the surrounding environment, configures data collectors, ensures the stability and security of power supply and communication, configures data transmission protocols and encryption methods, establishes a data storage system, implements data quality control measures, conducts system function and performance tests, and continuously improves and optimizes based on user feedback.

3. The new energy status monitoring method based on the Internet of Things according to claim 1 is characterized in that: The S200 real-time data collection and analysis is the basis of the dynamic adaptive monitoring strategy. The IoT data acquisition system obtains the operating parameters and environmental data of new energy equipment in real time, and performs preliminary processing to ensure data quality. Based on these data, the working status of the equipment is evaluated in real time, and the monitoring frequency and parameter range are dynamically adjusted considering the impact of environmental conditions.

4. The new energy status monitoring method based on the Internet of Things according to claim 3 is characterized in that: The S200 algorithm analysis and optimization is the key to improving the intelligence of monitoring strategies. By collecting and integrating historical monitoring data, machine learning algorithms are used to identify the patterns and trends of equipment status changes. Based on these analysis results, the monitoring strategy is automatically adjusted, including monitoring parameters and warning thresholds. The optimized strategy is applied to actual monitoring, and user feedback is continuously collected to perform closed-loop optimization of the strategy.

5. The new energy status monitoring method based on the Internet of Things according to claim 1 is characterized in that: The S300 sets warning thresholds for each monitoring parameter based on the dynamically adjusted monitoring strategy: Among them, T n is the warning threshold of parameter n, A n is the basic threshold of parameter n, α and β are adjustment coefficients, D n is the data dispersion of parameter n in the current time period, D avg is the average value of the discreteness of all monitoring parameter data, C n is the rate of change of parameter n, C avg It is the average value of the change rate of all monitored parameters.

6. The new energy status monitoring method based on the Internet of Things according to claim 1 is characterized in that: The S300 uses analytical technology to detect anomalies in real-time monitoring data and identify abnormal changes in device status: Among them, E represents the outlier index, n is the number of monitoring parameters, and A i is the real-time monitoring value of parameter i, M i is the dynamic mean of parameter i, w i is the weight of parameter i, γ is the adjustment coefficient, and D is the dispersion index of the data.

7. The new energy status monitoring method based on the Internet of Things according to claim 1 is characterized in that: The S400 optimizes the monitoring strategy and establishes a feedback mechanism. It collects feedback from operation and maintenance personnel on the accuracy of early warning and the efficiency of fault diagnosis through real-time channels, and integrates it with historical monitoring data to form a complete feedback data set. It uses association analysis and cluster analysis data analysis techniques to mine key information and provide data support for strategy adjustment.

8. The new energy status monitoring method based on the Internet of Things according to claim 7 is characterized in that: The S400 adjusts monitoring parameters, warning thresholds and data collection frequency based on the analysis results, and introduces new technologies such as deep learning and edge computing to improve the level of intelligence. It deploys the optimized strategy to the IoT data collection system, continuously monitors the equipment operation status and warning conditions, regularly updates equipment operation parameters and environmental condition monitoring data, and updates the expert system and knowledge base in combination with industry standards and the latest research results to achieve iterative optimization of strategies, form a closed-loop system, and continuously improve accuracy and reliability.

Images