New energy station operation and maintenance data intelligent management and control system based on event driving

Abstract

The invention relates to the technical field of operation and maintenance data management, and provides a new energy station operation and maintenance data intelligent management and control system based on event driving, which comprises a server, an event monitoring module, an intelligent analysis module and a response execution module, the intelligent analysis module dynamically analyzes the event data to generate an optimization decision, and the response execution module regulates and controls the equipment in real time according to the optimization decision and monitors an execution result. Through joint cooperation of the event monitoring module, the intelligent analysis module and the response execution module, a full-process closed loop of data acquisition-analysis decision-execution feedback is formed, so that the system can efficiently process multi-dimensional data, and it is ensured that the whole system has the advantages of comprehensive perception, accurate analysis, quick response and reliable regulation and control.

Description

Technical Field

[0001] The present invention relates to the technical field of operation and maintenance data management in the field of new energy, and in particular to an event-driven intelligent management and control system for operation and maintenance data of new energy stations. Background Art

[0002] New energy stations (such as wind power, photovoltaic power stations, etc.) have extremely high requirements for the real-time, accuracy and processing efficiency of operation and maintenance data due to their wide distribution, complex environment and diverse equipment types. Traditional operation and maintenance management methods are mainly based on periodic data collection and manual analysis, which have problems such as delayed response, data redundancy and inability to dynamically adapt to changes in station status.

[0003] For example, Chinese patent CN118763801A discloses a photovoltaic station operation and maintenance safety comprehensive management method and system. Although it uses deep learning methods to extract features and fuse attention from multimodal data to obtain a comprehensive, accurate, and high-dimensional system status representation, laying a data foundation for subsequent fault diagnosis and early warning, it lacks dynamic analysis and event correlation capabilities.

[0004] The prior art also has the following defects:

[0005] 1. Currently, most new energy stations collect data through periodic polling or scheduled collection. This method results in delayed data updates and is unable to respond to emergencies in real time. For example, if the equipment operating parameters exceed the safety threshold, it may not be discovered in time because the collection cycle has not yet arrived, resulting in further equipment damage or power generation loss.

[0006] 2. Periodic collection will bring a large amount of unused data, and redundant information will occupy storage resources and processing capabilities. The system lacks the ability to filter and dynamically process key data based on specific events, resulting in waste of resources and inefficient decision-making.

[0007] 3. In traditional systems, the abnormal handling process of equipment status is usually based on single instructions, lacking closed-loop management functions after event triggering, such as feedback on instruction execution results, continuous optimization, etc. As a result, the system lacks control over the overall status of the station.

[0008] The present invention is made to solve the common problems in the field, such as the lag in data collection methods, the difficulty in processing redundant data, the passive decision-making caused by untimely response, the lack of closed-loop management of operation and maintenance, and the insufficient evaluation capabilities. Summary of the invention

[0009] The purpose of the present invention is to propose an event-driven intelligent management and control system for operation and maintenance data of new energy stations in response to the current deficiencies.

[0010] In order to overcome the shortcomings of the prior art, the present invention adopts the following technical solutions:

[0011] An event-driven intelligent management and control system for operation and maintenance data of a new energy station, the intelligent management and control system for operation and maintenance data of a new energy station comprising a server, the intelligent management and control system for operation and maintenance data of a new energy station further comprising an event monitoring module, an intelligent analysis module and a response execution module, the server being connected to the event monitoring module, the intelligent analysis module and the response execution module respectively;

[0012] The event monitoring module captures event data of equipment in the station in real time, the intelligent analysis module dynamically analyzes the event data to generate optimization decisions, and the response execution module regulates the equipment in real time according to the optimization decisions and monitors the execution results;

[0013] The event monitoring module includes a data acquisition unit and an event determination unit. The data acquisition unit captures event data of equipment in the station in real time. The event determination unit determines whether the collected event data triggers an event based on a judgment rule.

[0014] The judgment rules include comprehensive determination based on equipment operating status, historical data and environmental conditions.

[0015] Optionally, the data acquisition unit includes an operation status acquisition component, an environment status acquisition component and a data storage device, the operation status acquisition component acquires operation status data of equipment in the station, the environment status acquisition component acquires environment data in the station, and the data storage device stores the operation data of the operation status acquisition component and the environment data acquired by the environment status acquisition component.

[0016] Optionally, the event determination unit includes a rule base and a manager, the rule base is pre-set with evaluation rules, and the manager manages the rule base;

[0017] The manager constructs a correlation matrix M based on the operation data and the environment data, and determines whether there is an abnormality by analyzing the global characteristics of the correlation matrix;

[0018] If an abnormality occurs, the collected data is determined as event data.

[0019] Optionally, the intelligent analysis module includes a fault diagnosis unit and a trend prediction unit, wherein the fault diagnosis unit diagnoses equipment faults in the station according to event data to form a diagnosis result, and the trend prediction unit predicts the trend of the equipment in the station and optimizes the decision according to the diagnosis result.

[0020] Optionally, the fault diagnosis unit obtains event data and constructs a feature vector X=[x1, x2, ..., xn] according to the event data, and the probability distribution of each parameter in the feature vector is p i , determine the entropy value H(X) of the current device state, and calculate the optimization decision index Plan according to the following formula:

[0021]

[0022] Where H(X) is the entropy value of the event data of the equipment in the station, D(X,X opt ) is the degree of deviation between the current event data and the ideal state, H max is the maximum entropy value of the system characteristic distribution, D max is the maximum deviation between the system eigenvalues;

[0023] When the optimization decision index plan is lower than the set monitoring threshold Threshold, it means that the device is in an abnormal state or has a potential problem, and the trend prediction unit is triggered to make a prediction for the device.

[0024] Optionally, the response execution module includes an instruction generation unit, a remote control unit and a feedback confirmation unit. The instruction generation unit generates a control instruction based on the optimization decision and transmits it to the remote control unit. The remote control unit transmits the generated control instruction to the on-site device and performs corresponding operations. The feedback confirmation unit confirms the result of the instruction execution and provides feedback on the execution status.

[0025] Optionally, the trend prediction unit predicts the trend of the equipment in the station according to the following steps:

[0026] S1, collect the current optimization decision index of the equipment in the station and the historical optimization decision index Plan of the last n time steps t-1 ,Plan t-2 ,…,Plan t-n ;

[0027] S2. According to the current optimization decision index Plan t and the optimization decision index Plan of the previous time step t-1 , to determine the rate of change of the current optimization decision index r t ;

[0028] S3, using the current optimization decision index Plant and change rate r t , directly calculate the optimal decision index for the next k time steps;

[0029] S4. Optimize the decision index plan based on the predicted future t+k' and the monitoring threshold set by the system, calculate the deviation degree Δ t+k ;

[0030] S5, according to the degree of deviation Δ t+k and the current rate of change r t Combination of,classification devices in the future;

[0031] S6. According to the status classification, output the prediction results and trigger the corresponding optimization decision.

[0032] Optionally, the operating status acquisition component includes a voltage sensor, a current sensor, a power sensor, a vibration sensor and a temperature sensor, the voltage sensor acquires voltage data of the device, the current sensor acquires current data of the device, the power sensor acquires power data of the device, the vibration sensor acquires mechanical vibration data of the device, and the temperature sensor acquires temperature data on the surface and inside of the device.

[0033] Optionally, the optimization decision includes suggestions for adjusting equipment operating parameters, maintenance suggestions, and operation suggestions triggered by time and conditions.

[0034] Optionally, the future state of the device includes state recovery, state deterioration and state stability.

[0035] The beneficial effects achieved by the present invention are:

[0036] 1. Through the cooperation of the event monitoring module and the intelligent analysis module, the new energy station can realize comprehensive perception and real-time analysis of multi-dimensional data, ensuring that the entire system has efficient data collection capabilities and redundant data processing capabilities, avoiding data collection delays and processing complexity.

[0037] 2. Through the cooperation of the intelligent analysis module and the response execution module, the system can quickly generate optimized decisions and transmit them to the on-site equipment in a timely manner, ensuring that the entire system has the ability to respond quickly and make proactive decisions, avoiding the problem of passive decision-making due to untimely response.

[0038] 3. Through the cooperation of the event monitoring module and the intelligent analysis module, comprehensive perception and accurate analysis of the operating status of equipment and environmental changes in the station can be achieved, so that the system can detect potential faults and abnormalities in real time, ensuring that the entire system has high sensitivity and real-time response capabilities.

[0039] 4. Through the joint cooperation of the event monitoring module, the intelligent analysis module and the response execution module, a full-process closed loop of data collection - analysis and decision-making - execution feedback is formed, enabling the system to efficiently process multi-dimensional data and ensure that the entire system has the advantages of comprehensive perception, accurate analysis, rapid response and reliable control. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The present invention can be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily drawn to scale, but the emphasis is placed on illustrating the principles of the embodiments. In different views, the same reference numerals designate the same parts.

[0041] Figure 1 It is an overall block diagram of the present invention.

[0042] Figure 2 Schematic diagram of a block diagram of an event monitoring module of the present invention.

[0043] Figure 3 It is a block diagram of the intelligent analysis module of the present invention.

[0044] Figure 4 It is a schematic diagram of the content of the control instruction of the present invention.

[0045] Figure 5 It is a block diagram of the response execution module of the present invention.

[0046] Figure 6 It is a schematic diagram comparing the effects of the application scheme of the present invention and the prior art scheme. DETAILED DESCRIPTION

[0047] The following is an explanation of the embodiments of the present invention through specific embodiments. Those skilled in the art can understand the advantages and effects of the present invention from the contents disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and the details in this specification can also be modified and changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. In addition, the drawings of the present invention are only simple schematic illustrations and are not depicted according to actual sizes. It is stated in advance. The following embodiments will further explain the relevant technical contents of the present invention in detail, but the disclosed contents are not intended to limit the scope of protection of the present invention.

[0048] Embodiment 1: According to Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5 As shown, this embodiment provides an event-driven intelligent management and control system for operation and maintenance data of new energy stations, the intelligent management and control system for operation and maintenance data of new energy stations includes a server, the intelligent management and control system for operation and maintenance data of new energy stations also includes an event monitoring module, an intelligent analysis module and a response execution module, the server is connected to the event monitoring module, the intelligent analysis module and the response execution module respectively, and the intermediate data and process data of the event monitoring module, the intelligent analysis module and the response execution module are stored in the database of the server for query and call;

[0049] The event monitoring module captures event data of equipment in the station in real time, the intelligent analysis module dynamically analyzes the event data to generate optimization decisions, and the response execution module regulates the equipment in real time according to the optimization decisions and monitors the execution results;

[0050] The new energy station operation and maintenance data intelligent management and control system also includes a central processing unit, which is respectively controlled and connected to the event monitoring module, the intelligent analysis module and the response execution module, and centrally controls the event monitoring module, the intelligent analysis module and the response execution module based on the central processing unit, and stores the control data in the database of the server to enhance the refined management and control of the equipment in the station by the entire system.

[0051] The event monitoring module includes a data acquisition unit and an event determination unit. The data acquisition unit captures event data of equipment in the station in real time. The event determination unit determines whether the collected event data triggers an event based on a judgment rule.

[0052] The judgment rules include comprehensive determination based on equipment operating status, historical data and environmental conditions.

[0053] Optionally, the data acquisition unit includes an operation status acquisition component, an environment status acquisition component and a data storage device, the operation status acquisition component acquires operation status data of equipment in the station, the environment status acquisition component acquires environment data in the station, and the data storage device stores the operation data of the operation status acquisition component and the environment data acquired by the environment status acquisition component.

[0054] Optionally, the operating status acquisition component includes a voltage sensor, a current sensor, a power sensor, a vibration sensor and a temperature sensor, the voltage sensor acquires voltage data of the device, the current sensor acquires current data of the device, the power sensor acquires power data of the device, the vibration sensor acquires mechanical vibration data of the device, and the temperature sensor acquires temperature data on the surface and inside of the device.

[0055] The environment collection component includes a wind speed sensor, a light intensity sensor and a humidity sensor. The wind speed sensor collects wind speed changes in the station, the light intensity sensor collects light intensity data in the station, and the humidity sensor collects humidity data in the air.

[0056] Optionally, the event determination unit includes a rule base and a manager, the rule base is pre-set with evaluation rules, and the manager manages the rule base;

[0057] The manager constructs a correlation matrix M based on the operation data and the environment data, and determines whether there is an abnormality by analyzing the global characteristics of the correlation matrix;

[0058] If an abnormality occurs, the collected data is determined as event data.

[0059] Specifically, n parameters of the device are obtained in a certain collection cycle, including operation data, environmental data and energy output data. For example, the operation data may include the temperature, pressure and power of the device, the environmental data may include temperature, humidity and wind speed, and the energy output data may include total power generation, instantaneous power generation and power generation efficiency. All these data are combined to form a parameter set: U = {U1, U2, ..., U b}, where U i Represents the i-th parameter.

[0060] For any two parameters U in the parameter set i and U j , calculate the Pearson Correlation Coefficient between them:

[0061]

[0062] In the formula, Cov(U i , U j ) is U i and U j The covariance of , whose value satisfies:

[0063] u ik and u jk are respectively the U at the kth moment in a collection cycle. i and

[0064] U j The observed value of and is a collection cycle U i and U j The mean value, σ Ui and σ Uj U i and U j The standard deviation of a collection cycle.

[0065] For U i and U j The standard deviation of is calculated based on the observations collected in a collection cycle. i = {u i1 ,u i2 ,…,u ib} and X j = {u j1 ,u j2 ,…,ujb}, where u i1 ,u i2 ,…,u ib is the parameter U i The observed values ​​at different time points in a collection cycle, u j1 ,u j2 ,…,u jb is the parameter U j The observed values ​​at the corresponding time points.

[0066]

[0067] Where b is the number of observations in the acquisition period, u ik and u jk are respectively the U at the kth moment in a collection cycle. i and U j The observed value of and It's U i and U j The mean value is calculated according to the following formula:

[0068]

[0069] In the formula, u ik and u jk are U at the kth moment i and U j , b is the number of observations in the collection period;

[0070] Apply the above correlation coefficients to all parameters and construct a b×b correlation matrix M:

[0071]

[0072] The diagonal elements M[i, i]=1 of the matrix M represent the complete correlation between each parameter and itself, and the off-diagonal elements M[i, j] represent the correlation between the i-th parameter and the j-th parameter.

[0073] In this embodiment, the global characteristics of the correlation matrix are calculated according to the following formula:

[0074]

[0075] Where S is the global feature of the correlation matrix M;

[0076] The real-time feature S is compared with the reference feature value S in the rule base. ref By comparison, when the deviation value ΔS>S ref When an exception is triggered, if the manager determines that it is abnormal, the collected data will be marked as event data;

[0077] Among them, the reference eigenvalue S ref It is set based on the rule base, and its value is determined by the system according to the type of equipment in the monitored site. This is a technical means well known to technicians in this field, so it will not be described in detail in this example.

[0078] Optionally, the intelligent analysis module includes a fault diagnosis unit and a trend prediction unit, wherein the fault diagnosis unit diagnoses equipment faults in the station according to event data to form a diagnosis result, and the trend prediction unit predicts the trend of the equipment in the station and optimizes the decision according to the diagnosis result.

[0079] Optionally, the fault diagnosis unit obtains event data and constructs a feature vector X=[x1, x2, ..., x n ], the probability distribution of each parameter in the feature vector is p i , determine the entropy value H(X) of the current device state, and calculate the optimization decision index Plan according to the following formula:

[0080]

[0081] Where H(X) is the entropy value of the event data of the equipment in the station, D(X,X opt ) is the degree of deviation between the current event data and the ideal state, H max is the maximum entropy value of the system characteristic distribution, D max is the maximum deviation between the system eigenvalues;

[0082] The entropy value H(X) of the event data of the equipment in the station is calculated according to the following formula:

[0083]

[0084] In the formula, p i is the normalized probability of event data xi, and its value is calculated according to the following formula:

[0085]

[0086] In the formula, x i is the value of the i-th element, is all x i The sum of the values ​​(from j=1 to j=n, where n is the total amount of data).

[0087] In this embodiment, the degree of deviation between the current event data and the ideal state is D(X,X opt ) is the current event data X = [x1, x2, ..., x n ] and ideal state data Xopt = [x nopt , x n opt , …, x n opt ], then D(X,X opt ) is calculated according to the following formula:

[0088]

[0089] The maximum entropy value H of the system characteristic distribution max Calculate according to the following formula:

[0090] H max = lg(m);

[0091] Where m is the total number of different states or categories in the event data set, that is, the total number of states or categories of the event data.

[0092] The maximum deviation between the system characteristic values ​​D max Calculate according to the following formula:

[0093]

[0094] In the formula, x i max is the maximum value of the ith dimension (or the ith element) of the eigenvector. In each dimension (or column) of the eigenvector data set, the maximum value of all data on that dimension is taken. i min It is the minimum value of the i-th dimension data (or the i-th element) of the feature vector. In each dimension (or each column) of the feature vector data set, the minimum value of all data on that dimension is taken. n is the number of dimensions of the feature vector data set or the number of features of the data.

[0095] When the optimization decision index plan is lower than the monitoring threshold Threshold set by the system, it means that the device is in an abnormal state or has a potential problem, and the trend prediction unit is triggered to make a prediction for the device.

[0096] When the optimization decision index plan is higher than the monitoring threshold Threshold set by the system, it indicates that the operation is normal or close to the ideal state.

[0097] Among them, the monitoring threshold Threshold set by the system is set by the system or the administrator according to the actual situation. This is a technical means well known to technicians in this field. Technicians in this field can refer to relevant technical manuals to learn about the technology, so it will not be described one by one in this embodiment.

[0098] Through the cooperation of the event monitoring module and the intelligent analysis module, comprehensive perception and accurate analysis of the operating status of equipment and environmental changes in the station can be achieved, enabling the system to detect potential faults and anomalies in real time, ensuring that the entire system has high sensitivity and real-time response capabilities.

[0099] Through the cooperation of the event monitoring module and the intelligent analysis module, the new energy station can achieve comprehensive perception and real-time analysis of multi-dimensional data, ensuring that the entire system has efficient data collection capabilities and redundant data processing capabilities, avoiding data collection delays and processing complexity.

[0100] Optionally, the trend prediction unit predicts the trend of the equipment in the station according to the following steps:

[0101] S1, collect the current optimization decision index of the equipment in the station and the historical optimization decision index Plan of the last n time steps t-1 ,Plan t-2 ,…,Plan t-n ;

[0102] Among them, by calculating the changing trend of the optimization decision index and the deviation from the relative threshold, it is predicted whether the future equipment status will return to normal or further deteriorate.

[0103] S2. According to the current optimization decision index Plan t and the optimization decision index Plan of the previous time step t-1 , to determine the rate of change of the current optimization decision index r t ;

[0104] Among them, the change rate of the optimization decision index r t Calculate according to the following formula:

[0105]

[0106] In the formula, r t is the rate of change of the current optimization index, Δt is the time step (can be set to 1). S3. Use the current optimization decision index Plan t and the rate of change r t , directly calculate the optimal decision index for the next k time steps;

[0107] Among them, the optimization decision index Plan for the next k time steps t+k 'Calculated according to the following formula:

[0108] Plan t+k ′=Plan t +k·r t ;

[0109] Where k is the number of predicted time steps, and its value is determined by the system or manager based on actual conditions.

[0110] S4. Optimize the decision index plan based on the predicted future t+k ' and the monitoring threshold set by the system, calculate the deviation degree Δ t+k ;

[0111] Among them, the deviation degree Δ t+k Calculated according to the following formula:

[0112] Δ t+k =Plan t+k ′-Threshold;

[0113] If Δ t+k >0, the status of the equipment in the station is returning to normal;

[0114] Δ t+k <0, the status of the equipment in the station is further deteriorating.

[0115] S5, according to the degree of deviation Δ t+k and the current rate of change r t Combination of,classification devices in the future;

[0116] The future state of the device includes state recovery, state deterioration and state stability.

[0117] Among them, when satisfying: Δ t+k >0 and r t >0, the optimization decision index is returning to normal and the status of the equipment in the station is improving;

[0118] When: Δ t+k <0 and r t <0, the optimization decision index continues to decline, and the status of the equipment in the station is deteriorating;

[0119] When: Δ t+k ≈0 and r t ≈0, the optimization decision index tends to be stable, and the status of the equipment in the station maintains the current level; S6, according to the status classification, output the prediction results and trigger the corresponding optimization decision.

[0120] Optionally, the optimization decision includes suggestions for adjusting equipment operating parameters, maintenance suggestions, and operation suggestions triggered by time and conditions.

[0121] Among them, when the state is in the state of recovery (the future optimization decision index deviates positively from the threshold, indicating that the equipment is improving, the current equipment adjustment has taken effect, and the state is developing in the ideal direction), the optimization decision is:

[0122] 1) It is recommended to adjust the equipment operating parameters to maintain the existing operating conditions.

[0123] For example, appropriately reducing the speed of wind turbines can reduce component wear and extend their operating life.

[0124] The adjustment of the parameters is determined according to the following formula:

[0125]

[0126] Where α is the buffer coefficient (usually in the range of 0.1 to 0.2). For example, when the equipment operation deviation is large and the adjustment target needs to be achieved quickly to restore normal operation, α = 0.2; when the adjustment target is not urgent and can be adjusted more slowly to reduce the impact on the equipment, α = 0.15. Margin is the closeness between the parameter and the target value, and its value is calculated according to the following formula:

[0127]

[0128] Among them, x i current is the actual value of the current device parameter, X i target It is the target value or ideal value of the equipment operating parameter (required not to be 0).

[0129] When margin=0, it means that the current parameter completely reaches the target value.

[0130] When margin>0, it indicates the ratio of the current parameter to the target value:

[0131] margin→0: Indicates that the parameter is close to the target value and the adjustment range can be small.

[0132] margin→1: Indicates that the parameter deviates greatly from the target value and needs to be significantly adjusted.

[0133] 2) Suggestions for phased optimization and maintenance:

[0134] It is recommended to perform minor maintenance on the equipment, such as:

[0135] Check key components for minor wear and tear.

[0136] Optimize the equipment operating environment (such as cleaning photovoltaic panels and improving ventilation conditions).

[0137] Establish a regular inspection mechanism to continue the current trend of operational improvement.

[0138] 3) Preventive action suggestions: set conditional trigger rules;

[0139] For example: Continue monitoring within the next 24 hours. If the device returns to normal (Δ t+k >Threshold), then reduce the monitoring frequency;

[0140] If the rate of change of the new parameter r is detected t When the status is deteriorating, the optimization decision is:

[0141] 1) Rapidly adjust operating parameters:

[0142] ① Make major adjustments to equipment operating parameters to avoid further deterioration.

[0143] For example, for wind turbines, quickly adjust the speed to a safe threshold:

[0144]

[0145] Where γ is the adjustment amplitude factor (the range is (0, 1]) γ = 1 is completely corrected, adjusted to x i max Target value, 0<γ<1: partial correction, moderate adjustment, x i new represents the adjusted equipment operating parameter value (optimized target value), x i max is the maximum allowable value of the equipment parameter (or the maximum value for safe operation), x i current It is the actual operating parameter value of the current device.

[0146] For photovoltaic equipment, increase system cooling time and reduce the risk of overheating.

[0147] ②Immediately reduce equipment load and prioritize safety.

[0148] 2) Emergency maintenance scheduling suggestions: Check the equipment operation status to see if there are any hardware failures or sensor errors; replace or repair key components in a timely manner.

[0149] Trigger deep maintenance based on equipment operating hours and operating conditions.

[0150] 3) Conditional trigger operation suggestion: Dynamically set multi-threshold control rules.

[0151] For example: when the degradation rate r t When the preset critical value is exceeded, the equipment will be automatically shut down or the load will be transferred;

[0152] If the equipment fails (such as overheating, abnormal vibration), the safety protection mode of the entire station equipment will be triggered.

[0153] 4) External condition adaptation: Dynamically adjust environmental data.

[0154] For example: for photovoltaic stations, automatically clean the surface of equipment to improve power generation efficiency;

[0155] For wind turbines, adjust the wind direction angle to optimize wind energy utilization. When the state is stable, the optimization decision is:

[0156] 1) Fine-tuning parameters to maintain status: Improve efficiency and prevent potential fluctuations by adjusting equipment parameters in small increments.

[0157]

[0158] Where ε is the fine-tuning coefficient, and its value range is [0.01, 0.03], x i current It is the actual operating parameter value of the current device.

[0159] 2) Monitoring and data optimization: Increase the frequency of monitoring data to ensure status stability.

[0160] 3) Preventive maintenance recommendations: Check for potentially aged components or high-load components, and perform low-intensity maintenance (such as cleaning, lubrication, etc.) when the equipment is in a stable state.

[0161] 4) Operational suggestions to improve system efficiency: adjust equipment operation strategy.

[0162] For example:

[0163] For wind turbines, reduce idling time and rationally dispatch energy distribution;

[0164] For photovoltaic stations, reduce operating load during off-peak hours to extend equipment life.

[0165] Optionally, the response execution module includes an instruction generation unit, a remote control unit and a feedback confirmation unit. The instruction generation unit generates a control instruction based on the optimization decision and transmits it to the remote control unit. The remote control unit transmits the generated control instruction to the on-site device and performs corresponding operations. The feedback confirmation unit confirms the result of the instruction execution and feeds back the execution status (to the remote control unit and the central processing unit).

[0166] Through the cooperation of the intelligent analysis module and the response execution module, the system can quickly generate optimized decisions and transmit them to the on-site equipment in a timely manner, ensuring that the entire system has the ability to respond quickly and make proactive decisions, avoiding the problem of passive decision-making due to untimely response.

[0167] The instruction generation unit generates a control instruction according to the following steps:

[0168] S100. The instruction generation unit receives the control suggestions output by the optimization decision module (such as adjusting equipment operating parameters, triggering maintenance tasks, etc.).

[0169] S101. Analyze equipment characteristics:

[0170] Query device characteristic parameters: obtain the operating parameter range, interface protocol, control mode, etc. of the target device.

[0171] Check the operating status of the equipment: Based on the real-time status data of the equipment (such as current power, current, etc.), analyze whether the prerequisites for optimizing decision execution are met.

[0172] For example: The optimization decision recommends adjusting the fan speed to 1200RPM.

[0173] The query shows that the fan's operating parameter range is 800-1500RPM, and the current speed is 1000RPM. Confirm that the adjustment can be performed.

[0174] S102, command generation:

[0175] Assemble control instructions: Assemble complete instructions according to device protocols and control interfaces.

[0176] Verify instruction format: Ensure that the generated instructions comply with device communication protocols and safety rules.

[0177] Additional checksum: Add checksum information (such as CRC checksum) to ensure the integrity of the instruction.

[0178] S103, instruction transmission:

[0179] The generated control command is sent to the remote control unit.

[0180] Record the sending status of the instruction (such as "pending to be sent" or "sent").

[0181] The remote control unit includes a communicator, a command parser and an actuator. The communicator is used to receive the control command transmitted by the command generation unit. The command parser parses the received control command and converts it into a command format that can be understood by the device. For example: speed adjustment of the wind turbine: convert the command "set the speed to 1200rpm" into a specific device command; power optimization of the photovoltaic inverter: convert the command "adjust the power output to 80%" into a control signal, and the actuator sends the parsed command to the device through an appropriate interface.

[0182] The communicator supports multiple communication protocols to achieve reliable connection with field devices. Specifically:

[0183] Wired protocols: such as Modbus, CAN bus, RS-485.

[0184] Wireless protocols: such as Zigbee, Wi-Fi, LoRa, NB-IoT, etc.

[0185] Industrial protocols: such as OPC-UA, for integration with industrial automation systems.

[0186] In this embodiment, the actuator supports different device interfaces and operation modes:

[0187] Digital signal interface (such as switch quantity control).

[0188] Analog signal interface (such as current or voltage control).

[0189] API interface (such as smart devices are controlled through API calls).

[0190] At the same time, in this embodiment, the remote control unit implementation process and steps are also provided:

[0191] S11. Receiving control instructions: receiving control instructions sent by the instruction generation unit through the communication module.

[0192] Verify the integrity and validity of the instruction (such as CRC check).

[0193] S12. Parse instructions: convert control instructions into low-level signals that comply with device protocols.

[0194] For example, convert the high-level instruction "adjust the temperature to 30°C" into a Modbus command.

[0195] S13, passing the command to the device: using the communication module, the parsed signal is transmitted to the target device.

[0196] Make sure the command was sent successfully and wait for the device to confirm.

[0197] S14, execute operation: after receiving the control signal, the device executes the corresponding operation (such as adjusting power, starting or stopping the device) according to the instruction.

[0198] The feedback confirmation unit includes a feedback data collector, a feedback analyzer and a status returner. The feedback data collector collects the operating status, feedback signal and execution result of the device. The feedback analyzer analyzes the status data returned by the device to determine whether the instruction is successfully executed. The status returner returns the feedback result to the instruction generation unit or other system modules.

[0199] The judgment criteria of the feedback analyzer are:

[0200] Whether the target value of the instruction is reached;

[0201] Check whether there are any exceptions during the command execution process (such as device failure to respond or execution failure).

[0202] In this embodiment, the implementation process and steps of the feedback confirmation unit are as follows:

[0203] S21. Collect feedback data:

[0204] Obtain the execution result returned by the device through the communicator.

[0205] For example: whether the current temperature value reaches the target temperature; whether the current speed reaches the set value.

[0206] Confirm the completeness and accuracy of feedback data.

[0207] S22. Analyze feedback data:

[0208] Determine whether the execution result meets expectations: Compare the feedback value with the target value (e.g., the set power is 80%, and the actual feedback power is 79.5%). Determine whether the deviation is within the allowable range (if the deviation is <1%, the execution is considered successful). If the feedback value exceeds the expected range or there is no feedback, it is recorded as a failure.

[0209] S23, feedback execution status:

[0210] If the command is executed successfully, the device status is updated and the result is returned to the upper system.

[0211] If the command is not executed or fails, an error report is generated and the fault handling process is triggered, such as sending the command again;

[0212] Trigger an alarm and prompt manual intervention.

[0213] Through the cooperation of the response execution module and the event monitoring module, the results of the optimized execution can be fed back in real time and closed-loop verified, ensuring that the entire system has full-process closed-loop management capabilities, improving decision-making execution effects and avoiding management gaps.

[0214] Through the cooperation of the trend prediction function of the intelligent analysis module and the status assessment capability of the feedback confirmation unit, the system can quantify the operating status and health level of the equipment, ensuring that the entire system has the ability to accurately assess the operating status, effectively solving the problem of insufficient assessment capabilities. In addition, through the cooperation of the intelligent analysis module and the response execution module, the optimization decision is quickly converted into executable specific instructions, so that the equipment can be timely regulated when it is abnormal or the status deviates, ensuring that the entire system has dynamic optimization capabilities and adaptive adjustment capabilities.

[0215] Through the cooperation of the event monitoring module and the response execution module, closed-loop feedback of the monitoring data is achieved, so that the optimized operation results can be continuously verified and adjusted, ensuring that the entire system has high reliability and closed-loop control capabilities.

[0216] Through the joint cooperation of the event monitoring module, the intelligent analysis module and the response execution module, a full-process closed loop of data collection - analysis and decision-making - execution and feedback is formed, enabling the system to efficiently process multi-dimensional data and ensure that the entire system has the advantages of comprehensive perception, accurate analysis, rapid response and reliable control.

[0217] Embodiment 2: This embodiment should be understood to include all the features of any of the above embodiments, and further improve upon them. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5 As shown, the new energy station operation and maintenance data intelligent management and control system also includes a priority evaluation module, which evaluates the priority of the control instruction to form an evaluation result, and triggers the priority transmission of the control instruction according to the evaluation result;

[0218] The priority evaluation module includes an instruction evaluation unit and a priority control unit, wherein the instruction evaluation unit evaluates the priority of the control instruction to form an evaluation result, and the priority control unit triggers the priority transmission of the control instruction according to the evaluation result;

[0219] The priority control unit triggers the priority transmission of instructions according to the evaluation results, so that the system can respond quickly to high-priority events, give priority to the operation and fault handling of key equipment, ensure that the system has rapid response and efficient scheduling capabilities, and reduce system downtime and energy output losses.

[0220] Through real-time evaluation of the priority of control instructions by the instruction evaluation unit, the system can dynamically determine the importance of instructions based on multi-dimensional factors such as the urgency of the event, the importance of the equipment, time urgency and historical risks, ensuring that the system has intelligent event priority management capabilities and effectively avoiding waste of resources and delays in instruction processing.

[0221] The instruction evaluation unit obtains the event urgency score U, the importance score I, the event triggering time weight T and the historical risk score R of the equipment in the station, and calculates the priority P according to the following formula:

[0222]

[0223] The event urgency score U corresponding to the equipment in the station is determined according to the following conditions:

[0224] When U=5, it is a high-risk event, a critical failure of the system or equipment (such as shutdown or overload of core equipment (such as main transformer, fan); failure of key sensors leading to interruption of data collection);

[0225] When U=4, the second most dangerous event (such as fan high temperature alarm: the equipment temperature exceeds the operating safety threshold by 80%, but has not reached the shutdown point; photovoltaic array abnormality: the output power of some photovoltaic modules drops by more than 30%, but does not affect the continuity of the overall output);

[0226] When U=3, the moderate event equipment or system deviates from the normal operating state, but has little impact on the current operation. (For example, equipment efficiency decreases: the actual speed of the fan deviates from the set speed by 5%-10%, data communication interruption: the monitoring data of non-core equipment is interrupted, but it does not affect decision-making, energy output deviation: the output power of the photovoltaic array decreases by 10%-30%, but it is still within the safety range overall);

[0227] When U=2, it is a secondary low-risk event, and there is a slight deviation in the equipment or environmental status, but it still needs attention to prevent deterioration. (For example: slight temperature abnormality: the equipment temperature is close to the warning value (such as exceeding 70% of the safe operation threshold), slight power fluctuation: the equipment output fluctuates for a short time, but does not reach the alarm threshold, wind speed exceeding the standard warning: the wind speed in the wind turbine operating environment is close to the maximum operating allowable value, but the shutdown condition is not triggered);

[0228] When U=1, it is a low-risk event, and the data or device status is slightly abnormal, but it does not affect the overall operation of the system.

[0229] (Slight deviation of parameters: equipment operating voltage or current deviation is less than 5%; environmental monitoring warning: ambient temperature or humidity is close to non-ideal values, but not to the extent that it affects operation);

[0230] The importance score I of the equipment in the station is determined according to the following conditions:

[0231] I=5: Core equipment, that is, it is crucial to the overall operation of the station. Any failure will directly affect the energy output or safe operation of the station (such as photovoltaic stations: inverters, combiner boxes; wind power stations: main transformers, wind turbine main shafts, generators; energy storage systems: battery management systems (BMS), inverters).

[0232] I=4: Key auxiliary equipment, that is, equipment that plays an important role in the operation of the station. Although it is not equipment that directly produces energy, its performance affects the efficiency and stability of the core equipment. (For example, photovoltaic stations: photovoltaic module monitoring modules, DC bus equipment; wind power stations: variable pitch systems, lubrication systems; energy storage systems: battery thermal management modules).

[0233] I=3: Minor equipment, which plays a certain auxiliary role in the operation of the station. Its failure may reduce the system operation efficiency, but will not significantly affect the overall energy output (such as photovoltaic stations: bracket tracking system; wind power stations: wind speed sensor, temperature sensor; energy storage system: secondary circuit control module).

[0234] I=2: Auxiliary equipment, that is, it has a slight impact on the operating efficiency and performance of the station, and its failure will not directly affect energy output (such as photovoltaic stations: environmental monitoring equipment (temperature, humidity sensors), wind power stations: cabin lighting systems, energy storage systems: low-priority sensor modules).

[0235] I=1: low-priority equipment, that is, it has no direct impact on the operation of the station and its failure is a low-priority event (such as photovoltaic station: cleaning system in non-critical areas; wind power station: auxiliary monitoring camera; energy storage system: environmental recording equipment).

[0236] The event trigger time weight T of the equipment in the station is calculated according to the following formula:

[0237]

[0238] Wherein, t is the time when the event is triggered by the equipment in the station and the current time interval (unit: minute). For example, if an event is triggered one hour ago, the time interval t is 60 minutes. At the same time, the event triggering standard is: the operating status of the equipment changes significantly or reaches the preset warning threshold, for example: the speed of the wind turbine exceeds the safety upper limit, the output power of the photovoltaic inverter is lower than the set lower limit, and the temperature of the energy storage battery exceeds the allowable range. The time of event triggering is retrieved from the historical data, and the current time and the time interval of triggering can be obtained. t0 is the set time threshold, and its value is set by the system (such as 10 minutes). k is the time attenuation factor (the value range is k = 0.1 ~ 0.2).

[0239] In this embodiment, the value of the time attenuation factor is exemplarily described as follows:

[0240] When in an emergency fault scenario, k=0.2, and the time weight decays rapidly, highlighting the priority handling of emergency events.

[0241] When in the daily maintenance scenario, k = 0.1, and the time weight decreases smoothly to ensure that low-urgency tasks are processed within a certain period of time.

[0242] When in a short-term regulation scenario, k = 0.15, and the time weight is moderate, reflecting urgency without being overly sensitive.

[0243] When in a short-term control scenario, k = 0.05, the time weight decays slowly, and it is suitable for processing tasks with low time sensitivity.

[0244] The historical risk score R of the equipment in the station is calculated according to the following formula:

[0245]

[0246] In the formula, r i is the risk level score of historical events, and a is the number of risk events that have occurred in history.

[0247] The priority control unit performs priority transmission according to the following steps:

[0248] S31, instruction sequencing:

[0249] Receiving instructions and their priorities: The system receives the instruction priority P generated by the instruction evaluation unit.

[0250] Add instructions to the queue: All control instructions are added to the priority queue. Each instruction in the queue contains the instruction content and its corresponding priority.

[0251] Priority-based sorting: Sort the instructions in the queue using a sorting algorithm (such as descending order based on P). High-priority instructions are placed at the front of the queue, and low-priority instructions are placed at the back.

[0252] Among them, the code of the priority queue is provided in this embodiment:

[0253]

[0254] S32, instruction scheduling:

[0255] In this embodiment, transmission is performed in a preemptive scheduling manner, that is, if a new high-priority instruction enters the queue, the low-priority instruction being executed can be interrupted, and the high-priority instruction can be immediately transmitted and executed.

[0256] S33, command transmission:

[0257] According to the scheduling results, high priority instructions are transmitted to the field devices through the communication module.

[0258] Use reliable transmission protocols (such as TCP / IP or industrial-specific protocol Modbus) to ensure the integrity and correctness of instructions.

[0259] Allocate more communication bandwidth or resources to high-priority instructions to reduce transmission delays.

[0260] Perform flow control on low-priority instructions to avoid occupying too many resources.

[0261] S34, Status Update:

[0262] Transmission status record: record the transmission status of the instruction (such as "transmitted" or "to be transmitted").

[0263] Dynamic priority adjustment: Update the priority in the queue based on real-time conditions.

[0264] For example, after a command has been waiting in the queue for more than a set time, its priority can be dynamically increased (to prevent low-priority commands from not being executed for a long time).

[0265] By dynamically sorting and scheduling the transmission of instructions through the priority control unit, we can ensure that resource allocation is more reasonable, avoid low-priority instructions occupying too much transmission bandwidth, and ensure that the system has the ability to optimize and fairly allocate transmission resources.

[0266] Through the coordinated cooperation between the instruction evaluation unit and the priority control unit, the entire process of control instructions from priority evaluation to transmission and execution is automated, reducing manual intervention, ensuring that the system has real-time and automation capabilities, and improving station operation and maintenance efficiency.

[0267] In this embodiment, through the comprehensive cooperation of the priority assessment module and the response execution module, a complete closed-loop process from instruction generation, priority assessment, priority transmission to execution feedback is realized, which improves the overall operation and maintenance efficiency of the system and ensures that the system has efficient closed-loop operation guarantee capabilities.

[0268] The contents disclosed above are only preferred feasible embodiments of the present invention, and do not limit the protection scope of the present invention. Therefore, all equivalent technical changes made using the contents of the present invention specification and drawings are included in the protection scope of the present invention. In addition, the elements therein can be updated as technology develops.

Claims

1. An event-driven intelligent management and control system for operation and maintenance data of new energy stations, characterized in that: The system includes an event monitoring module, an intelligent analysis module and a response execution module; The event monitoring module captures event data of equipment in the station in real time, the intelligent analysis module dynamically analyzes the event data to generate optimization decisions, and the response execution module regulates the equipment in real time according to the optimization decisions and monitors the execution results; The event monitoring module includes a data acquisition unit and an event determination unit. The data acquisition unit captures event data of equipment in the station in real time. The event determination unit determines whether the collected event data triggers an event based on a judgment rule. The judgment rules include comprehensive determination based on equipment operating status, historical energy output data and environmental conditions.

2. The event-driven intelligent management and control system for operation and maintenance data of new energy stations according to claim 1 is characterized in that: The data acquisition unit includes an operation status acquisition component, an environment status acquisition component and a data storage device. The operation status acquisition component acquires operation status data of equipment in the station, the environment status acquisition component acquires environment data in the station, and the data storage device stores the operation data of the operation status acquisition component and the environment data acquired by the environment status acquisition component.

3. According to claim 2, an event-driven intelligent management and control system for operation and maintenance data of new energy stations is characterized in that: The event determination unit includes a rule base and a manager, wherein the rule base is pre-set with judgment rules, and the manager manages the rule base; The manager constructs a correlation matrix M based on the operation data, environmental data and historical energy output data, and determines whether there is an anomaly by analyzing the global characteristics of the correlation matrix; If an abnormality occurs, the collected data is determined as event data.

4. The event-driven intelligent management and control system for operation and maintenance data of new energy stations according to claim 3 is characterized in that: The intelligent analysis module includes a fault diagnosis unit and a trend prediction unit. The fault diagnosis unit diagnoses the equipment fault in the station according to the event data to form a diagnosis result. The trend prediction unit predicts the trend of the equipment in the station and optimizes the decision according to the diagnosis result.

5. The event-driven intelligent management and control system for operation and maintenance data of new energy stations according to claim 4 is characterized in that: The fault diagnosis unit obtains event data and constructs a feature vector X=[x1, x2, ..., x n ], the probability distribution of each parameter in the feature vector is p i , determine the entropy value H(X) of the current device state, and calculate the optimization decision index Plan according to the following formula: Where H(X) is the entropy value of the event data of the equipment in the station, D(X,X opt ) is the degree of deviation between the current event data and the ideal state, H max is the maximum entropy value of the system characteristic distribution, D max is the maximum deviation between the system eigenvalues; When the optimization decision index plan is lower than the set monitoring threshold Threshold, it means that the device is in an abnormal state or has a potential problem, and the trend prediction unit is triggered to make a prediction for the device.

6. The event-driven intelligent management and control system for operation and maintenance data of new energy stations according to claim 5 is characterized in that: The response execution module includes an instruction generation unit, a remote control unit and a feedback confirmation unit. The instruction generation unit generates a control instruction according to the optimization decision and transmits it to the remote control unit. The remote control unit transmits the generated control instruction to the field device and performs corresponding operations. The feedback confirmation unit confirms the result of the instruction execution and feeds back the execution status.

7. The event-driven intelligent management and control system for operation and maintenance data of new energy stations according to claim 6 is characterized in that: The trend prediction unit predicts the trend of the equipment in the station according to the following steps: S1, collect the current optimization decision index of the equipment in the station and the historical optimization decision index Plan of the last n time steps t-1 ,Plan t-2 ,…,Plan t-n ; S2. According to the current optimization decision index Plan t and the optimization decision index Plan of the previous time step t-1 , to determine the rate of change of the current optimization decision index r t ; S3, using the current optimization decision index Plant and change rate r t , directly calculate the optimal decision index for the next k time steps; S4. Optimize the decision index plan based on the predicted future t+k ' and the monitoring threshold set by the system, calculate the deviation degree Δ t+k ; S5, according to the degree of deviation Δ t+k and the current rate of change r t Combination of,classification devices in the future; S6. According to the status classification, output the prediction results and trigger the corresponding optimization decision.

8. The event-driven intelligent management and control system for operation and maintenance data of new energy stations according to claim 7 is characterized in that: The operating status acquisition component includes a voltage sensor, a current sensor, a power sensor, a vibration sensor and a temperature sensor. The voltage sensor acquires voltage data of the device, the current sensor acquires current data of the device, the power sensor acquires power data of the device, the vibration sensor acquires mechanical vibration data of the device, and the temperature sensor acquires temperature data on the surface and inside of the device.

9. The event-driven intelligent management and control system for operation and maintenance data of new energy stations according to claim 8 is characterized in that: The optimization decisions include suggestions for adjusting equipment operating parameters, maintenance suggestions, and operation suggestions triggered by time and conditions.

10. The event-driven intelligent management and control system for operation and maintenance data of new energy stations according to claim 9 is characterized in that: The future states of the device include state recovery, state deterioration and state stability.

Images