Power plant data management method and system

Abstract

The invention discloses a power plant data management method and system, and the method comprises the steps: collecting the real-time data of a power plant, and dynamically adjusting the data collection frequency of a sensor; performing data preprocessing and compression on the real-time data of the power plant through an edge computing node, and transmitting the preprocessed data to a central database through a multi-level data transmission protocol; the central database manages the data through a dynamic storage strategy, extracts the data from the dynamic storage database for analysis, and obtains a data analysis result; and displaying the data analysis result through augmented reality equipment, wherein the data analysis result comprises key operation parameters and predictive maintenance suggestions. According to the invention, the accuracy of data acquisition and the resource utilization rate are optimized, the efficiency and accuracy of data processing are improved, efficient transmission and timely processing of different types of data are ensured, the high efficiency and flexibility of data storage are realized, and the overall efficiency of power plant data management is comprehensively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to a power plant data management method and system. Background Art

[0002] In the operation of power plants, data collection, transmission, storage and analysis are key links to ensure efficient and safe operation of power plants. Traditional power plant data management methods have the following problems:

[0003] 1. Traditional methods usually use a fixed data collection frequency, which cannot be adjusted dynamically according to actual conditions, resulting in low efficiency and accuracy of data collection. On the one hand, the fixed frequency may lead to untimely collection of key data and failure to reflect the operating status of the equipment in a timely manner; on the other hand, frequent collection of unimportant data will waste system resources, increase power consumption and bandwidth occupancy.

[0004] Second, in traditional methods, data preprocessing and classification usually rely on simple rules or manual operations, which cannot fully utilize the inherent characteristics of data for intelligent processing. This not only increases the complexity of data processing, but also reduces the accuracy and effectiveness of data classification.

[0005] 3. Traditional data transmission methods usually use a single protocol and cannot perform hierarchical management based on the importance and urgency of the data, resulting in low data transmission efficiency and the inability to prioritize the transmission and processing of key data, affecting the operation and maintenance of the power plant.

[0006] Fourth, traditional data storage strategies often lack dynamism and cannot be flexibly adjusted according to the access frequency and importance of data. This approach not only wastes storage space, but may also cause delays in accessing key data, affecting the timeliness of data analysis and decision-making.

[0007] 5. Traditional data analysis and presentation methods usually rely on two-dimensional charts and text reports, which lack intuitiveness and interactivity, and cannot meet the needs of power plant operators for real-time data and predictive maintenance, affecting the accuracy and efficiency of decision-making. Summary of the invention

[0008] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0009] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a power plant data management method to solve the problems of fixed data collection frequency, unintelligent preprocessing and classification, low data transmission efficiency, inflexible storage strategy, and unintuitive data analysis and display in the existing power plant data management method, as well as how to optimize the overall efficiency and effect of power plant data management.

[0010] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0011] In a first aspect, the present invention provides a power plant data management method, comprising:

[0012] Collect real-time data from power plants and dynamically adjust the data collection frequency of sensors;

[0013] Preprocessing and compressing the real-time data of the power plant through edge computing nodes, and transmitting the preprocessed data to a central database through a multi-level data transmission protocol;

[0014] The central database manages data through a dynamic storage strategy, extracts data from the dynamically stored database for analysis, and obtains data analysis results;

[0015] The data analysis results are displayed through an augmented reality device, and the data analysis results include key operating parameters and predictive maintenance recommendations.

[0016] As a preferred solution of the power plant data management method of the present invention, the dynamically adjusting the data acquisition frequency of the sensor includes:

[0017] The real-time data includes temperature, pressure, flow, vibration, power output, fuel usage, and emissions data;

[0018] Set a fixed acquisition frequency as the initial input;

[0019] Define optimization goals, maximize acquisition frequency, minimize power consumption, bandwidth usage, and storage resource usage, and build a multi-objective optimization function;

[0020] Initialize the particle swarm, the dimension of each particle corresponds to the acquisition frequency of the sensor, and set the initial position and speed of the particle;

[0021] Defining a fitness function according to the data collection frequency, power consumption, bandwidth occupancy and storage occupancy;

[0022] The particle speed and position are updated through the particle swarm optimization algorithm. The fitness value of the particle is calculated after each round of iteration, and the historical optimal position and the global optimal position of the particle are updated. When the set number of iterations or the fitness threshold is reached, the global optimal position is selected as the data collection frequency.

[0023] As a preferred solution of the power plant data management method described in the present invention, wherein: the data preprocessing and compression include:

[0024] The edge computing node receives the real-time power plant data, and the data preprocessing includes denoising, data cleaning, and formatting;

[0025] The edge computing node compresses the preprocessed data, classifies the compressed data through a data analysis algorithm, and the classification includes: real-time data, batch data, and emergency data, and transmits them to the central database through a multi-level data transmission protocol.

[0026] As a preferred solution of the power plant data management method described in the present invention, wherein: the data analysis algorithm is expressed as:

[0027]

[0028] S = α·R + β·P + γ·D

[0029] Wherein, R represents the real-time score, x represents the variable in the integral calculation, k represents the constant for adjusting exponential growth, t represents the current time of the data, t0 represents the generation time of the data, ω represents the frequency of periodic fluctuations, P represents the priority score, w i represents the weight of the i-th parameter, p i represents the score of the i-th parameter, q i represents the i-th related parameter, n represents the total number of parameters, D represents the sensor data score, d j represents the j-th sensor data, λ j represents the adjustment parameter of the j-th sensor data, m represents the total number of sensors, S represents the comprehensive data score, α represents the adjustment parameter of the real-time score, β represents the adjustment parameter of the priority score, and γ represents the adjustment parameter of the sensor data score;

[0030] Based on the comprehensive score of historical data, classification thresholds T1 and T2 are determined, and T1 < T2 is satisfied;

[0031] If S < T1, the data is classified as batch data. If T1 ≤ S < T2, the data is classified as real-time data. If S ≥ T2, the data is classified as emergency data.

[0032] As a preferred solution of the power plant data management method described in the present invention, wherein: the multi-level data transmission protocol includes a real-time data transmission layer, a batch data transmission layer, and an emergency data transmission layer;

[0033] The real-time data transmission layer transmits real-time data through the UDP protocol;

[0034] The bulk data transmission layer transmits bulk data via TCP protocol and packages them according to a set time interval or data volume threshold;

[0035] The emergency data transmission layer transmits the emergency data via the Advanced Message Queuing Protocol AMQP and transmits it to the central database;

[0036] During data transmission, a transmission scheduling algorithm is used to monitor transmission bandwidth and resource usage, and adjust the data transmission frequency and priority of each transmission layer;

[0037] The transmission scheduling algorithm allocates bandwidth and resources according to the classification results of real-time data, batch data and urgent data, and adjusts the data transmission frequency and priority of the real-time data transmission layer, batch data transmission layer and urgent data transmission layer according to the current bandwidth and resource conditions.

[0038] As a preferred solution of the power plant data management method described in the present invention, the dynamic storage strategy includes:

[0039] Optimize storage based on data access frequency, importance and storage space utilization, and store the real-time data and urgent data in high-performance storage devices first, and store the batch data in large-capacity storage devices first;

[0040] In the central database, the dynamic storage strategy periodically re-evaluates the data and adjusts the storage location according to the preset storage rules. When extracting data from the dynamically stored database for analysis, the central database calls the corresponding storage device and data access path according to the data type and analysis requirements;

[0041] Data analysis includes data cleaning, data integration and data modeling. Through multi-dimensional data analysis and mining, key operating parameters and predictive maintenance recommendations are obtained.

[0042] As a preferred solution of the power plant data management method of the present invention, displaying the data analysis results includes:

[0043] The augmented reality device is connected to the central database to obtain data analysis results in real time through the data interface;

[0044] The data analysis results include operating parameters and predictive maintenance recommendations, and the analysis results are displayed in a graphical interface;

[0045] The operating parameters include real-time data curves, charts, and key indicator prompts, and the predictive maintenance suggestions include equipment health status assessment, equipment failure warning, and maintenance time suggestions.

[0046] In a second aspect, the present invention provides a power plant data management system, comprising:

[0047] Data acquisition module, used to collect real-time data of the power plant and dynamically adjust the data acquisition frequency of the sensor;

[0048] A data transmission module, used to preprocess and compress the real-time data of the power plant through the edge computing node, and transmit the preprocessed data to the central database through a multi-level data transmission protocol;

[0049] A data storage module, used for the central database to manage data through a dynamic storage strategy, extract data from the dynamically stored database for analysis, and obtain data analysis results;

[0050] The analysis and display module is used to display the data analysis results through an augmented reality device, wherein the data analysis results include key operating parameters and predictive maintenance suggestions.

[0051] In a third aspect, the present invention provides an electronic device, comprising:

[0052] Memory and processor;

[0053] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the power plant data management method are implemented.

[0054] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the power plant data management method.

[0055] Compared with the prior art, the present invention has the following beneficial effects: the power plant data management method provided by the present invention optimizes the accuracy of data collection and resource utilization by dynamically adjusting the data collection frequency of sensors; performs data preprocessing and intelligent classification through edge computing nodes, thereby improving the efficiency and accuracy of data processing; adopts a multi-level data transmission protocol to ensure efficient transmission and timely processing of different types of data; uses a dynamic storage strategy to manage data, thereby achieving high efficiency and flexibility in data storage; displays analysis results through augmented reality devices, making data analysis more intuitive and interactive, providing key operating parameters and predictive maintenance suggestions, thereby comprehensively improving the overall effectiveness of power plant data management. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0057] Figure 1 A schematic diagram of the overall process of a power plant data management method according to an embodiment of the present invention;

[0058] Figure 2 The figure is a schematic diagram of the overall structure of a power plant data management system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0060] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0061] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0062] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0063] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0064] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0065] Example 1

[0066] Reference Figure 1-Figure 2 , is an embodiment of the present invention, and provides a power plant data management method, such as Figure 1 ,include:

[0067] S101, collect real-time data of the power plant and dynamically adjust the data collection frequency of the sensor;

[0068] S102, preprocessing and compressing the real-time data of the power plant through the edge computing node, and transmitting the preprocessed data to the central database through a multi-level data transmission protocol;

[0069] S103, the central database manages data through a dynamic storage strategy, extracts data from the dynamically stored database for analysis, and obtains data analysis results;

[0070] S104, displaying data analysis results through augmented reality equipment, where the data analysis results include key operating parameters and predictive maintenance recommendations.

[0071] Preferably, in step S101, dynamically adjusting the data acquisition frequency of the sensor includes:

[0072] Real-time data includes temperature, pressure, flow, vibration, power output, fuel usage, and emissions data;

[0073] Set a fixed acquisition frequency as the initial input;

[0074] Define optimization goals, maximize acquisition frequency, minimize power consumption, bandwidth usage, and storage resource usage, and build a multi-objective optimization function;

[0075] Initialize the particle swarm, the dimension of each particle corresponds to the acquisition frequency of the sensor, and set the initial position and speed of the particle;

[0076] Define the fitness function based on data collection frequency, power consumption, bandwidth occupancy, and storage occupancy;

[0077] The particle speed and position are updated through the particle swarm optimization algorithm, which is realized by inertia weight, acceleration constant and random number. The fitness value of the particle is calculated after each round of iteration, and the historical optimal position and global optimal position of the particle are updated. When the set number of iterations or fitness threshold is reached, the global optimal position is selected as the data collection frequency.

[0078] It should be noted that the optimal solution output by the optimization algorithm is used to dynamically adjust the sensor acquisition frequency, monitor the sensor status, power consumption, bandwidth and storage in real time, and continuously optimize the acquisition frequency through a feedback mechanism to ensure long-term and efficient operation of the system.

[0079] Exemplarily, the temperature data T, pressure data P, flow data F, vibration data V, power output data E, fuel usage data C and emission data R of the power plant are collected through sensors, and a fixed collection frequency is initially set, using these data as initial input; the optimization goal is defined to maximize the key data collection frequency and minimize power consumption, bandwidth occupancy and storage resource occupancy, which is achieved through a multi-objective optimization function.

[0080] Define optimization goals and constraints. The optimization goal is to maximize the quality and frequency of data collection while minimizing power consumption, network bandwidth usage, and data storage resource usage.

[0081] Specifically, the objective function is expressed as:

[0082]

[0083] Among them, maximize means maximization function, minimize means minimization function, s i represents the sensor weight, f i represents the acquisition frequency of the i-th sensor, Q(d i ) represents the data quality assessment function, D1, D2, and D3 represent weight parameters, which are set according to actual conditions, B(f) represents the power consumption function, N(f) represents the bandwidth occupancy function, and S(f) represents the storage occupancy function;

[0084] Define the constraint condition that the acquisition frequency of each sensor must be within a reasonable range, expressed as:

[0085] f min ≤f i ≤f max

[0086] Among them, f min 、f max Respectively represent the minimum and maximum values ​​of the sensor acquisition frequency;

[0087] The total power consumption, bandwidth usage, and storage resources must be within the system capacity, expressed as:

[0088] B(f)≤B max ,N(f)≤N max ,S(f)≤S max

[0089] Among them, B max Indicates the maximum power consumption allowed by the system, N max Indicates the maximum bandwidth usage allowed by the system, S max Indicates the maximum storage resource allowed by the system.

[0090] For example, the particle swarm is initialized, and the dimension of each particle corresponds to the data collection frequency of a sensor {f T ,f P ,f F ,f V ,f E ,f C ,f R}, set the initial position x of the particle i and speed v i , the initial position is the current acquisition frequency, and the initial speed is a random value.

[0091] The fitness function is defined as:

[0092]

[0093] Among them, the data quality assessment function Q(d i ) is expressed as:

[0094]

[0095] Among them, Δ(d i ) represents the data volatility, A(d i ) represents data accuracy, R(d i ,d j ) represents data correlation, T(d i ) represents the data trend, λ1, λ2, λ3, λ4 represent weight parameters, which are set according to the actual situation;

[0096] Volatility Δ(d i ) is expressed as:

[0097]

[0098] Among them, d i,j represents the data value of the i-th sensor at the j-th sampling time, represents the average data value of the i-th sensor, and N represents the number of sampling times.

[0099] Accuracy A(d i ) is expressed as:

[0100]

[0101] Among them, d ref Represents the reference value or standard value of the i-th sensor.

[0102] Correlation R(d i ,d j ) is expressed as:

[0103]

[0104] Among them, cov(d i ,d j ) represents the covariance of the i-th and j-th sensor data, σ(d i ),σ(d j ) represents the standard deviation of the i-th and j-th sensor data.

[0105] Trend T(d i ) is expressed as:

[0106]

[0107] It should be noted that the fitness function combines data quality assessment and resource consumption to provide a specific measure of the optimization goal.

[0108] Exemplarily, the power consumption function B(f) is expressed as:

[0109]

[0110] Among them, b i represents the power consumption per unit time of the i-th sensor, n represents the total number of sensors, and f i represents the acquisition frequency of the i-th sensor;

[0111] The bandwidth occupancy function N(f) is expressed as:

[0112]

[0113] Among them, n i represents the data transmission rate per unit time of the i-th sensor, n represents the total number of sensors, and f i Represents the acquisition frequency of the i-th sensor.

[0114] The storage occupancy function S(f) is expressed as:

[0115]

[0116] Among them, s i represents the amount of data stored per unit time by the i-th sensor, n represents the total number of sensors, and f i Represents the acquisition frequency of the i-th sensor.

[0117] Furthermore, the updated particle speed and position are expressed as:

[0118]

[0119] Among them, θ represents the inertia weight, c1 and c2 represent acceleration constants, r1 and r2 represent random numbers, represents the historical optimal position of the particle, g best represents the global optimal position, Represents the current position and velocity of the particle.

[0120] Specifically, by updating the particle speed and position, the optimal solution of the optimization objective function is explored, the fitness value of each particle is calculated, the historical optimal position and the global optimal position of the particle are updated, and when the set number of iterations or fitness threshold is reached, the iteration is stopped and the current global optimal position is selected as the final data collection frequency plan.

[0121] Apply the optimal solution output by the particle swarm optimization algorithm to dynamically adjust the data collection frequency of each sensor, collect new real-time data, continuously update the input of the particle swarm optimization algorithm, and continuously optimize the data collection frequency.

[0122] After each round of iteration, the fitness value of the particle is calculated, the historical optimal position and the global optimal position of the particle are updated, and when the set number of iterations or the fitness threshold is reached, the global optimal position is selected as the final acquisition frequency scheme; the optimal solution output by the optimization algorithm is used to dynamically adjust the sensor acquisition frequency, monitor the sensor status, power consumption, bandwidth and storage in real time, and continuously optimize the acquisition frequency through the feedback mechanism to ensure long-term and efficient operation of the system.

[0123] It should be noted that dynamically adjusting the acquisition frequency can increase the frequency of data acquisition during key operations and change periods, thereby capturing more details and providing higher quality data; at the same time, it can reduce the acquisition frequency during stable operation periods, reduce system load, and reduce power consumption, bandwidth usage, and storage requirements. Dynamic adjustment can reduce the acquisition frequency when high-frequency data is not needed, reduce the power consumption of sensors and edge computing nodes, and extend the life of the equipment; at the same time, it can reduce unnecessary data transmission and storage, optimize the use of bandwidth and storage resources, and avoid waste of system resources.

[0124] Dynamically adjusting the acquisition frequency can better respond to changes in real-time data, making data analysis and prediction more accurate; data collected at a high frequency plays a key role in the prediction and maintenance of key equipment failures, and can detect potential problems earlier. During equipment operation, certain parameters such as temperature, pressure, vibration, etc. change rapidly under abnormal conditions. By increasing the acquisition frequency, these abnormal changes can be captured more accurately, providing detailed data for subsequent analysis.

[0125] When the system is running stably, by reducing the acquisition frequency, unnecessary data redundancy can be reduced, the pressure of data processing and storage can be reduced, and the overall system efficiency can be improved. Dynamic adjustment of the acquisition frequency can achieve the optimal allocation of resources by weighing data quality and resource consumption, ensuring the timeliness and accuracy of data while controlling system costs. Power plant data management requires efficient analysis and processing of real-time data. Dynamic adjustment of the acquisition frequency ensures that key data can be collected and processed in a timely manner to meet real-time requirements.

[0126] The resources of the power plant data management system (such as power, bandwidth, and storage) are limited. By dynamically adjusting the acquisition frequency, these resources can be optimally utilized without affecting data quality. Predictive maintenance relies on high-quality historical and real-time data. By dynamically adjusting the acquisition frequency, more detailed data can be obtained at critical moments, enhancing the accuracy and effectiveness of the prediction model.

[0127] Dynamic adjustment of the acquisition frequency directly affects the real-time and accuracy of the data, ensuring that the pre-processed and compressed data is of high quality, providing a reliable data foundation for subsequent transmission and storage. Through a multi-level data transmission protocol, dynamic adjustment of the acquisition frequency ensures the effective classification and transmission of real-time data, batch data, and emergency data, and optimizes data transmission efficiency and storage management. Dynamic adjustment of the acquisition frequency provides high-quality real-time data, providing accurate basic data for subsequent data analysis and augmented reality display, ensuring the accuracy and timeliness of key operating parameters and predictive maintenance recommendations.

[0128] Dynamically adjusting the data collection frequency of sensors is a key step in the power plant data management method. The collection frequency determined by the particle swarm optimization algorithm not only improves the data quality and the overall performance of the system, but also optimizes the utilization of resources, providing a reliable foundation for subsequent data preprocessing, transmission, storage, analysis and display. This step ensures that the system can efficiently and accurately manage data and perform predictive maintenance, which is a necessary prerequisite for achieving the optimal effect.

[0129] Preferably, in step S102, data preprocessing and compression includes:

[0130] The edge computing node receives real-time data from the power plant, and data preprocessing includes denoising, data cleaning, and formatting;

[0131] The edge computing node compresses the preprocessed data, classifies the compressed data through a data analysis algorithm, and the classification includes: real-time data, batch data, and emergency data, and transmits them to the central database through a multi-level data transmission protocol.

[0132] Specifically, denoising uses low-pass filtering or Kalman filtering, data cleaning includes handling missing values and outliers, formatting converts the data into a unified format, and the compression algorithm selects a lossless compression algorithm such as Huffman coding or a lossy compression algorithm such as discrete wavelet transform, and selects an appropriate compression method according to the data type and accuracy requirements.

[0133] Preferably, the data analysis algorithm is expressed as:

[0134]

[0135] S = α·R + β·P + γ·D

[0136] Among them, R represents the real-time score, x represents the variable in the integral calculation, k represents the constant that adjusts the exponential growth, t represents the current time of the data, t0 represents the generation time of the data, ω represents the frequency of periodic fluctuations, P represents the priority score, w i represents the weight of the i-th parameter, p i represents the score of the i-th parameter, q i represents the i-th relevant parameter, n represents the total number of parameters, D represents the sensor data score, d j represents the j-th sensor data, λ j represents the adjustment parameter of the j-th sensor data, m represents the total number of sensors, S represents the comprehensive data score, α represents the adjustment parameter of the real-time score, β represents the adjustment parameter of the priority score, γ represents the adjustment parameter of the sensor data score;

[0137] Based on the historical data comprehensive score, classification thresholds T1 and T2 are determined, and T1 < T2 is satisfied;

[0138] If S < T1, the data is classified as batch data. If T1 ≤ S < T2, the data is classified as real-time data. If S ≥ T2, the data is classified as emergency data.

[0139] Specifically, by collecting the historical data of the data comprehensive score S over a period of time, preprocessing it to remove outliers and perform data cleaning, sorting the preprocessed historical data from low to high according to the comprehensive score value, taking the value at the one-third position in the sorted data as the classification threshold T1 between batch data and real-time data, and taking the value at the two-thirds position in the sorted data as the classification threshold T2 between real-time data and emergency data.

[0140] Preferably, the multi-layered data transmission protocol includes a real-time data transmission layer, a bulk data transmission layer, and an emergency data transmission layer;

[0141] The real-time data transmission layer transmits real-time data via the UDP protocol;

[0142] The bulk data transmission layer transmits bulk data through the TCP protocol and packages them according to the set time interval or data volume threshold;

[0143] The emergency data transmission layer transmits the emergency data via the Advanced Message Queuing Protocol AMQP and transmits it to the central database;

[0144] During data transmission, a transmission scheduling algorithm is used to monitor transmission bandwidth and resource usage, and adjust the data transmission frequency and priority of each transmission layer;

[0145] The transmission scheduling algorithm allocates bandwidth and resources according to the classification results of real-time data, batch data and urgent data, and adjusts the data transmission frequency and priority of the real-time data transmission layer, batch data transmission layer and urgent data transmission layer according to the current bandwidth and resource conditions.

[0146] Exemplary, initialization: Collect the current bandwidth requirements of real-time data, batch data, and urgent data B RT ,B BT ,B ET and priority P RT ,P BT ,P ET , get the current total bandwidth B total and total resources R total , the bandwidth and resource allocation of each transport layer are calculated by the following formula;

[0147] Calculate the real-time data transmission layer bandwidth B RT and Resources RT , expressed as:

[0148]

[0149] Among them, P RT is the priority of the real-time data transmission layer, B RT is the bandwidth of the real-time data transmission layer, R RT Resources for the real-time data transmission layer.

[0150] Calculate the bulk data transfer layer bandwidth B BT and Resources BT , expressed as:

[0151]

[0152] Among them, PBT is the priority of the bulk data transmission layer, B BT is the bandwidth of the bulk data transmission layer, R BT Resources for the bulk data transfer layer.

[0153] Calculate the bandwidth B of the emergency data transmission layer ET and Resources ET , expressed as:

[0154]

[0155] Among them, P ET is the priority of the emergency data transmission layer, B ET is the bandwidth of the emergency data transmission layer, R ET Resources for the emergency data transmission layer.

[0156] According to the calculation results, the data transmission frequency and priority of the real-time data transmission layer, bulk data transmission layer and emergency data transmission layer are adjusted. The specific adjustment calculation method is as follows:

[0157] According to the real-time data transmission layer bandwidth and resource allocation B RT and R RT , adjust the data transmission frequency f RT and priority P RT , expressed as:

[0158]

[0159] Among them, f RT is the real-time data transmission frequency, f max is the maximum transmission frequency.

[0160] According to the bulk data transmission layer bandwidth and resource allocation B BT and R BT , adjust the data transmission frequency f BT and priority P BT , expressed as:

[0161]

[0162] Among them, f BT is the bulk data transmission frequency, f max is the maximum transmission frequency.

[0163] According to the urgent data transmission layer bandwidth and resource allocation B ET and R ET , adjust the data transmission frequency f ET and priority P ET , expressed as:

[0164]

[0165] Among them, f ET is the emergency data transmission frequency, f max is the maximum transmission frequency.

[0166] Monitor bandwidth and resource usage during transmission, and record bandwidth usage of each transport layer. RT ,B BT ,B ET and resources using R RT ,R BT ,R ET ,According to the monitoring results, the parameters of the transmission scheduling algorithm are adjusted in real time to optimize the transmission frequency and priority allocation.

[0167] It should be noted that the method of classifying data into real-time data, batch data, and urgent data through the data comprehensive score S helps to accurately identify and distinguish data of different priorities and urgency. The comprehensive score S takes into account real-time, priority, and sensor data scores, and can fully reflect the importance and urgency of the data. This method avoids simple and crude fixed classification, improves the scientificity and accuracy of data classification, helps to more reasonably allocate system resources, and optimizes data processing and transmission.

[0168] Compared with traditional methods, the data comprehensive scoring S classification method can more comprehensively and accurately evaluate the importance and urgency of data by introducing real-time scoring, priority scoring and sensor data scoring. Traditional methods only classify based on data types or fixed rules, which lacks flexibility and accuracy. The comprehensive scoring method can dynamically adjust the classification criteria to adapt to different working conditions and data characteristics, thereby improving the accuracy and scientificity of classification.

[0169] Different types of data are processed through different transport layers, and the real-time data transmission layer, bulk data transmission layer and emergency data transmission layer are used to process real-time data, bulk data and emergency data respectively, ensuring that each type of data can get the most appropriate transmission method. Real-time data is transmitted through the low-latency UDP protocol, bulk data is transmitted through the reliable TCP protocol, and emergency data is transmitted through the high-priority AMQP protocol. The transmission path and protocol selection are optimized, the efficiency and reliability of data transmission are improved, and it is ensured that emergency data can be responded to quickly, real-time data can be processed in time, and bulk data can be transmitted efficiently.

[0170] Traditional methods generally use a single transmission protocol to process all data, which cannot distinguish the transmission requirements of different data types, and easily lead to low transmission efficiency or data delay. Multi-level data transmission protocols can significantly improve transmission efficiency and reliability by designing different transmission layers for real-time data, batch data, and urgent data, and using the most appropriate transmission protocol and path, ensuring that key data can be transmitted and processed in a timely manner, reducing the risk of transmission delays and data loss.

[0171] The transmission scheduling algorithm is used to dynamically adjust the data transmission frequency and priority of each transmission layer according to the classification results of real-time data, batch data and urgent data, further optimizing the utilization of system resources. The transmission scheduling algorithm monitors the transmission bandwidth and resource usage in real time, and dynamically adjusts the data transmission frequency and priority of each transmission layer according to the current bandwidth and resource conditions to achieve the optimal allocation of bandwidth and resources. Through dynamic adjustment, it can effectively respond to changes in data traffic and system resources, avoid resource overload or idleness, and improve the overall performance and stability of the system.

[0172] Traditional methods usually use static transmission strategies that cannot be adjusted dynamically according to actual conditions, which can easily lead to unbalanced resource utilization, bandwidth and resource waste or overload. The transmission scheduling algorithm monitors the transmission bandwidth and resource usage in real time, dynamically adjusts the data transmission frequency and priority of each transmission layer, and can flexibly allocate bandwidth and resources according to actual needs, thereby improving the adaptability and stability of the system. Through dynamic scheduling, it can better respond to emergencies and changes in data traffic, ensuring that the system can operate efficiently under various working conditions.

[0173] Preferably, in step S103, the dynamic storage strategy includes:

[0174] Optimize storage based on data access frequency, importance, and storage space utilization. Prioritize real-time and urgent data to be stored in high-performance storage devices, and prioritize batch data to be stored in large-capacity storage devices.

[0175] In the central database, the dynamic storage strategy regularly re-evaluates the data and adjusts the storage location according to the preset storage rules. When extracting data from the dynamic storage database for analysis, the central database calls the corresponding storage device and data access path according to the data type and analysis requirements;

[0176] The data analysis process includes data cleaning, data integration and data modeling. Through multi-dimensional data analysis and mining, key operating parameters and predictive maintenance recommendations are obtained.

[0177] Preferably, in step S104, displaying the analysis results includes:

[0178] The augmented reality device is connected to the central database to obtain data analysis results in real time through the data interface;

[0179] The data analysis results include operating parameters and predictive maintenance recommendations, and the analysis results are displayed in a graphical interface;

[0180] Operating parameters include real-time data curves, charts, and key indicator prompts, and predictive maintenance recommendations include equipment health status assessment, equipment failure warning, and maintenance time recommendations.

[0181] The augmented reality device is connected to the central database and obtains analysis results in real time through the data interface. The analysis results include operating parameters and predictive maintenance suggestions. The suggestions include equipment failure warnings and maintenance time suggestions. The augmented reality device displays the analysis results in a graphical interface, and the operating parameters display real-time data curves, charts and key indicator prompts. Predictive maintenance suggestions provide equipment health status assessment, fault prediction and maintenance suggestions.

[0182] The power plant data management method provided by the present invention optimizes the accuracy of data collection and resource utilization by dynamically adjusting the data collection frequency of sensors; performs data preprocessing and intelligent classification through edge computing nodes to improve the efficiency and accuracy of data processing; adopts a multi-level data transmission protocol to ensure efficient transmission and timely processing of different types of data; uses a dynamic storage strategy to manage data to achieve high efficiency and flexibility in data storage; displays analysis results through augmented reality devices to make data analysis more intuitive and interactive, and provides key operating parameters and predictive maintenance suggestions, thereby comprehensively improving the overall effectiveness of power plant data management.

[0183] The above is a schematic scheme of a power plant data management method of this embodiment. It should be noted that the technical scheme of the power plant data management system and the technical scheme of the above power plant data management method belong to the same concept, and the details of the technical scheme of the power plant data management system in this embodiment that are not described in detail can all be referred to the description of the technical scheme of the above power plant data management method.

[0184] In this embodiment, the power plant data management system, such as Figure 2 ,include:

[0185] Data acquisition module, used to collect real-time data of the power plant and dynamically adjust the data acquisition frequency of the sensor;

[0186] The data transmission module is used to preprocess and compress the real-time data of the power plant through the edge computing node, and transmit the preprocessed data to the central database through a multi-level data transmission protocol;

[0187] The data storage module is used for the central database to manage data through dynamic storage strategies, extract data from the dynamically stored database for analysis, and obtain data analysis results;

[0188] The analysis and display module is used to display data analysis results through augmented reality devices. The data analysis results include key operating parameters and predictive maintenance recommendations.

[0189] This embodiment also provides an electronic device suitable for power plant data management, including:

[0190] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the power plant data management method proposed in the above embodiment.

[0191] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the power plant data management method proposed in the above embodiment is implemented.

[0192] The storage medium proposed in this embodiment and the method for implementing power plant data management proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0193] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

[0194] Example 2

[0195] Referring to Table 1, an embodiment of the present invention provides a power plant data management method. In order to verify its beneficial effects, comparison results of two solutions are provided.

[0196] By comparing the power plant data management method invented by us with the traditional power plant data management method in terms of data collection efficiency, transmission delay, storage utilization and data analysis accuracy, the superiority of our invented method is verified.

[0197] Experimental objects: Part of the operating data of a power plant (temperature, pressure, flow, vibration, power output, fuel usage and emission data); Experimental equipment: sensors, edge computing nodes, central database, augmented reality equipment; Experimental time: 24 hours.

[0198] In the traditional method, sensors are used to collect real-time data of the power plant at a fixed frequency (once per second) in the experiment, including temperature, pressure, flow, vibration, power output, fuel usage and emission data. The edge computing node performs simple preprocessing on the collected data, including denoising, data cleaning and formatting. The preprocessed data is classified at fixed time intervals (every minute) and transmitted to the central database through a single TCP protocol. In the central database, all data is stored in chronological order, and batch analysis of the data is performed regularly. The analysis results are presented in the form of two-dimensional charts and text reports, and provided to power plant operators for decision-making and maintenance.

[0199] In the experiment, our invented method uses sensors to dynamically adjust the data collection frequency. The initial frequency is set to 1 time per second, and the particle swarm optimization algorithm is used to dynamically adjust the frequency according to the optimization target. The edge computing node preprocesses the collected real-time data, including denoising, data cleaning and compression. The preprocessed data is classified into real-time data, batch data and emergency data according to the data analysis algorithm, and transmitted to the central database through a multi-level data transmission protocol, where real-time data is transmitted using the UDP protocol, batch data is transmitted using the TCP protocol, and emergency data is transmitted using the AMQP protocol. In the central database, a dynamic storage strategy is used to manage data, optimize the storage location according to the access frequency and importance of the data, and perform data analysis in real time. The analysis results, including key operating parameters and predictive maintenance recommendations, are displayed through an augmented reality device. The augmented reality device is connected to the central database, and the analysis results are obtained and displayed in real time through the data interface. The experimental results are shown in Table 1.

[0200] Table 1: Comparison of experimental results

[0201]

[0202] Compared with the fixed frequency of traditional methods, our invented method dynamically adjusts the frequency according to actual needs, reducing power consumption and bandwidth occupancy. Our invented method uses a particle swarm optimization algorithm to dynamically adjust the collection frequency, ensuring that unnecessary data collection is reduced when key data is frequently collected, thereby optimizing resource utilization.

[0203] Compared with the traditional method of using a single TCP protocol to transmit all data, the transmission delay is significantly reduced. This is because UDP has low latency characteristics and AMQP can process urgent data with high priority, ensuring the timely transmission of critical data. Our invented method adopts a multi-level data transmission protocol to transmit real-time data through UDP, urgent data through AMQP, and batch data through TCP.

[0204] Compared with the traditional method of storing all data in chronological order, our invented method can utilize storage space more efficiently and improve storage utilization. Our invented method uses dynamic storage strategy to manage data, optimizes storage location according to data access frequency and importance, and gives priority to storing high-frequency access and important data in high-performance storage devices, thereby optimizing storage utilization.

[0205] Compared with the data analysis accuracy of traditional methods, the accuracy of our invented method is significantly improved. Our invented method performs intelligent processing in data preprocessing and classification, and improves the quality of data through denoising, data cleaning and compression, thereby improving the accuracy of data analysis. At the same time, the analysis results are intuitively displayed through augmented reality devices, making the analysis results easier to understand and use, further improving the effectiveness of data analysis.

[0206] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A power plant data management method, characterized in that: Including: Collecting real-time power plant data and dynamically adjusting the data collection frequency of sensors; Performing data preprocessing and compression on the real-time power plant data through an edge computing node, and transmitting the preprocessed data to a central database through a multi-level data transmission protocol; The central database manages data through a dynamic storage strategy, extracts data from the dynamically stored database for analysis, and obtains data analysis results; Displaying the data analysis results through an augmented reality device, where the data analysis results include key operation parameters and predictive maintenance suggestions.

2. The power plant data management method according to claim 1, characterized in that: The dynamically adjusting the data collection frequency of sensors includes: The real-time data includes temperature, pressure, flow rate, vibration, power output, fuel usage, and emission data; Setting a fixed collection frequency as the initial input; Defining an optimization objective, maximizing the collection frequency, and minimizing power consumption, bandwidth occupancy, and storage resource occupancy, and constructing a multi-objective optimization function; Initializing a particle swarm, where the dimension of each particle corresponds to the collection frequency of the sensor, and setting the initial position and velocity of the particle; Defining a fitness function based on the data collection frequency, power consumption, bandwidth occupancy, and storage occupancy; Updating the velocity and position of the particle through a particle swarm optimization algorithm, calculating the fitness value of the particle after each iteration, updating the historical best position and global best position of the particle, and when the set number of iterations or fitness threshold is reached, selecting the global best position as the data collection frequency.

3. The power plant data management method according to claim 1 or 2, characterized in that: The data preprocessing and compression includes: The edge computing node receives the real-time power plant data, and the data preprocessing includes denoising, data cleaning, and formatting; The edge computing node compresses the preprocessed data, classifies the compressed data through a data analysis algorithm, where the classification includes: real-time data, batch data, and emergency data, and transmits it to the central database through a multi-level data transmission protocol.

4. The power plant data management method according to claim 3, characterized in that: The data analysis algorithm is expressed as: S = α·R + β·P + γ·D Among them, R represents the real-time score, x represents the variable in the integral calculation, k represents the constant for adjusting the exponential growth, t represents the current time of the data, t0 represents the generation time of the data, ω represents the frequency of periodic fluctuations, P represents the priority score, and w i represents the weight of the i-th parameter, p i represents the score of the i-th parameter, q i represents the i-th relevant parameter, n represents the total number of parameters, D represents the sensor data score, and d j represents the jth sensor data, λ j represents the adjustment parameter of the jth sensor data, m represents the total number of sensors, S represents the comprehensive score of the data, α represents the adjustment parameter of the real-time score, β represents the adjustment parameter of the priority score, and γ represents the adjustment parameter of the sensor data score; Determining classification thresholds T1 and T2 based on the comprehensive score of historical data, and satisfying T1 < T2; If S < T1, then classify the data as batch data, if T1 ≤ S < T2, then classify the data as real-time data, if S ≥ T2, then classify the data as emergency data.

5. The power plant data management method according to claim 4, characterized in that: The multi-level data transmission protocol includes a real-time data transmission layer, a batch data transmission layer, and an emergency data transmission layer; The real-time data transmission layer transmits real-time data through the UDP protocol; The batch data transmission layer transmits batch data through the TCP protocol and packages it according to a set time interval or data volume threshold; The emergency data transmission layer transmits emergency data through the Advanced Message Queuing Protocol AMQP and transmits it to the central database; During the data transmission process, use a transmission scheduling algorithm to monitor the transmission bandwidth and resource usage, and adjust the data transmission frequency and priority of each transmission layer; The transmission scheduling algorithm allocates bandwidth and resources according to the classification results of real-time data, batch data, and emergency data, and adjusts the data transmission frequency and priority of the real-time data transmission layer, batch data transmission layer, and emergency data transmission layer according to the current bandwidth and resource conditions.

6. The power plant data management method according to claim 5, characterized in that: The dynamic storage strategy includes: Optimize storage based on data access frequency, importance and storage space utilization, and store the real-time data and urgent data in high-performance storage devices first, and store the batch data in large-capacity storage devices first; In the central database, the dynamic storage strategy periodically re-evaluates the data and adjusts the storage location according to the preset storage rules. When extracting data from the dynamically stored database for analysis, the central database calls the corresponding storage device and data access path according to the data type and analysis requirements; Data analysis includes data cleaning, data integration and data modeling. Through multi-dimensional data analysis and mining, key operating parameters and predictive maintenance recommendations are obtained.

7. The power plant data management method according to any one of claims 3 to 6, characterized in that: The data analysis results include: The augmented reality device is connected to the central database to obtain data analysis results in real time through the data interface; The data analysis results include operating parameters and predictive maintenance recommendations, and the analysis results are displayed in a graphical interface; The operating parameters include real-time data curves, charts, and key indicator prompts, and the predictive maintenance suggestions include equipment health status assessment, equipment failure warning, and maintenance time suggestions.

8. A power plant data management system, characterized in that: include, Data acquisition module, used to collect real-time data of the power plant and dynamically adjust the data acquisition frequency of the sensor; A data transmission module, used to preprocess and compress the real-time data of the power plant through the edge computing node, and transmit the preprocessed data to the central database through a multi-level data transmission protocol; A data storage module, used for the central database to manage data through a dynamic storage strategy, extract data from the dynamically stored database for analysis, and obtain data analysis results; The analysis and display module is used to display the data analysis results through an augmented reality device, wherein the data analysis results include key operating parameters and predictive maintenance suggestions.

9. An electronic device, characterized in that: include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the power plant data management method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: It stores computer executable instructions, which, when executed by a processor, implement the steps of the power plant data management method described in any one of claims 1 to 7.

Images