Thermal power plant energy consumption online monitoring and early warning system and method based on big data

Through big data technology, the energy consumption of thermal power plants is monitored online, and early warning information is generated using energy consumption prediction models and optimization models, which solves the problem of low energy consumption supervision efficiency in the existing technology, and realizes real-time and accurate monitoring and optimization of energy consumption of thermal power plants. Decision support.

CN118940934APending Publication Date: 2024-11-12HUANENG JINGMEN THERMAL POWER CO LTD
View PDF 0 Cites 5 Cited by

Patent Information

Application Number
CN202410827881.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-25
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing energy consumption monitoring system for thermal power plants is difficult to achieve online monitoring and dynamic early warning, resulting in low efficiency and uncertainty in energy consumption supervision.

Method used

Adopt the online monitoring and early warning system for energy consumption of thermal power plants based on big data, and obtain the original energy consumption data through the front-end sampling unit for preprocessing and integration, input the pre-built energy consumption prediction model and optimization model to generate energy consumption prediction results and optimization solutions. , and determine the dynamic warning threshold based on the prediction results to generate energy consumption abnormality warning information.

Benefits of technology

Real-time and accurate monitoring of energy consumption in thermal power plants is achieved, energy consumption optimization solutions are provided, the accuracy and reliability of energy consumption supervision are improved, and the level of energy efficiency management is enhanced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118940934A_ABST
    Figure CN118940934A_ABST
Patent Text Reader

Abstract

The invention provides a thermal power plant energy consumption on-line monitoring and early warning system and method based on big data, and the system comprises a front-end sampling unit which is used for obtaining the original energy consumption data of a plurality of key devices in a thermal power plant, and carrying out the preprocessing and integration of the original energy consumption data, and obtaining the effective energy consumption data; the big data server is used for respectively inputting the effective energy consumption data into a pre-constructed energy consumption prediction model and an energy consumption optimization model to obtain an energy consumption prediction result and an energy consumption optimization scheme; determining a dynamic early warning threshold based on the energy consumption prediction result, and generating energy consumption abnormity early warning information when the effective energy consumption data deviates from the dynamic early warning threshold; and the monitoring terminal is connected with the big data server and is used for receiving and displaying the energy consumption abnormity early warning information, the effective energy consumption data, the energy consumption prediction result and the energy consumption optimization scheme. According to the scheme provided by the invention, the energy consumption of the thermal power plant is accurately monitored in real time, and an effective energy consumption optimization scheme can be provided for supervisors, so that data support is provided for an energy consumption optimization decision.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption monitoring, and in particular to an online monitoring and early warning system and method for energy consumption of a thermal power plant based on big data. Background Art

[0002] With the rapid growth of energy consumption and the improvement of environmental protection awareness, thermal power plants, as one of the main areas of energy consumption, are receiving more and more attention for their energy consumption management and energy conservation and emission reduction. It is very important to conduct effective energy consumption monitoring of thermal power plants.

[0003] In the related technologies, the energy consumption monitoring system of thermal power plants mainly relies on manual or periodic data collection. The real-time and accuracy of the front-end data are difficult to guarantee, and online monitoring and dynamic early warning cannot be achieved. The energy consumption supervision efficiency is low, and it is difficult to guarantee the accuracy and reliability of energy consumption supervision.

[0004] Therefore, there is an urgent need for a real-time, accurate and reliable energy consumption monitoring solution. Summary of the invention

[0005] The present invention provides an online monitoring and early warning system and method for energy consumption of a thermal power plant based on big data, which is used to solve the defects of traditional energy consumption monitoring schemes, that is, low efficiency of energy consumption supervision and difficulty in ensuring the accuracy and reliability of energy consumption supervision.

[0006] On the one hand, the present invention provides an online monitoring and early warning system for energy consumption of a thermal power plant based on big data, comprising:

[0007] The front-end sampling unit is used to obtain the original energy consumption data of various key equipment in the thermal power plant, and obtain effective energy consumption data after preprocessing and integrating the original energy consumption data;

[0008] A big data service end is connected to the front-end sampling unit, and is used to input the effective energy consumption data into a pre-built energy consumption prediction model and an energy consumption optimization model after receiving the effective energy consumption data, and obtain the energy consumption prediction result output by the energy consumption prediction model and the energy consumption optimization plan output by the energy consumption optimization model; determine a dynamic warning threshold based on the energy consumption prediction result, and generate energy consumption abnormality warning information when the effective energy consumption data deviates from the dynamic warning threshold;

[0009] The monitoring terminal is connected to the big data server and is used to receive and display the abnormal energy consumption warning information, the effective energy consumption data, the energy consumption prediction result and the energy consumption optimization plan.

[0010] According to the thermal power plant energy consumption online monitoring and early warning system based on big data provided by the present invention, the front-end sampling unit includes a sensor network composed of a plurality of energy consumption sensors and a data processing device, the plurality of energy consumption sensors are installed on different key equipment in the thermal power plant, and the sensor network is connected to the data processing device;

[0011] The sensor network is used to obtain original energy consumption data of various key equipment in the thermal power plant and transmit the original energy consumption data to the data processing device;

[0012] The data processing device is used to pre-process and integrate the original energy consumption data to obtain effective energy consumption data;

[0013] Wherein, the preprocessing includes data cleaning and standardization.

[0014] According to the thermal power plant energy consumption online monitoring and early warning system based on big data provided by the present invention, the energy consumption prediction model is established through the following process:

[0015] Obtain historical energy consumption data of key equipment in thermal power plants;

[0016] According to the sampling timestamp information of the historical energy consumption data, the historical energy consumption data is split into multiple groups of energy consumption sample sequences, wherein each group of the energy consumption sample sequences includes an early energy consumption data segment and a subsequent trend data segment;

[0017] Based on the multiple groups of energy consumption sample sequences, establishing a training sample set;

[0018] The pre-built deep learning neural network is trained using the training sample set to obtain a trained energy consumption prediction model.

[0019] According to the big data-based online monitoring and early warning system for thermal power plant energy consumption provided by the present invention, the energy consumption optimization model is established through the following process:

[0020] Obtain historical energy consumption data, equipment operation data, and energy distribution data of key equipment in thermal power plants;

[0021] According to the historical energy consumption data, the equipment operation data and the energy distribution data corresponding to the same sampling time, a three-dimensional data point corresponding to each sampling time is established;

[0022] At least part of the three-dimensional data points are fitted to obtain an energy consumption optimization model.

[0023] According to the big data-based online monitoring and early warning system for energy consumption in thermal power plants provided by the present invention, the monitoring terminal has a first data display area, a second data display area and a third data display area;

[0024] Among them, the first data display area is used to display the energy consumption abnormality warning information in the form of a time series diagram, the second data display area is used to display a plant map marked with the effective energy consumption data and the energy consumption forecast results, and the third data display area is used to display the energy consumption optimization plan in the form of an optimization list.

[0025] According to the thermal power plant energy consumption online monitoring and early warning system based on big data provided by the present invention, the big data server determines a dynamic early warning threshold based on the energy consumption prediction result, including:

[0026] Based on the energy consumption forecast result, determining the comprehensive energy consumption limit value of the thermal power plant in a future preset period of time;

[0027] Determining the dynamic warning threshold based on the comprehensive energy consumption limit value and the preset mapping relationship;

[0028] The preset mapping relationship is used to characterize the corresponding relationship between the dynamic warning threshold and the comprehensive energy consumption limit value.

[0029] According to the big data-based online monitoring and early warning system for energy consumption in thermal power plants provided by the present invention, the preset mapping relationship is established through the following process:

[0030] Obtain historical energy consumption data of thermal power plants;

[0031] Dividing the historical energy consumption data into a plurality of historical energy consumption sections according to a preset time period;

[0032] Respectively determine the comprehensive energy consumption limit value corresponding to each of the historical energy consumption sections, and determine the warning threshold calibration value corresponding to each of the historical energy consumption sections;

[0033] Constructing a plurality of discrete data points according to the comprehensive energy consumption limit value corresponding to each of the historical energy consumption sections and the warning threshold calibration value;

[0034] The discrete data points are fitted to establish the preset mapping relationship.

[0035] On the other hand, the present invention also provides a method for online monitoring and early warning of energy consumption in a thermal power plant based on big data, comprising:

[0036] Receive effective energy consumption data obtained by preprocessing and integrating the original energy consumption data of various key equipment in the thermal power plant;

[0037] Inputting the effective energy consumption data into a pre-built energy consumption prediction model and an energy consumption optimization model respectively, obtaining an energy consumption prediction result output by the energy consumption prediction model and an energy consumption optimization solution output by the energy consumption optimization model;

[0038] A dynamic warning threshold is determined based on the energy consumption prediction result, and when the effective energy consumption data deviates from the dynamic warning threshold, energy consumption abnormality warning information is generated, so that the monitoring terminal displays the energy consumption abnormality warning information, the effective energy consumption data, the energy consumption prediction result and the energy consumption optimization plan.

[0039] According to the method for online monitoring and early warning of energy consumption in a thermal power plant based on big data provided by the present invention, the energy consumption prediction model is established through the following process:

[0040] Obtain historical energy consumption data of key equipment in thermal power plants;

[0041] According to the sampling timestamp information of the historical energy consumption data, the historical energy consumption data is split into multiple groups of energy consumption sample sequences, wherein each group of the energy consumption sample sequences includes an early energy consumption data segment and a subsequent trend data segment;

[0042] Based on the multiple groups of energy consumption sample sequences, establishing a training sample set;

[0043] The pre-built deep learning neural network is trained using the training sample set to obtain a trained energy consumption prediction model.

[0044] According to the method for online monitoring and early warning of energy consumption in a thermal power plant based on big data provided by the present invention, the energy consumption optimization model is established through the following process:

[0045] Obtain historical energy consumption data, equipment operation data, and energy distribution data of key equipment in thermal power plants;

[0046] According to the historical energy consumption data, the equipment operation data and the energy distribution data corresponding to the same sampling time, a three-dimensional data point corresponding to each sampling time is established;

[0047] At least part of the three-dimensional data points are fitted to obtain an energy consumption optimization model.

[0048] The thermal power plant energy consumption online monitoring and early warning system and method based on big data provided by the present invention can, through the cooperation of the front-end sampling unit, the big data service end and the monitoring terminal, input the effective energy consumption data into the pre-built energy consumption prediction model and the energy consumption optimization model respectively after receiving the effective energy consumption data, and obtain the energy consumption prediction result output by the energy consumption prediction model and the energy consumption optimization plan output by the energy consumption optimization model; determine the dynamic early warning threshold based on the energy consumption prediction result, and generate energy consumption abnormal early warning information when the effective energy consumption data deviates from the dynamic early warning threshold. Real-time and accurate monitoring of the energy consumption of thermal power plants is achieved, and effective energy consumption optimization plans can be provided to supervisors, thereby providing data support for energy consumption optimization decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 It is a structural schematic diagram of an online monitoring and early warning system for energy consumption of a thermal power plant based on big data provided by an embodiment of the present invention;

[0051] Figure 2 It is a flow chart of an online monitoring and early warning method for energy consumption of a thermal power plant based on big data provided by an embodiment of the present invention;

[0052] Figure 3 It is a structural diagram of a big data server in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Combine the following Figures 1 to 3 The detailed scheme of the online monitoring and early warning system and method for energy consumption of thermal power plants based on big data provided by the embodiments of the present invention is described.

[0055] Figure 1 It is a structural schematic diagram of an online monitoring and early warning system for energy consumption of a thermal power plant based on big data provided by an embodiment of the present invention.

[0056] like Figure 1 As shown, the thermal power plant energy consumption online monitoring and early warning system based on big data provided by the embodiment of the present invention specifically includes:

[0057] The front-end sampling unit 110 is used to obtain the original energy consumption data of various key equipment in the thermal power plant, and obtain effective energy consumption data after preprocessing and integrating the original energy consumption data.

[0058] The big data service end 120 is connected to the front-end sampling unit 110, and is used to input the effective energy consumption data into a pre-built energy consumption prediction model and an energy consumption optimization model after receiving the effective energy consumption data, so as to obtain the energy consumption prediction results output by the energy consumption prediction model and the energy consumption optimization plan output by the energy consumption optimization model; determine the dynamic warning threshold based on the energy consumption prediction result, and generate energy consumption abnormality warning information when the effective energy consumption data deviates from the dynamic warning threshold.

[0059] The monitoring terminal 130 is connected to the big data server 120 and is used to receive and display abnormal energy consumption warning information, effective energy consumption data, energy consumption prediction results and energy consumption optimization solutions.

[0060] In this embodiment, the front-end sampling unit 110 is mainly used for front-end data sampling and data pre-processing of various key equipment in the thermal power plant, so as to obtain effective energy consumption data of various key equipment.

[0061] In some embodiments, the various key equipment in a thermal power plant may include important equipment such as boilers, steam turbine units, generator units, and boiler auxiliary equipment.

[0062] In this embodiment, the big data server 120 may be a cloud server installed with a big data service platform, such as a cloud server installed with Hadoop or Spark, which can process and analyze the collected effective energy consumption data in real time.

[0063] The monitoring terminal 130 may be a computer deployed in a monitoring room, or may be a mobile terminal device carried by a supervisor, such as a smart phone, a tablet computer, or other mobile terminal devices.

[0064] The solution provided in this embodiment can monitor the energy consumption of a thermal power plant in real time and accurately through the cooperation of the front-end sampling unit 110, the big data service terminal 120 and the monitoring terminal 130, and can provide supervisors with effective energy consumption optimization solutions, making the monitoring process more automated and intelligent.

[0065] In one embodiment, see Figure 1 The front-end sampling unit 110 specifically includes a sensor network composed of multiple energy consumption sensors 1101 and a data processing device 1102. The multiple energy consumption sensors 1101 are installed on different key equipment in the thermal power plant, and the sensor network is connected to the data processing device 1102.

[0066] The sensor network is used to obtain the original energy consumption data of various key equipment in the thermal power plant, and transmit the original energy consumption data to the data processing device 1102.

[0067] The data processing device 1102 is used to pre-process and integrate the original energy consumption data to obtain effective energy consumption data.

[0068] Among them, preprocessing includes data cleaning and standardization.

[0069] It can be understood that the energy consumption sensor 1101 can collect key parameters of the corresponding key equipment in real time, such as voltage, current, temperature and other parameters. At the same time, the energy consumption sensor can convert the collected key parameters into a measurable signal containing the original energy consumption data, and then send the measurable signal to the data processing device 1102 via wired or wireless means.

[0070] The data processing device 1102 can perform pre-processing operations such as data cleaning and standardization on the original energy consumption data, and integrate the pre-processed original energy consumption data to obtain effective energy consumption data.

[0071] In some embodiments, the process of integrating the pre-processed raw energy consumption data is as follows:

[0072] First, according to the energy consumption level of each key equipment, determine the weighting coefficient corresponding to each key equipment.

[0073] Then, according to the weighted coefficients corresponding to each key equipment, the pre-processed original energy consumption data is weighted and summed to obtain the comprehensive energy consumption data of the thermal power plant.

[0074] In one embodiment, the energy consumption prediction model can be established through the following process:

[0075] The first step is to obtain the historical energy consumption data of key equipment in the thermal power plant.

[0076] In this embodiment, the current time point may be used as the time starting point to obtain the historical energy consumption data of the key equipment in the thermal power plant within a preset period before the time starting point.

[0077] In the second step, the historical energy consumption data is split into multiple groups of energy consumption sample sequences according to the sampling timestamp information of the historical energy consumption data, wherein each group of energy consumption sample sequences includes an early energy consumption data segment and a subsequent trend data segment.

[0078] It can be understood that since the historical energy consumption data obtained is a set of data points formed in a continuous period of time, the set of data points can be split. For example, a sample period can be set, such as 48 hours, and the entire set of data points can be split into multiple groups of data subsequences in such a way that each sample period corresponds to a group of data subsequences.

[0079] At the same time, any set of data subsequences can be further split into two parts, one as the early energy consumption sample and the other as the later prediction sample. For example, a set of data subsequences within 48 hours can be equally divided into two parts, the part with the earlier timestamp information as the early energy consumption data segment and the part with the later timestamp information as the later trend data segment, thereby obtaining a set of energy consumption sample sequences. After processing in the above manner, multiple sets of energy consumption sample sequences can be obtained.

[0080] The third step is to establish a training sample set based on multiple groups of energy consumption sample sequences.

[0081] In this embodiment, the previous energy consumption data segments in the multiple groups of energy consumption sample sequences are used as input data samples, and the subsequent trend data segments are used as label data samples, so that a training sample set can be established.

[0082] The fourth step is to train the pre-built deep learning neural network through the training sample set to obtain a trained energy consumption prediction model.

[0083] It can be understood that by training the pre-built deep learning neural network through the training sample set, and optimizing the network parameters of the deep learning neural network through continuous iteration, a trained energy consumption prediction model can be obtained after the training termination condition is finally reached.

[0084] In this embodiment, the energy consumption prediction model can use the currently input effective energy consumption data to achieve accurate prediction of the energy consumption of the thermal power plant within a future preset period of time, thereby obtaining energy consumption prediction results conveniently, efficiently and accurately.

[0085] In one embodiment, the energy consumption optimization model can be established through the following process:

[0086] The first step is to obtain the historical energy consumption data, equipment operation data and energy distribution data of key equipment in the thermal power plant.

[0087] It is understandable that in order to ensure the effectiveness of subsequent data processing, the timestamp information of three types of data, namely historical energy consumption data, equipment operation data and energy distribution data, must be synchronized during the data acquisition process. In other words, it is necessary to obtain the historical energy consumption data, equipment operation data and energy distribution data of key equipment at different time points during the same historical period.

[0088] In the second step, based on the historical energy consumption data, equipment operation data and energy distribution data corresponding to the same sampling time, the three-dimensional data points corresponding to each sampling time are established.

[0089] In actual applications, historical energy consumption data, equipment operation data and energy allocation data usually contain multiple key parameters. For example, historical energy consumption data may specifically include parameters such as current, voltage, temperature, etc. of key equipment; equipment operation data may specifically include parameters such as equipment operating time and operating power; and energy allocation data may specifically include energy allocation information of each key equipment.

[0090] In order to simplify the data processing process, the various key parameters corresponding to the historical energy consumption data, equipment operation data and energy distribution data can be integrated. For example, the current, voltage and temperature in the historical energy consumption data can be linearly normalized and then weighted summed to obtain the energy consumption standard value. The energy distribution data can be converted into proportional data.

[0091] In the process of establishing three-dimensional data points, historical energy consumption data can be used as X-axis data, equipment operation data as Y-axis data, and energy distribution data as Z-axis data to establish three-dimensional data points corresponding to each sampling moment.

[0092] In some embodiments, after obtaining multiple three-dimensional data points, error points that obviously deviate from a preset range can be eliminated, and new three-dimensional update points can be determined based on the three-dimensional data points before and after the error point to perform data completion operations through the three-dimensional update points.

[0093] In the third step, at least part of the three-dimensional data points are fitted to obtain an energy consumption optimization model.

[0094] In this embodiment, all three-dimensional data points may be fitted, or some three-dimensional data points in the middle segment with higher data accuracy may be fitted, and finally an energy consumption optimization model may be obtained.

[0095] In practical applications, we can first determine the highest point and the lowest point in the three-dimensional data points, set the deviation distance, and use all the data points in the three-dimensional data points whose straight-line distance to the highest point or the lowest point is within the deviation distance as the points to be fitted. In this way, we can obtain the energy consumption optimization model based on the fitting results of the points to be fitted.

[0096] In one embodiment, the monitoring terminal has a first data display area, a second data display area, and a third data display area.

[0097] Among them, the first data display area is used to display energy consumption abnormality warning information in the form of a time series diagram, the second data display area is used to display a plant map marked with valid energy consumption data and energy consumption forecast results, and the third data display area is used to display energy consumption optimization plans in the form of an optimization list.

[0098] This embodiment uses a graphical design to intuitively display the energy consumption distribution of the thermal power plant, which is convenient for supervisors to quickly understand the energy consumption status of the thermal power plant. Furthermore, the abnormal energy consumption warning information can be displayed in the form of a time sequence diagram, and the time point and processing flow of the warning trigger can be displayed in the form of a time sequence diagram to ensure the timeliness and accuracy of the abnormal energy consumption warning information.

[0099] In some embodiments, energy consumption comparison and analysis results can also be generated based on historical energy consumption data, effective energy consumption data and energy consumption forecast results, and displayed in the second data display area. Among them, the energy consumption forecast results include the energy consumption trend of the thermal power plant in the future preset period, and the energy consumption optimization plan includes energy consumption allocation strategy, equipment operation strategy and other energy consumption planning suggestions in the future preset period. Specifically, the energy consumption allocation strategy, equipment operation strategy and other energy consumption planning suggestions can be used as table content to establish an energy consumption optimization suggestion table, and the energy consumption optimization plan can be intuitively displayed, so as to provide scientific and reasonable energy consumption optimization suggestions for supervisors and improve the energy efficiency management level of thermal power plants.

[0100] In one embodiment, the big data server determines a dynamic warning threshold based on the energy consumption prediction result, specifically including:

[0101] First, based on the energy consumption forecast results, determine the comprehensive energy consumption limit of the thermal power plant in the future preset period of time.

[0102] In this step, the comprehensive energy consumption limit value may be an upper limit value of the comprehensive energy consumption or a lower limit value of the comprehensive energy consumption.

[0103] Then, based on the comprehensive energy consumption limit value and the preset mapping relationship, a dynamic warning threshold is determined.

[0104] Among them, the preset mapping relationship is used to characterize the corresponding relationship between the dynamic warning threshold and the comprehensive energy consumption limit value.

[0105] This embodiment can specifically determine the dynamic warning threshold according to the energy consumption prediction result, so that the warning threshold can be dynamically adjusted according to the actual energy consumption situation, thereby improving the accuracy and flexibility of the warning link.

[0106] In some embodiments, the early warning link can adopt multiple early warning methods, such as sound and light alarms, text message notifications, and email reminders, etc., which can realize the linkage early warning function combining on-site early warning with remote early warning, ensuring the timeliness and accuracy of the energy consumption abnormality early warning information push process.

[0107] In one embodiment, the preset mapping relationship can be established through the following process:

[0108] The first step is to obtain the historical energy consumption data of thermal power plants.

[0109] The second step is to divide the historical energy consumption data into multiple historical energy consumption sections according to the preset time period.

[0110] In this step, a preset time period may be set, such as 24 hours, so that the entire historical energy consumption data is divided into a plurality of historical energy consumption segments of equal length according to the preset time period.

[0111] The third step is to determine the comprehensive energy consumption limit value corresponding to each historical energy consumption section, and determine the warning threshold calibration value corresponding to each historical energy consumption section.

[0112] For each historical energy consumption section, the corresponding comprehensive energy consumption limit value, such as the upper limit value of comprehensive energy consumption, can be determined, and according to the energy consumption of the section, the warning threshold calibration value corresponding to the section can be manually calibrated.

[0113] The fourth step is to construct multiple discrete data points based on the comprehensive energy consumption limit value and warning threshold calibration value corresponding to each historical energy consumption section.

[0114] Specifically, the comprehensive energy consumption limit value can be used as the horizontal coordinate data, and the warning threshold calibration value can be used as the vertical coordinate data to establish a two-dimensional coordinate axis, and each discrete data point can be marked in the two-dimensional coordinate axis.

[0115] In practical applications, there are error points among multiple discrete data points that obviously deviate from the normal data range. In order to ensure the accuracy of the subsequent fitting process, the error points can be eliminated, and the update points can be determined based on the characteristics of the data points before and after the error points. The error points are replaced by the update points to achieve preprocessing of the discrete data points.

[0116] The fifth step is to fit the discrete data points and establish a preset mapping relationship.

[0117] In this embodiment, a preset mapping relationship can be established through a fitting operation. Subsequently, when the comprehensive energy consumption limit value is known, the dynamic warning threshold can be directly obtained according to the preset mapping relationship. Compared with the traditional warning link that uses a fixed warning threshold, this embodiment can achieve a better warning effect through a dynamic warning threshold. By integrating energy consumption warning and intelligent decision support functions, a complete energy consumption closed-loop management system can be formed to achieve comprehensive, real-time and accurate management of the energy consumption of thermal power plants.

[0118] Based on the same general inventive concept, the present invention also protects an online monitoring and early warning method for energy consumption of a thermal power plant based on big data. The online monitoring and early warning method for energy consumption of a thermal power plant based on big data provided by the present invention is described below. The online monitoring and early warning method for energy consumption of a thermal power plant based on big data described below and the online monitoring and early warning system for energy consumption of a thermal power plant based on big data described above can be referenced to each other.

[0119] Figure 2 The flowchart of the method for online monitoring and early warning of energy consumption of a thermal power plant based on big data provided by an embodiment of the present invention is exemplarily shown.

[0120] like Figure 2 As shown, the thermal power plant energy consumption online monitoring and early warning method based on big data provided by the embodiment of the present invention, the execution subject can be a computer or server with data receiving and sending and data processing functions, such as the big data server in the above-mentioned thermal power plant energy consumption online monitoring and early warning system, the method mainly includes the following steps:

[0121] Step 210: receiving effective energy consumption data obtained by preprocessing and integrating the original energy consumption data of various key equipment in the thermal power plant.

[0122] Step 220: input the effective energy consumption data into the pre-built energy consumption prediction model and energy consumption optimization model respectively, and obtain the energy consumption prediction result output by the energy consumption prediction model and the energy consumption optimization solution output by the energy consumption optimization model.

[0123] Step 230: Determine a dynamic warning threshold based on the energy consumption prediction result, and generate energy consumption abnormality warning information when the effective energy consumption data deviates from the dynamic warning threshold, so that the monitoring terminal can display the energy consumption abnormality warning information, effective energy consumption data, energy consumption prediction results and energy consumption optimization plan.

[0124] In one embodiment, the energy consumption prediction model can be established through the following process:

[0125] Obtain historical energy consumption data of key equipment in thermal power plants;

[0126] According to the sampling timestamp information of the historical energy consumption data, the historical energy consumption data is split into multiple groups of energy consumption sample sequences, wherein each group of energy consumption sample sequences includes a previous energy consumption data segment and a subsequent trend data segment;

[0127] Based on multiple groups of energy consumption sample sequences, a training sample set is established;

[0128] The pre-built deep learning neural network is trained through the training sample set to obtain a trained energy consumption prediction model.

[0129] In one embodiment, the energy consumption optimization model can be established through the following process:

[0130] Obtain historical energy consumption data, equipment operation data, and energy distribution data of key equipment in thermal power plants;

[0131] According to the historical energy consumption data, equipment operation data and energy distribution data corresponding to the same sampling time, the three-dimensional data points corresponding to each sampling time are established;

[0132] At least part of the three-dimensional data points are fitted to obtain an energy consumption optimization model.

[0133] In one embodiment, determining a dynamic warning threshold based on the energy consumption prediction result specifically includes:

[0134] Based on the energy consumption forecast results, determine the comprehensive energy consumption limit of the thermal power plant in the future preset period;

[0135] Determine the dynamic warning threshold based on the comprehensive energy consumption limit value and the preset mapping relationship;

[0136] Among them, the preset mapping relationship is used to characterize the corresponding relationship between the dynamic warning threshold and the comprehensive energy consumption limit value.

[0137] In one embodiment, the preset mapping relationship can be established through the following process:

[0138] Obtain historical energy consumption data of thermal power plants;

[0139] Divide the historical energy consumption data into multiple historical energy consumption sections according to the preset time period;

[0140] Determine the comprehensive energy consumption limit value corresponding to each historical energy consumption section respectively, and determine the warning threshold calibration value corresponding to each historical energy consumption section;

[0141] According to the comprehensive energy consumption limit value and warning threshold calibration value corresponding to each historical energy consumption section, multiple discrete data points are constructed;

[0142] Fit discrete data points and establish a preset mapping relationship.

[0143] The method for online monitoring and early warning of thermal power plant energy consumption based on big data provided by the embodiment of the present invention can input the effective energy consumption data into the pre-built energy consumption prediction model and energy consumption optimization model respectively after receiving the effective energy consumption data, obtain the energy consumption prediction result output by the energy consumption prediction model and the energy consumption optimization plan output by the energy consumption optimization model, determine the dynamic early warning threshold based on the energy consumption prediction result, and generate energy consumption abnormality early warning information when the effective energy consumption data deviates from the dynamic early warning threshold. Real-time and accurate monitoring of thermal power plant energy consumption is achieved, and effective energy consumption optimization plans can be provided for supervisors, thereby providing data support for supervisors to make energy consumption optimization decisions.

[0144] Figure 3 It is a structural diagram of a big data server in an embodiment of the present invention.

[0145] like Figure 3As shown, the big data service end may include: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the online monitoring and early warning method for energy consumption of a thermal power plant based on big data provided in the above-mentioned embodiments.

[0146] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0147] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the online monitoring and early warning method for energy consumption of thermal power plants based on big data provided in the above-mentioned embodiments.

[0148] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the online monitoring and early warning method for energy consumption of a thermal power plant based on big data provided in the above-mentioned embodiments.

[0149] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0150] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution 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 ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0151] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An online monitoring and early warning system for energy consumption in thermal power plants based on big data, characterized in that: include: The front-end sampling unit is used to obtain the original energy consumption data of various key equipment in the thermal power plant, and obtain effective energy consumption data after preprocessing and integrating the original energy consumption data; A big data server connected to the front-end sampling unit is used to input the effective energy consumption data into a pre-built energy consumption prediction model and an energy consumption optimization model after receiving the effective energy consumption data, and obtain the energy consumption prediction result output by the energy consumption prediction model and the energy consumption optimization solution output by the energy consumption optimization model; Determine a dynamic warning threshold based on the energy consumption prediction result, and generate energy consumption abnormality warning information when the effective energy consumption data deviates from the dynamic warning threshold; The monitoring terminal is connected to the big data server and is used to receive and display the abnormal energy consumption warning information, the effective energy consumption data, the energy consumption prediction result and the energy consumption optimization plan.

2. According to the big data-based online monitoring and early warning system for thermal power plant energy consumption in claim 1, it is characterized in that: The front-end sampling unit includes a sensor network composed of a plurality of energy consumption sensors and a data processing device, wherein the plurality of energy consumption sensors are installed on different key equipment in the thermal power plant, and the sensor network is connected to the data processing device; The sensor network is used to obtain original energy consumption data of various key equipment in the thermal power plant and transmit the original energy consumption data to the data processing device; The data processing device is used to pre-process and integrate the original energy consumption data to obtain effective energy consumption data; Wherein, the preprocessing includes data cleaning and standardization.

3. The online monitoring and early warning system for energy consumption of thermal power plants based on big data according to claim 1 is characterized in that: The energy consumption prediction model is established through the following process: Obtain historical energy consumption data of key equipment in thermal power plants; According to the sampling timestamp information of the historical energy consumption data, the historical energy consumption data is split into multiple groups of energy consumption sample sequences, wherein each group of the energy consumption sample sequences includes an early energy consumption data segment and a subsequent trend data segment; Based on the multiple groups of energy consumption sample sequences, establishing a training sample set; The pre-built deep learning neural network is trained using the training sample set to obtain a trained energy consumption prediction model.

4. The online monitoring and early warning system for energy consumption of thermal power plants based on big data according to claim 1 is characterized in that: The energy consumption optimization model is established through the following process: Obtain historical energy consumption data, equipment operation data, and energy distribution data of key equipment in thermal power plants; According to the historical energy consumption data, the equipment operation data and the energy distribution data corresponding to the same sampling time, a three-dimensional data point corresponding to each sampling time is established; At least part of the three-dimensional data points are fitted to obtain an energy consumption optimization model.

5. The online monitoring and early warning system for energy consumption of thermal power plants based on big data according to claim 1 is characterized in that: The monitoring terminal has a first data display area, a second data display area and a third data display area; Among them, the first data display area is used to display the energy consumption abnormality warning information in the form of a time series diagram, the second data display area is used to display a plant map marked with the effective energy consumption data and the energy consumption forecast results, and the third data display area is used to display the energy consumption optimization plan in the form of an optimization list.

6. The online monitoring and early warning system for energy consumption of thermal power plants based on big data according to claim 1 is characterized in that: The big data server determines a dynamic warning threshold based on the energy consumption prediction result, including: Based on the energy consumption forecast result, determining the comprehensive energy consumption limit value of the thermal power plant in a future preset period of time; Determining the dynamic warning threshold based on the comprehensive energy consumption limit value and the preset mapping relationship; The preset mapping relationship is used to characterize the corresponding relationship between the dynamic warning threshold and the comprehensive energy consumption limit value.

7. The online monitoring and early warning system for energy consumption of thermal power plants based on big data according to claim 6 is characterized in that: The preset mapping relationship is established through the following process: Obtain historical energy consumption data of thermal power plants; Dividing the historical energy consumption data into a plurality of historical energy consumption sections according to a preset time period; Respectively determine the comprehensive energy consumption limit value corresponding to each of the historical energy consumption sections, and determine the warning threshold calibration value corresponding to each of the historical energy consumption sections; Constructing a plurality of discrete data points according to the comprehensive energy consumption limit value corresponding to each of the historical energy consumption sections and the warning threshold calibration value; The discrete data points are fitted to establish the preset mapping relationship.

8. A method for online monitoring and early warning of energy consumption in thermal power plants based on big data, characterized in that: include: Receive effective energy consumption data obtained by preprocessing and integrating the original energy consumption data of various key equipment in the thermal power plant; Inputting the effective energy consumption data into a pre-built energy consumption prediction model and an energy consumption optimization model respectively, obtaining an energy consumption prediction result output by the energy consumption prediction model and an energy consumption optimization solution output by the energy consumption optimization model; A dynamic warning threshold is determined based on the energy consumption prediction result, and when the effective energy consumption data deviates from the dynamic warning threshold, energy consumption abnormality warning information is generated, so that the monitoring terminal displays the energy consumption abnormality warning information, the effective energy consumption data, the energy consumption prediction result and the energy consumption optimization plan.

9. The method for online monitoring and early warning of energy consumption in thermal power plants based on big data according to claim 8 is characterized in that: The energy consumption prediction model is established through the following process: Obtain historical energy consumption data of key equipment in thermal power plants; According to the sampling timestamp information of the historical energy consumption data, the historical energy consumption data is split into multiple groups of energy consumption sample sequences, wherein each group of the energy consumption sample sequences includes an early energy consumption data segment and a subsequent trend data segment; Based on the multiple groups of energy consumption sample sequences, establishing a training sample set; The pre-built deep learning neural network is trained using the training sample set to obtain a trained energy consumption prediction model.

10. The method for online monitoring and early warning of energy consumption in thermal power plants based on big data according to claim 8 is characterized in that: The energy consumption optimization model is established through the following process: Obtain historical energy consumption data, equipment operation data, and energy distribution data of key equipment in thermal power plants; According to the historical energy consumption data, the equipment operation data and the energy distribution data corresponding to the same sampling time, a three-dimensional data point corresponding to each sampling time is established; At least part of the three-dimensional data points are fitted to obtain an energy consumption optimization model.

Citation Information

Cited By

  • Energy consumption monitoring method and system based on industrial Internet of Things

    CN119987306A

  • An energy consumption monitoring method and system based on the Industrial Internet of Things

    CN119987306B

  • Energy consumption monitoring method and system based on machine learning

    CN120764723A

  • Production energy consumption analysis system based on big data

    CN121303578A

  • A production energy consumption analysis system based on big data

    CN121303578B