Power plant accident monitoring and early warning method and platform based on IoT data monitoring

Abstract

The present invention relates to a power plant accident monitoring and early warning method and platform for Internet of Things data monitoring, and relates to the field of Internet of Things monitoring, including: predicting the smoke components of incomplete combustion according to water temperature uniformity parameters, obtaining predicted smoke components, and obtaining a first incomplete combustion level for preliminary early warning when the predicted smoke components do not meet preset requirements; verifying the predicted smoke components according to the smoke component sequence, and continuing to issue early warnings according to the first incomplete combustion level when the verification coefficient is less than the verification coefficient threshold, and correcting the first incomplete combustion level to obtain a second incomplete combustion level for early warning when the verification coefficient is greater than or equal to the verification coefficient threshold. The present invention can solve the technical problem that traditional methods are difficult to monitor the dynamic changes of boiler combustion status in real time and comprehensively, resulting in insufficient timeliness and accuracy of boiler combustion accident monitoring and early warning; it can timely discover potential incomplete combustion phenomena and ensure efficient and safe operation of the boiler.

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things monitoring, and in particular to a power plant accident monitoring and early warning method and platform for Internet of Things data monitoring. Background Art

[0002] As a key equipment for energy conversion and heat supply, the operating status of power plant boilers directly affects the power generation efficiency, economy and environmental protection of the entire power plant. During the operation of the boiler, incomplete combustion failure is one of the common problems of power plant boilers, which manifests as incomplete combustion of fuel, reduced thermal efficiency, abnormal flue gas composition (such as increased carbon monoxide concentration and reduced carbon dioxide concentration) and uneven heat transfer distribution inside the boiler. This failure not only leads to fuel waste and excessive emissions, but may also cause equipment damage and even major safety accidents.

[0003] At present, the traditional power plant boiler combustion fault monitoring method is difficult to monitor the dynamic changes of the boiler combustion status in real time and comprehensively, resulting in insufficient timeliness and accuracy of boiler incomplete combustion accident monitoring and early warning, and unable to meet the efficient operation requirements of boiler equipment. Summary of the invention

[0004] The present invention aims to solve the technical problem that traditional power plant boiler combustion fault monitoring methods are difficult to monitor the dynamic changes of boiler combustion status in real time and comprehensively, resulting in insufficient timeliness and accuracy of boiler incomplete combustion accident monitoring and early warning. A power plant accident monitoring and early warning method and platform based on Internet of Things data monitoring are provided to solve the problem.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] In a first aspect, the present invention provides a power plant accident monitoring and early warning method based on Internet of Things data monitoring, comprising: detecting the water temperature at multiple positions of the boiler in the power plant through a water temperature sensor array arranged based on the Internet of Things, obtaining a water temperature distribution sequence, performing water temperature uniformity analysis and water temperature variability analysis according to the water temperature distribution sequence, and obtaining a water temperature uniformity parameter and a water temperature variability parameter; predicting the smoke components of incomplete combustion according to the water temperature uniformity parameter, obtaining predicted smoke components, and when the predicted smoke components do not meet the preset smoke component requirements, deciding to obtain a first incomplete combustion level and performing a preliminary early warning; According to the water temperature variability parameter, a smoke detection frequency for smoke sensing detection is configured, and according to the smoke detection frequency, smoke composition monitoring is performed through a smoke composition sensor deployed based on the Internet of Things to obtain a smoke composition sequence; according to the smoke composition sequence, the predicted smoke composition is verified and analyzed to obtain a verification coefficient, and when the verification coefficient is less than a verification coefficient threshold, an early warning is continued according to the first incomplete combustion level, and when the verification coefficient is greater than or equal to the verification coefficient threshold, the first incomplete combustion level is corrected to obtain a second incomplete combustion level, and an early warning is issued.

[0007] In the second aspect, the present invention provides an accident monitoring and early warning platform for power plants monitored by Internet of Things data, including: a boiler water temperature characteristic analysis module, which is used to detect the water temperature at multiple locations of the boiler in the power plant through a water temperature sensor array deployed based on the Internet of Things, and obtain a water temperature distribution sequence. According to the water temperature distribution sequence, water temperature uniformity analysis and water temperature variability analysis are performed to obtain water temperature uniformity parameters and water temperature variability parameters; a first incomplete combustion level acquisition module is used to predict the smoke gas components of incomplete combustion according to the water temperature uniformity parameters, and obtain predicted smoke gas components. When the predicted smoke gas components do not meet the preset smoke gas component requirements, a decision is made to obtain the first incomplete combustion level and perform preliminary Early warning; a smoke composition monitoring module, used to configure the smoke detection frequency for smoke sensor detection according to the water temperature variability parameter, and monitor the smoke composition according to the smoke detection frequency through the smoke composition sensor deployed based on the Internet of Things to obtain a smoke composition sequence; an incomplete combustion early warning module, used to verify and analyze the predicted smoke composition according to the smoke composition sequence to obtain a verification coefficient, and when the verification coefficient is less than the verification coefficient threshold, continue to issue an early warning according to the first incomplete combustion level, and when the verification coefficient is greater than or equal to the verification coefficient threshold, correct the first incomplete combustion level to obtain a second incomplete combustion level and issue an early warning.

[0008] In a third aspect, the present invention further provides an electronic device, comprising:

[0009] At least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor so that the at least one processor can perform the steps of any one of the methods described in the first aspect above.

[0010] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed, the steps of the method described in any one of the first aspects are implemented.

[0011] The beneficial effects of the present invention are as follows: the water temperature of multiple positions of the boiler in the power plant is detected by a water temperature sensor array arranged based on the Internet of Things, and a water temperature distribution sequence is obtained. According to the water temperature distribution sequence, water temperature uniformity analysis and water temperature variability analysis are performed to obtain water temperature uniformity parameters and water temperature variability parameters; then, according to the water temperature uniformity parameters, the smoke gas components of incomplete combustion are predicted to obtain predicted smoke gas components, and when the predicted smoke gas components do not meet the preset smoke gas component requirements, a decision is made to obtain a first incomplete combustion level and a preliminary warning is issued; further, according to the water temperature variability parameters, a smoke gas detection frequency for smoke gas sensing detection is configured, and according to the smoke gas detection frequency, smoke gas component monitoring is performed through a smoke gas component sensor arranged based on the Internet of Things to obtain a smoke gas component sequence; then, according to the smoke gas component sequence, the predicted smoke gas components are verified and analyzed to obtain a verification coefficient, and when the verification coefficient is less than the verification coefficient threshold, the warning is continued according to the first incomplete combustion level, and when the verification coefficient is greater than or equal to the verification coefficient threshold, the first incomplete combustion level is corrected to obtain a second incomplete combustion level, and a warning is issued according to the second incomplete combustion level. By combining the Internet of Things technology for data collection and monitoring, the dynamic changes in the boiler's combustion state can be fully captured, potential incomplete combustion phenomena can be discovered in a timely manner, and early monitoring and early warning can be achieved, thereby improving the timeliness, accuracy and reliability of boiler combustion fault warnings and ensuring the efficient and safe operation of the boiler. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A schematic diagram of the process of the power plant accident monitoring and early warning method based on Internet of Things data monitoring provided by the present invention;

[0013] Figure 2 A schematic diagram of the structure of a power plant accident monitoring and early warning platform for Internet of Things data monitoring provided by the present invention;

[0014] Figure 3 A schematic diagram of the structure of an electronic device provided by the present invention;

[0015] Figure 4A schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0016] In the accompanying drawings, the components represented by the reference numerals are described as follows:

[0017] Boiler water temperature characteristic analysis module 01, first incomplete combustion level acquisition module 02, flue gas composition monitoring module 03, incomplete combustion warning module 04, electronic device 500, memory 510, processor 520, first computer program 511, computer readable storage medium 600, second computer program 611. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0019] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0020] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0021] Embodiment 1, as Figure 1 As shown, the embodiment of the present invention provides a power plant accident monitoring and early warning method based on Internet of Things data monitoring, which specifically includes the following steps:

[0022] S100: Detect the water temperature of multiple positions of the boiler in the power plant through a water temperature sensor array deployed based on the Internet of Things, obtain a water temperature distribution sequence, perform water temperature uniformity analysis and water temperature variability analysis based on the water temperature distribution sequence, and obtain water temperature uniformity parameters and water temperature variability parameters.

[0023] Furthermore, step S100 of the present invention further includes:

[0024] S110: Using a water temperature sensor array formed by water temperature sensors deployed at multiple locations of the boiler based on the Internet of Things, the water temperature information of the multiple locations is detected to obtain water temperature distribution; S120: The water temperature distribution at multiple times is collected to obtain a water temperature distribution sequence.

[0025] Specifically, water temperature sensors are arranged at multiple key positions (such as different heights, cross sections or furnace areas) inside the boiler to form a water temperature sensor array, wherein each sensor is responsible for collecting water temperature data at a specific position, and the sensor array transmits the water temperature data to the central data processing platform in real time through the Internet of Things technology. Then, at a predetermined monitoring time node (such as monitoring once every 3 minutes), the water temperature information of the multiple positions is detected by the water temperature sensor array, and the multiple water temperature information is distributed according to the position mapping to obtain the water temperature distribution, wherein the water temperature distribution includes the water temperature data of multiple positions in the boiler, which can fully reflect the dynamic changes of the boiler heat distribution. Then the water temperature distribution under multiple continuous monitoring time nodes is obtained, and arranged in chronological order to generate a water temperature distribution sequence. By obtaining the water temperature distribution sequence based on the Internet of Things monitoring, the water temperature state in the boiler can be obtained in real time, which provides a basis for the subsequent analysis of the boiler combustion state.

[0026] S130: performing water temperature uniformity analysis on multiple water temperature distributions in the water temperature distribution sequence to obtain water temperature uniformity parameters at multiple moments.

[0027] Furthermore, step S130 of the present invention further includes:

[0028] S131: Randomly extract multiple groups of first water temperature information in the first water temperature distribution in the water temperature distribution sequence, each group of first water temperature information includes two first water temperature information; S132: Calculate the water temperature deviation percentage of two first water temperature information in the multiple groups of first water temperature information, obtain multiple water temperature deviation percentages, calculate the mean, and obtain the water temperature uniformity parameter at the first moment; S133: Continue to perform water temperature uniformity analysis on other multiple water temperature distributions to obtain water temperature uniformity parameters at multiple moments.

[0029] Specifically, when the boiler burns incompletely, it usually leads to a decrease in the heat transfer efficiency inside the boiler, which in turn manifests as uneven water temperature distribution. By monitoring the water temperature at multiple locations in the boiler and analyzing its distribution, the occurrence of incomplete combustion can be effectively identified. First, the water temperature distribution at any monitoring time node in the water temperature distribution sequence is randomly selected as the first water temperature distribution; then, a number of groups of first water temperature information are randomly selected from the first water temperature distribution, wherein each group of first water temperature information includes the first water temperature information of any two locations in the first water temperature distribution. For example, any two water temperature information from the first water temperature distribution are selected as a group of water temperature information for enumeration to obtain all possible water temperature information combinations; if the total number of water temperature information combinations is large, 50% of all water temperature information combinations can also be randomly selected as the extraction result.

[0030] Next, the water temperature deviation value and the water temperature mean of two first water temperature information in the multiple groups of first water temperature information are calculated respectively, the ratio of the absolute value of the water temperature deviation value to the water temperature mean is calculated, and it is expressed by percentage data to obtain multiple water temperature deviation percentages. Then, the multiple water temperature deviation percentages are averaged, and the average calculation result is used as the water temperature uniformity parameter at the first moment. Using the same method, continue to perform water temperature uniformity analysis on multiple other water temperature distributions to obtain water temperature uniformity parameters at multiple moments. Among them, the water temperature uniformity parameter characterizes the deviation between the water temperatures at different positions in the boiler at the same moment. The larger the uniformity parameter, the more uneven the water temperature distribution inside the boiler, and the more incomplete the combustion.

[0031] S140: Calculate the mean of the water temperature uniformity parameter at the multiple moments to obtain the water temperature uniformity parameter; S150: Calculate the variance of the water temperature uniformity parameter at the multiple moments to obtain the water temperature variability parameter.

[0032] Specifically, the water temperature uniformity parameters at the multiple moments are averaged, and the calculation result is used as the water temperature uniformity parameter, where the water temperature uniformity parameter reflects the average water temperature uniformity of the boiler during the entire monitoring period. The larger the value, the more uneven the overall heat distribution of the boiler and the more incomplete the combustion. On the other hand, the variance of the water temperature uniformity parameters at the multiple moments is calculated, and the variance calculation result is used as the water temperature variability parameter, where the water temperature variability parameter indicates the degree of fluctuation of the water temperature uniformity at multiple moments. The larger the water temperature variability parameter, the more violent the fluctuation of the boiler combustion state and the more unstable the combustion process. By calculating and obtaining the water temperature uniformity parameter and the water temperature variability parameter, the fluctuation state of the boiler combustion can be fully monitored, providing data support for the subsequent analysis of incomplete boiler combustion.

[0033] S200: Predict the flue gas composition with incomplete combustion based on the water temperature uniformity parameter to obtain the predicted flue gas composition. When the predicted flue gas composition does not meet the preset flue gas composition requirements, decide to obtain the first incomplete combustion level and issue a preliminary warning.

[0034] Further, step S200 of the present invention further includes:

[0035] S210: Collect a set of sample water temperature uniformity parameters and the flue gas composition under different sample water temperature uniformity parameters according to the Internet of Things monitoring data within the historical time to obtain a set of sample flue gas compositions, where the flue gas composition includes the ratio of the carbon dioxide concentration to the carbon monoxide concentration in the flue gas; S220: Use the set of sample water temperature uniformity parameters and the set of sample flue gas compositions as supervised training data to perform supervised training on the flue gas composition predictor until convergence; S230: Input the water temperature uniformity parameter into the flue gas composition predictor and predict the output to obtain the predicted flue gas composition; S240: Determine whether the predicted flue gas composition is greater than the preset flue gas composition threshold. If so, it meets the preset flue gas composition requirements; if not, it does not meet the preset flue gas composition requirements, where the preset flue gas composition threshold includes a preset ratio threshold of the carbon dioxide concentration to the carbon monoxide concentration in the flue gas.

[0036] Specifically, obtain the Internet of Things monitoring data of the boiler within the historical time (such as the past month), collect the sample water temperature uniformity parameters according to the Internet of Things monitoring data, and obtain a set of sample water temperature uniformity parameters; further collect the flue gas composition under different sample water temperature uniformity parameters, where the flue gas composition includes the ratio of the carbon dioxide concentration to the carbon monoxide concentration in the flue gas. When the combustion is incomplete, the carbon dioxide concentration in the flue gas will decrease and the carbon monoxide concentration will increase. Therefore, the incomplete combustion state can be identified through the flue gas composition. The smaller the flue gas composition, the more incomplete the combustion; obtain a set of sample flue gas compositions, where the sample water temperature uniformity parameters and the sample flue gas compositions correspond one by one.

[0037] BP neural network is a commonly used multi-layer feedforward neural network, which optimizes the error through the back propagation algorithm to realize a prediction model with strong nonlinear mapping ability. Next, a smoke component predictor is constructed based on the BP neural network. The smoke component predictor is a neural network model that can be iteratively optimized in machine learning, including an input layer, multiple hidden layers and an output layer, wherein the input data of the input layer is the water temperature uniformity parameter, and the output data of the output layer is the smoke composition. Then, the sample water temperature uniformity parameter set and the sample smoke component set are used as supervised training data, the sample water temperature uniformity parameter is used as input, and the sample smoke component is used as output to supervise the smoke component predictor. First, the water temperature uniformity parameter of the training sample is sequentially input into the input layer of the neural network, and each hidden layer node calculates the output value according to the input data and the corresponding weight and bias, and the hidden layer output is passed to the output layer to calculate the predicted value of the smoke component; then, the mean square error (MSE) is used as the loss function to calculate the error between the predicted value and the true value; further, the chain rule is used to calculate the gradient of the loss function to the network weight and bias, and back propagates from the output layer to the hidden layer, and then to the input layer layer by layer to update the weight and bias of each layer; the sample data is used to continuously perform iterative training until the loss function converges to obtain a trained smoke component predictor. By constructing a smoke component predictor based on the BP neural network, efficient and accurate prediction of smoke components can be achieved. The water temperature uniformity parameter is further input into the smoke component predictor for prediction, and the predicted smoke component is output.

[0038] Get the preset flue gas composition threshold, which represents the reasonable ratio of carbon dioxide concentration to carbon monoxide concentration under normal combustion conditions, and can be set according to the actual standard combustion conditions. For example, 750; then, judge the predicted flue gas composition according to the preset flue gas composition threshold. If the predicted flue gas composition is greater than the flue gas composition threshold, it means that the carbon dioxide concentration in the boiler is high, the carbon monoxide concentration is low, the combustion is sufficient, and the thermal efficiency is high, then the preset flue gas composition requirements are met. If the predicted flue gas composition is less than or equal to the preset flue gas composition threshold, it means that the carbon dioxide concentration is reduced, the carbon monoxide concentration is increased, and there may be incomplete combustion, then the preset flue gas composition requirements are not met.

[0039] When the predicted smoke composition does not meet the preset smoke composition requirement, a first incomplete combustion level is obtained according to the predicted smoke composition decision, and a preliminary warning is issued according to the first incomplete combustion level.

[0040] S250: When the predicted smoke composition does not meet the preset smoke composition requirement, a decision is made to obtain a first incomplete combustion level and to issue a preliminary warning.

[0041] Further, step S250 of the present invention further includes:

[0042] S251: Obtain multiple smoke component intervals, and mark multiple sample incomplete combustion levels according to the degree of incomplete combustion in each smoke component interval; S252: Construct a mapping relationship between the multiple smoke component intervals and the multiple sample incomplete combustion levels to obtain an early warning classifier; S253: According to the smoke component interval into which the predicted smoke component falls, decision classification is performed to obtain the first incomplete combustion level and make a preliminary early warning.

[0043] Specifically, first, the smoke components are divided into multiple intervals based on historical monitoring data to obtain multiple smoke component intervals; then, the degree of incomplete combustion in each smoke component interval is analyzed, and the incomplete combustion level is set, wherein the greater the degree of incomplete combustion, the higher the corresponding incomplete combustion level, and multiple sample incomplete combustion levels are marked, wherein each smoke component interval corresponds to a sample incomplete combustion level. Based on the decision tree principle, according to the mapping relationship between the smoke component interval and the sample incomplete combustion level, the smoke component interval is used as a child node, the corresponding sample incomplete combustion level is used as the leaf node of the child node, and the multiple smoke component intervals and multiple sample incomplete combustion levels are used as construction data to construct an early warning classifier.

[0044] Then the predicted smoke components are input into the warning classifier for matching, the smoke component interval into which the predicted smoke components fall is obtained, and the corresponding incomplete combustion level is obtained according to the smoke component interval into which it falls and is set as the first incomplete combustion level; finally, a preliminary warning is made according to the first incomplete combustion level. By inputting the predicted smoke components into the decision tree warning classifier, quickly matching the interval and generating the first incomplete combustion level, intelligent and real-time combustion state evaluation and preliminary warning can be achieved.

[0045] S300: According to the water temperature variability parameter, a smoke detection frequency for smoke sensing detection is configured, and according to the smoke detection frequency, smoke composition is monitored by a smoke composition sensor deployed based on the Internet of Things to obtain a smoke composition sequence.

[0046] Furthermore, step S300 of the present invention further includes:

[0047] S310: Obtain the standard flue gas monitoring frequency of the flue gas component sensor for flue gas component sensing monitoring; S320: Obtain the standard water temperature variability parameter under complete combustion; S330: Take the ratio of the water temperature variability parameter and the standard water temperature variability parameter, multiply by the standard flue gas monitoring frequency, to obtain the flue gas detection frequency; S340: According to the flue gas detection frequency, perform flue gas component monitoring through the flue gas component sensor deployed based on the Internet of Things, and obtain a flue gas component sequence, wherein each smoke component includes the ratio of the carbon dioxide concentration to the carbon monoxide concentration in the flue gas.

[0048] Specifically, the standard flue gas monitoring frequency of the flue gas component sensor for flue gas component sensing monitoring is obtained. The standard flue gas monitoring frequency refers to the sampling frequency of the flue gas component sensor when the boiler is completely burned and running stably. It can be set according to actual monitoring needs. For example, the standard flue gas monitoring frequency is monitored once every 5 seconds. On the other hand, the standard water temperature variability parameter under complete combustion is obtained, where the standard water temperature variability parameter refers to the water temperature variability parameter when the combustion is complete and the boiler is running stably, such as 0.05.

[0049] Then, the ratio of the water temperature variability parameter and the standard water temperature variability parameter is calculated to obtain the parameter ratio, and the parameter ratio is multiplied by the standard flue gas monitoring frequency, and the product of the two is used as the flue gas monitoring frequency. That is, when the boiler operating state fluctuates greatly, the flue gas detection frequency is increased to capture abnormalities in time; when the boiler operation is stable, the detection frequency is reduced to save resources; by dynamically adjusting the flue gas detection frequency according to the real-time water temperature change characteristics, accurate monitoring of the boiler operating state can be achieved, and at the same time, reasonable use of monitoring resources can be made to improve resource utilization.

[0050] Then, the smoke component sensors deployed based on the Internet of Things are used to monitor the smoke components according to the smoke detection frequency, wherein each smoke component includes the ratio of the carbon dioxide concentration to the carbon monoxide concentration in the smoke, and the smoke component monitoring data are arranged in the order of monitoring time to obtain the smoke component sequence.

[0051] S400: According to the flue gas component sequence, the predicted flue gas components are verified and analyzed to obtain a verification coefficient. When the verification coefficient is less than a verification coefficient threshold, an early warning is continued according to the first incomplete combustion level. When the verification coefficient is greater than or equal to the verification coefficient threshold, the first incomplete combustion level is corrected to obtain a second incomplete combustion level and an early warning is issued.

[0052] Furthermore, step S400 of the present invention further includes:

[0053] S410: randomly extract the first smoke component in the smoke component sequence, calculate the deviation percentage from the predicted smoke component, and obtain the first smoke verification coefficient; S420: continue to randomly extract and calculate multiple smoke verification coefficients, and calculate the average to obtain the verification coefficient; S430: obtain the verification coefficient threshold; S440: when the verification coefficient is less than the verification coefficient threshold, continue to issue an early warning according to the first incomplete combustion level; S450: when the verification coefficient is greater than or equal to the verification coefficient threshold, calculate the ratio of the verification coefficient to the verification coefficient threshold, multiply it by the first incomplete combustion level, correct it to obtain the second incomplete combustion level, and issue an early warning.

[0054] Specifically, first, randomly select a smoke component under any monitoring node in the smoke component sequence and set it as the first smoke component; then calculate the absolute value of the component deviation value between the first smoke component and the predicted smoke component, as well as the component mean of the first smoke component and the predicted smoke component, and set the percentage data of the ratio of the absolute value of the component deviation value to the component mean as the first smoke verification coefficient. Then, using the same method, continue to randomly select and calculate to obtain multiple smoke verification coefficients, wherein the number of smoke verification coefficients is the same as the number of smoke components in the smoke component sequence. Further calculate the mean of the multiple smoke verification coefficients, and set the coefficient mean as the verification coefficient, wherein the smaller the verification coefficient, the smaller the deviation between the predicted value and the actual detection value, the higher the accuracy of the prediction model, and the more reasonable the first incomplete combustion level; the larger the verification coefficient, the larger the deviation between the predicted value and the actual detection value, the lower the accuracy of the prediction model, and the more unreasonable the first incomplete combustion level, which needs to be corrected.

[0055] A verification coefficient threshold is obtained, where the verification coefficient threshold is a standard threshold for measuring the reliability of the prediction model, which can be set according to the empirical value of historical data, such as 5%; then the verification coefficient is judged according to the verification coefficient threshold. If the verification coefficient is less than the verification coefficient threshold, it indicates that the prediction value has a high credibility, that is, the first incomplete combustion level is very reasonable, then the warning continues according to the first incomplete combustion level.

[0056] If the verification coefficient is greater than or equal to the verification coefficient threshold, indicating that the first incomplete combustion level is unreasonable, the ratio of the verification coefficient to the verification coefficient threshold is calculated to obtain the coefficient ratio, and the coefficient ratio is multiplied by the first incomplete combustion level, and the product of the two is rounded to obtain the second incomplete combustion level; finally, an early warning is issued according to the second incomplete combustion level. By analyzing the rationality of the first incomplete combustion level and making timely corrections when the deviation is large, the accuracy and reliability of the boiler incomplete combustion early warning can be further improved.

[0057] The power plant accident monitoring and early warning method based on Internet of Things data monitoring provided by the embodiment of the present invention has at least the following technical effects:

[0058] The water temperature at multiple positions of the boiler in the power plant is detected by a water temperature sensor array deployed based on the Internet of Things to obtain a water temperature distribution sequence. According to the water temperature distribution sequence, water temperature uniformity analysis and water temperature variability analysis are performed to obtain water temperature uniformity parameters and water temperature variability parameters; then, according to the water temperature uniformity parameters, the smoke gas components of incomplete combustion are predicted to obtain predicted smoke gas components. When the predicted smoke gas components do not meet the preset smoke gas component requirements, a decision is made to obtain a first incomplete combustion level and a preliminary warning is issued; further, according to the water temperature variability parameters, a smoke gas detection frequency for smoke gas sensing detection is configured. According to the smoke gas detection frequency, smoke gas component monitoring is performed through a smoke gas component sensor deployed based on the Internet of Things to obtain a smoke gas component sequence; then, according to the smoke gas component sequence, the predicted smoke gas components are verified and analyzed to obtain a verification coefficient. When the verification coefficient is less than the verification coefficient threshold, the warning is continued according to the first incomplete combustion level. When the verification coefficient is greater than or equal to the verification coefficient threshold, the first incomplete combustion level is corrected to obtain a second incomplete combustion level, and a warning is issued according to the second incomplete combustion level. By combining the Internet of Things technology for data collection and monitoring, the dynamic changes in the boiler's combustion state can be fully captured, potential incomplete combustion phenomena can be discovered in a timely manner, and early monitoring and early warning can be achieved, thereby improving the timeliness, accuracy and reliability of boiler combustion fault warnings and ensuring the efficient and safe operation of the boiler.

[0059] Embodiment 2, as Figure 2As shown, based on the same inventive concept as the power plant accident monitoring and early warning method monitored by the Internet of Things data provided in the first embodiment, the embodiment of the present invention also provides a power plant accident monitoring and early warning platform monitored by the Internet of Things data, including: a boiler water temperature characteristic analysis module 01, used to detect the water temperature of multiple positions of the boiler in the power plant through a water temperature sensor array deployed based on the Internet of Things, obtain a water temperature distribution sequence, and perform water temperature uniformity analysis and water temperature variability analysis according to the water temperature distribution sequence to obtain water temperature uniformity parameters and water temperature variability parameters; a first incomplete combustion level acquisition module 02, used to predict the smoke components of incomplete combustion according to the water temperature uniformity parameters, and obtain predicted smoke components. When the predicted smoke components do not meet the preset smoke component requirements, The decision is made to obtain the first incomplete combustion level and make a preliminary warning; the smoke composition monitoring module 03 is used to configure the smoke detection frequency for smoke sensor detection according to the water temperature variability parameter, and according to the smoke detection frequency, the smoke composition is monitored by the smoke composition sensor deployed based on the Internet of Things to obtain a smoke composition sequence; the incomplete combustion warning module 04 is used to verify and analyze the predicted smoke composition according to the smoke composition sequence to obtain a verification coefficient, and when the verification coefficient is less than the verification coefficient threshold, continue to give a warning according to the first incomplete combustion level, and when the verification coefficient is greater than or equal to the verification coefficient threshold, correct the first incomplete combustion level to obtain a second incomplete combustion level and give a warning.

[0060] Furthermore, the power plant accident monitoring and early warning platform monitored by the Internet of Things data also includes: detecting the water temperature information of the multiple positions through a water temperature sensor array formed by water temperature sensors deployed at multiple positions of the boiler based on the Internet of Things, and obtaining the water temperature distribution; collecting the water temperature distribution at multiple times to obtain a water temperature distribution sequence; performing water temperature uniformity analysis on the multiple water temperature distributions in the water temperature distribution sequence to obtain water temperature uniformity parameters at multiple times; calculating the mean of the water temperature uniformity parameters at the multiple times to obtain the water temperature uniformity parameters; calculating the variance of the water temperature uniformity parameters at the multiple times to obtain the water temperature variability parameters.

[0061] Furthermore, the power plant accident monitoring and early warning platform monitored by the Internet of Things data also includes: randomly extracting multiple groups of first water temperature information in the first water temperature distribution in the water temperature distribution sequence, each group of first water temperature information includes two first water temperature information; calculating the water temperature deviation percentage of two first water temperature information in the multiple groups of first water temperature information, obtaining multiple water temperature deviation percentages, calculating the mean, and obtaining the water temperature uniformity parameter at the first moment; continuing to perform water temperature uniformity analysis on other multiple water temperature distributions to obtain water temperature uniformity parameters at multiple moments.

[0062] Furthermore, the power plant accident monitoring and early warning platform monitored by the Internet of Things data also includes: based on the Internet of Things monitoring data in the historical time, collecting a set of sample water temperature uniformity parameters, flue gas components under different sample water temperature uniformity parameters, and obtaining a set of sample flue gas components, wherein the flue gas components include the ratio of the carbon dioxide concentration and the carbon monoxide concentration in the flue gas; using the sample water temperature uniformity parameter set and the sample flue gas component set as supervised training data, and performing supervised training of the flue gas component predictor until convergence; inputting the water temperature uniformity parameter into the flue gas component predictor, and predicting and outputting the predicted flue gas components; judging whether the predicted flue gas components are greater than a preset flue gas component threshold, if so, the preset flue gas component requirements are met, if not, the preset flue gas component requirements are not met, wherein the preset flue gas component threshold includes a preset ratio threshold of the carbon dioxide concentration and the carbon monoxide concentration in the flue gas; when the predicted flue gas components do not meet the preset flue gas component requirements, a decision is made to obtain a first incomplete combustion level and a preliminary early warning is issued.

[0063] Furthermore, the power plant accident monitoring and early warning platform monitored by the Internet of Things data also includes: obtaining multiple flue gas component intervals, marking multiple sample incomplete combustion levels according to the degree of incomplete combustion in each flue gas component interval; constructing a mapping relationship between the multiple flue gas component intervals and the multiple sample incomplete combustion levels to obtain an early warning classifier; according to the flue gas component interval into which the predicted flue gas components fall, decision classification is performed to obtain a first incomplete combustion level, and a preliminary early warning is issued.

[0064] Furthermore, the power plant accident monitoring and early warning platform monitored by the Internet of Things data also includes: obtaining a standard flue gas monitoring frequency for flue gas component sensing monitoring by a flue gas component sensor; obtaining a standard water temperature variability parameter under complete combustion; using the ratio of the water temperature variability parameter and the standard water temperature variability parameter, multiplying it by the standard flue gas monitoring frequency, to obtain a flue gas detection frequency; according to the flue gas detection frequency, monitoring the flue gas components through a flue gas component sensor deployed based on the Internet of Things, to obtain a flue gas component sequence, wherein each flue gas component includes a ratio of the carbon dioxide concentration to the carbon monoxide concentration in the flue gas.

[0065] Furthermore, the power plant accident monitoring and early warning platform monitored by the Internet of Things data also includes: randomly extracting a first flue gas component in the flue gas component sequence, calculating the deviation percentage from the predicted flue gas component, and obtaining a first flue gas verification coefficient; continuing to randomly extract and calculate multiple flue gas verification coefficients, and calculating the mean to obtain the verification coefficient; obtaining a verification coefficient threshold; when the verification coefficient is less than the verification coefficient threshold, continuing to issue an early warning according to the first incomplete combustion level; when the verification coefficient is greater than or equal to the verification coefficient threshold, calculating the ratio of the verification coefficient to the verification coefficient threshold, multiplying it by the first incomplete combustion level, correcting it to obtain a second incomplete combustion level, and issuing an early warning.

[0066] For example 3, please refer to Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a first computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the first computer program 511, the following steps are implemented: by using a water temperature sensor array arranged based on the Internet of Things, the water temperature at multiple locations of the boiler in the power plant is detected to obtain a water temperature distribution sequence; based on the water temperature distribution sequence, water temperature uniformity analysis and water temperature variability analysis are performed to obtain water temperature uniformity parameters and water temperature variability parameters; based on the water temperature uniformity parameters, smoke components of incomplete combustion are predicted to obtain predicted smoke components; when the predicted smoke components are not satisfactory, the predicted smoke components are analyzed; When the preset smoke composition requirement is met, a decision is made to obtain a first incomplete combustion level and a preliminary warning is issued; according to the water temperature variability parameter, a smoke detection frequency for smoke sensor detection is configured, and according to the smoke detection frequency, smoke composition monitoring is performed through a smoke composition sensor deployed based on the Internet of Things to obtain a smoke composition sequence; according to the smoke composition sequence, the predicted smoke composition is verified and analyzed to obtain a verification coefficient, and when the verification coefficient is less than a verification coefficient threshold, a warning is continued according to the first incomplete combustion level, and when the verification coefficient is greater than or equal to the verification coefficient threshold, the first incomplete combustion level is corrected to obtain a second incomplete combustion level, and a warning is issued.

[0067] Example 4, please refer to Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4As shown, this embodiment provides a computer-readable storage medium 600, on which a second computer program 611 is stored. When the second computer program 611 is executed by a processor, the following steps are implemented: by using a water temperature sensor array deployed based on the Internet of Things, the water temperature at multiple locations of the boiler in the power plant is detected to obtain a water temperature distribution sequence, and according to the water temperature distribution sequence, water temperature uniformity analysis and water temperature variability analysis are performed to obtain water temperature uniformity parameters and water temperature variability parameters; according to the water temperature uniformity parameters, the smoke composition of incomplete combustion is predicted to obtain the predicted smoke composition, and when the predicted smoke composition does not meet the preset smoke composition requirements, a decision is made to obtain the first a preliminary warning is issued according to an incomplete combustion level; a smoke detection frequency for smoke sensor detection is configured according to the water temperature variability parameter, and smoke component monitoring is performed according to the smoke detection frequency through a smoke component sensor deployed based on the Internet of Things to obtain a smoke component sequence; according to the smoke component sequence, the predicted smoke component is verified and analyzed to obtain a verification coefficient, and when the verification coefficient is less than a verification coefficient threshold, the warning is continued according to the first incomplete combustion level, and when the verification coefficient is greater than or equal to the verification coefficient threshold, the first incomplete combustion level is corrected to obtain a second incomplete combustion level, and a warning is issued.

[0068] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0069] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0070] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0071] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0073] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0074] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A power plant accident monitoring and early warning method based on Internet of Things data monitoring, characterized in that: Methods include: By using a water temperature sensor array deployed based on the Internet of Things, the water temperature at multiple locations of the boiler in the power plant is detected to obtain a water temperature distribution sequence. Based on the water temperature distribution sequence, water temperature uniformity analysis and water temperature variability analysis are performed to obtain water temperature uniformity parameters and water temperature variability parameters; According to the water temperature uniformity parameter, the smoke components of incomplete combustion are predicted to obtain the predicted smoke components. When the predicted smoke components do not meet the preset smoke component requirements, a decision is made to obtain the first incomplete combustion level and to issue a preliminary warning; According to the water temperature variability parameter, a smoke detection frequency for smoke sensing detection is configured, and according to the smoke detection frequency, smoke component monitoring is performed through a smoke component sensor deployed based on the Internet of Things to obtain a smoke component sequence; According to the flue gas component sequence, the predicted flue gas component is verified and analyzed to obtain a verification coefficient. When the verification coefficient is less than a verification coefficient threshold, an early warning is continued according to the first incomplete combustion level. When the verification coefficient is greater than or equal to the verification coefficient threshold, the first incomplete combustion level is corrected to obtain a second incomplete combustion level and an early warning is issued.

2. The power plant accident monitoring and early warning method based on Internet of Things data monitoring according to claim 1 is characterized in that: Through the water temperature sensor array deployed based on the Internet of Things, the water temperature at multiple locations of the boiler in the power plant is detected to obtain the water temperature distribution sequence, including: By using a water temperature sensor array formed by water temperature sensors arranged at multiple locations of the boiler based on the Internet of Things, water temperature information at the multiple locations is detected to obtain water temperature distribution; Collect water temperature distribution at multiple times to obtain a water temperature distribution sequence; Performing water temperature uniformity analysis on multiple water temperature distributions in the water temperature distribution sequence to obtain water temperature uniformity parameters at multiple moments; Calculating the average of the water temperature uniformity parameters at the multiple moments to obtain the water temperature uniformity parameter; The variance of the water temperature uniformity parameter at the multiple moments is calculated to obtain the water temperature variability parameter.

3. The power plant accident monitoring and early warning method based on Internet of Things data monitoring according to claim 2 is characterized in that: Performing water temperature uniformity analysis on multiple water temperature distributions in the water temperature distribution sequence to obtain water temperature uniformity parameters at multiple moments includes: In the first water temperature distribution in the water temperature distribution sequence, a plurality of groups of first water temperature information are randomly selected, each group of first water temperature information includes two first water temperature information; Calculate the water temperature deviation percentage of two first water temperature information in the multiple groups of first water temperature information to obtain multiple water temperature deviation percentages, calculate the average, and obtain the water temperature uniformity parameter at the first moment; Continue to perform water temperature uniformity analysis on other multiple water temperature distributions to obtain water temperature uniformity parameters at multiple moments.

4. The power plant accident monitoring and early warning method based on Internet of Things data monitoring according to claim 1 is characterized in that: According to the water temperature uniformity parameter, the smoke composition of incomplete combustion is predicted to obtain the predicted smoke composition. When the predicted smoke composition does not meet the preset smoke composition requirements, a decision is made to obtain the first incomplete combustion level and a preliminary warning is issued, including: According to the IoT monitoring data in the historical time, a set of sample water temperature uniformity parameters and smoke components under different sample water temperature uniformity parameters are collected to obtain a set of sample smoke components, wherein the smoke components include the ratio of carbon dioxide concentration to carbon monoxide concentration in the smoke; Using the sample water temperature uniformity parameter set and the sample smoke component set as supervised training data, performing supervised training of the smoke component predictor until convergence; Inputting the water temperature uniformity parameter into the smoke composition predictor, and outputting the prediction to obtain the predicted smoke composition; Determine whether the predicted smoke composition is greater than a preset smoke composition threshold value, if so, the preset smoke composition requirement is met, if not, the preset smoke composition requirement is not met, wherein the preset smoke composition threshold value includes a preset ratio threshold value of the carbon dioxide concentration and the carbon monoxide concentration in the smoke; When the predicted smoke composition does not meet the preset smoke composition requirement, a decision is made to obtain a first incomplete combustion level and issue a preliminary warning.

5. The power plant accident monitoring and early warning method based on Internet of Things data monitoring according to claim 4 is characterized in that: When the predicted smoke composition does not meet the preset smoke composition requirements, a decision is made to obtain a first incomplete combustion level and to issue a preliminary warning, including: Obtain multiple smoke component intervals, and mark multiple samples with incomplete combustion levels according to the degree of incomplete combustion in each smoke component interval; Constructing a mapping relationship between the multiple smoke component intervals and multiple sample incomplete combustion levels to obtain an early warning classifier; According to the predicted smoke component interval into which the smoke component falls, a first combustion incompleteness level is obtained through decision classification, and a preliminary warning is issued.

6. The power plant accident monitoring and early warning method based on Internet of Things data monitoring according to claim 1 is characterized in that: According to the water temperature variability parameter, a smoke detection frequency for smoke sensing detection is configured, and according to the smoke detection frequency, smoke component monitoring is performed through a smoke component sensor deployed based on the Internet of Things to obtain a smoke component sequence, including: Obtaining the standard smoke monitoring frequency of the smoke component sensor for smoke component sensing monitoring; Obtain standard water temperature variability parameters under complete combustion; The ratio of the water temperature variability parameter to the standard water temperature variability parameter is multiplied by the standard smoke monitoring frequency to obtain the smoke detection frequency; According to the smoke detection frequency, smoke component monitoring is performed through a smoke component sensor deployed based on the Internet of Things to obtain a smoke component sequence, wherein each smoke component includes a ratio of carbon dioxide concentration to carbon monoxide concentration in the smoke.

7. The power plant accident monitoring and early warning method based on Internet of Things data monitoring according to claim 1 is characterized in that: According to the smoke component sequence, the predicted smoke component is verified and analyzed to obtain a verification coefficient, when the verification coefficient is less than a verification coefficient threshold, an early warning is continued according to the first incomplete combustion level, and when the verification coefficient is greater than or equal to the verification coefficient threshold, the first incomplete combustion level is corrected to obtain a second incomplete combustion level, and an early warning is issued, including: Randomly extracting a first smoke component from the smoke component sequence, calculating a deviation percentage from the predicted smoke component, and obtaining a first smoke verification coefficient; Continue to randomly select and calculate multiple smoke verification coefficients, and calculate the average to obtain the verification coefficient; Get the verification coefficient threshold; When the verification coefficient is less than the verification coefficient threshold, continuing to issue an early warning according to the first incomplete combustion level; When the verification coefficient is greater than or equal to the verification coefficient threshold, the ratio of the verification coefficient to the verification coefficient threshold is calculated, multiplied by the first incomplete combustion level, corrected to obtain the second incomplete combustion level, and an early warning is issued.

8. The power plant accident monitoring and early warning platform based on IoT data monitoring is characterized by: The steps for implementing the power plant accident monitoring and early warning method of Internet of Things data monitoring as described in any one of claims 1 to 7 include: The boiler water temperature characteristic analysis module is used to detect the water temperature of multiple positions of the boiler in the power plant through a water temperature sensor array deployed based on the Internet of Things, obtain a water temperature distribution sequence, and perform water temperature uniformity analysis and water temperature variability analysis based on the water temperature distribution sequence to obtain water temperature uniformity parameters and water temperature variability parameters; A first incomplete combustion level acquisition module is used to predict the smoke components of incomplete combustion according to the water temperature uniformity parameter, obtain the predicted smoke components, and when the predicted smoke components do not meet the preset smoke component requirements, decide to obtain the first incomplete combustion level and issue a preliminary warning; A smoke component monitoring module, configured to configure a smoke detection frequency for smoke sensing detection according to the water temperature variability parameter, and to monitor smoke components through a smoke component sensor deployed based on the Internet of Things according to the smoke detection frequency to obtain a smoke component sequence; The incomplete combustion warning module is used to verify and analyze the predicted smoke components according to the smoke component sequence to obtain a verification coefficient. When the verification coefficient is less than the verification coefficient threshold, the warning is continued according to the first incomplete combustion level. When the verification coefficient is greater than or equal to the verification coefficient threshold, the first incomplete combustion level is corrected to obtain a second incomplete combustion level and a warning is issued.

9. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the steps of the power plant accident monitoring and early warning method based on Internet of Things data monitoring as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, which, when executed by a processor, implements the steps of the power plant accident monitoring and early warning method based on Internet of Things data monitoring as described in any one of claims 1 to 7.

Images