Boiler energy saving method based on IOT data analysis

Abstract

The invention relates to the technical field of machine learning, in particular to a boiler energy saving method based on IOT data analysis, which comprises the following steps: acquiring a boiler operation parameter set in real time through an Internet of Things sensor, and substituting the boiler operation parameter set into a parameter optimization model to obtain a plurality of different boiler operation parameter combinations; the multiple different boiler operation parameter combinations are substituted into the boiler operation state prediction model, and then multiple sets of prediction results in one-to-one correspondence with the boiler operation parameter combinations are obtained; the fitness is evaluated based on the prediction result corresponding to each boiler operation parameter combination, the boiler operation parameter combination with the highest fitness is marked as the optimal boiler operation parameter, and a corresponding boiler operation parameter optimization suggestion is generated based on the optimal boiler operation parameter. According to the method, the boiler operation data collected in real time are analyzed, the optimization suggestions are generated, operators are helped to reasonably adjust the operation parameters of the boiler under various working conditions, and the effects of energy conservation and emission reduction are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of machine learning, and in particular to a boiler energy-saving method based on IOT data analysis. Background Art

[0002] At present, the operation control of the boiler system mainly relies on traditional empirical rules and manual adjustments, which makes it difficult to achieve accurate energy consumption optimization. The existing boiler operation adjustment means respond slowly to different working conditions and lack scientific methods to provide optimization suggestions, which affects the overall operation efficiency and economic benefits of the boiler. In traditional optimization schemes, the Internet of Things data is not effectively used to conduct in-depth analysis of boiler operation, resulting in a lack of effective decision-making basis for operators and difficulty in achieving intelligent energy-saving optimization. Summary of the invention

[0003] The purpose of the present invention is to provide a boiler energy-saving method based on IOT data analysis to improve the above technical problems.

[0004] In order to achieve the above objectives, the present application provides the following technical solutions:

[0005] On the one hand, an embodiment of the present application provides a boiler energy-saving method based on IOT data analysis, the method comprising: constructing a boiler operation status prediction model based on an LSTM model, and optimizing the boiler operation status prediction model through training set data training; collecting a boiler operation parameter set in real time through an Internet of Things sensor, and performing data standardization processing, data cleaning and outlier correction on it, and then bringing the boiler operation parameter set into the parameter optimization model, and obtaining multiple different boiler operation parameter combinations through continuous iteration; bringing multiple different boiler operation parameter combinations into the boiler operation status prediction model, and then obtaining multiple groups of prediction results corresponding to the boiler operation parameter combinations one by one; evaluating the fitness based on the prediction results corresponding to each group of boiler operation parameter combinations, and marking the boiler operation parameter combination with the highest fitness as the optimal boiler operation parameters, and generating corresponding boiler operation parameter optimization suggestions based on the optimal boiler operation parameters.

[0006] Optionally, the standardized processing of multiple parameters in the boiler operation parameter set is implemented as follows:

[0007]

[0008] Where: x' is the original input data; μ is the mean of the parameter; σ is the standard deviation of the parameter, and x is the standardized parameter.

[0009] Optionally, data cleaning of multiple parameters in the boiler operation parameter set is implemented as follows:

[0010]

[0011] Where: x missing Insert values ​​for missing values; X i are non-missing values; n is the total number.

[0012] Optionally, the abnormal value detection of multiple parameters in the boiler operation parameter set is implemented as follows:

[0013]

[0014] Among them, μ is the mean of the parameter; σ is the standard deviation of the parameter; Z is the standardized score, which measures the degree of deviation of x;

[0015] If |Z|>3, it is considered an outlier and processed using the median or neighboring point data.

[0016] Optionally, the input gate of the boiler operation state prediction model is:

[0017] i t =σ(W i ·[h t-1 ,x t ]+b i );

[0018] Among them, W i is the weight matrix of the input gate; h t-1 is the hidden state of the previous time step; x t is the input of the current time step; b i is the bias, i t is an input gate, and the input gate is used to determine the influence of the current input on the memory unit;

[0019] Secondly, the forget gate of the boiler operation status prediction model is:

[0020] f t =σ(W f ·[h t-1 ,x t ]+b f );

[0021] Among them, W f is the weight matrix of the input gate; h t-1 is the hidden state of the previous time step; x t is the input of the current time step; b f is the bias, f t is a forget gate, which is used to determine the part of the memory of the previous time step that needs to be retained in the current time step;

[0022] Candidate memory cell status Used to generate new candidate memories

[0023]

[0024] in, is the candidate memory cell state, indicating the candidate state at time step t; W C is the weight matrix; h t-1 is the hidden state at time step t-1, indicating the output information at the previous moment; x t is the input data at time step t; b C is the bias vector.

[0025] Memory cell status update (C t ):

[0026]

[0027] Among them, C t : The state of the memory unit at time step t, indicating the current memory information;

[0028] f t : The activation value of the forget gate, ranging from (0,1);

[0029] C t-1 : The memory cell state at the previous time step t-1;

[0030] i t : The activation value of the input gate, the value range is (0,1);

[0031] Candidate memory cell state, represents the candidate state at time step t.

[0032] Secondly, the output gate of the boiler operation status prediction model is:

[0033] o t =σ(W o ·[h t-1 ,x t ]+b o );

[0034] Among them, t : The output gate at time step t, which controls how the current memory cell state affects the hidden state;

[0035] W o : The weight matrix of the output gate, applied to the previous hidden state and the current input;

[0036] h t-1 : The hidden state at time step t-1, indicating the output information at the previous moment;

[0037] xt : Input data at time step t;

[0038] b o : Bias term.

[0039] Hide status update (h t ):

[0040] h t =o t tanh(C t );

[0041] h t : The hidden state at time step t, indicating the output information at the previous moment;

[0042] o t : The output gate at time step t, which controls how the current memory cell state affects the hidden state;

[0043] C t : The state of the memory unit at time step t, indicating the current memory information.

[0044] Optionally, using the training set data to train and optimize the boiler operation state prediction model includes: optimizing the model parameters by minimizing the following mean square error (MSE) loss function:

[0045]

[0046] Among them, yi is the actual observed value; is the predicted value of the model;

[0047] Secondly, the output items based on the boiler operation status prediction model can be further calculated:

[0048] Blowdown rate, which is used to predict the current blowdown rate of the boiler:

[0049]

[0050] R blowdown : Blowdown rate, which indicates the ratio of boiler wastewater discharge to water intake;

[0051] Q blowdown : The amount of wastewater discharged from the boiler;

[0052] Q water : Water intake of the boiler;

[0053] Thermal efficiency, which is used to predict the combustion efficiency of a boiler:

[0054]

[0055] η thermal: Thermal efficiency, which refers to the efficiency of the boiler in converting the heat in the fuel into useful heat;

[0056] Q useful : useful heat generated by the boiler;

[0057] Q fuel : fuel consumption;

[0058] HV fuel : The higher calorific value of the fuel;

[0059] Steam-to-gas ratio, which is used to predict the ratio of steam to fuel consumption:

[0060] Among them, R steam / gas Q is the steam-to-gas ratio, which indicates the ratio of the amount of steam generated by the boiler to the amount of fuel consumed; steam is the amount of steam generated by the boiler; Q fuel is the fuel consumption;

[0061] Heat load, which is used to calculate the heat power provided by the boiler:

[0062]

[0063] Among them, C psteam is the specific heat capacity of steam; Q heat is the heat load; Q steam is the mass flow rate of steam; C psteam is the specific heat capacity of steam; T steam is the temperature of the steam; T water is the inlet water temperature.

[0064] Optionally, the boiler operating parameter set is brought into the parameter optimization model, and a plurality of different boiler operating parameter combinations are obtained through continuous iteration as follows:

[0065] Initial population generation: Each individual in the initial population represents a combination of boiler input parameters; let the population size be P, and each individual contains n input parameters;

[0066] Fitness function definition: The fitness of each individual represents its effectiveness in achieving the goal. The fitness function is defined as:

[0067] Fitness=w 1 ·η thermal -w 2 ·R blowdown +w 3 ·R steam / gas ; Among them, w 1 、w 2 、w 3 Characterization weights;

[0068] η thermal : Thermal efficiency, which refers to the efficiency of the boiler in converting the heat in the fuel into useful heat;

[0069] R blowdown : Blowdown rate, which indicates the ratio of boiler wastewater discharge to water intake;

[0070] R steam / gas : Steam-gas ratio, which indicates the ratio of the amount of steam generated by the boiler to the amount of fuel consumed;

[0071] Selection, crossover, and mutation:

[0072] Selection: Based on fitness, individuals with higher fitness are selected from the population for reproduction through the roulette method; the higher the fitness, the greater the probability of being selected;

[0073] Crossover: Generate new individuals through crossover operation; assuming that the two parent individuals are A and B, the offspring individuals C and D after crossover can be expressed as:

[0074] C i =αA i +(1-α)B i

[0075] D i =(1-α)A i +αB i ;

[0076] Among them, A i and B i Used to represent two parents, C i and D i Used to characterize the offspring after crossover; α∈[0,1] is the crossover coefficient, which is used to control the proportion of the new individual inheriting the characteristics of the parent generation;

[0077] Mutation: mutate some offspring and randomly change some gene values ​​in individuals:

[0078] Qnew=Qold+ΔQ

[0079] Among them, ΔQ is the mutation value, which is randomly generated with a certain probability to increase the diversity of the population and prevent falling into the local optimal solution; Qold: the old value before the update, indicating the Q value in the previous iteration;

[0080] Qnew: the updated new value, indicating the new Q value obtained after mutation;

[0081] Fitness evaluation and iteration:

[0082] Evaluate the new population: Get the prediction results of the newly generated population through the boiler operation status prediction model, evaluate the fitness of the prediction results, and retain individuals with higher fitness;

[0083] Repeated iteration: The process of selection, crossover, mutation, and fitness evaluation is repeated until the maximum number of generations is reached or the fitness is no longer significantly improved.

[0084] In a second aspect, an embodiment of the present application provides a boiler energy-saving method and device based on IOT data analysis, wherein the device includes a memory and a processor.

[0085] The memory is used to store computer programs; the processor is used to implement the steps of the above-mentioned boiler energy-saving method based on IOT data analysis when executing the computer program.

[0086] In a third aspect, an embodiment of the present application provides a medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned boiler energy-saving method based on IOT data analysis are implemented.

[0087] The beneficial effects of the present invention are:

[0088] The purpose of this invention is to develop a boiler energy-saving algorithm model based on IoT data analysis, which generates optimization suggestions by analyzing the real-time collected boiler operation data, and helps operators to reasonably adjust the operating parameters of the boiler under various working conditions to achieve the effect of energy saving and emission reduction, specifically including:

[0089] Through IoT data collection and intelligent analysis, it provides energy-saving optimization suggestions based on scientific models, reducing dependence on manual experience;

[0090] Realize real-time analysis of boiler operating conditions, reduce fuel and water consumption while maintaining steam production, and improve the overall operating efficiency of the boiler;

[0091] The algorithm model is suitable for boiler systems of different types and sizes, can provide corresponding optimization suggestions for various operating conditions, and has good adaptability and scalability.

[0092] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0093] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0094] Figure 1 It is a schematic flow chart of a boiler energy-saving method based on IOT data analysis described in an embodiment of the present invention;

[0095] Figure 2 It is a schematic diagram of the equipment structure of a boiler energy-saving method based on IOT data analysis described in an embodiment of the present invention. DETAILED DESCRIPTION

[0096] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0097] It should be noted that similar reference numerals or letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0098] Embodiment 1:

[0099] like Figure 1 As shown, this embodiment provides a boiler energy-saving method based on IOT data analysis, and the method includes step S100, step S200 and step S300.

[0100] Step S100, collecting a boiler operating parameter set in real time through an Internet of Things sensor, performing data standardization processing, data cleaning and outlier correction on the boiler operating parameter set, and then bringing the boiler operating parameter set into a parameter optimization model, and obtaining a plurality of different boiler operating parameter combinations through continuous iteration, wherein the operating parameter set includes water inlet flow, water inlet temperature, natural gas flow, air flow, flue gas temperature, boiler pressure, boiler water level, boiler water level, blowdown flow, blowdown time, steam pressure, steam flow and flue gas oxygen content;

[0101] Since the magnitude of each feature is quite different (e.g., temperature is in degrees Celsius, while flow is in tons / hour), it is necessary to standardize each input feature so that it conforms to the following standardization formula. The implementation method for standardizing multiple parameters in the boiler operation parameter set is as follows:

[0102]

[0103] Among them, x' is the original input data; μ is the mean of the parameter; σ is the standard deviation of the parameter, and x is the standardized parameter.

[0104] Among them, the implementation method of data cleaning of various parameters in the boiler operation parameter set is:

[0105]

[0106] Where: x missing Insert values ​​for missing values; X i are non-missing values; n is the total number.

[0107] Among them, the implementation method of abnormal value detection of multiple parameters in the boiler operation parameter set is:

[0108]

[0109] Among them, μ is the mean of the parameter; σ is the standard deviation of the parameter; Z is the standardized score, which measures the degree of deviation of x;

[0110] If |Z|>3, it is considered an outlier and processed using the median or neighboring point data.

[0111] Step S200, constructing a boiler operation state prediction model based on the LSTM model, and optimizing the boiler operation state prediction model through training set data, bringing multiple different boiler operation parameter combinations into the boiler operation state prediction model, and then obtaining multiple groups of prediction results corresponding to the boiler operation parameter combinations one by one;

[0112] The specific implementation method of building a boiler operation status prediction model based on the LSTM model is as follows:

[0113] The LSTM model processes the boiler's time series data through a memory mechanism. Input features include the fuel flow rate and water inlet temperature in the previous period, which are input into the LSTM network in the form of time series.

[0114] Construction of boiler operation status prediction model:

[0115] The input gate of the boiler operation status prediction model is:

[0116] i t =σ(Wi ·[h t-1 ,x t ]+b i );

[0117] Among them, W i is the weight matrix of the input gate; h t-1 is the hidden state of the previous time step; x t is the input of the current time step; b i is the bias, i t is an input gate, and the input gate is used to determine the influence of the current input on the memory unit;

[0118] Secondly, the forget gate of the boiler operation status prediction model is:

[0119] f t =σ(W f ·[h t-1 ,x t ]+b f );

[0120] Among them, W f is the weight matrix of the input gate; h t-1 is the hidden state of the previous time step; x t is the input of the current time step; b f is the bias, f t is a forget gate, which is used to determine the part of the memory of the previous time step that needs to be retained in the current time step;

[0121] Candidate memory cell status Used to generate new candidate memories

[0122] in, is the candidate memory cell state, indicating the candidate state at time step t; W C is the weight matrix; h t-1 is the hidden state at time step t-1, indicating the output information at the previous moment; x t is the input data at time step t; b C is the bias vector.

[0123] Memory cell status update (C t ):

[0124] Among them, C t : The state of the memory unit at time step t, indicating the current memory information;

[0125] f t : The activation value of the forget gate, ranging from (0,1);

[0126] C t-1 : The memory cell state at the previous time step t-1;

[0127] i t : The activation value of the input gate, the value range is (0,1);

[0128] Candidate memory cell state, represents the candidate state at time step t.

[0129] Secondly, the output gate of the boiler operation status prediction model is:

[0130] o t =σ(W o ·[h t-1 ,x t ]+b o ), where o t : The output gate at time step t, which controls how the current memory cell state affects the hidden state;

[0131] W o : The weight matrix of the output gate, applied to the previous hidden state and the current input;

[0132] h t-1 : The hidden state at time step t-1, indicating the output information at the previous moment;

[0133] x t : Input data at time step t;

[0134] b o : Bias term.

[0135] Hide status update (h t ):

[0136] h t =o t tanh(C t );h t : The hidden state at time step t, indicating the output information at the previous moment;

[0137] o t : The output gate at time step t, which controls how the current memory cell state affects the hidden state;

[0138] C t : The state of the memory unit at time step t, indicating the current memory information.

[0139] Training of boiler operation status prediction model:

[0140] The boiler operation status prediction model is optimized using the training set data, including: optimizing the model parameters by minimizing the following mean square error (MSE) loss function:

[0141]

[0142] Among them, y i is the actual observed value; is the predicted value of the model;

[0143] Secondly, the output items based on the boiler operation status prediction model can be further calculated:

[0144] Blowdown rate, which is used to predict the current blowdown rate of the boiler:

[0145] R blowdown : Blowdown rate, which indicates the ratio of boiler wastewater discharge to water intake;

[0146] Q blowdown : The amount of wastewater discharged from the boiler;

[0147] Q water : Water intake of the boiler;

[0148] Thermal efficiency, which is used to predict the combustion efficiency of a boiler:

[0149] η thermal : Thermal efficiency, which refers to the efficiency of the boiler in converting the heat in the fuel into useful heat;

[0150] Q useful : useful heat generated by the boiler;

[0151] Q fuel : fuel consumption;

[0152] HV fuel : The higher calorific value of the fuel;

[0153] Steam-to-gas ratio, which is used to predict the ratio of steam to fuel consumption:

[0154] Among them, R steam / gas Q is the steam-to-gas ratio, which indicates the ratio of the amount of steam generated by the boiler to the amount of fuel consumed; steam is the amount of steam generated by the boiler; Q fuel is the fuel consumption;

[0155] Heat load, which is used to calculate the heat power provided by the boiler:

[0156]

[0157] Among them, C psteam is the specific heat capacity of steam; Q heat is the heat load; Q steam is the mass flow rate of steam; Cpsteam is the specific heat capacity of steam; T steam is the temperature of the steam; T water is the inlet water temperature.

[0158] Step S300, evaluating the fitness based on the prediction results corresponding to each group of boiler operating parameter combinations, marking the boiler operating parameter combination with the highest fitness as the optimal boiler operating parameters, and generating corresponding boiler operating parameter optimization suggestions based on the optimal boiler operating parameters;

[0159] Secondly, after the LSTM model predicts the operating state of the boiler, the genetic algorithm is used to optimize the input parameters, such as fuel flow and air flow. The genetic algorithm will simulate the process of natural selection to find the input parameter combination that optimizes the boiler performance. In this embodiment, the prediction data obtained based on the boiler operating state prediction model is optimized by the optimization model to achieve the corresponding boiler operating parameter set:

[0160] Initial population generation: Each individual in the initial population represents a combination of boiler input parameters; let the population size be P, and each individual contains n input parameters, for example, different combinations of fuel flow and air flow (such as natural gas flow, feed water flow);

[0161] Fitness function definition: The fitness (energy saving and efficiency) of each individual represents its effectiveness in achieving the goal. The fitness function is defined as:

[0162] Fitness=w 1 ·η thermal -w 2 ·R blowdown +w 3 ·R steam / gas ;

[0163] Goal: Maximize thermal efficiency, minimize blowdown rate, and minimize steam-to-gas ratio.

[0164] w 1 , w 2 , w 3 is the weight, controlling the relative importance of each optimization objective, η thermal : Thermal efficiency, which refers to the efficiency of the boiler in converting the heat in the fuel into useful heat;

[0165] R blowdown : Blowdown rate, which indicates the ratio of boiler wastewater discharge to water intake;

[0166] R steam / gas : Steam-to-gas ratio, which refers to the ratio of the amount of steam generated by the boiler to the amount of fuel consumed.

[0167] Selection, crossover and mutation process:

[0168] Selection: Based on fitness, individuals with higher fitness are selected from the population for reproduction through the roulette method; the higher the fitness, the greater the probability of being selected;

[0169] Crossover: Generate new individuals through crossover operation; assuming that the two parent individuals are A and B, the offspring individuals C and D after crossover can be expressed as:

[0170] C i =αA i +(1-α)B i

[0171] D i =(1-α)A i +αB i ;

[0172] Among them, A i and B i Used to represent two parents, C i and D i Used to characterize the offspring after crossover; α∈[0,1] is the crossover coefficient, which is used to control the proportion of the new individual inheriting the characteristics of the parent generation;

[0173] Mutation: mutate some offspring and randomly change some gene values ​​in individuals:

[0174] Qnew=Qold+ΔQ

[0175] Among them, ΔQ is the mutation value, which is randomly generated with a certain probability to increase the diversity of the population and prevent falling into the local optimal solution; Qold: the old value before the update, indicating the Q value in the previous iteration;

[0176] Qnew: the updated new value, indicating the new Q value obtained after mutation;

[0177] Fitness evaluation and iteration:

[0178] Evaluate the new population: Get the prediction results of the newly generated population through the boiler operation status prediction model, evaluate the fitness of the prediction results, and retain individuals with higher fitness.

[0179] Repeated iteration: The process of selection, crossover, mutation, and fitness evaluation is repeated until the maximum number of generations is reached or the fitness is no longer significantly improved.

[0180] That is, after finding the optimal combination of boiler operating parameters through the genetic algorithm (input parameter optimization model), actual optimization suggestions are generated, such as:

[0181] Natural gas flow rate: Adjust the fuel flow rate to the optimal value, such as 820 cubic meters per hour, to ensure the highest combustion efficiency.

[0182] Air flow: It is recommended to increase the air flow to 1250 m3 / h to ensure a moderate excess air rate, thereby reducing pollutants in the flue gas.

[0183] Blowdown flow: It is recommended to reduce the blowdown flow to reduce heat loss and improve the overall thermal efficiency of the boiler.

[0184] In this embodiment, by analyzing the boiler operation data collected in real time, optimization suggestions are generated to help operators reasonably adjust the operating parameters of the boiler under various operating conditions to achieve energy conservation and emission reduction effects. Specifically, it includes: providing energy-saving optimization suggestions based on scientific models through IoT data collection and intelligent analysis, reducing dependence on manual experience; realizing real-time analysis of boiler operating conditions, reducing fuel and water consumption while maintaining steam production, and improving the overall operating efficiency of the boiler; the algorithm model is suitable for boiler systems of different types and sizes, and can provide corresponding optimization suggestions for a variety of operating conditions, with good adaptability and expansibility.

[0185] Embodiment 2:

[0186] Corresponding to the above method embodiments, the embodiments of the present disclosure also provide a boiler energy-saving method and device based on IOT data analysis. The boiler energy-saving method and device based on IOT data analysis described below and the boiler energy-saving method based on IOT data analysis described above can be referenced to each other.

[0187] Figure 2 8 is a block diagram of a boiler energy saving method and device 800 based on IOT data analysis according to an exemplary embodiment. Figure 2 As shown, the electronic device 800 may include: a processor 801 and a memory 802. The electronic device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0188] The processor 801 is used to control the overall operation of the electronic device 800 to complete all or part of the steps in the above-mentioned boiler energy saving method based on IOT data analysis. The memory 802 is used to store various types of data to support the operation of the electronic device 800, and these data may include, for example, instructions for any application or method used to operate on the electronic device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone, which is used to receive external audio signals. The received audio signal may be further stored in the memory 802 or sent through the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the electronic device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 may include: Wi-Fi module, Bluetooth module, NFC module.

[0189] In an exemplary embodiment, the electronic device 800 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned boiler energy-saving method based on IOT data analysis.

[0190] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned boiler energy-saving method based on IOT data analysis are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions can be executed by the processor 801 of the electronic device 800 to complete the above-mentioned boiler energy-saving method based on IOT data analysis.

[0191] Embodiment 3:

[0192] Corresponding to the above method embodiment, the embodiment of the present disclosure further provides a readable storage medium. The readable storage medium described below and the boiler energy-saving method based on IOT data analysis described above can refer to each other.

[0193] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the boiler energy-saving method based on IOT data analysis of the above method embodiment.

[0194] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0195] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A boiler energy-saving method based on IOT data analysis, characterized in that: The method comprises: Build a boiler operation status prediction model based on the LSTM model, and optimize the boiler operation status prediction model through training set data; The boiler operating parameter set is collected in real time through IoT sensors, and data standardization, data cleaning and outlier correction are performed. The boiler operating parameter set is then brought into the parameter optimization model, and multiple different boiler operating parameter combinations are obtained through continuous iteration. Bringing multiple different boiler operating parameter combinations into the boiler operating state prediction model, and then obtaining multiple groups of prediction results corresponding to the boiler operating parameter combinations one by one; The fitness is evaluated based on the prediction results corresponding to each group of boiler operating parameter combinations, and the boiler operating parameter combination with the highest fitness is marked as the optimal boiler operating parameters, and corresponding boiler operating parameter optimization suggestions are generated based on the optimal boiler operating parameters.

2. The boiler energy saving method based on IOT data analysis according to claim 1 is characterized in that: The implementation method of standardizing the various parameters in the boiler operation parameter set is as follows: Where: x' is the original input data; μ is the mean of the parameter; σ is the standard deviation of the parameter, and x is the standardized parameter.

3. The boiler energy saving method based on IOT data analysis according to claim 2 is characterized in that: The implementation method of data cleaning for various parameters in the boiler operation parameter set is as follows: Where: x missing Insert values ​​for missing values; X i are non-missing values; n is the total number.

4. The boiler energy saving method based on IOT data analysis according to claim 3 is characterized in that: The implementation method of abnormal value detection for multiple parameters in the boiler operation parameter set is as follows: Among them, μ is the mean of the parameter; σ is the standard deviation of the parameter; Z is the standardized score, which measures the degree of deviation of x; If |Z|>3, it is considered an outlier and processed using the median or neighboring point data.

5. The boiler energy saving method based on IOT data analysis according to claim 4 is characterized in that: The input gate of the boiler operation status prediction model is: i t =σ(W i ·[h t-1 ,x t ]+b i ); Among them, W i is the weight matrix of the input gate; h t-1 is the hidden state of the previous time step; x t is the input of the current time step; b i is the bias, i t is an input gate, and the input gate is used to determine the influence of the current input on the memory unit; Secondly, the forget gate of the boiler operation status prediction model is: f t =σ(W f ·[h t-1 ,x t ]+b f ); Where Wf is the weight matrix of the input gate; ht-1 is the hidden state of the previous time step; x t is the input of the current time step; b f is the bias, f t is a forget gate, which is used to determine the part of the memory of the previous time step that needs to be retained in the current time step; Candidate memory cell state, used to generate new candidate memories in, is the candidate memory cell state, indicating the candidate state at time step t; W C is the weight matrix; h t-1 is the hidden state at time step t-1, indicating the output information at the previous moment; x t is the input data at time step t; b C is the bias vector; Memory cell status update (C t ): Among them, C t : The state of the memory unit at time step t, indicating the current memory information; f t : The activation value of the forget gate, ranging from (0,1); C t-1 : The memory cell state at the previous time step t-1; i t : The activation value of the input gate, the value range is (0,1); Candidate memory cell state, which represents the candidate state at time step t; Secondly, the output gate of the boiler operation status prediction model is: the t =σ(W o ·[h t-1 ,x t ]+b o ); Among them, t : The output gate at time step t, which controls how the current memory cell state affects the hidden state; W o : The weight matrix of the output gate, applied to the previous hidden state and the current input; h t -1: The hidden state at time step t-1, indicating the output information at the previous moment; x t : Input data at time step t; b o : bias term; Hide status update (h t ): h t =o t ·tanh(C t ); h t : The hidden state at time step t, indicating the output information at the previous moment; o t : The output gate at time step t, which controls how the current memory cell state affects the hidden state; C t : The state of the memory unit at time step t, indicating the current memory information.

6. The boiler energy saving method based on IOT data analysis according to claim 5 is characterized in that: The boiler operation status prediction model is optimized using the training set data, including: optimizing the model parameters by minimizing the following mean square error (MSE) loss function: Among them, y i is the actual observed value; is the predicted value of the model; Secondly, the output items based on the boiler operation status prediction model can be further calculated: Blowdown rate, which is used to predict the current blowdown rate of the boiler: R blowdown : Blowdown rate, which indicates the ratio of boiler wastewater discharge to water intake; Q blowdown : The amount of wastewater discharged from the boiler; Q water : Water intake of the boiler; Thermal efficiency, which is used to predict the combustion efficiency of a boiler: η thermal : Thermal efficiency, which refers to the efficiency of the boiler in converting the heat in the fuel into useful heat; Q useful : Useful heat generated by the boiler; Q fuel : fuel consumption; HV fuel : The higher calorific value of the fuel; Steam-to-gas ratio, which is used to predict the ratio of steam to fuel consumption: Among them, R steam / gas Q is the steam-to-gas ratio, which indicates the ratio of the amount of steam generated by the boiler to the amount of fuel consumed; steam is the amount of steam generated by the boiler; Q fuel is the fuel consumption; Heat load, which is used to calculate the heat power provided by the boiler: Among them, C psteam is the specific heat capacity of steam; Q heat is the heat load; Q steam is the mass flow rate of steam; C psteam is the specific heat capacity of steam; T steam is the temperature of steam; T water is the inlet water temperature.

7. The boiler energy saving method based on IOT data analysis according to claim 6 is characterized in that: The boiler operating parameter set is brought into the parameter optimization model, and the implementation method of obtaining multiple different boiler operating parameter combinations through continuous iteration is as follows: Initial population generation: Each individual in the initial population represents a combination of boiler input parameters; let the population size be P, and each individual contains n input parameters; Fitness function definition: The fitness of each individual represents its effectiveness in achieving the goal. The fitness function is defined as: Fitness=w1·η thermal -w2·R blowdown +w3·R steam / gas ; Among them, w1, w2, and w3 represent weights; η thermal : Thermal efficiency, which refers to the efficiency of the boiler in converting the heat in the fuel into useful heat; R blowdown : Blowdown rate, which indicates the ratio of boiler wastewater discharge to water intake; R steam / gas : Steam-gas ratio, which indicates the ratio of the amount of steam generated by the boiler to the amount of fuel consumed; Selection, crossover, and mutation: Selection: Based on fitness, individuals with higher fitness are selected from the population for reproduction through the roulette method; the higher the fitness, the greater the probability of being selected; Crossover: Generate new individuals through crossover operation; assuming that the two parent individuals are A and B, the offspring individuals C and D after crossover can be expressed as: C i =αA i +(1-α)B i D i =(1-α)A i +αB i ; Among them, A i and B i Used to represent two parents, C i and D i Used to characterize the offspring after crossover; α∈[0,1] is the crossover coefficient, which is used to control the proportion of the new individual inheriting the characteristics of the parent generation; Mutation: mutate some offspring and randomly change some gene values ​​in individuals: Qnew=Qold+ΔQ Among them, ΔQ is the mutation value, which is randomly generated with a certain probability to increase the diversity of the population and prevent falling into the local optimal solution; Qold: the old value before the update, indicating the Q value in the previous iteration; Qnew: the updated new value, indicating the new Q value obtained after mutation; Fitness evaluation and iteration: Evaluate the new population: Get the prediction results of the newly generated population through the boiler operation status prediction model, evaluate the fitness of the prediction results, and retain individuals with higher fitness; Repeated iteration: The process of selection, crossover, mutation, and fitness evaluation is repeated until the maximum number of generations is reached or the fitness is no longer significantly improved.

Images