Cleaning early warning system of organic heat carrier boiler

Abstract

The invention relates to the technical field of power system fault diagnosis, and particularly discloses a cleaning early warning system of an organic heat carrier boiler, which is characterized in that after the organic heat carrier boiler is cleaned once, an optical fiber sensor network is fixed at a specific position in the boiler; adjusting the sensitivity of the optical fiber sensor; signals from the optical fiber sensor network are received and analyzed, so that whether a cleaning dead angle area exists in the boiler or not is judged; if it is recognized that the cleaning dead angle areas exist in the boiler, cleaning parameters of all the cleaning dead angle areas are automatically adjusted; and the cleaning effect and efficiency can be greatly improved, and safe and stable operation of the boiler is ensured. The intelligent solution not only meets the requirement of industrial production for high efficiency and cleaning, but also provides powerful guarantee for long-term stable operation of the boiler, and has remarkable economic and environment-friendly values.

Description

Technical Field

[0001] The invention belongs to the technical field of power system fault diagnosis and relates to a cleaning early warning system for an organic heat carrier boiler. Background Art

[0002] During the operation of organic heat transfer medium boilers, post-cleaning inspection is essential to ensure the efficient and safe operation of the equipment. First of all, the boiler will accumulate a lot of dirt and sediments in long-term use. These sediments not only reduce the heat transfer efficiency, but also may cause equipment overheating, corrosion and failure. Therefore, post-cleaning inspection can ensure that all dirt is effectively removed to avoid potential risks caused by residues. Through inspection, the cleaning effect can be evaluated in real time to ensure the thermal efficiency and service life of the boiler, while reducing energy consumption and maintenance costs. In addition, inspection can also help identify wear and damage inside the boiler, make timely repairs, and prevent small problems from turning into serious failures, thereby ensuring the continuity and safety of production.

[0003] However, current technologies still have significant defects and drawbacks in detecting dead corners of organic heat carrier boilers. First, most traditional detection methods rely on manual inspection and simple visual inspection, which is not only time-consuming and labor-intensive, but also easy to miss residues in dead corners, especially in complex boiler structures, where dead corners are often difficult to access and observe. Secondly, many existing detection equipment lacks sufficient sensitivity and resolution to accurately identify tiny dirt and sediments, which results in an incomplete evaluation of the cleaning effect and may lead to a decrease in boiler operating efficiency. In addition, some detection technologies rely on operation in high temperature and high pressure environments, which poses a potential threat to the safety of equipment and personnel. Furthermore, many detection systems lack the ability to be intelligent and automated, and cannot be dynamically adjusted and optimized based on real-time data, resulting in detection results lagging behind actual conditions. Finally, existing detection methods are usually costly and difficult to promote and apply on a large scale in actual production. Summary of the invention

[0004] In view of the above problems existing in the prior art, the present invention provides a cleaning early warning system for an organic heat carrier boiler. By introducing an intelligent optical fiber sensor network and a machine learning algorithm, real-time monitoring and data analysis of every corner inside the boiler can be achieved, thereby greatly improving the accuracy and efficiency of detection and ensuring that the boiler operates in the best state, thereby solving the above technical problems.

[0005] In order to achieve the above purpose and other purposes, the technical solution adopted by the present invention is as follows:

[0006] The present invention provides a cleaning early warning system for an organic heat carrier boiler, comprising an instrument operation module, a data receiving module, a cleaning analysis module and a cleaning feedback terminal, wherein the above modules are connected by wired and / or wireless connection to realize data transmission between the modules;

[0007] The instrument operation module includes an instrument layout subunit and an instrument debugging subunit; the instrument layout subunit is used to fix the optical fiber sensor network at a specific position inside the boiler after the organic heat carrier boiler is cleaned once; the instrument debugging subunit is used to adjust the sensitivity of the optical fiber sensor;

[0008] Data receiving module: This module is connected to the optical fiber sensor network and is used to receive and analyze signals from the optical fiber sensor network to determine whether there are any cleaning dead corners inside the boiler;

[0009] Cleaning analysis module: If cleaning dead corners are identified inside the boiler, the cleaning parameters of each cleaning dead corner will be automatically adjusted;

[0010] Cleaning feedback terminal: used to feed back the cleaning parameters of each cleaning dead corner area to the cleaning background terminal, so as to set the corresponding cleaning parameters of the boiler cleaning tool for secondary cleaning.

[0011] The debugging logic of the instrument debugging subunit is:

[0012] According to the analysis formula The sensitivity G of the optical fiber sensor after adjustment is obtained through analysis;

[0013] In the above calculation formula, S is the output signal of the optical fiber sensor, N is the noise level; α is the signal correction coefficient, which is used to adjust the weight of the signal strength and optimize the ratio of signal to noise; β is the noise suppression coefficient, which is used to adjust the influence of noise on the signal and reduce noise interference; γ is the environmental response coefficient, which is used to measure the influence of environmental factors on sensitivity, E(t) is the environmental influence coefficient, which represents the factors that change with time, f(t) is the weight function of the environmental response, which is used to weight the environmental influences at different time points; δ is the baseline adjustment coefficient, which is used to set the basic value of sensitivity adjustment; ε is the variance response coefficient, which is used to adjust the influence of the positive signal room difference on the sensitivity, σ 2 is the variance of the signal, indicating the amplitude of signal change and reflecting the signal stability; η is the historical data weight coefficient, which is used to adjust the impact of historical data on current sensitivity;

[0014] x i is the i-th historical signal data point, i is the index of the historical signal data point, i=1,2,...n, n is the total number of historical signal data points; μ is the mean of the signal, which represents the average value of the historical signal data.

[0015] By calculating the formula

[0016] E(t)=ψ1×T(t)+ψ2×P(t)+ψ3×H(t)+ψ4×T(t)·P(t)+ψ5×P(t)·H(t)+ψ6×T(t)·H(t), and the environmental impact coefficient E(t) is calculated, where ψ1, ψ2, ψ3, ψ4, ψ5 and ψ6 represent the set weight coefficients, which represent the contribution of each environmental factor and its interaction to the environmental impact; T(t), P(t) and H(t) represent the function of temperature changing with time, the function of pressure changing with time and the function of humidity changing with time respectively;

[0017] By calculating the formula f(t) = g·e -λt +h, the weight function f(t) of the environmental response is calculated, g is the initial weight, which represents the initial impact of environmental change on the response; λ is the attenuation coefficient, which represents the decay rate of environmental impact over time; h is the basic weight, which represents the minimum weight of environmental impact, and t represents the time variable.

[0018] The steps to determine whether there is a cleaning dead corner area inside the boiler are as follows:

[0019] Divide the interior of the boiler into various internal areas;

[0020] The light intensity value of each internal area and the curvature of the optical fiber are collected;

[0021] Subtract the light intensity value of each internal area from the light intensity value of each internal area before cleaning to obtain the light intensity change difference ΔI of each internal area d , d is the number of each internal area;

[0022] Subtract the fiber curvature of each internal area from the fiber curvature of each internal area before cleaning to obtain the fiber curvature change difference ΔB of each internal area. d ;

[0023] The comprehensive dirt degree index C of each internal area is calculated comprehensively d =ω1×ΔI d +ω2×ΔB d , ω1 and ω2 represent the set weight coefficients, which are used to adjust the influence of light intensity change and curvature change in comprehensive judgment;

[0024] The comprehensive dirt degree index of each internal area is compared with the set judgment threshold. When the comprehensive dirt degree index of an internal area is greater than the set judgment threshold, the internal area is determined to be a dead angle area.

[0025] The cleaning parameters are divided into cleaning agent concentration, cleaning time and the optimal spray angle of the cleaning tool.

[0026] Automatically adjust the cleaning agent concentration in the cleaning parameters of each cleaning dead corner area. The specific adjustment process is as follows:

[0027] Obtain the initial cleaning agent concentration ND0 for cleaning the inside of the boiler;

[0028] And according to the comprehensive dirt index C of each cleaning dead corner area r , then the predetermined cleaning agent concentration of each cleaning dead corner area after adjustment is expressed as:

[0029] θ1 r =ND0+k·(C r -C0), θ1 r represents the predetermined cleaning agent concentration of the rth cleaning dead corner area, r is the number of each cleaning dead corner area, k is the adjustment coefficient used to control the sensitivity of concentration change; C0 is the threshold value of the comprehensive dirt level;

[0030] And obtain the upper threshold ND of the cleaning agent concentration corresponding to the boiler max and lower threshold ND min ;

[0031] The cleaning agent concentration of each cleaning dead corner area is calculated from this

[0032] θ1′ r =max(ND min ,min(θ1 r ,ND max )).

[0033] Automatically adjust the cleaning time in the cleaning parameters of each cleaning dead corner area. The specific adjustment process is as follows:

[0034] Obtain the basic cleaning time of each internal area of ​​the boiler, thereby extracting the basic cleaning time of each cleaning dead corner area

[0035] The cleaning time of each cleaning dead corner area is calculated comprehensively

[0036]

[0037] λ1 r is the detergent concentration coefficient of the rth cleaning dead corner area, λ1′ r is the optimal cleaning agent concentration for the rth cleaning dead corner area;

[0038] λ2 r is the pollution degree coefficient of the rth cleaning dead corner area, HD r is the dirt thickness in the rth cleaning dead corner area, and HDmax is the maximum allowable dirt thickness;

[0039] λ3 r is the historical data coefficient of the rth cleaning dead corner area, is the cleaning time of the rth cleaning dead corner area under similar historical conditions;

[0040] λ4 r is the environmental impact coefficient of the rth cleaning dead corner area,

[0041] are the temperature and pressure of the rth cleaning dead corner area, respectively, and f(·) is the set function expression formula.

[0042] Automatically adjust the optimal spray angle of the cleaning tool in the cleaning parameters of each cleaning dead corner area. The specific adjustment process is as follows:

[0043] Get the coordinates of the center point of each cleaning blind spot area (x1 r ,y1 r ,z1 r ), synchronously obtain the position coordinates (x2, y2, z2) of the nozzle corresponding to the cleaning tool;

[0044] The distance between the corresponding nozzle of the cleaning tool and the corresponding center point of each cleaning blind spot area is calculated accordingly.

[0045] Calculate the angle of the cleaning tool on the horizontal plane corresponding to each cleaning dead angle area and the angle on the vertical plane

[0046]

[0047] Use Bernoulli's equation and continuity equation to calculate the flow velocity υ, and then calculate the pressure lost by the fluid due to resistance during the injection process ρ is the density of the fluid, φ is the drag coefficient;

[0048] According to the angle of the cleaning tool on the horizontal plane, the angle on the vertical plane and △P of each cleaning dead angle area, the predetermined spray angle of the cleaning tool corresponding to each cleaning dead angle area is dynamically adjusted. F(·) is a function simulated from historical experimental data, expressed as a mapping relationship that converts input parameters into output predetermined injection angles;

[0049] After error correction, the optimal spray angle of the cleaning tool corresponding to each cleaning dead angle area is finally obtained. is the set adjustment coefficient, and △θ is the set allowable detection error.

[0050] As described above, the cleaning warning system for an organic heat carrier boiler provided by the present invention has at least the following beneficial effects:

[0051] The present invention provides a cleaning early warning system for an organic heat carrier boiler. During the cleaning process of the organic heat carrier boiler, a fiber optic sensor network is fixed at a specific position inside the boiler, and the sensitivity of the fiber optic sensor is adjusted, which can significantly improve the cleaning effect and efficiency. This method can accurately determine whether there are cleaning dead corners inside the boiler by receiving and analyzing the signals transmitted by the fiber optic sensor network in real time. Traditional boiler cleaning methods often rely on manual experience and fixed cleaning procedures, and cannot dynamically respond to the complex dirt distribution inside the boiler. Through the application of the fiber optic sensor network, real-time monitoring of the internal state of the boiler can be achieved to ensure the comprehensiveness and thoroughness of the cleaning process.

[0052] The fiber optic sensor network has the characteristics of high sensitivity and high precision. It can work stably under high temperature and high pressure environment and is suitable for the complex working conditions of organic heat carrier boilers. By adjusting the sensitivity of the fiber optic sensor, it can adapt to different dirt types and thicknesses and achieve accurate detection of small changes. This real-time monitoring capability enables the system to quickly identify cleaning blind spots and avoid areas that may be missed in traditional cleaning methods, thereby improving the overall operating efficiency and safety of the boiler.

[0053] Once the system identifies the blind spots in the boiler, it will automatically adjust the cleaning parameters for each blind spot. This automatic adjustment mechanism can optimize the parameters such as the spray angle, flow rate and pressure of the cleaning tool according to the specific needs of different areas to ensure that each area can be fully cleaned. This dynamic adjustment can not only reduce the waste of cleaning time and resources, but also reduce the wear and tear on the equipment during the cleaning process, extending the service life of the boiler.

[0054] In addition, this intelligent cleaning early warning system also has important economic and environmental significance. First, by improving cleaning efficiency and reducing energy consumption, operating costs can be significantly reduced. Second, thorough cleaning can prevent the accumulation of dirt in the boiler, which leads to a decrease in thermal efficiency and safety hazards, thereby reducing boiler failures and downtime, and further improving economic benefits. Finally, reducing the use of chemical cleaning agents and sewage discharge helps reduce environmental pollution, which is in line with the green development trend of modern industry.

[0055] In summary, applying the fiber optic sensor network to the cleaning process of organic heat carrier boilers can greatly improve the cleaning effect and efficiency and ensure the safe and stable operation of the boiler. This intelligent solution not only meets the needs of industrial production for efficient cleaning, but also provides a strong guarantee for the long-term stable operation of the boiler, with significant economic and environmental value. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0057] Figure 1 It is a schematic diagram of the connection of various modules of the system of the present invention. DETAILED DESCRIPTION

[0058] The above contents in combination with the implementation of the present invention are merely examples and explanations of the concept of the present invention. The technical personnel in the relevant technical field may make various modifications or supplements to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they shall all fall within the protection scope of the present invention.

[0059] Example 1

[0060] See also Figure 1 As shown, a cleaning warning system for an organic heat carrier boiler includes an instrument operation module, a data receiving module, a cleaning analysis module and a cleaning feedback terminal, wherein the above modules are connected by wired and / or wireless connection to realize data transmission between the modules;

[0061] The instrument operation module includes an instrument layout subunit and an instrument debugging subunit; the instrument layout subunit is used to fix the optical fiber sensor network at a specific position inside the boiler after the organic heat carrier boiler is cleaned once; the instrument debugging subunit is used to adjust the sensitivity of the optical fiber sensor;

[0062] The debugging logic of the instrument debugging subunit is:

[0063] According to the analysis formula The sensitivity G of the optical fiber sensor after adjustment is obtained through analysis;

[0064] The above calculation formula provides a dynamic and accurate method for adjusting the sensitivity of fiber optic sensors by combining signal processing and optimization algorithms. It takes into account the signal strength, environmental impact, noise level and statistical characteristics of historical data, ensuring the adaptability of the sensor to different boiler structures and cleaning conditions. The benefit of this complex formula is that it can optimize the sensitivity in real time, improve the accuracy and reliability of detection, and reduce the possibility of false alarms and missed alarms. Its necessity is reflected in its ability to cope with the complex and changing internal environment of the boiler and improve the intelligence and overall performance of the system;

[0065] In the above calculation formula, S is the output signal of the optical fiber sensor, N is the noise level; α is the signal correction coefficient, which is used to adjust the weight of the signal strength and optimize the ratio of signal to noise; β is the noise suppression coefficient, which is used to adjust the influence of noise on the signal and reduce noise interference; γ is the environmental response coefficient, which is used to measure the influence of environmental factors on sensitivity, E(t) is the environmental influence coefficient, which represents the factors that change with time, f(t) is the weight function of the environmental response, which is used to weight the environmental influences at different time points; δ is the baseline adjustment coefficient, which is used to set the basic value of sensitivity adjustment; ε is the variance response coefficient, which is used to adjust the influence of the positive signal room difference on the sensitivity, σ 2 is the variance of the signal, indicating the amplitude of signal change and reflecting the signal stability; η is the historical data weight coefficient, which is used to adjust the impact of historical data on current sensitivity;

[0066] x i is the i-th historical signal data point, i is the index of the historical signal data point, i=1,2,...n, n is the total number of historical signal data points; μ is the mean of the signal, which represents the average value of the historical signal data.

[0067] The environmental impact coefficient E(t) is calculated by the formula E(t) = ψ1×T(t)+ψ2×P(t)+ψ3×H(t)+ψ4×T(t)·P(t)+ψ5×P(t)·H(t)+ψ6×T(t)·H(t), where ψ1, ψ2, ψ3, ψ4, ψ5 and ψ6 represent the set weight coefficients, indicating the contribution of each environmental factor and its interaction to the environmental impact; T(t), P(t) and H(t) represent the function of temperature changing with time, the function of pressure changing with time and the function of humidity changing with time, respectively;

[0068] By calculating the formula f(t) = g·e -λt +h, the weight function f(t) of the environmental response is calculated, g is the initial weight, which represents the initial impact of environmental change on the response; λ is the attenuation coefficient, which represents the decay rate of environmental impact over time; h is the basic weight, which represents the minimum weight of environmental impact, and t represents the time variable.

[0069] Data receiving module: This module is connected to the optical fiber sensor network and is used to receive and analyze signals from the optical fiber sensor network to determine whether there are any cleaning dead corners inside the boiler;

[0070] The steps to determine whether there is a cleaning dead corner area inside the boiler are as follows:

[0071] Divide the interior of the boiler into various internal areas;

[0072] The light intensity value of each internal area and the curvature of the optical fiber are collected;

[0073] Subtract the light intensity value of each internal area from the light intensity value of each internal area before cleaning to obtain the light intensity change difference ΔI of each internal area d , d is the number of each internal area;

[0074] Subtract the fiber curvature of each internal area from the fiber curvature of each internal area before cleaning to obtain the fiber curvature change difference ΔB of each internal area. d ;

[0075] The comprehensive dirt degree index C of each internal area is calculated comprehensively d =ω1×ΔI d +ω2×ΔB d , ω1 and ω2 represent the set weight coefficients, which are used to adjust the influence of light intensity change and curvature change in comprehensive judgment;

[0076] The comprehensive dirt degree index of each internal area is compared with the set judgment threshold. When the comprehensive dirt degree index of an internal area is greater than the set judgment threshold, the internal area is determined to be a dead angle area.

[0077] Cleaning analysis module: If cleaning dead corners are identified inside the boiler, the cleaning parameters of each cleaning dead corner will be automatically adjusted;

[0078] The cleaning parameters are divided into cleaning agent concentration, cleaning time and the optimal spray angle of the cleaning tool.

[0079] Automatically adjust the cleaning agent concentration in the cleaning parameters of each cleaning dead corner area. The specific adjustment process is as follows:

[0080] Obtain the initial cleaning agent concentration ND0 for cleaning the inside of the boiler;

[0081] And according to the comprehensive dirt index C of each cleaning dead corner area r , then the predetermined cleaning agent concentration of each cleaning dead corner area after adjustment is expressed as:

[0082] θ1 r =ND0+k·(C r -C0), θ1 r represents the predetermined cleaning agent concentration of the rth cleaning dead corner area, r is the number of each cleaning dead corner area, k is the adjustment coefficient used to control the sensitivity of concentration change; C0 is the threshold value of the comprehensive dirt level;

[0083] And obtain the upper threshold ND of the cleaning agent concentration corresponding to the boiler max and lower threshold ND min ;

[0084] The cleaning agent concentration of each cleaning dead corner area is calculated from this

[0085] θ1′ r =max(ND min ,min(θ1 r ,ND max )).

[0086] Automatically adjust the cleaning time in the cleaning parameters of each cleaning dead corner area. The specific adjustment process is as follows:

[0087] Obtain the basic cleaning time of each internal area of ​​the boiler, thereby extracting the basic cleaning time of each cleaning dead corner area

[0088] The cleaning time of each cleaning dead corner area is calculated comprehensively

[0089]

[0090] λ1 r is the detergent concentration coefficient of the rth cleaning dead corner area, λ1′ r is the optimal cleaning agent concentration for the rth cleaning dead corner area;

[0091] λ2 r is the pollution degree coefficient of the rth cleaning dead corner area, HD r is the dirt thickness of the rth cleaning dead corner area, HD max is the maximum allowable dirt thickness;

[0092] λ3 r is the historical data coefficient of the rth cleaning dead corner area, is the cleaning time of the rth cleaning dead corner area under similar historical conditions;

[0093] λ4 r is the environmental impact coefficient of the rth cleaning dead corner area,

[0094] are the temperature and pressure of the rth cleaning dead corner area, respectively, and f(·) is the set function expression formula.

[0095] Automatically adjust the optimal spray angle of the cleaning tool in the cleaning parameters of each cleaning dead corner area. The specific adjustment process is as follows:

[0096] Get the coordinates of the center point of each cleaning blind spot area (x1 r ,y1 r ,z1 r ), synchronously obtain the position coordinates (x2, y2, z2) of the nozzle corresponding to the cleaning tool;

[0097] The distance between the corresponding nozzle of the cleaning tool and the corresponding center point of each cleaning blind spot area is calculated accordingly.

[0098] Calculate the angle of the cleaning tool on the horizontal plane corresponding to each cleaning dead angle area and the angle on the vertical plane

[0099]

[0100] Use Bernoulli's equation and continuity equation to calculate the flow velocity υ, and then calculate the pressure lost by the fluid due to resistance during the injection process ρ is the density of the fluid, φ is the drag coefficient;

[0101] According to the angle of the cleaning tool on the horizontal plane, the angle on the vertical plane and △P of each cleaning dead angle area, the predetermined spray angle of the cleaning tool corresponding to each cleaning dead angle area is dynamically adjusted. F(·) is a function simulated from historical experimental data, expressed as a mapping relationship that converts input parameters into output predetermined injection angles;

[0102] After error correction, the optimal spray angle of the cleaning tool corresponding to each cleaning dead angle area is finally obtained. is the set adjustment coefficient, and △θ is the set allowable detection error.

[0103] Adjusting the spray angle of the cleaning tool involves complex fluid dynamics and geometric calculations. The rationality of these formulas lies in that they combine geometric positioning and fluid characteristics to achieve precise cleaning effects. First, the geometric calculation part locates the position of the nozzle and the target dirt through a three-dimensional coordinate system, and uses the distance formula, angle formula and vertical angle to accurately determine the spray direction. These calculations ensure that the spray fluid can accurately reach the target area, avoiding unnecessary energy waste and excessive use of cleaning fluid;

[0104] In terms of fluid dynamics, it is crucial to consider the jet velocity and flow rate. Using the Bernoulli equation and the continuity equation, the behavior of the fluid under different pressure conditions can be calculated. This not only helps to optimize the jet velocity, but also adjusts the jet parameters according to the fluid resistance and energy loss to ensure that the jet fluid can effectively remove dirt under different working conditions. The benefit of this approach is that it can dynamically adjust the jet parameters according to actual conditions, improve cleaning efficiency, and reduce energy consumption; this optimization not only improves the cleaning effect, but also reduces the waste of cleaning time and resources. Combined with real-time sensor feedback and machine learning algorithms, the system can dynamically adjust the jet angle and parameters to further improve the response speed and accuracy. This adaptive capability enables the cleaning system to maintain efficient operation in complex and changing environments.

[0105] Cleaning feedback terminal: used to feed back the cleaning parameters to the cleaning background terminal, so as to set the corresponding cleaning parameters for the boiler cleaning tool for secondary cleaning.

[0106] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0107] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0108] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0109] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A cleaning warning system for an organic heat carrier boiler, characterized in that: It includes an instrument operation module, a data receiving module, a cleaning analysis module and a cleaning feedback terminal, and the above modules are connected by wired and / or wireless connection to achieve data transmission between the modules; The instrument operation module includes an instrument layout subunit and an instrument debugging subunit; the instrument layout subunit is used to fix the optical fiber sensor network at a specific position inside the boiler after the organic heat carrier boiler is cleaned once; The instrument debugging subunit is used to adjust the sensitivity of the optical fiber sensor; Data receiving module: This module is connected to the optical fiber sensor network and is used to receive and analyze signals from the optical fiber sensor network to determine whether there are any cleaning dead corners inside the boiler; Cleaning analysis module: If cleaning dead corners are identified inside the boiler, the cleaning parameters of each cleaning dead corner will be automatically adjusted; Cleaning feedback terminal: used to feed back the cleaning parameters of each cleaning dead corner area to the cleaning background terminal, so as to set the corresponding cleaning parameters of the boiler cleaning tool for secondary cleaning.

2. The cleaning warning system for an organic heat carrier boiler according to claim 1 is characterized in that: The debugging logic of the instrument debugging subunit is: According to the analysis formula The sensitivity G of the optical fiber sensor after adjustment is obtained through analysis; In the above calculation formula, S is the output signal of the optical fiber sensor, N is the noise level; α is the signal correction coefficient, which is used to adjust the weight of the signal strength and optimize the ratio of signal to noise; β is the noise suppression coefficient, which is used to adjust the impact of noise on the signal and reduce noise interference; γ is the environmental response coefficient, which is used to measure the impact of environmental factors on sensitivity; E(t) is the environmental impact coefficient, which represents the factors that change over time; f(t) is the weight function of the environmental response, which is used to weight the environmental impact at different time points; δ is the baseline adjustment coefficient, which is used to set the basic value of sensitivity adjustment; ε is the variance response coefficient, which is used to adjust the impact of the positive signal room difference on sensitivity; σ 2 is the variance of the signal, indicating the amplitude of signal change and reflecting the signal stability; η is the historical data weight coefficient, which is used to adjust the impact of historical data on current sensitivity; x i is the i-th historical signal data point, i is the index of the historical signal data point, i=1,2,...n, n is the total number of historical signal data points; μ is the mean of the signal, which represents the average value of the historical signal data.

3. The cleaning warning system for an organic heat carrier boiler according to claim 2 is characterized in that: The environmental impact coefficient E(t) is calculated by the formula E(t) = ψ1×T(t)+ψ2×P(t)+ψ3×H(t)+ψ4×T(t)·P(t)+ψ5×P(t)·H(t)+ψ6×T(t)·H(t), where ψ1, ψ2, ψ3, ψ4, ψ5 and ψ6 represent the set weight coefficients, indicating the contribution of each environmental factor and its interaction to the environmental impact; T(t), P(t) and H(t) represent the function of temperature changing with time, the function of pressure changing with time and the function of humidity changing with time, respectively; By calculating the formula f(t) = g·e -λt +h, the weight function f(t) of the environmental response is calculated, g is the initial weight, which represents the initial impact of environmental change on the response; λ is the attenuation coefficient, which represents the decay rate of environmental impact over time; h is the basic weight, which represents the minimum weight of environmental impact, and t represents the time variable.

4. The cleaning warning system for an organic heat carrier boiler according to claim 1 is characterized in that: The steps to determine whether there is a cleaning dead corner area inside the boiler are as follows: Divide the interior of the boiler into various internal areas; The light intensity value and the optical fiber curvature value of each internal area are collected; Subtract the light intensity value of each internal area from the light intensity value of each internal area before cleaning to obtain the light intensity change difference ΔI of each internal area d , d is the number of each internal area; Subtract the fiber curvature of each internal area from the fiber curvature of each internal area before cleaning to obtain the fiber curvature change difference ΔB of each internal area. d ; The comprehensive dirt degree index C of each internal area is calculated comprehensively d =ω1×ΔI d +ω2×ΔB d , ω1 and ω2 represent the set weight coefficients, which are used to adjust the influence of light intensity change and curvature change in comprehensive judgment; The comprehensive dirt degree index of each internal area is compared with the set judgment threshold. When the comprehensive dirt degree index of an internal area is greater than the set judgment threshold, the internal area is determined to be a dead angle area.

5. The cleaning warning system for an organic heat carrier boiler according to claim 1 is characterized in that: The cleaning parameters are divided into cleaning agent concentration, cleaning time and the optimal spray angle of the cleaning tool.

6. The cleaning warning system for an organic heat carrier boiler according to claim 5 is characterized in that: Automatically adjust the cleaning agent concentration in the cleaning parameters of each cleaning dead corner area. The specific adjustment process is as follows: Obtain the initial cleaning agent concentration ND0 for cleaning the inside of the boiler; And according to the comprehensive dirt index C of each cleaning dead corner area r , then the predetermined cleaning agent concentration of each cleaning dead corner area after adjustment is expressed as: represents the predetermined cleaning agent concentration of the rth cleaning dead corner area, r is the number of each cleaning dead corner area, k is the adjustment coefficient used to control the sensitivity of concentration change; C0 is the threshold value of the comprehensive dirt level; And obtain the upper threshold ND of the cleaning agent concentration corresponding to the boiler max and lower threshold ND min ; The cleaning agent concentration of each cleaning dead corner area is calculated from this 7. The cleaning warning system for an organic heat carrier boiler according to claim 5 is characterized in that: Automatically adjust the cleaning time in the cleaning parameters of each cleaning dead corner area. The specific adjustment process is as follows: Obtain the basic cleaning time of each internal area of ​​the boiler, thereby extracting the basic cleaning time of each cleaning dead corner area The cleaning time of each cleaning dead corner area is calculated comprehensively λ1r is the detergent concentration coefficient of the rth cleaning dead corner area, λ1′ r is the optimal cleaning agent concentration for the rth cleaning dead corner area; λ2r is the pollution degree coefficient of the rth cleaning dead corner area, HDr is the dirt thickness in the rth cleaning dead corner area, and HDmax is the maximum allowable dirt thickness; λ3r is the historical data coefficient of the rth cleaning dead corner area, is the cleaning time of the rth cleaning dead corner area under similar historical conditions; λ4r is the environmental impact coefficient of the rth cleaning dead corner area, are the temperature and pressure of the rth cleaning dead corner area, respectively, and f(·) is the set function expression formula.

8. The cleaning warning system for an organic heat transfer medium boiler according to claim 5, characterized in that: Automatically adjust the optimal spray angle of the cleaning tool in the cleaning parameters of each cleaning dead corner area. The specific adjustment process is as follows: Get the coordinates of the center point of each cleaning blind spot area (x1 r ,y1 r ,z1 r ), synchronously obtain the position coordinates (x2, y2, z2) of the nozzle corresponding to the cleaning tool; The distance between the corresponding nozzle of the cleaning tool and the corresponding center point of each cleaning blind spot area is calculated accordingly. Calculate the angle of the cleaning tool on the horizontal plane corresponding to each cleaning dead angle area and the angle on the vertical plane Use Bernoulli's equation and continuity equation to calculate the flow velocity υ, and then calculate the pressure lost by the fluid due to resistance during the injection process ρ is the density of the fluid, φ is the drag coefficient; Dynamically adjust the predetermined spray angle of the cleaning tool corresponding to each cleaning dead angle area according to the angle of the cleaning tool on the horizontal plane, the angle on the vertical plane and △P F(·) is a function simulated from historical experimental data, expressed as a mapping relationship that converts input parameters into output predetermined injection angles; After error correction, the optimal spray angle of the cleaning tool corresponding to each cleaning dead angle area is finally obtained. is the set adjustment coefficient, and △θ is the set allowable detection error.

Images