Parameter analysis method for preparing non-phosphorus grey water dispersing agent
By removing particles with excellentness less than the threshold and weighted average fitness values in the particle swarm algorithm, the problem of low efficiency during the iterative update process is solved, and the optimal parameters of apatoma-free water dispersant are efficiently and accurately determined, which improves the Preparation efficiency and accuracy.
Patent Information
- Application Number
- CN202411472284.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-22
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-10-22
AI Technical Summary
When determining the optimal parameters of apatoma-free water dispersant using particle swarm algorithm, frequent simulation tests are required during the iterative update process, resulting in low efficiency.
In the particle swarm algorithm, by randomly initializing particles, particles with excellentness less than the preset threshold are removed, the number of particles updated iteratively is reduced, and the optimal parameters are determined through weighted average of fitness values and search capabilities, reducing the difficulty of calculation and experiments .
The efficiency of determining the optimal parameters is improved, the accuracy of parameters and the efficient preparation of dispersants is ensured, the number of experiments is reduced, and the application of particle swarm algorithm in the process of parameter optimization is improved.
Smart Images

Figure CN119007874A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data processing, and more specifically, to a parameter analysis method for preparing a phosphorus-free water dispersant. Background Art
[0002] Phosphorus-free water dispersant is an environmentally friendly chemical used in industrial cooling water systems and boiler water treatment to prevent scale formation and disperse existing scale, keep water clean, and avoid equipment corrosion and reduced efficiency. In the process of preparing dispersants, the values of multiple parameters are crucial. Analyzing and optimizing various parameters can ensure the stable and reliable quality of dispersants. Particle swarm algorithm can determine the optimal solution in the problem solution space. Therefore, the optimal parameters for preparing dispersants can be determined by the optimization process of particle swarm algorithm.
[0003] In the related technology, for example, a patent application document with publication number CN117829034A discloses a method for identifying parameters of an unmanned sailboat based on a particle swarm optimization algorithm, the method comprising: collecting state information of the unmanned sailboat; constructing an MMG dynamics model of the unmanned sailboat to determine the parameters to be identified; optimizing the hull parameters to be identified using a particle swarm optimization algorithm to obtain the optimal parameters to be identified; performing CFD simulation on the sail to obtain the parameters to be identified of the sail; substituting the hull parameters and the sail parameters into the dynamics model, and outputting the model parameter identification results.
[0004] However, when the above scheme uses the particle swarm algorithm to optimize parameters, each iterative update process requires simulation tests on the iterated particles, and then updating the speed and position of the iterative particles, which is time-consuming and leads to low efficiency in determining the optimal parameters to a certain extent. Summary of the invention
[0005] In order to solve the problem of low efficiency when using particle swarm algorithm to determine the optimal parameters, the present invention proposes a parameter analysis method for preparing a phosphorus-free ash water dispersant, which comprises the following steps: The value range of multiple parameters when preparing the dispersant is used as the solution space of the particle swarm algorithm. Several particles are randomly initialized in the solution space to obtain the fitness value of each particle. The fitness value reflects the comprehensive performance of the dispersant prepared under the corresponding parameters at the location of the particle. The particle swarm algorithm is used to iteratively update the position and fitness value of each particle. During the current update process, the particles whose excellence is less than the preset threshold in the previous update process are removed until all particles converge. The optimal parameters are determined based on the particle with the largest fitness value to prepare the dispersant. In any updating process, the product of the average value of the required search degree of the position around any particle and the search ability is taken as the excellence of the particle; The search capability is positively correlated with the growth rate of the particle's fitness value during the historical update process and the fitness value of the particle during the current update process. The search degree required for any position in the solution space during the current update process is , For the Updated at The fitness value of the historically updated particle, To solve the space Locations, For the Updated at The history updates the position of the particle, For the The number of historical update particles at the time of update, The natural constant The exponential function with base , is the normalization function.
[0006] The present invention can reduce the number of iteratively updated particles by removing particles whose excellence is less than a preset threshold during the iterative update process, thereby reducing the number of times the dispersant is prepared based on the parameters corresponding to the positions of the updated particles, thereby reducing the number of times the dispersant is prepared, thereby improving the efficiency of determining the optimal parameters for preparing the dispersant.
[0007] Preferably, the growth rate of the fitness value of the particle during the historical update process satisfies the following relationship: ; In the formula, For the historical update process The growth rate of the fitness value of each particle; , Respectively Second and During the update process, The fitness value of each particle; is a function that retains positive numbers; The number of updates at that time; is the normalization function.
[0008] The present invention can limit the range of the growth rate to within 0-1, thereby reducing the difficulty of calculation.
[0009] Preferably, the method for acquiring the search capability includes: The fitness value of any particle in any update process is normalized, and the product of the normalization result and the growth rate of the fitness value of any particle in the historical update process is used as the search ability of any particle in any update process.
[0010] The present invention integrates the fitness value and the growth rate of the fitness value to ensure the accuracy of the determined search capability.
[0011] Preferably, the method for obtaining the degree of excellence includes: During any update process, all positions within a preset radius centered on the position of any particle are regarded as the surrounding positions of any particle; The average value of the required search degree of all positions in the surrounding positions is calculated, and the product of the search ability of any particle in any update process is obtained to obtain the excellence of any particle in any update process.
[0012] Preferably, obtaining the fitness value of each particle includes: The scale inhibition test of the dispersant prepared under the corresponding parameters at any particle position is carried out using the calcium carbonate precipitation method to obtain the scale inhibition efficiency and temperature resistance of the dispersant; An acute toxicity test is conducted on the dispersant to obtain the environmental performance of the dispersant, and the scale inhibition efficiency, temperature resistance and environmental performance are weighted averaged to obtain the fitness value of any particle, and then the fitness values of all particles are determined.
[0013] Preferably, the method for obtaining the scale inhibition efficiency comprises: Obtaining a normal temperature range of the dispersant, and selecting a plurality of temperatures at equal intervals from the normal temperature range as first test temperatures; The scale inhibition test of the dispersant is carried out at the first test temperature, and the average scale inhibition rate of the dispersant at the first test temperature is taken as the scale inhibition efficiency of the dispersant.
[0014] Preferably, the method for obtaining the temperature resistance performance comprises: Obtaining an extreme temperature range of the dispersant, and selecting a plurality of temperatures at equal intervals from the extreme temperature range as second test temperatures; The scale inhibition test of the dispersant is carried out at the second test temperature, and the ratio of the average scale inhibition rate of the dispersant at the second test temperature to the scale inhibition efficiency is taken as the temperature resistance performance of the dispersant.
[0015] The present invention can comprehensively evaluate the performance of the dispersant at different temperatures, ensure the accuracy of the fitness value of the particles, and the applicability of the particle swarm algorithm in the process of optimizing the dispersant preparation parameters.
[0016] Preferably, the method for obtaining the optimal parameters includes: When the positions of all particles converge, the particle with the largest fitness value is taken as the target particle, and the values of various parameters corresponding to the position of the target particle are obtained to obtain the optimal parameters, so as to prepare the dispersant based on the optimal parameters.
[0017] The invention can efficiently and accurately determine the optimal parameters for preparing the dispersant.
[0018] The present invention has the following effects: The present invention randomly initializes a number of particles in the solution space, so that the entire solution space can be effectively searched, and the search for the optimal solution in a local range is avoided, thereby ensuring the accuracy of the optimal parameters; and in the process of iteratively updating the position and fitness value of each particle using the particle swarm algorithm, since the update of each particle requires the preparation of a dispersant based on various parameters corresponding to the updated position, the fitness value of the updated particle is determined based on the weighted average of various performance data of the prepared dispersant, and the number of experiments can be reduced by removing particles whose excellence is less than a preset threshold, thereby improving the efficiency of determining the optimal parameters for preparing the dispersant. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 1. It is a schematic flow chart of the steps of a parameter analysis method for preparing a phosphorus-free water dispersant according to an embodiment of the present invention; Figure 2 It is a schematic flow chart of the steps for determining the excellence of any particle in any updating process in an embodiment of the present invention. DETAILED DESCRIPTION
[0020] 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 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.
[0021] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.
[0022] Reference Figure 1 , a parameter analysis method for preparing a phosphorus-free water dispersant includes steps S1 to S3, which are specifically as follows: S1: The value range of multiple parameters when preparing the dispersant is used as the solution space of the particle swarm algorithm. Several particles are randomly initialized in the solution space to obtain the fitness value of each particle. The fitness value reflects the comprehensive performance of the dispersant prepared under the corresponding parameters at the particle location.
[0023] Specifically, the ratio of various raw materials when preparing the phosphorus-free ash water dispersant, as well as the pH value, temperature, total time, stirring speed and other data during the reaction can be selected as multiple parameters when preparing the dispersant, and the range of the selected multiple data is used as the solution space of the particle swarm algorithm. It should be noted that the solution space and fitness value are both professional terms in the particle swarm algorithm, and this embodiment will not be described in detail here.
[0024] Optionally, after determining the value ranges of various parameters when preparing the phosphate-free water dispersant, the value ranges of various parameters can be discretized to obtain a finite number of different values of each parameter as the solution space of the particle swarm algorithm, ensuring that the number of positions in the solution space is limited.
[0025] Optionally, a certain number of particles, such as 200 particles, can be randomly selected in the solution space to ensure that the positions of the particles are randomly distributed in the solution space; the component velocity of the initial velocity of each particle in each dimension can be randomly selected within the range of the product of the upper limit of the corresponding parameter range and the empirical proportional coefficient. In this embodiment, the empirical proportional coefficient is , thereby obtaining the positions and velocities of several particles after initialization. Of course, a suitable method can also be selected according to specific circumstances to initialize several particles in the solution space. This embodiment does not specifically limit the initialization method.
[0026] It should be noted that in the process of initializing several particles, the position and speed of each particle are determined randomly, which can prevent the particle swarm algorithm from falling into the local optimal solution too early, so that the entire solution space can be effectively searched.
[0027] In an exemplary embodiment of the present invention, the fitness value of each particle can be determined by the following steps: Step 1: Use the calcium carbonate precipitation method to conduct a scale inhibition test on the dispersant prepared under the corresponding parameters at any particle position to obtain the scale inhibition efficiency and temperature resistance of the dispersant; Optionally, the scale inhibition test of the dispersant may be performed in other ways, such as using the interaction between calcium and magnesium ions to perform the scale inhibition test, etc. This embodiment does not particularly limit the specific method used for the scale inhibition test.
[0028] In an exemplary embodiment of the present invention, the determination of the scale inhibition efficiency of the dispersant can be achieved by the following steps: Obtain the normal temperature range of the dispersant, and select multiple temperatures at equal intervals from the normal temperature range as the first test temperature; perform a scale inhibition test on the dispersant at the first test temperature, and use the average scale inhibition rate of the dispersant at the first test temperature as the scale inhibition efficiency of the dispersant.
[0029] The normal temperature range of the dispersant refers to the general temperature range of the environment in which the dispersant is used. For example, in industrial production, if the dispersant is used for pipe descaling, the normal temperature range should be the general temperature range inside the pipe.
[0030] It should be noted that the method of using the calcium carbonate precipitation method to perform scale inhibition test on the dispersant and calculating the corresponding scale inhibition rate is a prior art and will not be described in detail in this embodiment.
[0031] In an exemplary embodiment of the present invention, the determination of the temperature resistance of the dispersant can be achieved by the following steps: Obtain the extreme temperature range of the dispersant, and select multiple temperatures at equal intervals from the extreme temperature range as the second test temperature; perform a scale inhibition test on the dispersant at the second test temperature, and use the ratio of the average scale inhibition rate of the dispersant at the second test temperature to the scale inhibition efficiency as the temperature resistance of the dispersant.
[0032] The extreme temperature range refers to the extreme temperature range of the environment in which the dispersant is applicable. For example, in industrial production, if the dispersant is used for pipe descaling, the extreme temperature range should be the value range adjacent to the highest temperature or the lowest temperature inside the pipe. This embodiment does not specifically limit the adjacent value range.
[0033] Optionally, the number of the selected second test temperatures may be the same as or different from the number of the selected first test temperatures, which is not particularly limited in this embodiment.
[0034] Optionally, when the ratio between the average scale inhibition rate of the dispersant at the second test temperature and the scale inhibition efficiency of the dispersant is larger, it means that the average scale inhibition rate of the dispersant at the second test temperature is relatively less attenuated, and the temperature resistance of the dispersant is higher.
[0035] Step 2: Conduct acute toxicity test on the dispersant to obtain the environmental performance of the dispersant; Optionally, the dispersant can be subjected to an acute toxicity test to obtain LC50, and the reciprocal of LC50 can be used as the environmental performance of the dispersant. It should be noted that the process of conducting an acute toxicity test on a reagent is a prior art and will not be described in detail in this embodiment.
[0036] Step 3: Take a weighted average of the scale inhibition efficiency, temperature resistance and environmental protection performance to obtain the fitness value of any particle, and then determine the fitness values of all particles.
[0037] Specifically, after determining the scale inhibition efficiency, heat resistance and environmental performance of the dispersant prepared based on the corresponding parameters of any particle position, the weights of the scale inhibition efficiency, heat resistance and environmental performance can be set as , and the weighted average value is used as the fitness value of the particle.
[0038] In another embodiment, other performance data may be selected to evaluate the comprehensive performance of the prepared dispersant, such as taking a weighted average of the scale inhibition rate, temperature resistance and dispersion effect of the dispersant. Of course, the weighted average method may not be adopted, such as setting corresponding weights for different performance data according to specific circumstances. This embodiment does not specifically limit the type and quantity of performance data used to determine the fitness value of each particle.
[0039] S2: Use the particle swarm algorithm to iteratively update the position and fitness value of each particle. During the current update process, remove the particles whose excellence is less than the preset threshold in the previous update process until all particles converge.
[0040] In an exemplary embodiment of the present invention, the degree of excellence refers to an indicator for screening particles participating in the updating process. It should be noted that when the position of each particle is updated, the fitness value of the updated particle can be a weighted average value of the scale inhibition efficiency, temperature resistance and environmental protection performance of the dispersant prepared under the parameters corresponding to the position of the updated particle.
[0041] The process of iteratively updating the position of each particle using the particle swarm algorithm is a prior art and will not be described in detail in the present invention.
[0042] refer to Figure 2 As shown, in any updating process, the process of determining the excellence of any particle includes the following steps: S201: Calculate the search capability of any particle in any update process. The search capability is positively correlated with the growth rate of the fitness value of the particle in the historical update process and the fitness value of the particle in the current update process.
[0043] Specifically, the growth rate of the fitness value of any particle during the historical update process satisfies the following relationship: ; In the formula, For the historical update process The growth rate of the fitness value of each particle; , Respectively Second and During the update process, The fitness value of each particle; is a function that retains positive numbers; The number of updates at that time; is the normalization function.
[0044] In an exemplary embodiment of the present invention, the determination of the search capability of any particle in any update process can be achieved by the following steps: The fitness value of any particle in any update process is normalized, and the product of the normalization result and the growth rate of the fitness value of any particle in the historical update process is used as the search ability of any particle in any update process.
[0045] Specifically, the search capability of any particle in any update process satisfies the following relationship: ; In the formula, For the During the update process The search capability of each particle; For the During the update process The fitness value of each particle; For the historical update process The growth rate of the fitness value of each particle; is the normalization function.
[0046] Optionally, other normalization methods may be used to normalize the fitness value of any particle in any update process, such as using quantiles for normalization. This embodiment does not specifically limit the normalization method used.
[0047] Optionally, if the fitness of any particle is high during any update process, and the growth rate of the fitness value of the particle is high during the historical update process, it means that there is a high possibility that the optimal solution exists around the location of the particle, and the search range of the particle is large, and the corresponding search ability of the particle is strong.
[0048] In another embodiment, the search capability of a particle may also be determined by other methods, such as by a summation formula instead of a product calculation formula.
[0049] S202: Calculate the required search degree of any position in the solution space during the update process, and use the product of the average value of the required search degree of the positions around the particle and the search ability as the excellence of the particle.
[0050] In an exemplary embodiment of the present invention, the degree of search required refers to the possibility of searching any position in the solution space. It should be noted that in any update process, if there are many particles with low fitness values near any position in the solution space, it means that the possibility of the optimal solution existing in the area where the position is located is low, and the degree of search required for the position is relatively low.
[0051] Specifically, the required search degree of any position in the solution space during any update process satisfies the following relationship: ; In the formula, For the The first update in the solution space The searchability of the location; For the Updated at The fitness value of each historically updated particle; For the solution space positions; For the Updated at The location of the historically updated particle; For the The number of historical update particles at the time of update; The natural constant An exponential function with base ; is the normalization function.
[0052] in, Reflects the When the update is The position of the history update particle is related to the The normalized distance between the positions. The smaller the value, the closer the position of the historical update particle is to the first position in the solution space. Positions, if the history updates the fitness value of the particle When it is higher, it means that the There is a high probability that there is an optimal solution near the position, and the corresponding The search demand for each location is relatively large.
[0053] In an exemplary embodiment of the present invention, the determination of the excellence of any particle in any updating process can be achieved by the following steps: (1) In any update process, all positions within a preset radius centered on the position of any particle are regarded as the surrounding positions of any particle; Optionally, the preset radius can be set to 3 based on empirical values, and then in any update process, all positions within a circle with a radius of 3, centered at the position of any particle, are used as the surrounding positions of the particle.
[0054] (2) Calculate the average value of the search degree of all surrounding positions and multiply it by the search ability of any particle in any update process to obtain the excellence of any particle in any update process.
[0055] Specifically, in any update process, the excellence of any particle satisfies the following relationship: ; In the formula, For the Updated at The excellence of each particle; For the Updated at The search capability of each particle; For the When updating for the first time, The first particle within the preset radius centered on The searchability of the location; For the When updating for the first time, The number of positions within a preset radius from the center of a particle.
[0056] Optionally, if the search capability of any particle is poor during any update process, and the overall level of the degree of search required for the position around the particle is low, it means that the possibility of the optimal solution in the solution space existing in the area where the particle is located is low, and the particle can be removed in the subsequent update process.
[0057] Further, after determining the excellence of each particle in any update process, particles with excellence less than a preset threshold, such as 0.3, may be removed in the next update process until the positions of all particles converge. This embodiment does not specifically limit the setting of the preset threshold.
[0058] Optionally, during the current update process, particles whose excellence is less than a preset threshold in the previous update process are removed, which can reduce the number of times the dispersant is prepared, thereby reducing the number of experiments, and further improving the efficiency of using the particle swarm algorithm to find the optimal solution in the solution space. It should be noted that each time the position of a particle is updated using the particle swarm algorithm, a dispersant needs to be prepared based on the parameters corresponding to the updated position. Therefore, the present invention can reduce the number of times the dispersant is prepared.
[0059] S3: When all particles converge, the optimal parameters are determined based on the particle with the largest fitness value to prepare the dispersant.
[0060] In an exemplary embodiment of the present invention, the determination of the optimal parameters can be achieved by the following steps: When the positions of all particles converge, the particle with the largest fitness value is taken as the target particle, and the values of various parameters corresponding to the position of the target particle are obtained to obtain the optimal parameters, so as to prepare the dispersant based on the optimal parameters.
[0061] Optionally, the location of the target particle is the optimal solution determined in the solution space using the particle swarm algorithm, so that the values of various parameters corresponding to the location of the target particle can be used as the optimal parameters for preparing the dispersant, and the optimal parameters can be applied to the mass production of the dispersant.
[0062] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.
[0063] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.
Claims
1. A parameter analysis method for preparing a phosphorus-free water dispersant, characterized in that: include: The value ranges of multiple parameters when preparing the dispersant are used as the solution space of the particle swarm algorithm, a number of particles are randomly initialized in the solution space, and the scale inhibition test is performed on the dispersant prepared under the corresponding parameters at the position of any particle using the calcium carbonate precipitation method to obtain the scale inhibition efficiency and temperature resistance of the dispersant. The dispersant is subjected to an acute toxicity test to obtain the environmental protection performance of the dispersant, and the average values of the scale inhibition efficiency, temperature resistance and environmental protection performance are used as the fitness value of the particle; Iteratively updating the position and fitness value of each particle using a particle swarm algorithm, removing particles whose excellence is less than a preset threshold in the previous update process during the current update process, until all particles converge, and determining the optimal parameters based on the particle with the largest fitness value to prepare the dispersant; In any updating process, the product of the average value of the required search degree of the position around any particle and the search ability is taken as the excellence of the particle; The search capability is positively correlated with the growth rate of the particle's fitness value during the historical update process and the fitness value of the particle during the current update process. The search capability of any position in the solution space during the current update process is positively correlated with the growth rate of the particle's fitness value during the historical update process and the fitness value of the particle during the current update process. , For the Updated at The fitness value of the historically updated particle, To solve the space Locations, For the Updated at The history updates the position of the particle, For the The number of historical update particles at the time of update, The natural constant The exponential function with base , is the normalization function.
2. The parameter analysis method for preparing a phosphorus-free water dispersant according to claim 1, characterized in that: The growth rate of the fitness value of the particle during the historical update process satisfies the following relationship: ; In the formula, For the historical update process The growth rate of the fitness value of each particle; , Respectively Second and During the update process, The fitness value of each particle; is a function that retains positive numbers; The number of updates at that time; is the normalization function.
3. The parameter analysis method for preparing a phosphorus-free water dispersant according to claim 2, characterized in that: The method for acquiring the search capability includes: The fitness value of any particle in any update process is normalized, and the product of the normalization result and the growth rate of the fitness value of any particle in the historical update process is used as the search ability of any particle in the update process.
4. The parameter analysis method for preparing a phosphorus-free water dispersant according to claim 1, characterized in that: The method for obtaining the excellence degree includes: In any updating process, all positions within a preset radius centered on the position of any particle are regarded as the surrounding positions of the particle; The excellence of any particle in any updating process is obtained by calculating the average value of the required search degree of all positions in the surrounding positions and multiplying the average value by the search ability of any particle in any updating process.
5. The parameter analysis method for preparing a phosphorus-free water dispersant according to claim 1, characterized in that: The method for obtaining the scale inhibition efficiency comprises: Acquire a normal temperature range of the dispersant, and select multiple temperatures at equal intervals from the normal temperature range as first test temperatures; A scale inhibition test is performed on the dispersant at the first test temperature, and the average scale inhibition rate of the dispersant at the first test temperature is taken as the scale inhibition efficiency of the dispersant.
6. The parameter analysis method for preparing a phosphorus-free water dispersant according to claim 5, characterized in that: The method for obtaining the temperature resistance performance comprises: Obtaining an extreme temperature range of the dispersant, and selecting a plurality of temperatures at equal intervals from the extreme temperature range as second test temperatures; A scale inhibition test is performed on the dispersant at the second test temperature, and the ratio of the average scale inhibition rate of the dispersant at the second test temperature to the scale inhibition efficiency is taken as the temperature resistance of the dispersant.
7. The parameter analysis method for preparing a phosphorus-free water dispersant according to claim 1, characterized in that: The method for obtaining the optimal parameters includes: When the positions of all particles converge, the particle with the largest fitness value is used as the target particle, and the values of various parameters corresponding to the position of the target particle are obtained to obtain the optimal parameters, so as to prepare the dispersant based on the optimal parameters.
Citation Information
Patent Citations
Multi-parameter optimization method
CN107145066A
Circulating water quality stability control method
CN112978816A
Global optimal solution searching method based on improved particle swarm optimization algorithm
CN115983130A
Boiler scaling fault prediction method, device, equipment and medium
CN116738862A
Evaporation energy-saving optimization method and system based on intelligent control
CN118643906A
