An intelligent monitoring method for HPAM microbial degradation in coal slime water treatment

Abstract

The present invention relates to the technical field of coal wastewater treatment, and in particular to an intelligent monitoring method for HPAM microbial degradation for coal slime water treatment. The content includes: real-time collection and pre-treatment of index data in coal slime water, intelligent processing and analysis of the pre-treated index data using a hybrid dynamics model and an adaptive optimization algorithm to obtain analysis results; according to the analysis results, the reaction conditions and operating parameters are automatically adjusted through multi-dimensional time series feedback and nonlinear adaptive learning algorithms; at the same time, the degradation process is detected to obtain detection data; abnormal analysis is performed based on the detection data to obtain abnormal analysis results, and abnormal diagnosis and alarm are performed according to the abnormal analysis results. The problem of low accuracy and poor adaptability in the analysis of microbial degradation process in the process of coal slime water treatment is solved.

Description

Technical Field

[0001] The invention relates to the technical field of coal wastewater treatment, and in particular to an intelligent monitoring method for HPAM microbial degradation for coal slime water treatment. Background Art

[0002] The treatment of coal slime water has always been a difficult problem in the coal industry. Coal slime water is a coal-containing and water-containing waste generated during coal mining and coal preparation. It usually contains high levels of organic and inorganic matter. Due to its high polluting properties, improper treatment will have a serious impact on the environment. Therefore, an efficient and green technical solution is urgently needed to treat coal slime water.

[0003] At present, the main methods for treating coal slime water include chemical precipitation, physical adsorption and microbial degradation. Chemical precipitation precipitates harmful substances in water by adding chemical agents. Although it can effectively remove pollutants, its operation process is relatively complicated and will produce secondary pollution. Physical adsorption uses adsorbent materials to adsorb harmful components in water, but this method requires a large amount of adsorbent materials and is less environmentally friendly. Microbial degradation, as a green and economical treatment method, has received widespread attention in recent years. Microbial degradation decomposes organic matter in coal slime water into harmless substances by utilizing the metabolism of microorganisms, which is an environmentally friendly method. However, microbial degradation faces some challenges in practical applications, mainly including the control of microbial populations, the improvement of degradation efficiency and the optimization of reaction conditions. Therefore, an intelligent monitoring method for HPAM microbial degradation for coal slime water treatment is proposed. Summary of the invention

[0004] The present invention provides an intelligent monitoring method for HPAM microbial degradation for coal slime water treatment, so as to solve the problems of low accuracy and poor adaptability in analyzing the microbial degradation process during the coal slime water treatment process.

[0005] An intelligent monitoring method for HPAM microbial degradation for coal slime water treatment comprises the following steps:

[0006] S1. Real-time collection and pre-processing of index data in coal slime water, intelligent processing and analysis of the pre-processed index data using a hybrid dynamics model and an adaptive optimization algorithm to obtain analysis results; the hybrid dynamics model and the adaptive optimization algorithm combine the microbial degradation model, nonlinear dynamic characteristics and the adaptive gain optimization algorithm; in the implementation process of the hybrid dynamics model and the adaptive optimization algorithm, a microbial degradation model is constructed based on the pre-processed index data; the microbial degradation model is based on biochemical kinetics and nonlinear dynamic characteristics to calculate the degradation rate of microorganisms;

[0007] S2. According to the analysis results, the reaction conditions and operating parameters are automatically adjusted through multi-dimensional time series feedback and nonlinear adaptive learning algorithms; at the same time, the degradation process is detected to obtain detection data; based on the detection data, anomaly analysis is performed to obtain abnormal analysis results, and abnormal diagnosis and alarm are performed based on the abnormal analysis results.

[0008] Preferably, the S1 specifically includes:

[0009] In the process of implementing the hybrid dynamics model and the adaptive optimization algorithm, the change of the HPAM concentration after pretreatment is analyzed based on the degradation rate of microorganisms; the differential equation of HPAM concentration is introduced to calculate the change rate of the HPAM concentration after pretreatment over time, and then the HPAM concentration at the current moment is calculated based on the differential equation of HPAM concentration; the differential equation of HPAM concentration is as follows:

[0010] ,

[0011] in, is the rate of change of HPAM concentration after pretreatment; is the degradation rate of microorganisms; It is at the moment Next, the concentration of HPAM after pretreatment; It is the correction factor of dissolved oxygen concentration after pretreatment on the degradation rate of microorganisms; It is at the moment Dissolved oxygen concentration after pretreatment; is the maximum concentration of dissolved oxygen; It is a correction factor used to describe the effect of dissolved oxygen concentration on the degradation rate of microorganisms.

[0012] Preferably, the S1 specifically includes:

[0013] In the process of realizing the hybrid dynamics model and the adaptive optimization algorithm, an adaptive gain optimization algorithm is introduced to optimize the degradation rate of microorganisms.

[0014] Preferably, the S1 specifically includes:

[0015] In the process of implementing the adaptive gain optimization algorithm, an adaptive gain coefficient is introduced to correct the degradation rate of the microorganisms to obtain the corrected degradation rate of the microorganisms; based on the corrected degradation rate of the microorganisms, the HPAM concentration at the current moment and the microbial activity calculation and analysis results in the pretreated coal slime water, the specific calculation formula is:

[0016] ,

[0017] in, From the beginning to the present moment The cumulative degradation amount represents the analysis result; is the corrected microbial degradation rate; Indicates the HPAM concentration at the current moment; is the adaptive gain coefficient.

[0018] Preferably, the S2 specifically includes:

[0019] The goal of the multidimensional temporal feedback and nonlinear adaptive learning algorithm is to optimize the reaction conditions and operating parameters in the HPAM degradation process.

[0020] Preferably, the S2 specifically includes:

[0021] In the process of implementing the multi-dimensional time series feedback and nonlinear adaptive learning algorithm, based on the analysis results, error calculation is performed, including cumulative degradation error, dissolved oxygen concentration error, reaction temperature error, and pH value error; and the adjustment amount of the reaction conditions is calculated according to the error to obtain the adjusted reaction conditions; the calculation formula for the adjustment amount of the reaction conditions is:

[0022] ,

[0023] in, It is the current moment No. The amount of adjustment of each reaction condition; is the feedback coefficient; It is the current moment No. The error of the reaction conditions; is the feedback coefficient of the historical error term; It is The historical error integral of each reaction condition; is the integration variable; It's time No. The error of the reaction conditions; is the feedback coefficient of the error change rate; It is The error rate of change of each reaction condition; is the nonlinear function feedback coefficient; is a nonlinear function, which indicates the combined effect of two or more reaction conditions on the The influence of reaction conditions; It's time The current state of each reaction condition.

[0024] Preferably, the S2 specifically includes:

[0025] In the process of implementing the multi-dimensional time series feedback and nonlinear adaptive learning algorithm, the error is combined with the weight coefficient, and the adjustment amount of the operating parameter is calculated through the feedback mechanism to generate the adjusted operating parameter; the calculation formula of the adjustment amount of the operating parameter is as follows:

[0026] ,

[0027] in, It is the current moment No. The adjustment amount of an operating parameter; It is Adjustment factors for operating parameters; is the weight of the error in the cumulative degradation amount; It is The weight of the error for each reaction condition; is the error in the cumulative degradation amount; is the adjusted current moment No. The value of a reaction condition.

[0028] The beneficial effects of the technical solution of the present invention are:

[0029] 1. Utilize the hybrid dynamics model and adaptive optimization algorithm, combine the nonlinear dynamic characteristics and biochemical dynamics in the microbial degradation process, and intelligently adjust the degradation rate of microorganisms to improve the degradation efficiency. By constructing a microbial degradation model, the degradation of pollutants in coal slime water can be predicted more accurately, thereby improving the overall treatment effect.

[0030] 2. By introducing an adaptive gain optimization algorithm, the degradation rate of microorganisms is adjusted according to the index data, and the degradation rate is corrected to cope with dynamically changing environmental conditions. By dynamically correcting the degradation rate of microorganisms, the adaptability and flexibility of the treatment process are improved.

[0031] 3. Through multi-dimensional time series feedback and non-linear adaptive learning algorithms, the reaction conditions and operating parameters are automatically adjusted to optimize the degradation efficiency. The multi-dimensional time series feedback and non-linear adaptive learning algorithms enable the reaction conditions to be accurately adjusted according to the actual situation through real-time error calculation and feedback mechanisms, thereby realizing intelligent optimization of the degradation process. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 The present invention is a flow chart of an intelligent monitoring method for HPAM microbial degradation for coal slime water treatment. DETAILED DESCRIPTION

[0033] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0035] The specific scheme of the intelligent monitoring method for HPAM microbial degradation for coal slime water treatment provided by the present invention is described in detail below with reference to the accompanying drawings.

[0036] See attached Figure 1 , which shows a flow chart of an intelligent monitoring method for HPAM microbial degradation for coal slime water treatment provided by an embodiment of the present invention, the method comprising the following steps:

[0037] S1. Real-time collection and pre-processing of index data in coal slime water, intelligent processing and analysis of the pre-processed index data using a hybrid dynamics model and an adaptive optimization algorithm to obtain analysis results;

[0038] During the treatment of coal slime water, online sensors such as dissolved oxygen sensors, pH sensors, temperature sensors, ultraviolet spectrometers, etc. are used to collect index data in real time, including HPAM concentration, dissolved oxygen, pH value, temperature, microbial activity, etc.; the index data are preprocessed by such means as data cleaning, data standardization, and time synchronization to obtain preprocessed index data. The above preprocessing adopts existing technical means and will not be elaborated here.

[0039] Furthermore, the pre-processed index data is intelligently processed and analyzed using a hybrid dynamics model and an adaptive optimization algorithm to obtain analysis results; the hybrid dynamics model and the adaptive optimization algorithm combine the microbial degradation model, nonlinear dynamic characteristics and an adaptive gain optimization algorithm. The specific implementation process is as follows:

[0040] First, a microbial degradation model was constructed; the microbial degradation model takes into account the pre-treated index data in the coal slime water, including HPAM (polymer compound) concentration, microbial activity, environmental factors (such as dissolved oxygen, temperature, pH value, etc.) and the dynamic relationship between them. The microbial degradation model describes the microbial degradation rate , we must consider both biochemical dynamics and nonlinear dynamic characteristics. The specific expression is:

[0041] ,

[0042] in, is the degradation rate of microorganisms, expressed at time The rate of microbial degradation of HPAM under ; is the microbial degradation efficiency constant, which indicates the maximum efficiency or maximum rate of microbial degradation of HPAM; For at the moment Microbial activity in pretreated coal slime water under ; It is at the moment Next, the concentration of HPAM after pretreatment; is the half-saturation constant of HPAM, which indicates the half-saturation concentration of the effect of HPAM concentration on the degradation rate of microorganisms; is the Michalis-Menden kinetic coefficient, which indicates the affinity of microorganisms to HPAM and is used to describe the nonlinear effect of HPAM concentration on the degradation rate of microorganisms; It is the environmental fluctuation correction factor, which is used to indicate the effect of fluctuations caused by environmental factors (such as temperature, dissolved oxygen concentration, etc.) on the degradation rate of microorganisms; is the environmental periodic fluctuation frequency, indicating the fluctuation frequency of environmental factors; It is the phase shift of the environmental fluctuation, indicating the initial phase of the environmental fluctuation and reflecting the starting time point of the fluctuation; is the periodic environmental fluctuation term, which represents the effect of periodic fluctuations of environmental factors (such as temperature, oxygen concentration, etc.) after pretreatment on the degradation rate of microorganisms. The key to the above formula is to introduce the sine function to incorporate the dynamic changes of environmental factors (such as temperature, oxygen concentration, etc.) after pretreatment into the microbial degradation model. Since environmental fluctuations are periodic and directly affect the growth and degradation activities of microorganisms, this correction term enables the microbial degradation model to flexibly adapt to actual environmental conditions; at the same time, biochemical kinetics is (Michalis-Menden equation); nonlinear dynamic characteristics are reflected by exponential relationships and sinusoidal fluctuations, that is, and .

[0043] Furthermore, the change of HPAM concentration after pretreatment was analyzed. The change of HPAM concentration over time is determined by the degradation rate of microorganisms and the effect of environmental conditions. The differential equation of HPAM concentration is introduced:

[0044] ,

[0045] in, is the rate of change of HPAM concentration after pretreatment, indicating the change in HPAM concentration per unit time; It is the correction coefficient of dissolved oxygen concentration after pretreatment on the degradation rate of microorganisms, which describes the influence of the change of dissolved oxygen concentration on the degradation rate of microorganisms; It is at the moment The dissolved oxygen concentration after pretreatment is the concentration of dissolved oxygen in water; It is the maximum concentration of dissolved oxygen, representing the maximum tolerable oxygen concentration of microorganisms; It is a correction factor used to describe the effect of dissolved oxygen concentration on the degradation rate of microorganisms.

[0046] The above equation shows that the change of HPAM concentration is not only directly affected by the degradation rate of microorganisms, but also has a nonlinear relationship with the dissolved oxygen concentration. The change of dissolved oxygen concentration directly affects the degradation rate of microorganisms. The degradation efficiency of microorganisms decreases at low dissolved oxygen concentrations. Therefore, a correction factor is introduced to consider the dynamic effect of dissolved oxygen concentration on the degradation process of microorganisms. The differential equation based on HPAM concentration uses the existing Euler method to obtain the HPAM concentration at the current moment .

[0047] Furthermore, in order to improve the adaptability and intelligent regulation ability of the microbial degradation process, an adaptive gain optimization algorithm was introduced to optimize the changes in the microbial degradation rate. The core purpose of the adaptive gain optimization algorithm is to optimize the growth environment of microorganisms by adjusting microbial activity, HPAM concentration and environmental factors in real time, thereby improving the degradation efficiency.

[0048] Adaptive gain coefficient The degradation rate of microorganisms can be dynamically changed by adjusting the deviation between environmental factors and microorganisms. The specific formula is:

[0049] ,

[0050] in, is the adaptive gain coefficient, which is used to adjust the degradation rate of microorganisms. It varies between 0 and 1, indicating the degree of correction of the degradation rate of microorganisms and reflecting whether the growth environment of microorganisms is close to the optimal conditions; It is the optimal value of microbial activity and the degradation rate of microorganisms at a certain moment. The maximum ideal microbial activity, at which the microorganisms can participate in the degradation of HPAM with the best efficiency, is obtained according to the expert experience method; It is the optimal concentration of dissolved oxygen and the best oxygen concentration for microbial degradation. When the dissolved oxygen concentration is close to this optimal value, the microbial degradation efficiency reaches the maximum. is the gain coefficient adjustment factor, which is used to control the sensitivity of the relationship between microbial activity and dissolved oxygen concentration and the adaptive gain coefficient; It is the weight factor of the influence of HPAM concentration on the adaptive gain coefficient, which determines the influence of HPAM concentration on the gain coefficient; It is the optimal HPAM concentration, which means the ideal HPAM concentration and is the concentration that microorganisms can degrade most effectively.

[0051] Through adaptive gain coefficient , further affecting the degradation rate of microorganisms The modified microbial degradation rate formula is as follows:

[0052] ,

[0053] in, is the corrected microbial degradation rate; is the renewal step length, which is used to control the renewal rate of the degradation rate of microorganisms; Indicates at time Under the action of the microorganisms, the degradation rate of

[0054] After the above-mentioned microbial degradation model and adaptive gain optimization algorithm, the comprehensive effect of HPAM degradation in coal slime water was finally obtained. It can be calculated by the following integral formula:

[0055] ,

[0056] in, It represents the cumulative degradation amount from the beginning to the current moment, that is, the analysis result; the integral operation accumulates the degradation process from the beginning to the current moment, taking into account the influence of the corrected microbial degradation rate, HPAM concentration and adaptive gain coefficient.

[0057] S2. According to the analysis results, the reaction conditions and operating parameters are automatically adjusted through multi-dimensional time series feedback and nonlinear adaptive learning algorithms; at the same time, the degradation process is detected to obtain detection data; based on the detection data, anomaly analysis is performed to obtain abnormal analysis results, and abnormal diagnosis and alarm are performed based on the abnormal analysis results.

[0058] According to the analysis results, the reaction conditions and operating parameters are automatically adjusted through multi-dimensional time series feedback and non-linear adaptive learning algorithms to optimize the degradation efficiency; the goal of the multi-dimensional time series feedback and non-linear adaptive learning algorithm is to optimize the reaction conditions and operating parameters in the HPAM degradation process to achieve higher degradation efficiency; reaction conditions such as dissolved oxygen, temperature, pH value, etc.; operating parameters such as feed amount, reaction time, etc. The specific implementation process is as follows:

[0059] First, based on the analysis results, the error calculation is performed in combination with the target values ​​preset according to the expert experience method, including the cumulative degradation amount error, dissolved oxygen concentration error, reaction temperature error, and pH value error; the calculation formula is as follows:

[0060] ,

[0061] in, It is the current moment No. The error of the reaction conditions; It is the current moment No. The ideal value of the reaction conditions; It is the current moment No. The actual value of each reaction condition; the cumulative degradation error is also calculated using the above error formula;

[0062] Further, the adjustment amount of the reaction condition is calculated according to the error, and the adjustment amount calculation formula is:

[0063] ,

[0064] in, It is the current moment No. The amount of adjustment of each reaction condition; is the feedback coefficient, which indicates the degree of response to the current error; is the feedback coefficient of the historical error term, indicating the degree of response to the historical error; It is The historical error integral of each reaction condition; is the integration variable; It's time No. The error of the reaction conditions; is the feedback coefficient of the error change rate, which indicates the degree of response to the error change rate; It is The error rate of change of each reaction condition; is the nonlinear function feedback coefficient, which indicates the degree of response to the influence of the overall state, that is, the degree of response to the influence of the combination of multiple reaction conditions; is a nonlinear function, indicating the combined effect of multiple reaction conditions on the The effect of multiple reaction conditions at time The joint state of The adjustment amount of each reaction condition is obtained using the existing support vector regression machine learning model; It's time The current state of each reaction condition.

[0065] The adjusted reaction conditions are further obtained:

[0066] ,

[0067] in, is the adjusted current moment No. The value of a reaction condition.

[0068] Furthermore, the error is combined with the weight coefficient and a feedback mechanism is used to calculate the adjustment amount of the operating parameter. The calculation formula of the adjustment amount is as follows:

[0069] ,

[0070] in, It is the current moment No. The adjustment amount of an operating parameter; It is An adjustment factor of an operating parameter, used to control the amplitude of the adjustment; is the weight of the error in the cumulative degradation amount; It is The weight of the error for each reaction condition; is the error in the cumulative degradation amount.

[0071] Further get at the current moment Adjusted operating parameters :

[0072] ,

[0073] in, Indicates the current time No. operation parameters.

[0074] The degradation process is detected to obtain detection data, and abnormal analysis is performed based on the detection data using the existing deviation analysis method to obtain abnormal analysis results. When abnormal data is shown in the abnormal analysis results, the abnormal model defined in advance according to the expert experience method is used to diagnose possible causes based on the detected abnormal data, and the abnormal data and the diagnosis reasons are sent to the staff via SMS and email for alarm to achieve intelligent monitoring.

[0075] In summary, an intelligent monitoring method for HPAM microbial degradation for coal slime water treatment was completed.

[0076] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0077] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0078] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. An intelligent monitoring method for HPAM microbial degradation for coal slime water treatment, characterized in that: The following steps are involved: S1. Real-time collection and pre-processing of index data in coal slime water, intelligent processing and analysis of the pre-processed index data using a hybrid dynamics model and an adaptive optimization algorithm to obtain analysis results; the hybrid dynamics model and the adaptive optimization algorithm combine the microbial degradation model, nonlinear dynamic characteristics and an adaptive gain optimization algorithm; In the process of implementing the hybrid dynamics model and adaptive optimization algorithm, a microbial degradation model is constructed based on the preprocessed index data; The microbial degradation model calculates the degradation rate of microorganisms based on biochemical kinetics and nonlinear dynamic characteristics; S2. According to the analysis results, the reaction conditions and operating parameters are automatically adjusted through multi-dimensional time series feedback and nonlinear adaptive learning algorithms; at the same time, the degradation process is detected to obtain detection data; based on the detection data, anomaly analysis is performed to obtain abnormal analysis results, and abnormal diagnosis and alarm are performed based on the abnormal analysis results.

2. The intelligent monitoring method for HPAM microbial degradation for coal slime water treatment according to claim 1, characterized in that: The S1 specifically includes: In the process of implementing the hybrid dynamics model and the adaptive optimization algorithm, the change of the HPAM concentration after pretreatment is analyzed based on the degradation rate of microorganisms; the differential equation of HPAM concentration is introduced to calculate the change rate of the HPAM concentration after pretreatment over time, and then the HPAM concentration at the current moment is calculated based on the differential equation of HPAM concentration; the differential equation of HPAM concentration is as follows: ， in, is the rate of change of HPAM concentration after pretreatment; is the degradation rate of microorganisms; It is at the moment Next, the concentration of HPAM after pretreatment; It is the correction factor of dissolved oxygen concentration after pretreatment on the degradation rate of microorganisms; It is at the moment Dissolved oxygen concentration after pretreatment; is the maximum concentration of dissolved oxygen; It is a correction factor used to describe the effect of dissolved oxygen concentration on the degradation rate of microorganisms.

3. The intelligent monitoring method for HPAM microbial degradation for coal slime water treatment according to claim 1, characterized in that: The S1 specifically includes: In the process of realizing the hybrid dynamics model and the adaptive optimization algorithm, an adaptive gain optimization algorithm is introduced to optimize the degradation rate of microorganisms.

4. The intelligent monitoring method for HPAM microbial degradation for coal slime water treatment according to claim 3 is characterized in that: The S1 specifically includes: In the process of implementing the adaptive gain optimization algorithm, an adaptive gain coefficient is introduced to correct the degradation rate of the microorganisms to obtain the corrected degradation rate of the microorganisms; based on the corrected degradation rate of the microorganisms, the HPAM concentration at the current moment and the microbial activity calculation and analysis results in the pretreated coal slime water, the specific calculation formula is: ， in, From the beginning to the present moment The cumulative degradation amount represents the analysis result; is the corrected microbial degradation rate; Indicates the HPAM concentration at the current moment; is the adaptive gain coefficient.

5. The intelligent monitoring method for HPAM microbial degradation for coal slime water treatment according to claim 1, characterized in that: The S2 specifically includes: The goal of the multidimensional temporal feedback and nonlinear adaptive learning algorithm is to optimize the reaction conditions and operating parameters in the HPAM degradation process.

6. The intelligent monitoring method for HPAM microbial degradation for coal slime water treatment according to claim 1, characterized in that: The S2 specifically includes: In the process of implementing the multi-dimensional time series feedback and nonlinear adaptive learning algorithm, based on the analysis results, error calculation is performed, including cumulative degradation error, dissolved oxygen concentration error, reaction temperature error, and pH value error; and the adjustment amount of the reaction conditions is calculated according to the error to obtain the adjusted reaction conditions; the calculation formula for the adjustment amount of the reaction conditions is: ， in, It is the current moment No. The amount of adjustment of each reaction condition; is the feedback coefficient; It is the current moment No. The error of the reaction conditions; is the feedback coefficient of the historical error term; It is The historical error integral of each reaction condition; is the integration variable; It's time No. The error of the reaction conditions; is the feedback coefficient of the error change rate; It is The error rate of change of each reaction condition; is the nonlinear function feedback coefficient; is a nonlinear function, indicating the combined effect of two or more reaction conditions on the The influence of reaction conditions; It's time The current state of each reaction condition.

7. The intelligent monitoring method for HPAM microbial degradation for coal slime water treatment according to claim 6, characterized in that: The S2 specifically includes: In the process of implementing the multi-dimensional time series feedback and nonlinear adaptive learning algorithm, the error is combined with the weight coefficient, and the adjustment amount of the operating parameter is calculated through the feedback mechanism to generate the adjusted operating parameter; the calculation formula of the adjustment amount of the operating parameter is as follows: ， in, It is the current moment No. The adjustment amount of an operating parameter; It is Adjustment factors for operating parameters; is the weight of the error in the cumulative degradation amount; It is The weight of the error for each reaction condition; is the error in the cumulative degradation amount; is the adjusted current moment No. The value of a reaction condition.

Images